Right - there's no reason to guess here;
#dtrace -n 'syscall:::entry { @[execname,probefunc] = count() }'
Control c after 10-30 seconds or or.
You'll get a sorted list of process names and which system
calls they're calling.
Change "execname" to "pid" or PIDs are more usefull,
or use both....
@[execname, pid, probefunc]
/jim
Paul Riethmuller - PAE wrote:
Hi Matt,
why "suppose" who is making the syscalls when you can know ?
run prstat -mL and check it SCL rate
or truss -c the process.
HTH
Paul
----- Begin Included Message -----<
Date: Fri, 23 Oct 2009 00:06:31 -0700 (PDT)
From: "Matt V." <opensolaris....@mygaia.org>
Subject: Re: [perf-discuss] Kernel usage
To: perf-discuss@opensolaris.org
Thanks for your response.
For moment, we can't patch Oracle version (production environment).
But on another server (which contains containers too), we have the same problem:
sar 1 100
SunOS 5.10 Generic_137137-09 sun4u 10/23/2009
09:00:17 %usr %sys %wio %idle
09:00:18 12 79 0 8
09:00:19 10 86 0 4
09:00:20 19 79 0 3
09:00:21 20 80 0 0
09:00:23 19 64 0 17
09:00:24 19 51 0 30
09:00:25 5 40 0 55
09:00:26 8 64 0 28
09:00:27 4 57 0 39
09:00:29 3 54 0 43
09:00:30 11 59 0 30
09:00:31 8 22 0 70
[...]
We're suspecting "rcapd" daemon to make a lot of system calls.
What do you think about this supposition ?
Matt
_______________________________________________
perf-discuss mailing list
perf-discuss@opensolaris.org
