| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 12 Jan 2011 17:59:36 +0300
From: Kirill Smelkov <kirr@....spb.ru>
To: Frederic Weisbecker <fweisbec@...il.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
linux-kernel@...r.kernel.org,
Arnaldo Carvalho de Melo <acme@...hat.com>,
Ingo Molnar <mingo@...e.hu>, Mike Galbraith <efault@....de>,
Paul Mackerras <paulus@...ba.org>,
Stephane Eranian <eranian@...gle.com>,
Tom Zanussi <tzanussi@...il.com>
Subject: Re: Q: perf log mode?
On Wed, Jan 12, 2011 at 03:42:43PM +0100, Frederic Weisbecker wrote:
> On Wed, Jan 12, 2011 at 03:08:08PM +0100, Peter Zijlstra wrote:
> > On Wed, 2011-01-12 at 17:06 +0300, Kirill Smelkov wrote:
> > > I'm trying to use perf together with e.g. kprobes as a tool to show what
> > > is happening with my system in "live-log" mode. The problem is, for
> > > seldom events, actual info output is largely delayed because perf reads
> > > sample data in whole pages. Could something be done with it or am I'm
> > > missing something? Here is detailed description:
> >
> > perf_event_attr = {
> > .watermark = 0,
> > .wakeup_events = 1,
> > };
Ah, thanks for pointing it out!
> Which is perhaps something we want as a default when perf record -c 1
> and the output is the pipe mode.
Maybe not always, because as I understand it, tracepoints are handled
with -c 1, but there could be lots of them, and in such cases buffering
helps.
Anyway, maybe something like this could be useful?
---- 8< ----
From: Kirill Smelkov <kirr@....spb.ru>
Date: Wed, 12 Jan 2011 17:43:16 +0300
Subject: [PATCH] perf record: Add support for "nodelay" mode
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@...hat.com>
Cc: Frederic Weisbecker <fweisbec@...il.com>
Cc: Ingo Molnar <mingo@...e.hu>, Mike Galbraith <efault@....de>
Cc: Paul Mackerras <paulus@...ba.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Tom Zanussi <tzanussi@...il.com>
LKML-Reference: <20110112140613.GA11698@...rik.mns.mnsspb.ru>
Signed-off-by: Kirill Smelkov <kirr@....spb.ru>
---
tools/perf/Documentation/perf-record.txt | 3 +++
tools/perf/builtin-record.c | 8 ++++++++
2 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 52462ae..e032716 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 1210e64..df6064a 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,
--
1.7.4.rc1.7.g2cf08
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists