linux_dsm_epyc7002/tools/perf/util/dso.h

175 lines
4.8 KiB
C
Raw Normal View History

#ifndef __PERF_DSO
#define __PERF_DSO
#include <linux/types.h>
#include <linux/rbtree.h>
#include <stdbool.h>
#include "types.h"
#include "map.h"
#include "build-id.h"
enum dso_binary_type {
DSO_BINARY_TYPE__KALLSYMS = 0,
DSO_BINARY_TYPE__GUEST_KALLSYMS,
DSO_BINARY_TYPE__VMLINUX,
DSO_BINARY_TYPE__GUEST_VMLINUX,
DSO_BINARY_TYPE__JAVA_JIT,
DSO_BINARY_TYPE__DEBUGLINK,
DSO_BINARY_TYPE__BUILD_ID_CACHE,
DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
DSO_BINARY_TYPE__GUEST_KMODULE,
DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
DSO_BINARY_TYPE__KCORE,
DSO_BINARY_TYPE__GUEST_KCORE,
DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
DSO_BINARY_TYPE__NOT_FOUND,
};
enum dso_kernel_type {
DSO_TYPE_USER = 0,
DSO_TYPE_KERNEL,
DSO_TYPE_GUEST_KERNEL
};
enum dso_swap_type {
DSO_SWAP__UNSET,
DSO_SWAP__NO,
DSO_SWAP__YES,
};
#define DSO__SWAP(dso, type, val) \
({ \
type ____r = val; \
BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \
if (dso->needs_swap == DSO_SWAP__YES) { \
switch (sizeof(____r)) { \
case 2: \
____r = bswap_16(val); \
break; \
case 4: \
____r = bswap_32(val); \
break; \
case 8: \
____r = bswap_64(val); \
break; \
default: \
BUG_ON(1); \
} \
} \
____r; \
})
#define DSO__DATA_CACHE_SIZE 4096
#define DSO__DATA_CACHE_MASK ~(DSO__DATA_CACHE_SIZE - 1)
struct dso_cache {
struct rb_node rb_node;
u64 offset;
u64 size;
char data[0];
};
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
struct rb_root cache;
void *a2l;
char *symsrc_filename;
unsigned int a2l_fails;
enum dso_kernel_type kernel;
enum dso_swap_type needs_swap;
enum dso_binary_type symtab_type;
enum dso_binary_type binary_type;
u8 adjust_symbols:1;
u8 has_build_id:1;
u8 has_srcline:1;
u8 hit:1;
u8 annotate_warned:1;
u8 short_name_allocated:1;
u8 long_name_allocated:1;
u8 sorted_by_name;
u8 loaded;
u8 rel;
u8 build_id[BUILD_ID_SIZE];
const char *short_name;
const char *long_name;
u16 long_name_len;
u16 short_name_len;
char name[0];
};
static inline void dso__set_loaded(struct dso *dso, enum map_type type)
{
dso->loaded |= (1 << type);
}
struct dso *dso__new(const char *name);
void dso__delete(struct dso *dso);
void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
int dso__name_len(const struct dso *dso);
bool dso__loaded(const struct dso *dso, enum map_type type);
bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
void dso__set_sorted_by_name(struct dso *dso, enum map_type type);
void dso__sort_by_name(struct dso *dso, enum map_type type);
void dso__set_build_id(struct dso *dso, void *build_id);
bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
void dso__read_running_kernel_build_id(struct dso *dso,
struct machine *machine);
int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
char dso__symtab_origin(const struct dso *dso);
int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
char *root_dir, char *filename, size_t size);
int dso__data_fd(struct dso *dso, struct machine *machine);
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size);
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
struct machine *machine, u64 addr,
u8 *data, ssize_t size);
struct map *dso__new_map(const char *name);
struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
const char *short_name, int dso_type);
void dsos__add(struct list_head *head, struct dso *dso);
struct dso *dsos__find(const struct list_head *head, const char *name,
perf symbols: Fix vdso list searching When "perf record" was used on a large machine with a lot of CPUs, the perf post-processing time (the time after the workload was done until the perf command itself exited) could take a lot of minutes and even hours depending on how large the resulting perf.data file was. While running AIM7 1500-user high_systime workload on a 80-core x86-64 system with a 3.9 kernel (with only the -s -a options used), the workload itself took about 2 minutes to run and the perf.data file had a size of 1108.746 MB. However, the post-processing step took more than 10 minutes. With a gprof-profiled perf binary, the time spent by perf was as follows: % cumulative self self total time seconds seconds calls s/call s/call name 96.90 822.10 822.10 192156 0.00 0.00 dsos__find 0.81 828.96 6.86 172089958 0.00 0.00 rb_next 0.41 832.44 3.48 48539289 0.00 0.00 rb_erase So 97% (822 seconds) of the time was spent in a single dsos_find() function. After analyzing the call-graph data below: ----------------------------------------------- 0.00 822.12 192156/192156 map__new [6] [7] 96.9 0.00 822.12 192156 vdso__dso_findnew [7] 822.10 0.00 192156/192156 dsos__find [8] 0.01 0.00 192156/192156 dsos__add [62] 0.01 0.00 192156/192366 dso__new [61] 0.00 0.00 1/45282525 memdup [31] 0.00 0.00 192156/192230 dso__set_long_name [91] ----------------------------------------------- 822.10 0.00 192156/192156 vdso__dso_findnew [7] [8] 96.9 822.10 0.00 192156 dsos__find [8] ----------------------------------------------- It was found that the vdso__dso_findnew() function failed to locate VDSO__MAP_NAME ("[vdso]") in the dso list and have to insert a new entry at the end for 192156 times. This problem is due to the fact that there are 2 types of name in the dso entry - short name and long name. The initial dso__new() adds "[vdso]" to both the short and long names. After that, vdso__dso_findnew() modifies the long name to something like /tmp/perf-vdso.so-NoXkDj. The dsos__find() function only compares the long name. As a result, the same vdso entry is duplicated many time in the dso list. This bug increases memory consumption as well as slows the symbol processing time to a crawl. To resolve this problem, the dsos__find() function interface was modified to enable searching either the long name or the short name. The vdso__dso_findnew() will now search only the short name while the other call sites search for the long name as before. With this change, the cpu time of perf was reduced from 848.38s to 15.77s and dsos__find() only accounted for 0.06% of the total time. 0.06 15.73 0.01 192151 0.00 0.00 dsos__find Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: "Chandramouleeswaran, Aswin" <aswin@hp.com> Cc: "Norton, Scott J" <scott.norton@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1368110568-64714-1-git-send-email-Waiman.Long@hp.com [ replaced TRUE/FALSE with stdbool.h equivalents, fixing builds where those macros are not present (NO_LIBPYTHON=1 NO_LIBPERL=1), fix from Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-05-09 21:42:48 +07:00
bool cmp_short);
struct dso *__dsos__findnew(struct list_head *head, const char *name);
bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm);
size_t __dsos__fprintf(struct list_head *head, FILE *fp);
size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
size_t dso__fprintf_symbols_by_name(struct dso *dso,
enum map_type type, FILE *fp);
size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
static inline bool dso__is_vmlinux(struct dso *dso)
{
return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
}
static inline bool dso__is_kcore(struct dso *dso)
{
return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
}
void dso__free_a2l(struct dso *dso);
#endif /* __PERF_DSO */