From 8d51327090ac025d7f4ce6c059786b5e93513321 Mon Sep 17 00:00:00 2001 From: Brice Goglin Date: Fri, 7 Aug 2009 13:55:24 +0200 Subject: perf report: Fix and improve the displaying of per-thread event counters Improve and fix the handling of per-thread counter stats recorded via perf record -s. Previously we only displayed it in debug printouts (-D) and even that output was hard to disambiguate. I moved everything to utils/values.[ch] so that we may reuse it in perf stat. We get something like this now: # PID TID cache-misses cache-references 4658 4659 495581 3238779 4658 4662 498246 3236823 4658 4663 499531 3243162 Then it'll be easy to add --pretty=raw to display a single line per thread/event. By the way, -S was also used for --symbol... So I used -T/--thread here. perf report: Add -T/--threads to display per-thread counter values We get something like this now: # PID TID cache-misses cache-references 4658 4659 495581 3238779 4658 4662 498246 3236823 4658 4663 499531 3243162 Per-thread arrays of counter values are managed in utils/values.[ch] Signed-off-by: Brice Goglin Cc: Peter Zijlstra Cc: paulus@samba.org Signed-off-by: Ingo Molnar --- tools/perf/util/values.c | 171 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 171 insertions(+) create mode 100644 tools/perf/util/values.c (limited to 'tools/perf/util/values.c') diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c new file mode 100644 index 00000000000..8551c0b8b23 --- /dev/null +++ b/tools/perf/util/values.c @@ -0,0 +1,171 @@ +#include + +#include "util.h" +#include "values.h" + +void perf_read_values_init(struct perf_read_values *values) +{ + values->threads_max = 16; + values->pid = malloc(values->threads_max * sizeof(*values->pid)); + values->tid = malloc(values->threads_max * sizeof(*values->tid)); + values->value = malloc(values->threads_max * sizeof(*values->value)); + if (!values->pid || !values->tid || !values->value) + die("failed to allocate read_values threads arrays"); + values->threads = 0; + + values->counters_max = 16; + values->counterrawid = malloc(values->counters_max + * sizeof(*values->counterrawid)); + values->countername = malloc(values->counters_max + * sizeof(*values->countername)); + if (!values->counterrawid || !values->countername) + die("failed to allocate read_values counters arrays"); + values->counters = 0; +} + +void perf_read_values_destroy(struct perf_read_values *values) +{ + int i; + + if (!values->threads_max || !values->counters_max) + return; + + for (i = 0; i < values->threads; i++) + free(values->value[i]); + free(values->pid); + free(values->tid); + free(values->counterrawid); + for (i = 0; i < values->counters; i++) + free(values->countername[i]); + free(values->countername); +} + +static void perf_read_values__enlarge_threads(struct perf_read_values *values) +{ + values->threads_max *= 2; + values->pid = realloc(values->pid, + values->threads_max * sizeof(*values->pid)); + values->tid = realloc(values->tid, + values->threads_max * sizeof(*values->tid)); + values->value = realloc(values->value, + values->threads_max * sizeof(*values->value)); + if (!values->pid || !values->tid || !values->value) + die("failed to enlarge read_values threads arrays"); +} + +static int perf_read_values__findnew_thread(struct perf_read_values *values, + u32 pid, u32 tid) +{ + int i; + + for (i = 0; i < values->threads; i++) + if (values->pid[i] == pid && values->tid[i] == tid) + return i; + + if (values->threads == values->threads_max) + perf_read_values__enlarge_threads(values); + + i = values->threads++; + values->pid[i] = pid; + values->tid[i] = tid; + values->value[i] = malloc(values->counters_max * sizeof(**values->value)); + if (!values->value[i]) + die("failed to allocate read_values counters array"); + + return i; +} + +static void perf_read_values__enlarge_counters(struct perf_read_values *values) +{ + int i; + + values->counters_max *= 2; + values->counterrawid = realloc(values->counterrawid, + values->counters_max * sizeof(*values->counterrawid)); + values->countername = realloc(values->countername, + values->counters_max * sizeof(*values->countername)); + if (!values->counterrawid || !values->countername) + die("failed to enlarge read_values counters arrays"); + + for (i = 0; i < values->threads; i++) { + values->value[i] = realloc(values->value[i], + values->counters_max * sizeof(**values->value)); + if (!values->value[i]) + die("failed to enlarge read_values counters arrays"); + } +} + +static int perf_read_values__findnew_counter(struct perf_read_values *values, + u64 rawid, char *name) +{ + int i; + + for (i = 0; i < values->counters; i++) + if (values->counterrawid[i] == rawid) + return i; + + if (values->counters == values->counters_max) + perf_read_values__enlarge_counters(values); + + i = values->counters++; + values->counterrawid[i] = rawid; + values->countername[i] = strdup(name); + + return i; +} + +void perf_read_values_add_value(struct perf_read_values *values, + u32 pid, u32 tid, + u64 rawid, char *name, u64 value) +{ + int tindex, cindex; + + tindex = perf_read_values__findnew_thread(values, pid, tid); + cindex = perf_read_values__findnew_counter(values, rawid, name); + + values->value[tindex][cindex] = value; +} + +void perf_read_values_display(FILE *fp, struct perf_read_values *values) +{ + int i, j; + int pidwidth, tidwidth; + int *counterwidth; + + counterwidth = malloc(values->counters * sizeof(*counterwidth)); + if (!counterwidth) + die("failed to allocate counterwidth array"); + tidwidth = 3; + pidwidth = 3; + for (j = 0; j < values->counters; j++) + counterwidth[j] = strlen(values->countername[j]); + for (i = 0; i < values->threads; i++) { + int width; + + width = snprintf(NULL, 0, "%d", values->pid[i]); + if (width > pidwidth) + pidwidth = width; + width = snprintf(NULL, 0, "%d", values->tid[i]); + if (width > tidwidth) + tidwidth = width; + for (j = 0; j < values->counters; j++) { + width = snprintf(NULL, 0, "%Lu", values->value[i][j]); + if (width > counterwidth[j]) + counterwidth[j] = width; + } + } + + fprintf(fp, "# %*s %*s", pidwidth, "PID", tidwidth, "TID"); + for (j = 0; j < values->counters; j++) + fprintf(fp, " %*s", counterwidth[j], values->countername[j]); + fprintf(fp, "\n"); + + for (i = 0; i < values->threads; i++) { + fprintf(fp, " %*d %*d", pidwidth, values->pid[i], + tidwidth, values->tid[i]); + for (j = 0; j < values->counters; j++) + fprintf(fp, " %*Lu", + counterwidth[j], values->value[i][j]); + fprintf(fp, "\n"); + } +} -- cgit v1.2.3-18-g5258 From 9f8666971185b86615a074bcac67c90fdf8af8bc Mon Sep 17 00:00:00 2001 From: Brice Goglin Date: Mon, 10 Aug 2009 15:26:32 +0200 Subject: perf report: Add raw displaying of per-thread counters If --pretty=raw is given to perf report -T, it now displays one line per-thread per-counter with the raw event id added. We get: # PID TID Name Raw Count 18608 18609 cache-misses 28e 416744 18608 18609 cache-references 28f 6456792 18608 18608 cache-misses 28e 448219 18608 18608 cache-references 28f 7270244 instead of: # PID TID cache-misses cache-references 18608 18609 416744 6456792 18608 18608 448219 7270244 Signed-off-by: Brice Goglin Acked-by: Peter Zijlstra LKML-Reference: <4A802008.5050409@inria.fr> Signed-off-by: Ingo Molnar --- tools/perf/util/values.