linux_dsm_epyc7002/tools/perf/util/callchain.c

1453 lines
33 KiB
C
Raw Normal View History

/*
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
* Copyright (C) 2009-2011, Frederic Weisbecker <fweisbec@gmail.com>
*
* Handle the callchains from the stream in an ad-hoc radix tree and then
* sort them in an rbtree.
*
* Using a radix for code path provides a fast retrieval and factorizes
* memory use. Also that lets us use the paths in a hierarchical graph view.
*
*/
#include <inttypes.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdbool.h>
#include <errno.h>
#include <math.h>
#include "asm/bug.h"
#include "hist.h"
perf annotate: Use build-ids to find the right DSO We were still using the pathname found on the MMAP event, that could not be the one we used when recording, so use the build-id cache for that, only falling back to use the pathname in the MMAP event if no build-ids are available. With this we now also are able to do secure, seamless offline annotation. Example: [root@doppio linux-2.6-tip]# perf report -g none -v 2> /dev/null | head -10 8.12% Xorg /usr/lib64/libpixman-1.so.0.14.0 0x0000000000026d02 B [.] pixman_rasterize_edges 4.68% firefox /usr/lib64/xulrunner-1.9.1/libxul.so 0x00000000005dbdba B [.] 0x000000005dbdba 3.70% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet 2.96% init /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff81022cea ! [k] read_hpet 2.73% swapper /lib/modules/2.6.34-rc6/build/vmlinux 0xffffffff8100a738 ! [k] mwait_idle_with_hints [root@doppio linux-2.6-tip]# perf annotate -v pixman_rasterize_edges 2>&1 | grep Executing Executing: objdump --start-address=0x000000371ce26670 --stop-address=0x000000371ce2709f -dS /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|grep -v /root/.debug/.build-id/bd/6ac5199137aaeb279f864717d8d061477466c1|expand [root@doppio linux-2.6-tip]# perf buildid-list | grep libpixman-1.so.0.14.0 bd6ac5199137aaeb279f864717d8d061477466c1 /usr/lib64/libpixman-1.so.0.14.0 [root@doppio linux-2.6-tip]# Reported-by: Stephane Eranian <eranian@google.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-20 22:15:33 +07:00
#include "util.h"
#include "sort.h"
#include "machine.h"
#include "callchain.h"
#define CALLCHAIN_PARAM_DEFAULT \
.mode = CHAIN_GRAPH_ABS, \
.min_percent = 0.5, \
.order = ORDER_CALLEE, \
.key = CCKEY_FUNCTION, \
.value = CCVAL_PERCENT, \
struct callchain_param callchain_param = {
CALLCHAIN_PARAM_DEFAULT
};
struct callchain_param callchain_param_default = {
CALLCHAIN_PARAM_DEFAULT
};
__thread struct callchain_cursor callchain_cursor;
int parse_callchain_record_opt(const char *arg, struct callchain_param *param)
{
return parse_callchain_record(arg, param);
}
static int parse_callchain_mode(const char *value)
{
if (!strncmp(value, "graph", strlen(value))) {
callchain_param.mode = CHAIN_GRAPH_ABS;
return 0;
}
if (!strncmp(value, "flat", strlen(value))) {
callchain_param.mode = CHAIN_FLAT;
return 0;
}
if (!strncmp(value, "fractal", strlen(value))) {
callchain_param.mode = CHAIN_GRAPH_REL;
return 0;
}
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:37 +07:00
if (!strncmp(value, "folded", strlen(value))) {
callchain_param.mode = CHAIN_FOLDED;
return 0;
}
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
pr_err("Invalid callchain mode: %s\n", value);
return -1;
}
static int parse_callchain_order(const char *value)
{
if (!strncmp(value, "caller", strlen(value))) {
callchain_param.order = ORDER_CALLER;
callchain_param.order_set = true;
return 0;
}
if (!strncmp(value, "callee", strlen(value))) {
callchain_param.order = ORDER_CALLEE;
callchain_param.order_set = true;
return 0;
}
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
pr_err("Invalid callchain order: %s\n", value);
return -1;
}
static int parse_callchain_sort_key(const char *value)
{
if (!strncmp(value, "function", strlen(value))) {
callchain_param.key = CCKEY_FUNCTION;
return 0;
}
if (!strncmp(value, "address", strlen(value))) {
callchain_param.key = CCKEY_ADDRESS;
return 0;
}
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
if (!strncmp(value, "srcline", strlen(value))) {
callchain_param.key = CCKEY_SRCLINE;
return 0;
}
perf callchain: Support handling complete branch stacks as histograms Currently branch stacks can be only shown as edge histograms for individual branches. I never found this display particularly useful. This implements an alternative mode that creates histograms over complete branch traces, instead of individual branches, similar to how normal callgraphs are handled. This is done by putting it in front of the normal callgraph and then using the normal callgraph histogram infrastructure to unify them. This way in complex functions we can understand the control flow that lead to a particular sample, and may even see some control flow in the caller for short functions. Example (simplified, of course for such simple code this is usually not needed), please run this after the whole patchkit is in, as at this point in the patch order there is no --branch-history, that will be added in a patch after this one: tcall.c: volatile a = 10000, b = 100000, c; __attribute__((noinline)) f2() { c = a / b; } __attribute__((noinline)) f1() { f2(); f2(); } main() { int i; for (i = 0; i < 1000000; i++) f1(); } % perf record -b -g ./tsrc/tcall [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.044 MB perf.data (~1923 samples) ] % perf report --no-children --branch-history ... 