From f382842fa0244ae1e2c28c8377732c85ec1fe7a9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 25 Mar 2020 21:45:35 +0900 Subject: perf top: Add --all-cgroups option The --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that 'perf top' can identify task/cgroup association later. Committer testing: Use: # perf top --all-cgroups -s cgroup_id,cgroup,pid Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200325124536.2800725-9-namhyung@kernel.org Link: http://lore.kernel.org/lkml/20200402015249.3800462-1-namhyung@kernel.org [ Extracted the HAVE_FILE_HANDLE from the followup patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'tools/perf/builtin-top.c') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d2539b793f9d..02ea2cf2a3d9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1246,6 +1246,14 @@ static int __cmd_top(struct perf_top *top) if (opts->record_namespaces) top->tool.namespace_events = true; + if (opts->record_cgroup) { +#ifdef HAVE_FILE_HANDLE + top->tool.cgroup_events = true; +#else + pr_err("cgroup tracking is not supported.\n"); + return -1; +#endif + } ret = perf_event__synthesize_bpf_events(top->session, perf_event__process, &top->session->machines.host, @@ -1253,6 +1261,11 @@ static int __cmd_top(struct perf_top *top) if (ret < 0) pr_debug("Couldn't synthesize BPF events: Pre-existing BPF programs won't have symbols resolved.\n"); + ret = perf_event__synthesize_cgroups(&top->tool, perf_event__process, + &top->session->machines.host); + if (ret < 0) + pr_debug("Couldn't synthesize cgroup events.\n"); + machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->core.threads, false, top->nr_threads_synthesize); @@ -1545,6 +1558,8 @@ int cmd_top(int argc, const char **argv) "number of thread to run event synthesize"), OPT_BOOLEAN(0, "namespaces", &opts->record_namespaces, "Record namespaces events"), + OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup, + "Record cgroup events"), OPTS_EVSWITCH(&top.evswitch), OPT_END() }; -- cgit v1.2.3 From df7deb2cceef0546ab2115702da3421b7c61a8c0 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 25 Mar 2020 06:07:10 +0800 Subject: perf top: Support --group-sort-idx to change the sort order 'perf report' supports the option --group-sort-idx, which sorts the output by the event at the index n in event group. For example: perf record -e cycles,instructions,cache-misses perf report --group --group-sort-idx 2 --stdio The perf-report output is sorted by cache-misses. This patch supports --group-sort-idx in perf-top. For example: perf top --group -e cycles,instructions,cache-misses --group-sort-idx 2 The perf-top output is sorted by cache-misses. Signed-off-by: Jin Yao Suggested-by: Arnaldo Carvalho de Melo Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200324220711.6025-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-top.txt | 5 +++++ tools/perf/builtin-top.c | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'tools/perf/builtin-top.c') diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index ddab103af8c7..487737a725e9 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -53,6 +53,11 @@ Default is to monitor all CPUS. --group:: Put the counters into a counter group. +--group-sort-idx:: + Sort the output by the event at the index n in group. If n is invalid, + sort by the first event. It can support multiple groups with different + amount of events. WARNING: This should be used on grouped events. + -F :: --freq=:: Profile at this frequency. Use 'max' to use the currently maximum diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 02ea2cf2a3d9..9ff7943d2014 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1560,6 +1560,10 @@ int cmd_top(int argc, const char **argv) "Record namespaces events"), OPT_BOOLEAN(0, "all-cgroups", &opts->record_cgroup, "Record cgroup events"), + OPT_INTEGER(0, "group-sort-idx", &symbol_conf.group_sort_idx, + "Sort the output by the event at the index n in group. " + "If n is invalid, sort by the first event. " + "WARNING: should be used on grouped events."), OPTS_EVSWITCH(&top.evswitch), OPT_END() }; -- cgit v1.2.3 From 2605af0f32d1bf434dd6819732c7851a97f5cbc0 Mon Sep 17 00:00:00 2001 From: Jin Yao Date: Wed, 25 Mar 2020 06:07:11 +0800 Subject: perf top: Support hotkey to change sort order It would be nice if we can use a hotkey in perf top browser to select a event for sorting. For example: perf top --group -e cycles,instructions,cache-misses Samples Overhead Shared Object Symbol 40.03% 45.71% 0.03% div [.] main 20.46% 14.67% 0.21% libc-2.27.so [.] __random_r 20.01% 19.54% 0.02% libc-2.27.so [.] __random 9.68% 10.68% 0.00% div [.] compute_flag 4.32% 4.70% 0.00% libc-2.27.so [.] rand 3.84% 3.43% 0.00% div [.] rand@plt 0.05% 0.05% 2.33% libc-2.27.so [.] __strcmp_sse2_unaligned 0.04% 0.08% 2.43% perf [.] perf_hpp__is_dynamic_en 0.04% 0.02% 6.64% perf [.] rb_next 0.04% 0.01% 3.87% perf [.] dso__find_symbol 0.04% 0.04% 1.77% perf [.] sort__dso_cmp When user press hotkey '2' (event index, starting from 0), it indicates to sort output by the third event in group (cache-misses). Samples Overhead Shared Object Symbol 4.07% 1.28% 6.68% perf [.] rb_next 3.57% 3.98% 4.11% perf [.] __hists__insert_output 3.67% 11.24% 3.60% perf [.] perf_hpp__is_dynamic_e 3.67% 3.20% 3.20% perf [.] hpp__sort_overhead 0.81% 0.06% 3.01% perf [.] dso__find_symbol 1.62% 5.47% 2.51% perf [.] hists__match 2.70% 1.86% 2.47% libc-2.27.so [.] _int_malloc 0.19% 0.00% 2.29% [kernel] [k] copy_page 0.41% 0.32% 1.98% perf [.] hists__decay_entries 1.84% 3.67% 1.68% perf [.] sort__dso_cmp 0.16% 0.00% 1.63% [kernel] [k] clear_page_erms Now the output is sorted by cache-misses. v2: --- Zero the history if hotkey is pressed. Signed-off-by: Jin Yao Suggested-by: Arnaldo Carvalho de Melo Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Andi Kleen Cc: Jin Yao Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20200324220711.6025-2-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-top.c') diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9ff7943d2014..289cf83e658a 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -616,6 +616,7 @@ static void *display_thread_tui(void *arg) .arg = top, .refresh = top->delay_secs, }; + int ret; /* In order to read symbols from other namespaces perf to needs to call * setns(2). This isn't permitted if the struct_fs has multiple users. @@ -626,6 +627,7 @@ static void *display_thread_tui(void *arg) prctl(PR_SET_NAME, "perf-top-UI", 0, 0, 0); +repeat: perf_top__sort_new_samples(top); /* @@ -638,13 +640,18 @@ static void *display_thread_tui(void *arg) hists->uid_filter_str = top->record_opts.target.uid_str; } - perf_evlist__tui_browse_hists(top->evlist, help, &hbt, + ret = perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent, &top->session->header.env, !top->record_opts.overwrite, &top->annotation_opts); - stop_top(); + if (ret == K_RELOAD) { + top->zero = true; + goto repeat; + } else + stop_top(); + return NULL; } -- cgit v1.2.3