From e5bed564485b340d87f2d8945643a393e55b8225 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Sep 2015 10:45:24 +0900 Subject: [PATCH 01/10] perf record: Allocate area for sample_id_hdr in a synthesized comm event A previous patch added a synthesized comm event for forked child process but it missed that the event should contain area for sample_id_hdr at the end. It worked by accident since the perf_event union contains bigger event structs like mmap_events. This patch fixes it by dynamically allocating event struct including those area like in perf_event__synthesize_thread_map(). Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1443577526-3240-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index a01c8ae1ee07..5e01c070dbf2 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -637,17 +637,25 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * Let the child rip */ if (forks) { - union perf_event event; + union perf_event *event; + + event = malloc(sizeof(event->comm) + machine->id_hdr_size); + if (event == NULL) { + err = -ENOMEM; + goto out_child; + } + /* * Some H/W events are generated before COMM event * which is emitted during exec(), so perf script * cannot see a correct process name for those events. * Synthesize COMM event to prevent it. */ - perf_event__synthesize_comm(tool, &event, + perf_event__synthesize_comm(tool, event, rec->evlist->workload.pid, process_synthesized_event, machine); + free(event); perf_evlist__start_workload(rec->evlist); } From 4b37af595742977f1bdd8c0fd0f3e6e55b36e7b7 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Sep 2015 10:45:25 +0900 Subject: [PATCH 02/10] perf top: Fix unresolved comm when -s comm is used The perf top uses 'dso,symbol' sort keys by default so it overlooked a problem in task's comm resolving. When the sort key contains 'comm', some task's comm is not shown properly. This is because the perf_top__mmap_read_idx() checks the cpumode value improperly. The cpumode value of non-sample events are 0 (PERF_RECORD_MISC_CPUMODE_ UNKNOWN) so the events will be ignored by the switch statement. This patch allows it for non-sample events. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1443577526-3240-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 38d4d6cac823..ae4c6420300b 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -857,9 +857,12 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx) * TODO: we don't process guest user from host side * except simple counting. */ - /* Fall thru */ - default: goto next_event; + default: + if (event->header.type == PERF_RECORD_SAMPLE) + goto next_event; + machine = &session->machines.host; + break; } From c53d138d41a7f33cf085762c64b4b61e8d223e1c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Sep 2015 10:45:26 +0900 Subject: [PATCH 03/10] perf top: Register idle thread The perf top didn't add the idle/swapper thread to the machine's thread list and its comm was displayed as ':0'. Fix it. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1443577526-3240-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 3 +++ tools/perf/util/session.c | 2 +- tools/perf/util/session.h | 2 ++ 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index ae4c6420300b..6f641fd68296 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -964,6 +964,9 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; + if (perf_session__register_idle_thread(top->session) == NULL) + goto out_delete; + machine__synthesize_threads(&top->session->machines.host, &opts->target, top->evlist->threads, false, opts->proc_map_timeout); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 84a02eae4394..428149bc64d2 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1311,7 +1311,7 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) return machine__findnew_thread(&session->machines.host, -1, pid); } -static struct thread *perf_session__register_idle_thread(struct perf_session *session) +struct thread *perf_session__register_idle_thread(struct perf_session *session) { struct thread *thread; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index b44afc75d1cc..3e900c0efc73 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -89,6 +89,8 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_ } struct thread *perf_session__findnew(struct perf_session *session, pid_t pid); +struct thread *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); From 208e7607459477432d3df52c32d4b961a96d4a94 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 30 Sep 2015 13:34:00 +0900 Subject: [PATCH 04/10] perf report: Fix a bug on "--call-graph none" option The patch f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event") added an ability to enable/disable callchain recording per event. But it had a problem when the enablement setting is changed at 'perf report' time using -g/--call-graph option. For example, the following scenario will get a segfault. $ perf record -ag sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.500 MB perf.data (2555 samples) ] $ perf report -g none perf: Segmentation fault -------- backtrace -------- perf[0x53a98a] /usr/lib/libc.so.6(+0x335af)[0x7f4e91df95af] This is because callchain_param.sort() callback was not set but it tried to call the function as it had the PERF_SAMPLE_CALLCHAIN bit. Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Fixes: f9db0d0f1b2c ("perf callchain: Allow disabling call graphs per event") Link: http://lkml.kernel.org/r/1443587640-24242-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0cad9e07c5b4..c346b331b892 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1151,7 +1151,7 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog) struct perf_evsel *evsel = hists_to_evsel(hists); bool use_callchain; - if (evsel && !symbol_conf.show_ref_callgraph) + if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph) use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN; else use_callchain = symbol_conf.use_callchain; From 0edd453368c6b9cdb756bde2b6675bb0d5d0eb0a Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:48 +0300 Subject: [PATCH 05/10] perf callchain: Allow for max_stack greater than PERF_MAX_STACK_DEPTH Adjust the validation to allow for max_stack greater than PERF_MAX_STACK_DEPTH. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-18-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 76fe167c359e..5ef90be2a249 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1831,7 +1831,7 @@ static int thread__resolve_callchain_sample(struct thread *thread, } check_calls: - if (chain->nr > PERF_MAX_STACK_DEPTH) { + if (chain->nr > PERF_MAX_STACK_DEPTH && (int)chain->nr > max_stack) { pr_warning("corrupted callchain. skipping...\n"); return 0; } From dbc67409fa912ba063dfa956af0543af1258fc97 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Oct 2015 12:12:22 -0300 Subject: [PATCH 06/10] perf list: Do event name substring search as last resort when no events found Before: # perf list _alloc_ | head -10 # After: # perf list _alloc_ | head -10 ext4:ext4_alloc_da_blocks [Tracepoint event] ext4:ext4_get_implied_cluster_alloc_exit [Tracepoint event] kmem:kmem_cache_alloc_node [Tracepoint event] kmem:mm_page_alloc_extfrag [Tracepoint event] kmem:mm_page_alloc_zone_locked [Tracepoint event] xen:xen_mmu_alloc_ptpage [Tracepoint event] # And it works for all types of events: # perf list br List of pre-defined events (to be used in -e): branch-instructions OR branches [Hardware event] branch-misses [Hardware event] branch-load-misses [Hardware cache event] branch-loads [Hardware cache event] branch-instructions OR cpu/branch-instructions/ [Kernel PMU event] branch-misses OR cpu/branch-misses/ [Kernel PMU event] filelock:break_lease_block [Tracepoint event] filelock:break_lease_noblock [Tracepoint event] filelock:break_lease_unblock [Tracepoint event] syscalls:sys_enter_brk [Tracepoint event] syscalls:sys_exit_brk [Tracepoint event] # Suggested-by: Ingo Molnar Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-qieivl18jdemoaghgndj36e6@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-list.txt | 2 ++ tools/perf/builtin-list.c | 18 ++++++++++++++++-- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index bada8933fdd4..ad60c6ea1997 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -125,6 +125,8 @@ To limit the list use: . If none of the above is matched, it will apply the supplied glob to all events, printing the ones that match. +. As a last resort, it will do a substring search in all event names. + One or more types can be used at the same time, listing the events for the types specified. diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 602414040344..bf679e2c978b 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -45,6 +45,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) } for (i = 0; i < argc; ++i) { + char *sep, *s; + if (strcmp(argv[i], "tracepoint") == 0) print_tracepoint_events(NULL, NULL, raw_dump); else if (strcmp(argv[i], "hw") == 0 || @@ -60,8 +62,7 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) print_hwcache_events(NULL, raw_dump); else if (strcmp(argv[i], "pmu") == 0) print_pmu_events(NULL, raw_dump); - else { - char *sep = strchr(argv[i], ':'), *s; + else if ((sep = strchr(argv[i], ':')) != NULL) { int sep_idx; if (sep == NULL) { @@ -76,6 +77,19 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) s[sep_idx] = '\0'; print_tracepoint_events(s, s + sep_idx + 1, raw_dump); free(s); + } else { + if (asprintf(&s, "*%s*", argv[i]) < 0) { + printf("Critical: Not enough memory! Trying to continue...