From 334fe7a3c63624eb1bba42f81eb088d5665d9f3e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 11 Mar 2013 16:43:12 +0900 Subject: perf evlist: Remove cpus and threads arguments from perf_evlist__new() It's almost always used with NULL for both arguments. Get rid of the arguments from the signature and use perf_evlist__set_maps() if needed. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1362987798-24969-1-git-send-email-namhyung@kernel.org [ committer note: replaced spaces with tabs in some of the affected lines ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f1a939ebc19..e3261eae0ad 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -964,7 +964,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) struct perf_record *rec = &record; char errbuf[BUFSIZ]; - evsel_list = perf_evlist__new(NULL, NULL); + evsel_list = perf_evlist__new(); if (evsel_list == NULL) return -ENOMEM; -- cgit v1.2.3-70-g09d2 From 6ef73ec449af998ca34673636d00decc8e808544 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 11 Mar 2013 16:43:15 +0900 Subject: perf evlist: Pass struct perf_target to perf_evlist__prepare_workload() It's a preparation step of removing @opts arg from the function so that it can be used more widely. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1362987798-24969-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 3 ++- tools/perf/builtin-trace.c | 3 ++- tools/perf/tests/perf-record.c | 2 +- tools/perf/util/evlist.c | 3 ++- tools/perf/util/evlist.h | 1 + 5 files changed, 8 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e3261eae0ad..a80301797e8 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -474,7 +474,8 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) } if (forks) { - err = perf_evlist__prepare_workload(evsel_list, opts, argv); + err = perf_evlist__prepare_workload(evsel_list, &opts->target, + opts, argv); if (err < 0) { pr_err("Couldn't run the workload!\n"); goto out_delete_session; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 6198eb11e1c..1de3971437c 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -461,7 +461,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv) signal(SIGINT, sig_handler); if (forks) { - err = perf_evlist__prepare_workload(evlist, &trace->opts, argv); + err = perf_evlist__prepare_workload(evlist, &trace->opts.target, + &trace->opts, argv); if (err < 0) { printf("Couldn't run the workload!\n"); goto out_delete_evlist; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index f6ba75a983a..adf6b4a21a6 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -93,7 +93,7 @@ int test__PERF_RECORD(void) * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts, argv); + err = perf_evlist__prepare_workload(evlist, &opts.target, &opts, argv); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_maps; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7d71a691b86..291884c804e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -745,6 +745,7 @@ out_err: } int perf_evlist__prepare_workload(struct perf_evlist *evlist, + struct perf_target *target, struct perf_record_opts *opts, const char *argv[]) { @@ -800,7 +801,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, exit(-1); } - if (perf_target__none(&opts->target)) + if (perf_target__none(target)) evlist->threads->map[0] = evlist->workload.pid; close(child_ready_pipe[1]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 9a7b76e3a87..e089906cb4d 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -86,6 +86,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct perf_record_opts *opts); int perf_evlist__prepare_workload(struct perf_evlist *evlist, + struct perf_target *target, struct perf_record_opts *opts, const char *argv[]); int perf_evlist__start_workload(struct perf_evlist *evlist); -- cgit v1.2.3-70-g09d2 From 119fa3c922ff53a334507e198b2e3c66e99f54dc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 11 Mar 2013 16:43:16 +0900 Subject: perf evlist: Do not pass struct record_opts to perf_evlist__prepare_workload() Since it's only used for checking ->pipe_output, we can pass the result directly. Now the perf_evlist__prepare_workload() don't have a dependency of struct perf_record_opts, it can be called from other places like perf stat. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1362987798-24969-5-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-trace.c | 2 +- tools/perf/tests/perf-record.c | 2 +- tools/perf/util/evlist.c | 5 ++--- tools/perf/util/evlist.h | 3 +-- 5 files changed, 6 insertions(+), 8 deletions(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a80301797e8..2a43c4423f6 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -475,7 +475,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) if (forks) { err = perf_evlist__prepare_workload(evsel_list, &opts->target, - opts, argv); + argv, opts->pipe_output); if (err < 0) { pr_err("Couldn't run the workload!\n"); goto out_delete_session; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 1de3971437c..3d9944c3d85 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -462,7 +462,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (forks) { err = perf_evlist__prepare_workload(evlist, &trace->opts.target, - &trace->opts, argv); + argv, false); if (err < 0) { printf("Couldn't run the workload!