[zzh@ncic.ac.cn: RE: Why systemtap loses events and what can be done about it?]

Frank Ch. Eigler fche@redhat.com
Wed Sep 5 15:05:00 GMT 2007


----- 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.



More information about the Systemtap mailing list