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 61 insertions(+), 1 deletion(-) (limited to 'tools/perf/util/values.c') diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 8551c0b8b23..614cfaf4712 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -126,7 +126,8 @@ void perf_read_values_add_value(struct perf_read_values *values, values->value[tindex][cindex] = value; } -void perf_read_values_display(FILE *fp, struct perf_read_values *values) +static void perf_read_values__display_pretty(FILE *fp, + struct perf_read_values *values) { int i, j; int pidwidth, tidwidth; @@ -169,3 +170,62 @@ void perf_read_values_display(FILE *fp, struct perf_read_values *values) fprintf(fp, "\n"); } } + +static void perf_read_values__display_raw(FILE *fp, + struct perf_read_values *values) +{ + int width, pidwidth, tidwidth, namewidth, rawwidth, countwidth; + int i, j; + + tidwidth = 3; /* TID */ + pidwidth = 3; /* PID */ + namewidth = 4; /* "Name" */ + rawwidth = 3; /* "Raw" */ + countwidth = 5; /* "Count" */ + + for (i = 0; i < values->threads; i++) { + width = snprintf(NULL, 0, "%d", values->pid[i]); + if (width > pidwidth) + pidwidth = width; + width = snprintf(NULL, 0, "%d", values->tid[i]); + if (width > tidwidth) + tidwidth = width; + } + for (j = 0; j < values->counters; j++) { + width = strlen(values->countername[j]); + if (width > namewidth) + namewidth = width; + width = snprintf(NULL, 0, "%llx", values->counterrawid[j]); + if (width > rawwidth) + rawwidth = width; + } + for (i = 0; i < values->threads; i++) { + for (j = 0; j < values->counters; j++) { + width = snprintf(NULL, 0, "%Lu", values->value[i][j]); + if (width > countwidth) + countwidth = width; + } + } + + fprintf(fp, "# %*s %*s %*s %*s %*s\n", + pidwidth, "PID", tidwidth, "TID", + namewidth, "Name", rawwidth, "Raw", + countwidth, "Count"); + for (i = 0; i < values->threads; i++) + for (j = 0; j < values->counters; j++) + fprintf(fp, " %*d %*d %*s %*llx %*Lu\n", + pidwidth, values->pid[i], + tidwidth, values->tid[i], + namewidth, values->countername[j], + rawwidth, values->counterrawid[j], + countwidth, values->value[i][j]); +} + +void perf_read_values_display(FILE *fp, struct perf_read_values *values, + int raw) +{ + if (raw) + perf_read_values__display_raw(fp, values); + else + perf_read_values__display_pretty(fp, values); +} -- cgit v1.2.3-18-g5258 From 83a0944fa919fb2ebcfc1f8933d86e437b597ca6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 15 Aug 2009 12:26:57 +0200 Subject: perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker LKML-Reference: Signed-off-by: Ingo Molnar --- tools/perf/util/values.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'tools/perf/util/values.c') diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c index 614cfaf4712..1c15e39f99e 100644 --- a/tools/perf/util/values.c +++ b/tools/perf/util/values.c @@ -96,7 +96,7 @@ static void perf_read_values__enlarge_counters(struct perf_read_values *values) } static int perf_read_values__findnew_counter(struct perf_read_values *values, - u64 rawid, char *name) + u64 rawid, const char *name) { int i; @@ -116,7 +116,7 @@ static int perf_read_values__findnew_counter(struct perf_read_values *values, void perf_read_values_add_value(struct perf_read_values *values, u32 pid, u32 tid, - u64 rawid, char *name, u64 value) + u64 rawid, const char *name, u64 value) { int tindex, cindex; @@ -221,8 +221,7 @@ static void perf_read_values__display_raw(FILE *fp, countwidth, values->value[i][j]); } -void perf_read_values_display(FILE *fp, struct perf_read_values *values, - int raw) +void perf_read_values_display(FILE *fp, struct perf_read_values *values, int raw) { if (raw) perf_read_values__display_raw(fp, values); -- cgit v1.2.3-18-g5258