54.91% tcall.c:6 [.] f2 tcall | |--65.53%-- f2 tcall.c:5 | | | |--70.83%-- f1 tcall.c:11 | | f1 tcall.c:10 | | main tcall.c:18 | | main tcall.c:18 | | main tcall.c:17 | | main tcall.c:17 | | f1 tcall.c:13 | | f1 tcall.c:13 | | f2 tcall.c:7 | | f2 tcall.c:5 | | f1 tcall.c:12 | | f1 tcall.c:12 | | f2 tcall.c:7 | | f2 tcall.c:5 | | f1 tcall.c:11 | | | --29.17%-- f1 tcall.c:12 | f1 tcall.c:12 | f2 tcall.c:7 | f2 tcall.c:5 | f1 tcall.c:11 | f1 tcall.c:10 | main tcall.c:18 | main tcall.c:18 | main tcall.c:17 | main tcall.c:17 | f1 tcall.c:13 | f1 tcall.c:13 | f2 tcall.c:7 | f2 tcall.c:5 | f1 tcall.c:12 The default output is unchanged. This is only implemented in perf report, no change to record or anywhere else. This adds the basic code to report: - add a new "branch" option to the -g option parser to enable this mode - when the flag is set include the LBR into the callstack in machine.c. The rest of the history code is unchanged and doesn't know the difference between LBR entry and normal call entry. - detect overlaps with the callchain - remove small loop duplicates in the LBR Current limitations: - The LBR flags (mispredict etc.) are not shown in the history and LBR entries have no special marker. - It would be nice if annotate marked the LBR entries somehow (e.g. with arrows) v2: Various fixes. v3: Merge further patches into this one. Fix white space. v4: Improve manpage. Address review feedback. v5: Rename functions. Better error message without -g. Fix crash without -b. v6: Rebase v7: Rebase. Use NO_ENTRY in memset. v8: Port to latest tip. Move add_callchain_ip to separate patch. Skip initial entries in callchain. Minor cleanups. Signed-off-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1415844328-4884-3-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-11-13 09:05:20 +07:00
if (!strncmp(value, "branch", strlen(value))) {
callchain_param.branch_callstack = 1;
return 0;
}
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
pr_err("Invalid callchain sort key: %s\n", value);
return -1;
}
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
static int parse_callchain_value(const char *value)
{
if (!strncmp(value, "percent", strlen(value))) {
callchain_param.value = CCVAL_PERCENT;
return 0;
}
if (!strncmp(value, "period", strlen(value))) {
callchain_param.value = CCVAL_PERIOD;
return 0;
}
if (!strncmp(value, "count", strlen(value))) {
callchain_param.value = CCVAL_COUNT;
return 0;
}
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
pr_err("Invalid callchain config key: %s\n", value);
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
return -1;
}
static int get_stack_size(const char *str, unsigned long *_size)
{
char *endptr;
unsigned long size;
unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
size = strtoul(str, &endptr, 0);
do {
if (*endptr)
break;
size = round_up(size, sizeof(u64));
if (!size || size > max_size)
break;
*_size = size;
return 0;
} while (0);
pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
max_size, str);
return -1;
}
static int
__parse_callchain_report_opt(const char *arg, bool allow_record_opt)
{
char *tok;
char *endptr, *saveptr = NULL;
bool minpcnt_set = false;
bool record_opt_set = false;
bool try_stack_size = false;
callchain_param.enabled = true;
symbol_conf.use_callchain = true;
if (!arg)
return 0;
while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) {
if (!strncmp(tok, "none", strlen(tok))) {
callchain_param.mode = CHAIN_NONE;
callchain_param.enabled = false;
symbol_conf.use_callchain = false;
return 0;
}
if (!parse_callchain_mode(tok) ||
!parse_callchain_order(tok) ||
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
!parse_callchain_sort_key(tok) ||
!parse_callchain_value(tok)) {
/* parsing ok - move on to the next */
try_stack_size = false;
goto next;
} else if (allow_record_opt && !record_opt_set) {
if (parse_callchain_record(tok, &callchain_param))
goto try_numbers;
/* assume that number followed by 'dwarf' is stack size */
if (callchain_param.record_mode == CALLCHAIN_DWARF)
try_stack_size = true;
record_opt_set = true;
goto next;
}
try_numbers:
if (try_stack_size) {
unsigned long size = 0;
if (get_stack_size(tok, &size) < 0)
return -1;
callchain_param.dump_size = size;
try_stack_size = false;
} else if (!minpcnt_set) {
/* try to get the min percent */
callchain_param.min_percent = strtod(tok, &endptr);
if (tok == endptr)
return -1;
minpcnt_set = true;
} else {
/* try print limit at last */
callchain_param.print_limit = strtoul(tok, &endptr, 0);
if (tok == endptr)
return -1;
}
next:
arg = NULL;
}
if (callchain_register_param(&callchain_param) < 0) {
pr_err("Can't register callchain params\n");
return -1;
}
return 0;
}
int parse_callchain_report_opt(const char *arg)
{
return __parse_callchain_report_opt(arg, false);
}
int parse_callchain_top_opt(const char *arg)
{
return __parse_callchain_report_opt(arg, true);
}
int parse_callchain_record(const char *arg, struct callchain_param *param)
{
char *tok, *name, *saveptr = NULL;
char *buf;
int ret = -1;
/* We need buffer that we know we can write to. */
buf = malloc(strlen(arg) + 1);
if (!buf)
return -ENOMEM;
strcpy(buf, arg);
tok = strtok_r((char *)buf, ",", &saveptr);
name = tok ? : (char *)buf;
do {
/* Framepointer style */
if (!strncmp(name, "fp", sizeof("fp"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_FP;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph fp\n");
break;
/* Dwarf style */
} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
const unsigned long default_stack_dump_size = 8192;
ret = 0;
param->record_mode = CALLCHAIN_DWARF;
param->dump_size = default_stack_dump_size;
tok = strtok_r(NULL, ",", &saveptr);
if (tok) {
unsigned long size = 0;
ret = get_stack_size(tok, &size);
param->dump_size = size;
}
} else if (!strncmp(name, "lbr", sizeof("lbr"))) {
if (!strtok_r(NULL, ",", &saveptr)) {
param->record_mode = CALLCHAIN_LBR;
ret = 0;
} else
pr_err("callchain: No more arguments "
"needed for --call-graph lbr\n");
break;
} else {
pr_err("callchain: Unknown --call-graph option "
"value: %s\n", arg);
break;
}
} while (0);
free(buf);
return ret;
}
int perf_callchain_config(const char *var, const char *value)
{
char *endptr;
if (prefixcmp(var, "call-graph."))
