From 21394d948a0c7c451d4a4d68afed9a06c4969636 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 4 Sep 2015 10:45:44 -0400 Subject: perf report: Introduce --socket-filter option Introduce --socket-filter option for 'perf report' to only show entries for a processor socket that match this filter. $ perf report --socket-filter 1 --stdio # To display the perf.data header info, please use --header/--header-only options. # # Total Lost Samples: 0 # # Samples: 752 of event 'cycles' # Event count (approx.): 350995599 # Processor Socket: 1 # # Overhead Command Shared Object Symbol # ........ ......... ................ ................................. # 97.02% test test [.] plusB_c 0.97% test test [.] plusA_c 0.23% swapper [kernel.vmlinux] [k] acpi_idle_do_entry 0.09% rcu_sched [kernel.vmlinux] [k] dyntick_save_progress_counter 0.01% swapper [kernel.vmlinux] [k] task_waking_fair 0.00% swapper [kernel.vmlinux] [k] run_timer_softirq Signed-off-by: Kan Liang Cc: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1441377946-44429-3-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 62b285e32aa5..9b5083630a56 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -62,6 +62,7 @@ struct report { float min_percent; u64 nr_entries; u64 queue_size; + int socket_filter; DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; @@ -286,6 +287,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report struct perf_evsel *evsel = hists_to_evsel(hists); char buf[512]; size_t size = sizeof(buf); + int socket = hists->socket_filter; if (symbol_conf.filter_relative) { nr_samples = hists->stats.nr_non_filtered_samples; @@ -326,6 +328,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report ret += fprintf(fp, "\n# Sort order : %s", sort_order ? : default_mem_sort_order); } else ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); + + if (socket > -1) + ret += fprintf(fp, "\n# Processor Socket: %d", socket); + return ret + fprintf(fp, "\n#\n"); } @@ -450,6 +456,8 @@ static void report__collapse_hists(struct report *rep) if (pos->idx == 0) hists->symbol_filter_str = rep->symbol_filter_str; + hists->socket_filter = rep->socket_filter; + hists__collapse_resort(hists, &prog); /* Non-group events are considered as leader */ @@ -635,6 +643,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) }, .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", + .socket_filter = -1, }; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", @@ -747,6 +756,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Show full source file name path for source lines"), OPT_BOOLEAN(0, "show-ref-call-graph", &symbol_conf.show_ref_callgraph, "Show callgraph from reference event"), + OPT_INTEGER(0, "socket-filter", &report.socket_filter, + "only show processor socket that match with this filter"), OPT_END() }; struct perf_data_file file = { -- cgit From 84734b06b63093cd44533f4caa43d4452fb11ec3 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 4 Sep 2015 10:45:45 -0400 Subject: perf hists browser: Zoom in/out for processor socket Currently, users can zoom in/out for threads and dso in 'perf top' and 'perf report'. This patch extends it for the processor sockets. 'S' is the short key to zoom into current Processor Socket. Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1441377946-44429-4-git-send-email-kan.liang@intel.com [ - Made it elide the Socket column when zooming into it, just like with the other zoom ops; - Make it use browser->pstack, to unzoom level by level; - Rename 'socket' variables to 'socket_id' to make it build on older systems where it shadows a global glibc declaration ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 9b5083630a56..e4e3f1432622 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -287,7 +287,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report struct perf_evsel *evsel = hists_to_evsel(hists); char buf[512]; size_t size = sizeof(buf); - int socket = hists->socket_filter; + int socked_id = hists->socket_filter; if (symbol_conf.filter_relative) { nr_samples = hists->stats.nr_non_filtered_samples; @@ -329,8 +329,8 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report } else ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); - if (socket > -1) - ret += fprintf(fp, "\n# Processor Socket: %d", socket); + if (socked_id > -1) + ret += fprintf(fp, "\n# Processor Socket: %d", socked_id); return ret + fprintf(fp, "\n#\n"); } -- cgit From d062ac16f53d1a24047bcc9eded5514a71c363b8 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:33 +0300 Subject: perf report: Fix sample type validation for synthesized callchains Processing instruction tracing data (e.g. Intel PT) can synthesize callchains e.g. $ perf record -e intel_pt//u uname $ perf report --stdio --itrace=ige However perf report's callgraph option gets extra validation, so: $ perf report --stdio --itrace=ige -gflat Error: Selected -g or --branch-history but no callchain data. Did you call 'perf record' without -g? # To display the perf.data header info, # please use --header/--header-only options. # Fix the validation to know about instruction tracing options so above command works. A side-effect of the change is that the default