linux_dsm_epyc7002/tools/perf/util/session.h
Alexey Budankov cb62c6f1f5 perf report: Implement perf.data record decompression
zstd_init(, comp_level = 0) initializes decompression part of API only
hat now consists of zstd_decompress_stream() function.

The perf.data PERF_RECORD_COMPRESSED records are decompressed using
zstd_decompress_stream() function into a linked list of mmaped memory
regions of mmap_comp_len size (struct decomp).

After decompression of one COMPRESSED record its content is iterated and
fetched for usual processing. The mmaped memory regions with
decompressed events are kept in the linked list till the tool process
termination.

When dumping raw records (e.g., perf report -D --header) file offsets of
events from compressed records are printed as zero.

Committer notes:

Since now we have support for processing PERF_RECORD_COMPRESSED, we see
none, in raw form, like we saw in the previous patch commiter notes,
they were decompressed into the usual PERF_RECORD_{FORK,MMAP,COMM,etc}
records, we only see the stats for those PERF_RECORD_COMPRESSED events,
and since I used the file generated in the commiter notes for the
previous patch, there they are, 2 compressed records:

  $ perf report --header-only | grep cmdline
  # cmdline : /home/acme/bin/perf record -z2 sleep 1
  $ perf report -D | grep COMPRESS
        COMPRESSED events:          2
        COMPRESSED events:          0
  $ perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 15  of event 'cycles:u'
  # Event count (approx.): 962227
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ...........................
  #
      46.99%  sleep    libc-2.28.so      [.] _dl_addr
      29.24%  sleep    [unknown]         [k] 0xffffffffaea00a67
      16.45%  sleep    libc-2.28.so      [.] __GI__IO_un_link.part.1
       5.92%  sleep    ld-2.28.so        [.] _dl_setup_hash
       1.40%  sleep    libc-2.28.so      [.] __nanosleep
       0.00%  sleep    [unknown]         [k] 0xffffffffaea00163

  #
  # (Tip: To see callchains in a more compact form: perf report -g folded)
  #
  $

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/304b0a59-942c-3fe1-da02-aa749f87108b@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-15 16:36:49 -03:00

146 lines
4.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __PERF_SESSION_H
#define __PERF_SESSION_H
#include "trace-event.h"
#include "event.h"
#include "header.h"
#include "machine.h"
#include "data.h"
#include "ordered-events.h"
#include "util/compress.h"
#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <linux/perf_event.h>
struct ip_callchain;
struct symbol;
struct thread;
struct auxtrace;
struct itrace_synth_opts;
struct perf_session {
struct perf_header header;
struct machines machines;
struct perf_evlist *evlist;
struct auxtrace *auxtrace;
struct itrace_synth_opts *itrace_synth_opts;
struct list_head auxtrace_index;
struct trace_event tevent;
struct time_conv_event time_conv;
bool repipe;
bool one_mmap;
void *one_mmap_addr;
u64 one_mmap_offset;
struct ordered_events ordered_events;
struct perf_data *data;
struct perf_tool *tool;
u64 bytes_transferred;
u64 bytes_compressed;
struct zstd_data zstd_data;
struct decomp *decomp;
struct decomp *decomp_last;
};
struct decomp {
struct decomp *next;
u64 file_pos;
u64 head;
size_t size;
char data[];
};
struct perf_tool;
struct perf_session *perf_session__new(struct perf_data *data,
bool repipe, struct perf_tool *tool);
void perf_session__delete(struct perf_session *session);
void perf_event_header__bswap(struct perf_event_header *hdr);
int perf_session__peek_event(struct perf_session *session, off_t file_offset,
void *buf, size_t buf_sz,
union perf_event **event_ptr,
struct perf_sample *sample);
int perf_session__process_events(struct perf_session *session);
int perf_session__queue_event(struct perf_session *s, union perf_event *event,
u64 timestamp, u64 file_offset);
void perf_tool__fill_defaults(struct perf_tool *tool);
int perf_session__resolve_callchain(struct perf_session *session,
struct perf_evsel *evsel,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent);
bool perf_session__has_traces(struct perf_session *session, const char *msg);
void perf_event__attr_swap(struct perf_event_attr *attr);
int perf_session__create_kernel_maps(struct perf_session *session);
void perf_session__set_id_hdr_size(struct perf_session *session);
static inline
struct machine *perf_session__find_machine(struct perf_session *session, pid_t pid)
{
return machines__find(&session->machines, pid);
}
static inline
struct machine *perf_session__findnew_machine(struct perf_session *session, pid_t pid)
{
return machines__findnew(&session->machines, pid);
}
struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
int perf_session__register_idle_thread(struct perf_session *session);
size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp);
size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
bool (fn)(struct dso *dso, int parm), int parm);
size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
struct perf_evsel_str_handler;
int __perf_session__set_tracepoints_handlers(struct perf_session *session,
const struct perf_evsel_str_handler *assocs,
size_t nr_assocs);
#define perf_session__set_tracepoints_handlers(session, array) \
__perf_session__set_tracepoints_handlers(session, array, ARRAY_SIZE(array))
extern volatile int session_done;
#define session_done() READ_ONCE(session_done)
int perf_session__deliver_synth_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample);
int perf_event__process_id_index(struct perf_session *session,
union perf_event *event);
int perf_event__synthesize_id_index(struct perf_tool *tool,
perf_event__handler_t process,
struct perf_evlist *evlist,
struct machine *machine);
#endif /* __PERF_SESSION_H */