return 0;
var += sizeof("call-graph.") - 1;
if (!strcmp(var, "record-mode"))
return parse_callchain_record_opt(value, &callchain_param);
if (!strcmp(var, "dump-size")) {
unsigned long size = 0;
int ret;
ret = get_stack_size(value, &size);
callchain_param.dump_size = size;
return ret;
}
if (!strcmp(var, "print-type"))
return parse_callchain_mode(value);
if (!strcmp(var, "order"))
return parse_callchain_order(value);
if (!strcmp(var, "sort-key"))
return parse_callchain_sort_key(value);
if (!strcmp(var, "threshold")) {
callchain_param.min_percent = strtod(value, &endptr);
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
if (value == endptr) {
pr_err("Invalid callchain threshold: %s\n", value);
return -1;
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
}
}
if (!strcmp(var, "print-limit")) {
callchain_param.print_limit = strtod(value, &endptr);
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
if (value == endptr) {
pr_err("Invalid callchain print limit: %s\n", value);
return -1;
perf tools: Propagate perf_config() errors Previously these were being ignored, sometimes silently. Stop doing that, emitting debug messages and handling the errors. Testing it: $ cat ~/.perfconfig cat: /home/acme/.perfconfig: No such file or directory $ perf stat -e cycles usleep 1 Performance counter stats for 'usleep 1': 938,996 cycles:u 0.003813731 seconds time elapsed $ perf top --stdio Error: You may not have permission to collect system-wide stats. Consider tweaking /proc/sys/kernel/perf_event_paranoid, <SNIP> [ perf record: Captured and wrote 0.019 MB perf.data (7 samples) ] [acme@jouet linux]$ perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # Overhead Command Shared Object Symbol # ........ ....... ................. ......................... 71.77% usleep libc-2.24.so [.] _dl_addr 27.07% usleep ld-2.24.so [.] _dl_next_ld_env_entry 1.13% usleep [kernel.kallsyms] [k] page_fault $ $ touch ~/.perfconfig $ ls -la ~/.perfconfig -rw-rw-r--. 1 acme acme 0 Jan 27 12:14 /home/acme/.perfconfig $ $ perf stat -e instructions usleep 1 Performance counter stats for 'usleep 1': 244,610 instructions:u 0.000805383 seconds time elapsed $ [root@jouet ~]# chown acme.acme ~/.perfconfig [root@jouet ~]# perf stat -e cycles usleep 1 Warning: File /root/.perfconfig not owned by current user or root, ignoring it. Performance counter stats for 'usleep 1': 937,615 cycles 0.000836931 seconds time elapsed # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-j2rq96so6xdqlr8p8rd6a3jx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-24 23:44:10 +07:00
}
}
return 0;
}
static void
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
enum chain_mode mode)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct callchain_node *rnode;
u64 chain_cumul = callchain_cumul_hits(chain);
while (*p) {
u64 rnode_cumul;
parent = *p;
rnode = rb_entry(parent, struct callchain_node, rb_node);
rnode_cumul = callchain_cumul_hits(rnode);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
switch (mode) {
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
case CHAIN_FLAT:
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:37 +07:00
case CHAIN_FOLDED:
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
if (rnode->hit < chain->hit)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
break;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
case CHAIN_GRAPH_ABS: /* Falldown */
case CHAIN_GRAPH_REL:
if (rnode_cumul < chain_cumul)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
break;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 17:26:57 +07:00
case CHAIN_NONE:
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
default:
break;
}
}
rb_link_node(&chain->rb_node, parent, p);
rb_insert_color(&chain->rb_node, root);
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
static void
__sort_chain_flat(struct rb_root *rb_root, struct callchain_node *node,
u64 min_hit)
{
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct rb_node *n;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
struct callchain_node *child;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
n = rb_first(&node->rb_root_in);
while (n) {
child = rb_entry(n, struct callchain_node, rb_node_in);
n = rb_next(n);
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
__sort_chain_flat(rb_root, child, min_hit);
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
if (node->hit && node->hit >= min_hit)
rb_insert_callchain(rb_root, node, CHAIN_FLAT);
}
/*
* Once we get every callchains from the stream, we can now
* sort them by hit
*/
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
static void
sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 05:15:03 +07:00
u64 min_hit, struct callchain_param *param __maybe_unused)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
{
*rb_root = RB_ROOT;
__sort_chain_flat(rb_root, &root->node, min_hit);
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
}
static void __sort_chain_graph_abs(struct callchain_node *node,
u64 min_hit)
{
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct rb_node *n;
struct callchain_node *child;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
node->rb_root = RB_ROOT;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
n = rb_first(&node->rb_root_in);
while (n) {
child = rb_entry(n, struct callchain_node, rb_node_in);
n = rb_next(n);
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
__sort_chain_graph_abs(child, min_hit);
if (callchain_cumul_hits(child) >= min_hit)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_ABS);
}
}
static void
sort_chain_graph_abs(struct rb_root *rb_root, struct callchain_root *chain_root,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 05:15:03 +07:00
u64 min_hit, struct callchain_param *param __maybe_unused)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
{
__sort_chain_graph_abs(&chain_root->node, min_hit);
rb_root->rb_node = chain_root->node.rb_root.rb_node;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
static void __sort_chain_graph_rel(struct callchain_node *node,
double min_percent)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
{
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct rb_node *n;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
struct callchain_node *child;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
u64 min_hit;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
node->rb_root = RB_ROOT;
min_hit = ceil(node->children_hit * min_percent);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
n = rb_first(&node->rb_root_in);
while (n) {
child = rb_entry(n, struct callchain_node, rb_node_in);
n = rb_next(n);
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
__sort_chain_graph_rel(child, min_percent);
if (callchain_cumul_hits(child) >= min_hit)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
rb_insert_callchain(&node->rb_root, child,
CHAIN_GRAPH_REL);
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
}
}
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
static void
sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_root *chain_root,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 05:15:03 +07:00
u64 min_hit __maybe_unused, struct callchain_param *param)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 22:58:21 +07:00
{
__sort_chain_graph_rel(&chain_root->node, param->min_percent / 100.0);
rb_root->rb_node = chain_root->node.rb_root.rb_node;
}
int callchain_register_param(struct callchain_param *param)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
{
switch (param->mode) {
case CHAIN_GRAPH_ABS:
param->sort = sort_chain_graph_abs;
break;
case CHAIN_GRAPH_REL:
param->sort = sort_chain_graph_rel;
break;
case CHAIN_FLAT:
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:37 +07:00
case CHAIN_FOLDED:
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
param->sort = sort_chain_flat;
break;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 17:26:57 +07:00
case CHAIN_NONE:
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 12:39:21 +07:00
default:
return -1;
}
return 0;
}
/*
* Create a child for a parent. If inherit_children, then the new child
* will become the new parent of it's parent children
*/
static struct callchain_node *
create_child(struct callchain_node *parent, bool inherit_children)
{
struct callchain_node *new;
new = zalloc(sizeof(*new));
if (!new) {
perror("not enough memory to create child for code path tree");
return NULL;
}