\n"); + continue; + } + print_symbol_events(s, PERF_TYPE_HARDWARE, + event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump); + print_symbol_events(s, PERF_TYPE_SOFTWARE, + event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump); + print_hwcache_events(s, raw_dump); + print_pmu_events(s, raw_dump); + print_tracepoint_events(NULL, s, raw_dump); + free(s); } } return 0; From fa52ceabc2a3e70431a82bca2bc547a15eaf19df Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 2 Oct 2015 15:28:16 -0300 Subject: [PATCH 07/10] perf list: Honour 'event_glob' whem printing selectable PMUs Some PMUs, like the 'intel_bts' one can be used as an event name, i.e.: $ perf record -e intel_bts:// usleep 1 Is a valid event name. But the code printing such PMUs was not honouring the 'event_glob' parameter, so the following line was always appearing: $ intel_bts// [Kernel PMU event] Fix it: $ [acme@felicio linux]$ perf list data List of pre-defined events (to be used in -e): uncore_imc/data_reads/ [Kernel PMU event] uncore_imc/data_writes/ [Kernel PMU event] $ Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-ajb71858n7q7ao77b8pyy74w@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 41a356ba3cfe..e4b173dec4b9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1008,7 +1008,8 @@ void print_pmu_events(const char *event_glob, bool name_only) goto out_enomem; j++; } - if (pmu->selectable) { + if (pmu->selectable && + (event_glob == NULL || strglobmatch(pmu->name, event_glob))) { char *s; if (asprintf(&s, "%s//", pmu->name) < 0) goto out_enomem; From 1a8ac29cbffc261f6d7c92e573878110a7dcbd94 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 2 Oct 2015 21:58:32 +0900 Subject: [PATCH 08/10] perf probe: Allow probing on kmodules without dwarf Allow probing on kernel modules when 'perf' is built without debuginfo support. Currently perf-probe --module requires linking with libdw, but this doesn't make sense. E.g. ---- # make NO_DWARF=1 # ./perf probe -m pcspkr pcspkr_event%return Error: unknown switch `m' ---- With this patch ---- # ./perf probe -m pcspkr pcspkr_event%return Added new event: probe:pcspkr_event (on pcspkr_event%return in pcspkr) You can now use it in all perf tools, such as: perf record -e probe:pcspkr_event -aR sleep 1 ---- Signed-off-by: Masami Hiramatsu Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/r/20151002125832.18617.78721.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-probe.c | 8 +++----- tools/perf/util/probe-event.c | 8 +++++--- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index f7882ae9ebc6..530c3a28a58c 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -182,10 +182,8 @@ static int opt_set_target(const struct option *opt, const char *str, if (str) { if (!strcmp(opt->long_name, "exec")) params.uprobes = true; -#ifdef HAVE_DWARF_SUPPORT else if (!strcmp(opt->long_name, "module")) params.uprobes = false; -#endif else return ret; @@ -490,9 +488,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) "file", "vmlinux pathname"), OPT_STRING('s', "source", &symbol_conf.source_prefix, "directory", "path to kernel source"), - OPT_CALLBACK('m', "module", NULL, "modname|path", - "target module name (for online) or path (for offline)", - opt_set_target), OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines, "Don't search inlined functions"), #endif @@ -509,6 +504,9 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) opt_set_filter), OPT_CALLBACK('x', "exec", NULL, "executable|path", "target executable name or path", opt_set_target), + OPT_CALLBACK('m', "module", NULL, "modname|path", + "target module name (for online) or path (for offline)", + opt_set_target), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Enable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 3010abc071ff..b51a8bfb40f9 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2543,7 +2543,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, goto out; } - if (!pev->uprobes && !pp->retprobe) { + /* Note that the symbols in the kmodule are not relocated */ + if (!pev->uprobes && !pp->retprobe && !pev->target) { reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -2580,8 +2581,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, } /* Add one probe point */ tp->address = map->unmap_ip(map, sym->start) + pp->offset; - /* If we found a wrong one, mark it by NULL symbol */ - if (!pev->uprobes && + + /* Check the kprobe (not in module) is within .text */ + if (!pev->uprobes && !pev->target && kprobe_warn_out_range(sym->name, tp->address)) { tp->symbol = NULL; /* Skip it */ skipped++; From 9f065194e2a505bb6fd23946b410a0036e9de2ca Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 29 Sep 2015 14:49:43 -0700 Subject: [PATCH 09/10] perf record: Change 'record.samples' type to unsigned long long When run "perf record -e", the number of samples showed up is wrong on some 32 bit systems, i.e. powerpc and arm. For example, run the below commands on 32 bit powerpc: perf probe -x /lib/libc.so.6 malloc perf record -e probe_libc:malloc -a ls perf.data [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.036 MB perf.data (13829241621624967218 samples) ] Actually, "perf script" just shows 21 samples. The number of samples is also absurd since samples is long type, but it is printed as PRIu64. Build test ran on x86-64, x86, aarch64, arm, mips, ppc and ppc64. Signed-off-by: Yang Shi Cc: linaro-kernel@lists.linaro.org Link: http://lkml.kernel.org/r/1443563383-4064-1-git-send-email-yang.shi@linaro.org [ Bumped the 'hits' var used together with record.samples to 'unsigned long long' too ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 5e01c070dbf2..24ace2f318c1 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -49,7 +49,7 @@ struct record { int realtime_prio; bool no_buildid; bool no_buildid_cache; - long samples; + unsigned long long samples; }; static int record__write(struct record *rec, void *bf, size_t size) @@ -667,7 +667,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) auxtrace_snapshot_enabled = 1; for (;;) { - int hits = rec->samples; + unsigned long long hits = rec->samples; if (record__mmap_read_all(rec) < 0) { auxtrace_snapshot_enabled = 0; From 19afd10410957b1c808c2c49a88e6dd8b23aa894 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 2 Oct 2015 05:04:34 -0400 Subject: [PATCH 10/10] perf stat: Reduce min --interval-print to 10ms The --interval-print parameter was limited to 100ms. However, for example, 10ms is required to do sophisticated bandwidth analysis using uncore events. The test shows that the overhead of the system-wide uncore monitoring with 10ms interval is only ~2%. So this patch reduces the minimal interval-print allowd to 10ms. But 10ms may not work well for all cases. For example, when the cpus/threads number is very large, for system-wide core event monitoring the overhead could be high. To handle this issue, a warning will be displayed when the interval-print is set between 10ms to 100ms. So users can make a decision according to their specific cases. # perf stat -e uncore_imc_1/cas_count_read/ -a --interval-print 10 -- sleep 1 print interval < 100ms. The overhead percentage could be high in some cases. Please proceed with caution. # time counts unit events 0.010200451 0.10 MiB uncore_imc_1/cas_count_read/ 0.020475117 0.02 MiB uncore_imc_1/cas_count_read/ 0.030692800 0.01 MiB uncore_imc_1/cas_count_read/ 0.040948161 0.02 MiB uncore_imc_1/cas_count_read/ 0.051159564 0.00 MiB uncore_imc_1/cas_count_read/ Signed-off-by: Kan Liang Acked-by: Jiri Olsa Cc: Andi Kleen Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1443776674-42511-1-git-send-email-kan.liang@intel.com [ Added warning about overhead when using sub 100ms intervals to the man page ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 5 +++-- tools/perf/builtin-stat.c | 13 +++++++++---- 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 47469abdcc1c..4e074a660826 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -128,8 +128,9 @@ perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- m -I msecs:: --interval-print msecs:: - Print count deltas every N milliseconds (minimum: 100ms) - example: perf stat -I 1000 -e cycles -a sleep 5 +Print count deltas every N milliseconds (minimum: 10ms) +The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution. + example: 'perf stat -I 1000 -e cycles -a sleep 5' --per-socket:: Aggregate counts per processor socket for system-wide mode measurements. This diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a96fb5c3bedb..5ef88f760b12 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1179,7 +1179,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING(0, "post", &post_cmd, "command", "command to run after to the measured command"), OPT_UINTEGER('I', "interval-print", &stat_config.interval, - "print counts at regular interval in ms (>= 100)"), + "print counts at regular interval in ms (>= 10)"), OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, @@ -1332,9 +1332,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) thread_map__read_comms(evsel_list->threads); if (interval && interval < 100) { - pr_err("print interval must be >= 100ms\n"); - parse_options_usage(stat_usage, options, "I", 1); - goto out; + if (interval < 10) { + pr_err("print interval must be >= 10ms\n"); + parse_options_usage(stat_usage, options, "I", 1); + goto out; + } else + pr_warning("print interval < 100ms. " + "The overhead percentage could be high in some cases. " + "Please proceed with caution.\n"); } if (perf_evlist__alloc_stats(evsel_list, interval))