diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-11-28 17:57:40 -0200 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-11-28 17:57:40 -0200 |
commit | ee29be625bd7b115d45eba4b0526ff3e24bf3ca0 (patch) | |
tree | 1ef1189e0fe02511642e5f74f463d888dfa34bec /tools/perf/util | |
parent | e7984b7bee2fca8f582f5bc2bf1e6c93420a5dd5 (diff) | |
download | linux-ee29be625bd7b115d45eba4b0526ff3e24bf3ca0.tar.gz linux-ee29be625bd7b115d45eba4b0526ff3e24bf3ca0.tar.bz2 linux-ee29be625bd7b115d45eba4b0526ff3e24bf3ca0.zip |
perf tools: Save some loops using perf_evlist__id2evsel
Since we already ask for PERF_SAMPLE_ID and use it to quickly find the
associated evsel, add handler func + data to struct perf_evsel to avoid
using chains of if(strcmp(event_name)) and also to avoid all the linear
list searches via trace_event_find.
To demonstrate the technique convert 'perf sched' to it:
# perf sched record sleep 5m
And then:
Performance counter stats for '/tmp/oldperf sched lat':
646.929438 task-clock # 0.999 CPUs utilized
9 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
20,901 page-faults # 0.032 M/sec
1,290,144,450 cycles # 1.994 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,606,158,439 instructions # 1.24 insns per cycle
339,088,395 branches # 524.151 M/sec
4,550,735 branch-misses # 1.34% of all branches
0.647524759 seconds time elapsed
Versus:
Performance counter stats for 'perf sched lat':
473.564691 task-clock # 0.999 CPUs utilized
9 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
20,903 page-faults # 0.044 M/sec
944,367,984 cycles # 1.994 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,442,385,571 instructions # 1.53 insns per cycle
308,383,106 branches # 651.195 M/sec
4,481,784 branch-misses # 1.45% of all branches
0.474215751 seconds time elapsed
[root@emilia ~]#
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util')
-rw-r--r-- | tools/perf/util/evlist.c | 42 | ||||
-rw-r--r-- | tools/perf/util/evlist.h | 11 | ||||
-rw-r--r-- | tools/perf/util/evsel.h | 4 | ||||
-rw-r--r-- | tools/perf/util/tool.h | 5 |
4 files changed, 62 insertions, 0 deletions
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d44e3df13a8f..b36f26fe767a 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -207,6 +207,48 @@ out_free_attrs: return err; } +static struct perf_evsel * + perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id) +{ + struct perf_evsel *evsel; + + list_for_each_entry(evsel, &evlist->entries, node) { + if (evsel->attr.type == PERF_TYPE_TRACEPOINT && + (int)evsel->attr.config == id) + return evsel; + } + + return NULL; +} + +int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs) +{ + struct perf_evsel *evsel; + int err; + size_t i; + + for (i = 0; i < nr_assocs; i++) { + err = trace_event__id(assocs[i].name); + if (err < 0) + goto out; + + evsel = perf_evlist__find_tracepoint_by_id(evlist, err); + if (evsel == NULL) + continue; + + err = -EEXIST; + if (evsel->handler.func != NULL) + goto out; + evsel->handler.func = assocs[i].handler; + } + + err = 0; +out: + return err; +} + void perf_evlist__disable(struct perf_evlist *evlist) { int cpu, thread; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 2202e7b04103..f94ed7e0d987 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -36,6 +36,11 @@ struct perf_evlist { struct perf_evsel *selected; }; +struct perf_evsel_str_handler { + const char *name; + void *handler; +}; + struct perf_evsel; struct perf_evlist *perf_evlist__new(struct cpu_map *cpus, @@ -51,6 +56,9 @@ int perf_evlist__add_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs); int perf_evlist__add_tracepoints(struct perf_evlist *evlist, const char *tracepoints[], size_t nr_tracepoints); +int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist, + const struct perf_evsel_str_handler *assocs, + size_t nr_assocs); #define perf_evlist__add_attrs_array(evlist, array) \ perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array)) @@ -58,6 +66,9 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist, #define perf_evlist__add_tracepoints_array(evlist, array) \ perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array)) +#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \ + perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array)) + void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6421c07f5015..326b8e4d5035 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -61,6 +61,10 @@ struct perf_evsel { off_t id_offset; }; struct cgroup_sel *cgrp; + struct { + void *func; + void *data; + } handler; bool supported; }; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 89ff1b551a74..b0e1aadba8d5 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -1,8 +1,13 @@ #ifndef __PERF_TOOL_H #define __PERF_TOOL_H +#include <stdbool.h> + struct perf_session; +union perf_event; +struct perf_evlist; struct perf_evsel; +struct perf_sample; struct perf_tool; struct machine; |