new->parent = parent;
INIT_LIST_HEAD(&new->val);
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
INIT_LIST_HEAD(&new->parent_val);
if (inherit_children) {
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct rb_node *n;
struct callchain_node *child;
new->rb_root_in = parent->rb_root_in;
parent->rb_root_in = RB_ROOT;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
n = rb_first(&new->rb_root_in);
while (n) {
child = rb_entry(n, struct callchain_node, rb_node_in);
child->parent = new;
n = rb_next(n);
}
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
/* make it the first child */
rb_link_node(&new->rb_node_in, NULL, &parent->rb_root_in.rb_node);
rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
}
return new;
}
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
/*
* Fill the node with callchain values
*/
static int
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
{
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
struct callchain_cursor_node *cursor_node;
node->val_nr = cursor->nr - cursor->pos;
if (!node->val_nr)
pr_warning("Warning: empty node in callchain tree\n");
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
cursor_node = callchain_cursor_current(cursor);
while (cursor_node) {
struct callchain_list *call;
call = zalloc(sizeof(*call));
if (!call) {
perror("not enough memory for the code path tree");
return -1;
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
call->ip = cursor_node->ip;
call->ms.sym = cursor_node->sym;
call->ms.map = map__get(cursor_node->map);
if (cursor_node->branch) {
call->branch_count = 1;
if (cursor_node->branch_flags.predicted)
call->predicted_count = 1;
if (cursor_node->branch_flags.abort)
call->abort_count = 1;
call->cycles_count = cursor_node->branch_flags.cycles;
call->iter_count = cursor_node->nr_loop_iter;
call->samples_count = cursor_node->samples;
}
list_add_tail(&call->list, &node->val);
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
callchain_cursor_advance(cursor);
cursor_node = callchain_cursor_current(cursor);
}
return 0;
}
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
static struct callchain_node *
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
add_child(struct callchain_node *parent,
struct callchain_cursor *cursor,
u64 period)
{
struct callchain_node *new;
new = create_child(parent, false);
if (new == NULL)
return NULL;
if (fill_node(new, cursor) < 0) {
struct callchain_list *call, *tmp;
list_for_each_entry_safe(call, tmp, &new->val, list) {
list_del(&call->list);
map__zput(call->ms.map);
free(call);
}
free(new);
return NULL;
}
new->children_hit = 0;
new->hit = period;
new->children_count = 0;
new->count = 1;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
return new;
}
enum match_result {
MATCH_ERROR = -1,
MATCH_EQ,
MATCH_LT,
MATCH_GT,
};
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
struct callchain_list *cnode)
{
perf report: Don't crash on invalid maps in `-g srcline` mode I just hit a segfault when doing `perf report -g srcline`. Valgrind pointed me at this code as the culprit: ==8359== Invalid read of size 8 ==8359== at 0x3096D9: map__rip_2objdump (map.c:430) ==8359== by 0x2FC1A3: match_chain_srcline (callchain.c:645) ==8359== by 0x2FC1A3: match_chain (callchain.c:700) ==8359== by 0x2FC1A3: append_chain (callchain.c:895) ==8359== by 0x2FC1A3: append_chain_children (callchain.c:846) ==8359== by 0x2FF719: callchain_append (callchain.c:944) ==8359== by 0x2FF719: hist_entry__append_callchain (callchain.c:1058) ==8359== by 0x32FA06: iter_add_single_cumulative_entry (hist.c:908) ==8359== by 0x33195C: hist_entry_iter__add (hist.c:1050) ==8359== by 0x258F65: process_sample_event (builtin-report.c:204) ==8359== by 0x30D60C: perf_session__deliver_event (session.c:1310) ==8359== by 0x30D60C: ordered_events__deliver_event (session.c:119) ==8359== by 0x310D12: __ordered_events__flush (ordered-events.c:210) ==8359== by 0x310D12: ordered_events__flush.part.3 (ordered-events.c:277) ==8359== by 0x30DD3C: perf_session__process_user_event (session.c:1349) ==8359== by 0x30DD3C: perf_session__process_event (session.c:1475) ==8359== by 0x30FC3C: __perf_session__process_events (session.c:1867) ==8359== by 0x30FC3C: perf_session__process_events (session.c:1921) ==8359== by 0x25A985: __cmd_report (builtin-report.c:575) ==8359== by 0x25A985: cmd_report (builtin-report.c:1054) ==8359== by 0x2B9A80: run_builtin (perf.c:296) ==8359== Address 0x70 is not stack'd, malloc'd or (recently) free'd This patch fixes the issue. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> [ Remove dependency from another change ] Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-2-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 13:21:23 +07:00
char *left = NULL;
char *right = NULL;
enum match_result ret = MATCH_EQ;
int cmp;
if (cnode->ms.map)
left = get_srcline(cnode->ms.map->dso,
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
map__rip_2objdump(cnode->ms.map, cnode->ip),
cnode->ms.sym, true, false);
perf report: Don't crash on invalid maps in `-g srcline` mode I just hit a segfault when doing `perf report -g srcline`. Valgrind pointed me at this code as the culprit: ==8359== Invalid read of size 8 ==8359== at 0x3096D9: map__rip_2objdump (map.c:430) ==8359== by 0x2FC1A3: match_chain_srcline (callchain.c:645) ==8359== by 0x2FC1A3: match_chain (callchain.c:700) ==8359== by 0x2FC1A3: append_chain (callchain.c:895) ==8359== by 0x2FC1A3: append_chain_children (callchain.c:846) ==8359== by 0x2FF719: callchain_append (callchain.c:944) ==8359== by 0x2FF719: hist_entry__append_callchain (callchain.c:1058) ==8359== by 0x32FA06: iter_add_single_cumulative_entry (hist.c:908) ==8359== by 0x33195C: hist_entry_iter__add (hist.c:1050) ==8359== by 0x258F65: process_sample_event (builtin-report.c:204) ==8359== by 0x30D60C: perf_session__deliver_event (session.c:1310) ==8359== by 0x30D60C: ordered_events__deliver_event (session.c:119) ==8359== by 0x310D12: __ordered_events__flush (ordered-events.c:210) ==8359== by 0x310D12: ordered_events__flush.part.3 (ordered-events.c:277) ==8359== by 0x30DD3C: perf_session__process_user_event (session.c:1349) ==8359== by 0x30DD3C: perf_session__process_event (session.c:1475) ==8359== by 0x30FC3C: __perf_session__process_events (session.c:1867) ==8359== by 0x30FC3C: perf_session__process_events (session.c:1921) ==8359== by 0x25A985: __cmd_report (builtin-report.c:575) ==8359== by 0x25A985: cmd_report (builtin-report.c:1054) ==8359== by 0x2B9A80: run_builtin (perf.c:296) ==8359== Address 0x70 is not stack'd, malloc'd or (recently) free'd This patch fixes the issue. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> [ Remove dependency from another change ] Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Yao Jin <yao.jin@linux.intel.com> Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/20170524062129.32529-2-namhyung@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-24 13:21:23 +07:00
if (node->map)
right = get_srcline(node->map->dso,
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
map__rip_2objdump(node->map, node->ip),
node->sym, true, false);
if (left && right)
cmp = strcmp(left, right);
else if (!left && right)
cmp = 1;
else if (left && !right)
cmp = -1;
else if (cnode->ip == node->ip)
cmp = 0;
else
cmp = (cnode->ip < node->ip) ? -1 : 1;
if (cmp != 0)
ret = cmp < 0 ? MATCH_LT : MATCH_GT;
free_srcline(left);
free_srcline(right);
return ret;
}
static enum match_result match_chain(struct callchain_cursor_node *node,
struct callchain_list *cnode)
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
{
struct symbol *sym = node->sym;
u64 left, right;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
if (callchain_param.key == CCKEY_SRCLINE) {
enum match_result match = match_chain_srcline(node, cnode);
if (match != MATCH_ERROR)
return match;
}
if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
left = cnode->ms.sym->start;
right = sym->start;
} else {
left = cnode->ip;
right = node->ip;
}
if (left == right) {
if (node->branch) {
cnode->branch_count++;
if (node->branch_flags.predicted)
cnode->predicted_count++;
if (node->branch_flags.abort)
cnode->abort_count++;
cnode->cycles_count += node->branch_flags.cycles;
cnode->iter_count += node->nr_loop_iter;
cnode->samples_count += node->samples;
}
return MATCH_EQ;
}
return left > right ? MATCH_GT : MATCH_LT;
}
/*
* Split the parent in two parts (a new child is created) and
* give a part of its callchain to the created child.