\n"); goto out_delete_evlist; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index adf6b4a21a6..a1c41b7d3c0 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -93,7 +93,7 @@ int test__PERF_RECORD(void) * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts.target, &opts, argv); + err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_maps; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 291884c804e..9a337f091b2 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -746,8 +746,7 @@ out_err: int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, - struct perf_record_opts *opts, - const char *argv[]) + const char *argv[], bool pipe_output) { int child_ready_pipe[2], go_pipe[2]; char bf; @@ -769,7 +768,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, } if (!evlist->workload.pid) { - if (opts->pipe_output) + if (pipe_output) dup2(2, 1); close(child_ready_pipe[0]); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index e089906cb4d..276a5acc56e 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,8 +87,7 @@ void perf_evlist__config(struct perf_evlist *evlist, int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, - struct perf_record_opts *opts, - const char *argv[]); + const char *argv[], bool pipe_output); int perf_evlist__start_workload(struct perf_evlist *evlist); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, -- cgit v1.2.3-70-g09d2 From 55e162ea764cb5b38f27ea0b16ee7d31c1a5aedb Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 11 Mar 2013 16:43:17 +0900 Subject: perf evlist: Add want_signal parameter to perf_evlist__prepare_workload() In case a caller doesn't want to receive SIGUSR1 when the child failed to exec(). Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1362987798-24969-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 3 ++- tools/perf/builtin-trace.c | 2 +- tools/perf/tests/perf-record.c | 3 ++- tools/perf/util/evlist.c | 6 ++++-- tools/perf/util/evlist.h | 3 ++- 5 files changed, 11 insertions(+), 6 deletions(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 2a43c4423f6..80cc3ea0778 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -475,7 +475,8 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv) if (forks) { err = perf_evlist__prepare_workload(evsel_list, &opts->target, - argv, opts->pipe_output); + argv, opts->pipe_output, + true); if (err < 0) { pr_err("Couldn't run the workload!\n"); goto out_delete_session; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 3d9944c3d85..f0c20ef0cd1 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -462,7 +462,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (forks) { err = perf_evlist__prepare_workload(evlist, &trace->opts.target, - argv, false); + argv, false, false); if (err < 0) { printf("Couldn't run the workload!\n"); goto out_delete_evlist; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index a1c41b7d3c0..ffab5a41ff0 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -93,7 +93,8 @@ int test__PERF_RECORD(void) * so that we have time to open the evlist (calling sys_perf_event_open * on all the fds) and then mmap them. */ - err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false); + err = perf_evlist__prepare_workload(evlist, &opts.target, argv, + false, false); if (err < 0) { pr_debug("Couldn't run the workload!\n"); goto out_delete_maps; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9a337f091b2..5b012b8d7a1 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -746,7 +746,8 @@ out_err: int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, - const char *argv[], bool pipe_output) + const char *argv[], bool pipe_output, + bool want_signal) { int child_ready_pipe[2], go_pipe[2]; char bf; @@ -796,7 +797,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, execvp(argv[0], (char **)argv); perror(argv[0]); - kill(getppid(), SIGUSR1); + if (want_signal) + kill(getppid(), SIGUSR1); exit(-1); } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 276a5acc56e..c096da7d6d5 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -87,7 +87,8 @@ void perf_evlist__config(struct perf_evlist *evlist, int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct perf_target *target, - const char *argv[], bool pipe_output); + const char *argv[], bool pipe_output, + bool want_signal); int perf_evlist__start_workload(struct perf_evlist *evlist); int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages, -- cgit v1.2.3-70-g09d2 From 8fa60e1fbaecd2e652abe41f68a934c1759663f3 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 15 Mar 2013 14:48:51 +0900 Subject: perf record: Fixup return path of cmd_record() The error path of calling perf_target__parse_uid wrongly went to out_free_fd. Also add missing evlist cleanup routines. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1363326533-3310-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 80cc3ea0778..9f2344a2c50 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1028,7 +1028,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) ui__error("%s", errbuf); err = -saved_errno; - goto out_free_fd; + goto out_symbol_exit; } err = -ENOMEM; @@ -1059,6 +1059,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) } err = __cmd_record(&record, argc, argv); + + perf_evlist__munmap(evsel_list); + perf_evlist__close(evsel_list); out_free_fd: perf_evlist__delete_maps(evsel_list); out_symbol_exit: -- cgit v1.2.3-70-g09d2 From 62baca8aed636eb10f9274761aa1dcbfd48a7caa Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 19 Mar 2013 18:46:16 +0900 Subject: perf tools: Get rid of redundant _FILE_OFFSET_BITS definition We define it in the Makefile so no need to duplicate it. Signed-off-by: Namhyung Kim Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1363686376-29525-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 -- tools/perf/util/header.c | 2 -- tools/perf/util/session.c | 2 -- tools/perf/util/trace-event-read.c | 2 -- tools/perf/util/util.h | 2 -- 5 files changed, 10 deletions(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 9f2344a2c50..78a41fdbe56 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -5,8 +5,6 @@ * (or a CPU, or a PID) into the perf.data output file - for * later analysis via perf report. */ -#define _FILE_OFFSET_BITS 64 - #include "builtin.h" #include "perf.h" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index a9b7349f7c5..79e48c72693 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1,5 +1,3 @@ -#define _FILE_OFFSET_BITS 64 - #include "util.h" #include #include diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ab265c2cfab..c8ba120b0db 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1,5 +1,3 @@ -#define _FILE_OFFSET_BITS 64 - #include #include diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c index 7cb24635adf..8c8181aa286 100644 --- a/tools/perf/util/trace-event-read.c +++ b/tools/perf/util/trace-event-read.c @@ -18,8 +18,6 @@ * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -#define _FILE_OFFSET_BITS 64 - #include #include #include diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 6a0781c3a57..a45710b70a5 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -1,8 +1,6 @@ #ifndef GIT_COMPAT_UTIL_H #define GIT_COMPAT_UTIL_H -#define _FILE_OFFSET_BITS 64 - #ifndef FLEX_ARRAY /* * See if our compiler is known to support flexible array members. -- cgit v1.2.3-70-g09d2 From 05484298cbfebbf8c8c55b000541a245bc286bec Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 24 Jan 2013 16:10:29 +0100 Subject: perf tools: Add support for weight v7 (modified) perf record has a new option -W that enables weightened sampling. Add sorting support in top/report for the average weight per sample and the total weight sum. This allows to both compare relative cost per event and the total cost over the measurement period. Add the necessary glue to perf report, record and the library. v2: Merge with new hist refactoring. v3: Fix manpage. Remove value check. Rename global_weight to weight and weight to local_weight. v4: Readd sort keys to manpage v5: Move weight to end v6: Move weight to template v7: Rename weight key. Original patch from Andi modified by Stephane Eranian to include ONLY the weight supporting code and apply to pristine 3.8.0-rc4. Signed-off-by: Andi Kleen Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1359040242-8269-6-git-send-email-eranian@google.com [ committer note: changed to cope with fc5871ed and the hists_link perf test entry ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 6 +++++ tools/perf/Documentation/perf-report.txt | 2 +- tools/perf/Documentation/perf-top.txt | 2 +- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-diff.c | 7 ++--- tools/perf/builtin-record.c | 2 ++ tools/perf/builtin-report.c | 8 +++--- tools/perf/builtin-top.c | 5 ++-- tools/perf/perf.h | 1 + tools/perf/tests/hists_link.c | 4 +-- tools/perf/util/event.h | 1 + tools/perf/util/evsel.c | 10 +++++++ tools/perf/util/hist.c | 23 +++++++++++----- tools/perf/util/hist.h | 8 ++++-- tools/perf/util/session.c | 3 +++ tools/perf/util/sort.c | 45 ++++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 3 +++ 17 files changed, 110 insertions(+), 22 deletions(-) (limited to 'tools/perf/builtin-record.c') diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 938e8904f64..d4da111ef53 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -182,6 +182,12 @@ is enabled for all the sampling events. The sampled branch type is the same for The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. +-W:: +--weight:: +Enable weightened sampling. An additional weight is recorded per sample and can be +displayed with the weight and local_weight sort keys. This currently works for TSX +abort events and some memory events in precise mode on modern Intel CPUs. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 71f15510ca0..7d5f4f38aa5 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -59,7 +59,7 @@ OPTIONS --sort=:: Sort histogram entries by given key(s) - multiple keys can be specified in CSV format. Following sort keys are available: - pid, comm, dso, symbol, parent, cpu, srcline. + pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight. Each key has following meaning: diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index a414bc95fd5..9f1a2fe5475 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -112,7 +112,7 @@ Default is to monitor all CPUS. -s:: --sort:: - Sort by key(s): pid, comm, dso, symbol, parent, srcline. + Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight. -n:: --show-nr-samples:: diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index ae36f3cb541..db491e9a812 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -63,7 +63,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(&evsel->hists, al, NULL, 1); + he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index d207a97a2db..2d0462d89a9 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -231,9 +231,10 @@ int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair, } static int hists__add_entry(struct hists *self, - struct addr_location *al, u64 period) + struct addr_location *al, u64 period, + u64 weight) { - if (__hists__add_entry(self, al, NULL, period) != NULL) + if (__hists__add_entry(self, al, NULL, period, weight) != NULL) return 0; return -ENOMEM; } @@ -255,7 +256,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, if (al.filtered) return 0; - if (hists__add_entry(&evsel->hists, &al, sample->period)) { + if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) { pr_warning("problem incrementing symbol period, skipping event\n"); return -1; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 78a41fdbe56..cdf58ecc04b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -953,6 +953,8 @@ const struct option record_options[] = { OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack, "branch filter mask", "branch stack filter modes", parse_branch_stack), + OPT_BOOLEAN('W', "weight", &record.opts.sample_weight, + "sample by weight (on special events only)"), OPT_END() }; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b5ea26cc7eb..e31f070abe2 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -98,7 +98,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool, * and not events sampled. Thus we use a pseudo period of 1. */ he = __hists__add_branch_entry(&evsel->hists, al, parent, - &bi[i], 1); + &bi[i], 1, 1); if (he) { struct annotation *notes; err = -ENOMEM; @@ -156,7 +156,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel, return err; } - he = __hists__add_entry(&evsel->hists, al, parent, sample->period); + he = __hists__add_entry(&evsel->hists, al, parent, sample->period, + sample->weight); if (he == NULL) return -ENOMEM; @@ -644,7 +645,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline," - " dso_to, dso_from, symbol_to, symbol_from, mispredict"), + " dso_to, dso_from, symbol_to, symbol_from, mispredict," + " weight, local_weight"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b5520ad0dbb..67bdb9f14ad 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -251,7 +251,8 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel, { struct hist_entry *he; - he = __hists__add_entry(&evsel->hists, al, NULL, sample->period); + he = __hists__add_entry(&evsel->hists, al, NULL, sample->period, + sample->weight); if (he == NULL) return NULL; @@ -1088,7 +1089,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", - "sort by key(s): pid, comm, dso, symbol, parent"), + "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"), OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples, "Show a column with the number of samples"), OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 74659ecf93e..32bd102c32b 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -218,6 +218,7 @@ struct perf_record_opts { bool pipe_output; bool raw_samples; bool sample_address; + bool sample_weight; bool sample_time; bool period; unsigned int freq; diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index e0c0267858a..89085a9615e 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -223,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample, 0) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); if (he == NULL) goto out; @@ -247,7 +247,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) &sample, 0) < 0) goto out; - he = __hists__add_entry(&evsel->hists, &al, NULL, 1); + he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1); if (he == NULL) goto out; diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 0d573ff4771..a97fbbe6b3b 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -88,6 +88,7 @@ struct perf_sample { u64 id; u64 stream_id; u64 period; + u64 weight; u32 cpu; u32 raw_size; void *raw_data; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1adb824610f..23061a6ccd7 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -563,6 +563,9 @@ void perf_evsel__config(struct perf_evsel *evsel, attr->branch_sample_type = opts->branch_stack; } + if (opts->sample_weight) + attr->sample_type |= PERF_SAMPLE_WEIGHT; + attr->mmap = track; attr->comm = track; @@ -1017,6 +1020,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = 1; + data->weight = 0; if (event->header.type != PERF_RECORD_SAMPLE) { if (!evsel->attr.sample_id_all) @@ -1167,6 +1171,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, } } + data->weight = 0; + if (type & PERF_SAMPLE_WEIGHT) { + data->weight = *array; + array++; + } + return 0; } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index f855941bebe..97ddd18acd7 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -155,9 +155,11 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he, } } -static void he_stat__add_period(struct he_stat *he_stat, u64 period) +static void he_stat__add_period(struct he_stat *he_stat, u64 period, + u64 weight) { he_stat->period += period; + he_stat->weight += weight; he_stat->nr_events += 1; } @@ -169,12 +171,14 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src) dest->period_guest_sys += src->period_guest_sys; dest->period_guest_us += src->period_guest_us; dest->nr_events += src->nr_events; + dest->weight += src->weight; } static void hist_entry__decay(struct hist_entry *he) { he->stat.period = (he->stat.period * 7) / 8; he->stat.nr_events = (he->stat.nr_events * 7) / 8; + /* XXX need decay for weight too? */ } static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) @@ -282,7 +286,8 @@ static u8 symbol__parent_filter(const struct symbol *parent) static struct hist_entry *add_hist_entry(struct hists *hists, struct hist_entry *entry, struct addr_location *al, - u64 period) + u64 period, + u64 weight) { struct rb_node **p; struct rb_node *parent = NULL; @@ -306,7 +311,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists, cmp = hist_entry__cmp(he, entry); if (!cmp) { - he_stat__add_period(&he->stat, period); + he_stat__add_period(&he->stat, period, weight); /* If the map of an existing hist_entry has * become out-of-date due to an exec() or @@ -345,7 +350,8 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, struct addr_location *al, struct symbol *sym_parent, struct branch_info *bi, - u64 period) + u64 period, + u64 weight) { struct hist_entry entry = { .thread = al->thread, @@ -359,6 +365,7 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, .stat = { .period = period, .nr_events = 1, + .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), @@ -366,12 +373,13 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, .hists = self, }; - return add_hist_entry(self, &entry, al, period); + return add_hist_entry(self, &entry, al, period, weight); } struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *sym_parent, u64 period) + struct symbol *sym_parent, u64 period, + u64 weight) { struct hist_entry entry = { .thread = al->thread, @@ -385,13 +393,14 @@ struct hist_entry *__hists__add_entry(struct hists *self, .stat = { .period = period, .nr_events = 1, + .weight = weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent), .hists = self, }; - return add_hist_entry(self, &entry, al, period); + return add_hist_entry(self, &entry, al, period, weight); } int64_t diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 848331377bd..121cc14b604 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -49,6 +49,8 @@ enum hist_column { HISTC_DSO_FROM, HISTC_DSO_TO, HISTC_SRCLINE, + HISTC_LOCAL_WEIGHT, + HISTC_GLOBAL_WEIGHT, HISTC_NR_COLS, /* Last entry */ }; @@ -73,7 +75,8 @@ struct hists { struct hist_entry *__hists__add_entry(struct hists *self, struct addr_location *al, - struct symbol *parent, u64 period); + struct symbol *parent, u64 period, + u64 weight); int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right); int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right); int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size, @@ -84,7 +87,8 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, struct addr_location *al, struct symbol *sym_parent, struct branch_info *bi, - u64 period); + u64 period, + u64 weight); void hists__output_resort(struct hists *self); void hists__output_resort_threaded(struct hists *hists); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c8ba120b0db..627be09b479 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -798,6 +798,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, if (sample_type & PERF_SAMPLE_STACK_USER) stack_user__printf(&sample->user_stack); + + if (sample_type & PERF_SAMPLE_WEIGHT) + printf("... weight: %" PRIu64 "\n", sample->weight); } static struct machine * diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index d41926cb9e3..d66bcd33248 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -464,6 +464,49 @@ struct sort_entry sort_mispredict = { .se_width_idx = HISTC_MISPREDICT, }; +static u64 he_weight(struct hist_entry *he) +{ + return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0; +} + +static int64_t +sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return he_weight(left) - he_weight(right); +} + +static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self)); +} + +struct sort_entry sort_local_weight = { + .se_header = "Local Weight", + .se_cmp = sort__local_weight_cmp, + .se_snprintf = hist_entry__local_weight_snprintf, + .se_width_idx = HISTC_LOCAL_WEIGHT, +}; + +static int64_t +sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right) +{ + return left->stat.weight - right->stat.weight; +} + +static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight); +} + +struct sort_entry sort_global_weight = { + .se_header = "Weight", + .se_cmp = sort__global_weight_cmp, + .se_snprintf = hist_entry__global_weight_snprintf, + .se_width_idx = HISTC_GLOBAL_WEIGHT, +}; + struct sort_dimension { const char *name; struct sort_entry *entry; @@ -480,6 +523,8 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_SRCLINE, "srcline", sort_srcline), + DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), + DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index b13e56f6ccb..39392501279 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -49,6 +49,7 @@ struct he_stat { u64 period_us; u64 period_guest_sys; u64 period_guest_us; + u64 weight; u32 nr_events; }; @@ -130,6 +131,8 @@ enum sort_type { SORT_PARENT, SORT_CPU, SORT_SRCLINE, + SORT_LOCAL_WEIGHT, + SORT_GLOBAL_WEIGHT, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, -- cgit v1.2.3-70-g09d2