From: Waiman Long Date: Fri, 18 Oct 2013 14:38:49 +0000 (-0400) Subject: perf top: Add --max-stack option to limit callchain stack scan X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=5dbb6e81d85e55ee2b4cf523c1738e16f63e5400;p=openwrt%2Fstaging%2Fblogic.git perf top: Add --max-stack option to limit callchain stack scan When the callgraph function is enabled (-G), it may take a long time to scan all the stack data and merge them accordingly. This patch adds a new --max-stack option to perf-top to limit the depth of callchain stack data to look at to reduce the time it takes for perf-top to finish its processing. It reduces the amount of information provided to the user in exchange for faster speed. Signed-off-by: Waiman Long Acked-by: David Ahern Tested-by: Davidlohr Bueso Cc: Adrian Hunter Cc: Aswin Chandramouleeswaran Cc: David Ahern Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Scott J Norton Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1382107129-2010-5-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo --- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index f65777c1f723..c16a09e2f182 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -158,6 +158,14 @@ Default is to monitor all CPUS. Default: fractal,0.5,callee. +--max-stack:: + Set the stack depth limit when parsing the callchain, anything + beyond the specified depth will be ignored. This is a trade-off + between information loss and faster processing especially for + workloads that can have a very long callchain stack. + + Default: 127 + --ignore-callees=:: Ignore callees of the function(s) matching the given regex. This has the effect of collecting the callers of each such diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 112cb7d68e64..386d83324a8d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -771,7 +771,7 @@ static void perf_event__process_sample(struct perf_tool *tool, err = machine__resolve_callchain(machine, evsel, al.thread, sample, &parent, &al, - PERF_MAX_STACK_DEPTH); + top->max_stack); if (err) return; } @@ -1048,10 +1048,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, .freq = 4000, /* 4 KHz */ - .target = { + .target = { .uses_mmap = true, }, }, + .max_stack = PERF_MAX_STACK_DEPTH, .sym_pcnt_filter = 5, }; struct perf_record_opts *opts = &top.record_opts; @@ -1110,6 +1111,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts, "mode[,dump_size]", record_callchain_help, &parse_callchain_opt, "fp"), + OPT_INTEGER(0, "max-stack", &top.max_stack, + "Set the maximum stack depth when parsing the callchain. " + "Default: " __stringify(PERF_MAX_STACK_DEPTH)), OPT_CALLBACK(0, "ignore-callees", NULL, "regex", "ignore callees of these functions in call graphs", report_parse_ignore_callees_opt), diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h index b554ffc462b6..88cfeaff600b 100644 --- a/tools/perf/util/top.h +++ b/tools/perf/util/top.h @@ -24,6 +24,7 @@ struct perf_top { u64 exact_samples; u64 guest_us_samples, guest_kernel_samples; int print_entries, count_filter, delay_secs; + int max_stack; bool hide_kernel_symbols, hide_user_symbols, zero; bool use_tui, use_stdio; bool kptr_restrict_warned;