* Then create another child to host the given callchain of new branch
*/
static int
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
split_add_child(struct callchain_node *parent,
struct callchain_cursor *cursor,
struct callchain_list *to_split,
u64 idx_parents, u64 idx_local, u64 period)
{
struct callchain_node *new;
struct list_head *old_tail;
unsigned int idx_total = idx_parents + idx_local;
/* split */
new = create_child(parent, true);
if (new == NULL)
return -1;
/* split the callchain and move a part to the new child */
old_tail = parent->val.prev;
list_del_range(&to_split->list, old_tail);
new->val.next = &to_split->list;
new->val.prev = old_tail;
to_split->list.prev = &new->val;
old_tail->next = &new->val;
/* split the hits */
new->hit = parent->hit;
new->children_hit = parent->children_hit;
parent->children_hit = callchain_cumul_hits(new);
new->val_nr = parent->val_nr - idx_local;
parent->val_nr = idx_local;
new->count = parent->count;
new->children_count = parent->children_count;
parent->children_count = callchain_cumul_counts(new);
/* create a new child for the new branch if any */
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (idx_total < cursor->nr) {
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct callchain_node *first;
struct callchain_list *cnode;
struct callchain_cursor_node *node;
struct rb_node *p, **pp;
parent->hit = 0;
parent->children_hit += period;
parent->count = 0;
parent->children_count += 1;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
node = callchain_cursor_current(cursor);
new = add_child(parent, cursor, period);
if (new == NULL)
return -1;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
/*
* This is second child since we moved parent's children
* to new (first) child above.
*/
p = parent->rb_root_in.rb_node;
first = rb_entry(p, struct callchain_node, rb_node_in);
cnode = list_first_entry(&first->val, struct callchain_list,
list);
if (match_chain(node, cnode) == MATCH_LT)
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
pp = &p->rb_left;
else
pp = &p->rb_right;
rb_link_node(&new->rb_node_in, p, pp);
rb_insert_color(&new->rb_node_in, &parent->rb_root_in);
} else {
parent->hit = period;
parent->count = 1;
}
return 0;
}
static enum match_result
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
append_chain(struct callchain_node *root,
struct callchain_cursor *cursor,
u64 period);
static int
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
append_chain_children(struct callchain_node *root,
struct callchain_cursor *cursor,
u64 period)
{
struct callchain_node *rnode;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct callchain_cursor_node *node;
struct rb_node **p = &root->rb_root_in.rb_node;
struct rb_node *parent = NULL;
node = callchain_cursor_current(cursor);
if (!node)
return -1;
/* lookup in childrens */
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
while (*p) {
enum match_result ret;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
parent = *p;
rnode = rb_entry(parent, struct callchain_node, rb_node_in);
/* If at least first entry matches, rely to children */
ret = append_chain(rnode, cursor, period);
if (ret == MATCH_EQ)
goto inc_children_hit;
if (ret == MATCH_ERROR)
return -1;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
if (ret == MATCH_LT)
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
p = &parent->rb_left;
else
p = &parent->rb_right;
}
/* nothing in children, add to the current node */
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
rnode = add_child(root, cursor, period);
if (rnode == NULL)
return -1;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
rb_link_node(&rnode->rb_node_in, parent, p);
rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
inc_children_hit:
root->children_hit += period;
root->children_count++;
return 0;
}
static enum match_result
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
append_chain(struct callchain_node *root,
struct callchain_cursor *cursor,
u64 period)
{
struct callchain_list *cnode;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
u64 start = cursor->pos;
bool found = false;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
u64 matches;
enum match_result cmp = MATCH_ERROR;
/*
* Lookup in the current node
* If we have a symbol, then compare the start to match
* anywhere inside a function, unless function
* mode is disabled.
*/
list_for_each_entry(cnode, &root->val, list) {
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
struct callchain_cursor_node *node;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
node = callchain_cursor_current(cursor);
if (!node)
break;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
cmp = match_chain(node, cnode);
if (cmp != MATCH_EQ)
break;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
found = true;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
callchain_cursor_advance(cursor);
}
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
/* matches not, relay no the parent */
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (!found) {
WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
return cmp;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
}
matches = cursor->pos - start;
/* we match only a part of the node. Split it and add the new chain */
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (matches < root->val_nr) {
if (split_add_child(root, cursor, cnode, start, matches,
period) < 0)
return MATCH_ERROR;
return MATCH_EQ;
}
/* we match 100% of the path, increment the hit */
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (matches == root->val_nr && cursor->pos == cursor->nr) {
root->hit += period;
root->count++;
return MATCH_EQ;
}
/* We match the node and still have a part remaining */
if (append_chain_children(root, cursor, period) < 0)
return MATCH_ERROR;
return MATCH_EQ;
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
int callchain_append(struct callchain_root *root,
struct callchain_cursor *cursor,
u64 period)
{
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (!cursor->nr)
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
return 0;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
callchain_cursor_commit(cursor);
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
if (append_chain_children(&root->node, cursor, period) < 0)
return -1;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (cursor->nr > root->max_depth)
root->max_depth = cursor->nr;
perf: Fix orphan callchain branches Callchains have markers inside their capture to tell we enter a context (kernel, user, ...). Those are not displayed in the callchains but they are incidentally an active part of the radix tree where callchains are stored, just like any other address. If we have the two following callchains: addr1 -> addr2 -> user context -> addr3 addr1 -> addr2 -> user context -> addr4 addr1 -> addr2 -> addr 5 This is pretty common if addr1 and addr2 are part of an interrupt path, addr3 and addr4 are user addresses and addr5 is a kernel non interrupt path. This will be stored as follows in the tree: addr1 addr2 / \ / addr5 user context / \ addr3 addr4 But we ignore the context markers in the report, hence the addr3 and addr4 will appear as orphan branches: |--28.30%-- hrtimer_interrupt | smp_apic_timer_interrupt | apic_timer_interrupt | | <------------- here, no parent! | | | | | |--11.11%-- 0x7fae7bccb875 | | | | | |--11.11%-- 0xffffffffff60013b | | | | | |--11.11%-- __pthread_mutex_lock_internal | | | | | |--11.11%-- __errno_location Fix this by removing the context markers when we process the callchains to the tree. Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1269274173-20328-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-22 23:09:33 +07:00