option to accumulate the callchain of child functions comes into force. To get the previous behaviour the --no-children option can be used e.g. $ perf report --stdio --itrace=ige -gflat --no-children Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index e4e3f1432622..0d53b485a87b 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -214,6 +214,12 @@ static int report__setup_sample_type(struct report *rep) u64 sample_type = perf_evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data_file__is_pipe(session->file); + if (session->itrace_synth_opts->callchain || + (!is_pipe && + perf_header__has_feat(&session->header, HEADER_AUXTRACE) && + !session->itrace_synth_opts->set)) + sample_type |= PERF_SAMPLE_CALLCHAIN; + if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { ui__error("Selected --sort parent, but no " -- cgit From c7eced63f2f67bd06ceb2269062416db9d81d29d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:40 +0300 Subject: perf report: Adjust sample type validation for synthesized branch stacks perf report looks at event sample types to determine if branch stacks have been sampled. Adjust the validation to know about instruction tracing options. This change allows the use of the -b option which otherwise would complain with an error like: Error: Selected -b but no branch data. Did you call perf record without -b? # To display the perf.data header info, # please use --header/--header-only options. # Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-10-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 0d53b485a87b..7af35af5a5e5 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -220,6 +220,9 @@ static int report__setup_sample_type(struct report *rep) !session->itrace_synth_opts->set)) sample_type |= PERF_SAMPLE_CALLCHAIN; + if (session->itrace_synth_opts->last_branch) + sample_type |= PERF_SAMPLE_BRANCH_STACK; + if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) { if (sort__has_parent) { ui__error("Selected --sort parent, but no " -- cgit From fb9fab66e6e3ee737e521c899684c6d684b24a22 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:41 +0300 Subject: perf report: Also do default setup for synthesized branch stacks The 'perf report' tool will default to displaying branch stacks (-b option) if they are present. Make that also happen for synthesized branch stacks. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-11-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 7af35af5a5e5..92f7c5a75208 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -829,6 +829,9 @@ repeat: has_br_stack = perf_header__has_feat(&session->header, HEADER_BRANCH_STACK); + if (itrace_synth_opts.last_branch) + has_br_stack = true; + /* * Branch mode is a tristate: * -1 means default, so decide based on the file having branch data. -- cgit From f86225db3aa0e394915af45eea1c3cca6f3e2dba Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:42 +0300 Subject: perf report: Skip events with null branch stacks A non-synthesized event might not have a branch stack if branch stacks have been synthesized (using itrace options). An example of that is when Intel PT records sched_switch events for decoding purposes. Those sched_switch events do not have branch stacks even though the Intel PT decoder may be synthesizing other events that do due to the itrace options. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-12-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 92f7c5a75208..e94e5c7155af 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -163,14 +163,21 @@ static int process_sample_event(struct perf_tool *tool, if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) goto out_put; - if (sort__mode == SORT_MODE__BRANCH) + if (sort__mode == SORT_MODE__BRANCH) { + /* + * A non-synthesized event might not have a branch stack if + * branch stacks have been synthesized (using itrace options). + */ + if (!sample->branch_stack) + goto out_put; iter.ops = &hist_iter_branch; - else if (rep->mem_mode) + } else if (rep->mem_mode) { iter.ops = &hist_iter_mem; - else if (symbol_conf.cumulate_callchain) + } else if (symbol_conf.cumulate_callchain) { iter.ops = &hist_iter_cumulative; - else + } else { iter.ops = &hist_iter_normal; + } if (al.map != NULL) al.map->dso->hit = 1; -- cgit From 188bb5e2ce112463428994f91291e5df6fc05521 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Sep 2015 16:15:46 +0300 Subject: perf report: Make max_stack value allow for synthesized callchains perf report has an option (--max-stack) to set the maximum stack depth when processing callchains. The option defaults to the hard-coded maximum definition PERF_MAX_STACK_DEPTH which is 127. The intention of the option is to allow the user to reduce the processing time by reducing the amount of the callchain that is processed. It is also possible, when processing instruction traces, to synthesize callchains. Synthesized callchains do not have the kernel size limitation and are whatever size the user requests, although validation presently prevents the user requested a value greater that 1024. The default value is 16. To allow for synthesized callchains, make the max_stack value at least the same size as the