summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorKirill Smelkov <kirr@mns.spb.ru>2011-01-12 17:59:36 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2011-01-13 11:38:44 -0200
commitacac03fa15a8684bb60489ed87b5aae5258c0838 (patch)
treeabaeaadf91bd4191d62904509815bcc372c42ba3
parent9710118bd4e7f3406865171cb9b9c94547c1c2f9 (diff)
perf record: Add "nodelay" mode, disabled by default
Sometimes there is a need to use perf in "live-log" mode. The problem is, for seldom events, actual info output is largely delayed because perf-record reads sample data in whole pages. So for such scenarious, add flag for perf-record to go in "nodelay" mode. To track e.g. what's going on in icmp_rcv while ping is running Use it with something like this: (1) $ perf probe -L icmp_rcv | grep -U8 '^ *43\>' goto error; } 38 if (!pskb_pull(skb, sizeof(*icmph))) goto error; icmph = icmp_hdr(skb); 43 ICMPMSGIN_INC_STATS_BH(net, icmph->type); /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ 50 if (icmph->type > NR_ICMP_TYPES) goto error; $ perf probe icmp_rcv:43 'type=icmph->type' (2) $ cat trace-icmp.py [...] def trace_begin(): print "in trace_begin" def trace_end(): print "in trace_end" def probe__icmp_rcv(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, __probe_ip, type): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) print "__probe_ip=%u, type=%u\n" % \ (__probe_ip, type), [...] (3) $ perf record -a -D -e probe:icmp_rcv -o - | \ perf script -i - -s trace-icmp.py Thanks to Peter Zijlstra for pointing how to do it. Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu>, Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <20110112140613.GA11698@tugrik.mns.mnsspb.ru> Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-rw-r--r--tools/perf/Documentation/perf-record.txt3
-rw-r--r--tools/perf/builtin-record.c8
2 files changed, 11 insertions, 0 deletions
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 52462ae2645..e032716c839 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -61,6 +61,9 @@ OPTIONS
-r::
--realtime=::
Collect data with this RT SCHED_FIFO priority.
+-D::
+--no-delay::
+ Collect data without buffering.
-A::
--append::
Append to the output file to do incremental profiling.
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1210e6484ad..df6064ad9bf 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -49,6 +49,7 @@ static int pipe_output = 0;
static const char *output_name = "perf.data";
static int group = 0;
static int realtime_prio = 0;
+static bool nodelay = false;
static bool raw_samples = false;
static bool sample_id_all_avail = true;
static bool system_wide = false;
@@ -307,6 +308,11 @@ static void create_counter(struct perf_evsel *evsel, int cpu)
attr->sample_type |= PERF_SAMPLE_CPU;
}
+ if (nodelay) {
+ attr->watermark = 0;
+ attr->wakeup_events = 1;
+ }
+
attr->mmap = track;
attr->comm = track;
attr->inherit = !no_inherit;
@@ -843,6 +849,8 @@ const struct option record_options[] = {
"record events on existing thread id"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
+ OPT_BOOLEAN('D', "no-delay", &nodelay,
+ "collect data without buffering"),
OPT_BOOLEAN('R', "raw-samples", &raw_samples,
"collect raw sample records from all opened counters"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,