return 0;
}
static int
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
merge_chain_branch(struct callchain_cursor *cursor,
struct callchain_node *dst, struct callchain_node *src)
{
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
struct callchain_cursor_node **old_last = cursor->last;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct callchain_node *child;
struct callchain_list *list, *next_list;
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
struct rb_node *n;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
int old_pos = cursor->nr;
int err = 0;
list_for_each_entry_safe(list, next_list, &src->val, list) {
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
callchain_cursor_append(cursor, list->ip,
perf report: Add branch flag to callchain cursor node Since the branch ip has been added to call stack for easier browsing, this patch adds more branch information. For example, add a flag to indicate if this ip is a branch, and also add with the branch flag. Then we can know if the cursor node represents a branch and know what the branch flag it has. The branch history code has a loop detection pass that removes loops. It would be nice for knowing how many loops were removed then in next steps, we can compute out the average number of iterations. For example: Before remove_loops(), entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x300, to = 0x250 entry3: from = 0x300, to = 0x250 entry4: from = 0x700, to = 0x800 After remove_loops() entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x700, to = 0x800 The original entry2 and entry3 are removed. So the number of iterations (from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1). iterations = removed number + 1; average iteractions = Sum(iteractions) / number of samples This formula ignores other cases, for example, iterations cross multiple buffers and one buffer contains 2+ loops. Because in practice, it's good enough. Signed-off-by: Yao Jin <yao.jin@linux.intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linux-kernel@vger.kernel.org Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com [ Renamed 'iter' to 'nr_loop_iter' for clarity ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 08:19:49 +07:00
list->ms.map, list->ms.sym,
false, NULL, 0, 0);
list_del(&list->list);
map__zput(list->ms.map);
free(list);
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (src->hit) {
callchain_cursor_commit(cursor);
if (append_chain_children(dst, cursor, src->hit) < 0)
return -1;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
}
perf callchain: Convert children list to rbtree Current collapse stage has a scalability problem which can be reproduced easily with a parallel kernel build. This is because it needs to traverse every children of callchains linearly during the collapse/merge stage. Converting it to a rbtree reduced the overhead significantly. On my 400MB perf.data file which recorded with make -j32 kernel build: $ time perf --no-pager report --stdio > /dev/null before: real 6m22.073s user 6m18.683s sys 0m0.706s after: real 0m20.780s user 0m19.962s sys 0m0.689s During the perf report the overhead on append_chain_children went down from 96.69% to 18.16%: - 18.16% perf perf [.] append_chain_children - append_chain_children - 77.48% append_chain_children + 69.79% merge_chain_branch - 22.96% append_chain_children + 67.44% merge_chain_branch + 30.15% append_chain_children + 2.41% callchain_append + 7.25% callchain_append + 12.26% callchain_append + 10.22% merge_chain_branch + 11.58% perf perf [.] dso__find_symbol + 8.02% perf perf [.] sort__comm_cmp + 5.48% perf libc-2.17.so [.] malloc_consolidate Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1381468543-25334-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-11 12:15:36 +07:00
n = rb_first(&src->rb_root_in);
while (n) {
child = container_of(n, struct callchain_node, rb_node_in);
n = rb_next(n);
rb_erase(&child->rb_node_in, &src->rb_root_in);
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
err = merge_chain_branch(cursor, dst, child);
if (err)
break;
free(child);
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
cursor->nr = old_pos;
cursor->last = old_last;
return err;
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
int callchain_merge(struct callchain_cursor *cursor,
struct callchain_root *dst, struct callchain_root *src)
{
return merge_chain_branch(cursor, &dst->node, &src->node);
}
int callchain_cursor_append(struct callchain_cursor *cursor,
perf report: Add branch flag to callchain cursor node Since the branch ip has been added to call stack for easier browsing, this patch adds more branch information. For example, add a flag to indicate if this ip is a branch, and also add with the branch flag. Then we can know if the cursor node represents a branch and know what the branch flag it has. The branch history code has a loop detection pass that removes loops. It would be nice for knowing how many loops were removed then in next steps, we can compute out the average number of iterations. For example: Before remove_loops(), entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x300, to = 0x250 entry3: from = 0x300, to = 0x250 entry4: from = 0x700, to = 0x800 After remove_loops() entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x700, to = 0x800 The original entry2 and entry3 are removed. So the number of iterations (from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1). iterations = removed number + 1; average iteractions = Sum(iteractions) / number of samples This formula ignores other cases, for example, iterations cross multiple buffers and one buffer contains 2+ loops. Because in practice, it's good enough. Signed-off-by: Yao Jin <yao.jin@linux.intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linux-kernel@vger.kernel.org Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com [ Renamed 'iter' to 'nr_loop_iter' for clarity ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 08:19:49 +07:00
u64 ip, struct map *map, struct symbol *sym,
bool branch, struct branch_flags *flags,
int nr_loop_iter, int samples)
{
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
struct callchain_cursor_node *node = *cursor->last;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (!node) {
node = calloc(1, sizeof(*node));
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
if (!node)
return -ENOMEM;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
*cursor->last = node;
}
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
node->ip = ip;
map__zput(node->map);
node->map = map__get(map);
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
node->sym = sym;
