This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
[zzh@ncic.ac.cn: RE: Why systemtap loses events and what can be done about it?]
- From: "Frank Ch. Eigler" <fche at redhat dot com>
- To: systemtap at sources dot redhat dot com
- Date: Wed, 5 Sep 2007 09:38:08 -0400
- Subject: [zzh@ncic.ac.cn: RE: Why systemtap loses events and what can be done about it?]
----- Forwarded message from ??? <zzh@ncic.ac.cn> -----
Subject: RE: Why systemtap loses events and what can be done about it?
Date: Wed, 5 Sep 2007 21:13:48 +0800
Hi-
I optimize my script by getting rid of the global str_sock,
and add a ".maxactive(1000)" probe point suffix to tcp.recvmsg.return.
It works very well. I have tried 800 clients concurrently explore the
web site monitored by systemtap script and no event loss was found.
Sometimes the ejb server and database server have nearly 100% cpu
usage!
Thank You very much! Your suggestion really give me great help.