synthesized callchain size. Signed-off-by: Adrian Hunter Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1443186956-18718-16-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index e94e5c7155af..37c9f5125887 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -809,6 +809,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (report.inverted_callchain) callchain_param.order = ORDER_CALLER; + if (itrace_synth_opts.callchain && + (int)itrace_synth_opts.callchain_sz > report.max_stack) + report.max_stack = itrace_synth_opts.callchain_sz; + if (!input_name || !strlen(input_name)) { if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) input_name = "-"; -- cgit From 77e65977495cd6f6fcfacd8c16bdd9c8c18a1d72 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 30 Sep 2015 11:08:58 -0300 Subject: perf machine: Use machine__kernel_map() thoroughly In places where we were using its open coded equivalent. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-khkdugcdoqy3tkszm3jdxgbe@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 37c9f5125887..7962605b3576 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -387,7 +387,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, static void report__warn_kptr_restrict(const struct report *rep) { - struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION]; + struct map *kernel_map = machine__kernel_map(&rep->session->machines.host, MAP__FUNCTION); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; if (kernel_map == NULL || -- cgit From a5e813c68649366aaa3f785772b00ea6ccad7b8d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 30 Sep 2015 11:54:04 -0300 Subject: perf machine: Add method for common kernel_map(FUNCTION) operation And it is also a step in the direction of killing the separation of data and text maps in map_groups. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-rrds86kb3wx5wk8v38v56gw8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 7962605b3576..b5623639f67d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -387,7 +387,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, static void report__warn_kptr_restrict(const struct report *rep) { - struct map *kernel_map = machine__kernel_map(&rep->session->machines.host, MAP__FUNCTION); + struct map *kernel_map = machine__kernel_map(&rep->session->machines.host); struct kmap *kernel_kmap = kernel_map ? map__kmap(kernel_map) : NULL; if (kernel_map == NULL || -- cgit From def02db0d662b0edd83f80e3c18f660fc414decb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 5 Oct 2015 17:05:35 -0300 Subject: perf callchain: Switch default to 'graph,0.5,caller' Which is the most common default found in other similar tools. Requested-by: Ingo Molnar Cc: Adrian Hunter Cc: Borislav Petkov Cc: Chandler Carruth Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Cc: Wang Nan Link: https://www.youtube.com/watch?v=nXaxk27zwlk Link: http://lkml.kernel.org/n/tip-v8lq36aispvdwgxdmt9p9jd9@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b5623639f67d..3b23b25d1589 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -633,7 +633,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) bool has_br_stack = false; int branch_mode = -1; bool branch_call_mode = false; - char callchain_default_opt[] = "fractal,0.5,callee"; + char callchain_default_opt[] = "graph,0.5,caller"; const char * const report_usage[] = { "perf report []", NULL @@ -701,7 +701,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Only display entries with parent-match"), OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order[,branch]", "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address), add branches. " - "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt), + "Default: graph,0.5,caller", &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, "Accumulate callchains of children and show total overhead as well"), OPT_INTEGER(0, "max-stack", &report.max_stack, -- cgit From 21cf62847d29392e51c37460856d3c3c57769c5e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 22 Oct 2015 15:28:48 +0900 Subject: perf tools: Move callchain help messages to callchain.h These messages will be used by 'perf top' in the next patch. Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Borislav Petkov Cc: Brendan Gregg Cc: Chandler Carruth Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1445495330-25416-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3b23b25d1589..18a8c52d921e 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -625,6 +625,9 @@ parse_percent_limit(const struct option *opt, const char *str, return 0; } +const char report_callchain_help[] = "Display callchains using " CALLCHAIN_REPORT_HELP ". " + "Default: graph,0.5,caller"; + int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) { struct perf_session *session; @@ -699,9 +702,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), - OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order[,branch]", - "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address), add branches. " - "Default: graph,0.5,caller", &report_parse_callchain_opt, callchain_default_opt), + OPT_CALLBACK_DEFAULT('g', "call-graph", &report, + "output_type,min_percent[,print_limit],call_order[,branch]", + report_callchain_help, &report_parse_callchain_opt, + callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, "Accumulate callchains of children and show total overhead as well"), OPT_INTEGER(0, "max-stack", &report.max_stack, -- cgit From 792aeafa8ed08e5e18fb66ab93b470f78e619f75 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 22 Oct 2015 16:45:46 +0900 Subject: perf tools: Defaults to 'caller' callchain order only if --children is enabled The caller callchain order is useful with --children option since it can show 'overview' style output, but other commands which don't use --children feature like 'perf script' or even 'perf report/top' without --children are better to keep callee order. Signed-off-by: Namhyung Kim Acked-by: Brendan Gregg Acked-by: Frederic Weisbecker Acked-by: Ingo Molnar Cc: Adrian Hunter Cc: Borislav Petkov Cc: Chandler Carruth Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1445499946-29817-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 18a8c52d921e..545c51cef7f7 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -812,6 +812,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) if (report.inverted_callchain) callchain_param.order = ORDER_CALLER; + if (symbol_conf.cumulate_callchain && !callchain_param.order_set) + callchain_param.order = ORDER_CALLER; if (itrace_synth_opts.callchain && (int)itrace_synth_opts.callchain_sz > report.max_stack) -- cgit From 76a26549eb367f683fbb394b7246bef5dc665f8c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 22 Oct 2015 23:28:32 +0900 Subject: perf tools: Improve call graph documents and help messages The --call-graph option is complex so we should provide better guide for users. Also change help message to be consistent with config option names. Now perf top will show help like below: $ perf top --call-graph Error: option `call-graph' requires a value Usage: perf top [] --call-graph setup and enables call-graph (stack chain/backtrace): record_mode: call graph recording mode (fp|dwarf|lbr) record_size: if record_mode is 'dwarf', max size of stack recording () default: 8192 (bytes) print_type: call graph printing style (graph|flat|fractal|none) threshold: minimum call graph inclusion threshold () print_limit: maximum number of call graph entry () order: call graph order (caller|callee) sort_key: call graph sort key (function|address) branch: include last branch info to call graph (branch) Default: fp,graph,0.5,caller,function Requested-by: Ingo Molnar Signed-off-by: Namhyung Kim Acked-by: Frederic Weisbecker Cc: Adrian Hunter Cc: Borislav Petkov Cc: Brendan Gregg Cc: Chandler Carruth Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 545c51cef7f7..50dd4d3d8667 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -625,8 +625,11 @@ parse_percent_limit(const struct option *opt, const char *str, return 0; } -const char report_callchain_help[] = "Display callchains using " CALLCHAIN_REPORT_HELP ". " - "Default: graph,0.5,caller"; +#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function" + +const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" + CALLCHAIN_REPORT_HELP + "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT; int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) { @@ -636,7 +639,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) bool has_br_stack = false; int branch_mode = -1; bool branch_call_mode = false; - char callchain_default_opt[] = "graph,0.5,caller"; + char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT; const char * const report_usage[] = { "perf report []", NULL @@ -703,7 +706,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), OPT_CALLBACK_DEFAULT('g', "call-graph", &report, - "output_type,min_percent[,print_limit],call_order[,branch]", + "print_type,threshold[,print_limit],order,sort_key[,branch]", report_callchain_help, &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, -- cgit From b272a59d835cd8ca6b45f41c66c61b473996c759 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 25 Oct 2015 00:49:25 +0900 Subject: perf report: Rename to --show-cpu-utilization So that it can be more consistent with other --show-* options. The old name (--showcpuutilization) is provided only for compatibility. Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1445701767-12731-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-report.c') diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 50dd4d3d8667..2853ad2bd435 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -699,8 +699,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) " Please refer the man page for the complete list."), OPT_STRING('F', "fields", &field_order, "key[,keys...]", "output field(s): overhead, period, sample plus all of sort keys"), - OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, + OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), + OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, + "Show sample percentage for different cpu modes", PARSE_OPT_HIDDEN), OPT_STRING('p', "parent", &parent_pattern, "regex", "regex filter to identify parent, see: '--sort parent'"), OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, -- cgit