perf report: Add branch flag to callchain cursor node Since the branch ip has been added to call stack for easier browsing, this patch adds more branch information. For example, add a flag to indicate if this ip is a branch, and also add with the branch flag. Then we can know if the cursor node represents a branch and know what the branch flag it has. The branch history code has a loop detection pass that removes loops. It would be nice for knowing how many loops were removed then in next steps, we can compute out the average number of iterations. For example: Before remove_loops(), entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x300, to = 0x250 entry3: from = 0x300, to = 0x250 entry4: from = 0x700, to = 0x800 After remove_loops() entry0: from = 0x100, to = 0x200 entry1: from = 0x300, to = 0x250 entry2: from = 0x700, to = 0x800 The original entry2 and entry3 are removed. So the number of iterations (from = 0x300, to = 0x250) is equal to removed number + 1 (2 + 1). iterations = removed number + 1; average iteractions = Sum(iteractions) / number of samples This formula ignores other cases, for example, iterations cross multiple buffers and one buffer contains 2+ loops. Because in practice, it's good enough. Signed-off-by: Yao Jin <yao.jin@linux.intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Linux-kernel@vger.kernel.org Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/n/1477876794-30749-2-git-send-email-yao.jin@linux.intel.com [ Renamed 'iter' to 'nr_loop_iter' for clarity ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-31 08:19:49 +07:00
node->branch = branch;
node->nr_loop_iter = nr_loop_iter;
node->samples = samples;
if (flags)
memcpy(&node->branch_flags, flags,
sizeof(struct branch_flags));
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
cursor->nr++;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 10:51:58 +07:00
cursor->last = &node->next;
return 0;
}
int sample__resolve_callchain(struct perf_sample *sample,
struct callchain_cursor *cursor, struct symbol **parent,
struct perf_evsel *evsel, struct addr_location *al,
int max_stack)
{
if (sample->callchain == NULL)
return 0;
if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
perf_hpp_list.parent) {
return thread__resolve_callchain(al->thread, cursor, evsel, sample,
parent, al, max_stack);
}
return 0;
}
int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
{
if (!symbol_conf.use_callchain || sample->callchain == NULL)
return 0;
return callchain_append(he->callchain, &callchain_cursor, sample->period);
}
int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
bool hide_unresolved)
{
al->map = node->map;
al->sym = node->sym;
if (node->map)
al->addr = node->map->map_ip(node->map, node->ip);
else
al->addr = node->ip;
if (al->sym == NULL) {
if (hide_unresolved)
return 0;
if (al->map == NULL)
goto out;
}
if (al->map->groups == &al->machine->kmaps) {
if (machine__is_host(al->machine)) {
al->cpumode = PERF_RECORD_MISC_KERNEL;
al->level = 'k';
} else {
al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
al->level = 'g';
}
} else {
if (machine__is_host(al->machine)) {
al->cpumode = PERF_RECORD_MISC_USER;
al->level = '.';
} else if (perf_guest) {
al->cpumode = PERF_RECORD_MISC_GUEST_USER;
al->level = 'u';
} else {
al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
al->level = 'H';
}
}
out:
return 1;
}
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso)
{
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
bool show_addr = callchain_param.key == CCKEY_ADDRESS;
bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
int printed;
if (cl->ms.sym) {
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
if (show_srcline && cl->ms.map && !cl->srcline)
cl->srcline = get_srcline(cl->ms.map->dso,
map__rip_2objdump(cl->ms.map,
cl->ip),
perf report: Enable sorting by srcline as key Often it is interesting to know how costly a given source line is in total. Previously, one had to build these sums manually based on all addresses that pointed to the same source line. This patch introduces srcline as a sort key, which will do the aggregation for us. Paired with the recent addition of showing inline frames, this makes perf report much more useful for many C++ work loads. The following shows the new feature in action. First, let's show the status quo output when we sort by address. The result contains many hist entries that generate the same output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g address # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--60.31%--hypot +20 | | | | | |--8.52%--__hypot_finite +273 | | | | | |--7.32%--__hypot_finite +411 ... --35.34%--_start +4194346 __libc_start_main +241 | |--6.65%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--2.70%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) | |--1.69%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ With this patch and `-g srcline` we instead get the following output: ~~~~~~~~~~~~~~~~ $ perf report --stdio --inline -g srcline # Children Self Command Shared Object Symbol # ........ ........ ............ ................... ......................................... # 99.89% 35.34% cpp-inlining cpp-inlining [.] main | |--64.55%--main complex:655 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/complex:664 (inline) | | | |--64.02%--hypot | | | | | --59.81%--__hypot_finite | | | --0.53%--cabs | --35.34%--_start __libc_start_main | |--12.48%--main random.tcc:3326 | /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline) | /usr/include/c++/6.3.1/bits/random.h:1809 (inline) | /usr/include/c++/6.3.1/bits/random.h:1818 (inline) | /usr/include/c++/6.3.1/bits/random.h:185 (inline) ... ~~~~~~~~~~~~~~~~ Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Yao Jin <yao.jin@linux.intel.com> Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-19 04:49:28 +07:00
cl->ms.sym, false, show_addr);
if (cl->srcline)
printed = scnprintf(bf, bfsize, "%s %s",
cl->ms.sym->name, cl->srcline);
else
printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
} else
printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
if (show_dso)
scnprintf(bf + printed, bfsize - printed, " %s",
cl->ms.map ?
cl->ms.map->dso->short_name :
"unknown");
return bf;
}
char *callchain_node__scnprintf_value(struct callchain_node *node,
char *bf, size_t bfsize, u64 total)
{
double percent = 0.0;
u64 period = callchain_cumul_hits(node);
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
unsigned count = callchain_cumul_counts(node);
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
if (callchain_param.mode == CHAIN_FOLDED) {
period = node->hit;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
count = node->count;
}
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
switch (callchain_param.value) {
case CCVAL_PERIOD:
scnprintf(bf, bfsize, "%"PRIu64, period);
break;
case CCVAL_COUNT:
scnprintf(bf, bfsize, "%u", count);
break;
case CCVAL_PERCENT:
default:
if (total)
percent = period * 100.0 / total;
scnprintf(bf, bfsize, "%.2f%%", percent);
break;
}
return bf;
}
int callchain_node__fprintf_value(struct callchain_node *node,
FILE *fp, u64 total)
{
double percent = 0.0;
u64 period = callchain_cumul_hits(node);
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
unsigned count = callchain_cumul_counts(node);
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
if (callchain_param.mode == CHAIN_FOLDED) {
period = node->hit;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
count = node->count;
}
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:41 +07:00
switch (callchain_param.value) {
case CCVAL_PERIOD:
return fprintf(fp, "%"PRIu64, period);
case CCVAL_COUNT:
return fprintf(fp, "%u", count);
case CCVAL_PERCENT:
default:
if (total)
percent = period * 100.0 / total;
return percent_color_fprintf(fp, "%.2f%%", percent);
}
return 0;
}
static void callchain_counts_value(struct callchain_node *node,
u64 *branch_count, u64 *predicted_count,
u64 *abort_count, u64 *cycles_count)
{
struct callchain_list *clist;
list_for_each_entry(clist, &node->val, list) {
if (branch_count)
*branch_count += clist->branch_count;
if (predicted_count)
*predicted_count += clist->predicted_count;
if (abort_count)
*abort_count += clist->abort_count;
if (cycles_count)
*cycles_count += clist->cycles_count;
}
}
static int callchain_node_branch_counts_cumul(struct callchain_node *node,
u64 *branch_count,
u64 *predicted_count,
u64 *abort_count,
u64 *cycles_count)
{
struct callchain_node *child;
struct rb_node *n;
n = rb_first(&node->rb_root_in);
while (n) {
child = rb_entry(n, struct callchain_node, rb_node_in);
n = rb_next(n);
callchain_node_branch_counts_cumul(child, branch_count,
predicted_count,
abort_count,
cycles_count);
callchain_counts_value(child, branch_count,
predicted_count, abort_count,
cycles_count);
}
return 0;
}
int callchain_branch_counts(struct callchain_root *root,
u64 *branch_count, u64 *predicted_count,
u64 *abort_count, u64 *cycles_count)
{
if (branch_count)
*branch_count = 0;
if (predicted_count)
*predicted_count = 0;
if (abort_count)
*abort_count = 0;
if (cycles_count)
*cycles_count = 0;
return callchain_node_branch_counts_cumul(&root->node,
branch_count,
predicted_count,
abort_count,
cycles_count);
}
2017-07-18 19:13:12 +07:00
static int count_pri64_printf(int idx, const char *str, u64 value, char *bf, int bfsize)
{
int printed;
printed = scnprintf(bf, bfsize, "%s%s:%" PRId64 "", (idx) ? " " : " (", str, value);
return printed;
}
static int count_float_printf(int idx, const char *str, float value, char *bf, int bfsize)
{
int printed;
printed = scnprintf(bf, bfsize, "%s%s:%.1f%%", (idx) ? " " : " (", str, value);
return printed;
}
static int counts_str_build(char *bf, int bfsize,
u64 branch_count, u64 predicted_count,
u64 abort_count, u64 cycles_count,
u64 iter_count, u64 samples_count)
{
u64 cycles;
2017-07-18 19:13:12 +07:00
int printed = 0, i = 0;
if (branch_count == 0)
return scnprintf(bf, bfsize, " (calltrace)");
2017-07-18 19:13:12 +07:00
if (predicted_count < branch_count) {
printed += count_float_printf(i++, "predicted",
predicted_count * 100.0 / branch_count,
bf + printed, bfsize - printed);
}
2017-07-18 19:13:12 +07:00
if (abort_count) {
printed += count_float_printf(i++, "abort",
abort_count * 100.0 / branch_count,
bf + printed, bfsize - printed);
}
2017-07-18 19:13:12 +07:00
cycles = cycles_count / branch_count;
if (cycles) {
printed += count_pri64_printf(i++, "cycles",
cycles,
bf + printed, bfsize - printed);
}
2017-07-18 19:13:12 +07:00
if (iter_count && samples_count) {
printed += count_pri64_printf(i++, "iterations",
iter_count / samples_count,
bf + printed, bfsize - printed);
}
2017-07-18 19:13:12 +07:00
if (i)
return scnprintf(bf + printed, bfsize - printed, ")");
2017-07-18 19:13:12 +07:00
bf[0] = 0;
return 0;
}
static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
u64 branch_count, u64 predicted_count,
u64 abort_count, u64 cycles_count,
u64 iter_count, u64 samples_count)
{
char str[128];
counts_str_build(str, sizeof(str), branch_count,
predicted_count, abort_count, cycles_count,
iter_count, samples_count);
if (fp)
return fprintf(fp, "%s", str);
return scnprintf(bf, bfsize, "%s", str);
}
int callchain_list_counts__printf_value(struct callchain_node *node,
struct callchain_list *clist,
FILE *fp, char *bf, int bfsize)
{
u64 branch_count, predicted_count;
u64 abort_count, cycles_count;
u64 iter_count = 0, samples_count = 0;
branch_count = clist->branch_count;
predicted_count = clist->predicted_count;
abort_count = clist->abort_count;
cycles_count = clist->cycles_count;
if (node) {
struct callchain_list *call;
list_for_each_entry(call, &node->val, list) {
iter_count += call->iter_count;
samples_count += call->samples_count;
}
}
return callchain_counts_printf(fp, bf, bfsize, branch_count,
predicted_count, abort_count,
cycles_count, iter_count, samples_count);
}
static void free_callchain_node(struct callchain_node *node)
{
struct callchain_list *list, *tmp;
struct callchain_node *child;
struct rb_node *n;
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
list_del(&list->list);
map__zput(list->ms.map);
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
free(list);
}
list_for_each_entry_safe(list, tmp, &node->val, list) {
list_del(&list->list);
map__zput(list->ms.map);
free(list);
}
n = rb_first(&node->rb_root_in);
while (n) {
child = container_of(n, struct callchain_node, rb_node_in);
n = rb_next(n);
rb_erase(&child->rb_node_in, &node->rb_root_in);
free_callchain_node(child);
free(child);
}
}
void free_callchain(struct callchain_root *root)
{
if (!symbol_conf.use_callchain)
return;
free_callchain_node(&root->node);
}
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
static u64 decay_callchain_node(struct callchain_node *node)
{
struct callchain_node *child;
struct rb_node *n;
u64 child_hits = 0;
n = rb_first(&node->rb_root_in);
while (n) {
child = container_of(n, struct callchain_node, rb_node_in);
child_hits += decay_callchain_node(child);
n = rb_next(n);
}
node->hit = (node->hit * 7) / 8;
node->children_hit = child_hits;
return node->hit;
}
void decay_callchain(struct callchain_root *root)
{
if (!symbol_conf.use_callchain)
return;
decay_callchain_node(&root->node);
}
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
int callchain_node__make_parent_list(struct callchain_node *node)
{
struct callchain_node *parent = node->parent;
struct callchain_list *chain, *new;
LIST_HEAD(head);
while (parent) {
list_for_each_entry_reverse(chain, &parent->val, list) {
new = malloc(sizeof(*new));
if (new == NULL)
goto out;
*new = *chain;
new->has_children = false;
map__get(new->ms.map);
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
list_add_tail(&new->list, &head);
}
parent = parent->parent;
}
list_for_each_entry_safe_reverse(chain, new, &head, list)
list_move_tail(&chain->list, &node->parent_val);
if (!list_empty(&node->parent_val)) {
chain = list_first_entry(&node->parent_val, struct callchain_list, list);
chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node);
chain = list_first_entry(&node->val, struct callchain_list, list);
chain->has_children = false;
}
return 0;
out:
list_for_each_entry_safe(chain, new, &head, list) {
list_del(&chain->list);
map__zput(chain->ms.map);
perf hists browser: Support flat callchains The flat callchain mode is to print all chains in a single, simple hierarchy so make it easy to see. Currently perf report --tui doesn't show flat callchains properly. With flat callchains, only leaf nodes are added to the final rbtree so it should show entries in parent nodes. To do that, add parent_val list to struct callchain_node and show them along with the (normal) val list. For example, consider following callchains with '-g graph'. $ perf report -g graph - 39.93% swapper [kernel.vmlinux] [k] intel_idle intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle - cpu_startup_entry 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Before: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle 28.63% start_secondary - 11.30% rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report -g flat - 39.93% swapper [kernel.vmlinux] [k] intel_idle - 28.63% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary - 11.30% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 12:45:43 +07:00
free(chain);
}
return -ENOMEM;
}
int callchain_cursor__copy(struct callchain_cursor *dst,
struct callchain_cursor *src)
{
int rc = 0;
callchain_cursor_reset(dst);
callchain_cursor_commit(src);
while (true) {
struct callchain_cursor_node *node;
node = callchain_cursor_current(src);
if (node == NULL)
break;
rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
node->branch, &node->branch_flags,
node->nr_loop_iter, node->samples);
if (rc)
break;
callchain_cursor_advance(src);
}
return rc;
}