[Mimedefang] memory leak? is it an IBM x-series?

Anthony.Caetano at t-systems.co.za Anthony.Caetano at t-systems.co.za
Fri Feb 13 03:44:34 EST 2004


Hi Ron

We had similar problems with an IBM x345 server -- we tried many things 
eventually updating to 2.4.23-pre7 and up fixed it.

I updated the tg3 driver and stability improved a bit, I updated the ibm 
ServeRaid driver (ips module) level to 610 and stability improved a bit, 
disabled hyperthreading did many and various other things 
(bios/driver/patch), but for us 2.4.23-pre7 and up fixed it -- running 
2.4.25-pre6 now without problems.

The box would just die on us -- but still respond to SysRQ and a term of 
all processes would sometimes bring it back -- check the sysstat context 
switching -- it would climb to 10's of thousands i think we got close to 
50000 once!!  System cpu and loadavg was very high (obviously) and nothing 
else could run, although you could ping the box merrily.

Regards
Anthony






Ron Peterson <rpeterso at mtholyoke.edu>
Sent by: mimedefang-bounces at lists.roaringpenguin.com
02/12/2004 07:56 PM
Please respond to mimedefang

 
        To:     mimedefang at lists.roaringpenguin.com@SMTP at debisEx
        cc: 
        Subject:        Re: [Mimedefang] memory leak?

>>>

There were 200+ sendmail processes running at this time.  No single
process was consuming any great amount of memory.  Swap utilization was
creeping up, but not high.  The load average shot over 100, and the CPU
free dropped from it's usual 80-90 to around 10.

Other network applications started throwing errors at this time
also: apache and imapproxyd are the ones I noticed.  I killed all
sendmail, mimedefang, apache, and imapproxyd processes, but nothing
brought the machine back.  I had to run over and use console because the
ssh connections I had were almost unuseable.

I'm somewhat suspicious the broadcom network interfaces / tg3 driver may
be involved.  I've started logging /proc/net/dev once a minute to see if
the interfaces start throwing errors.  I also started logging vmstat
output every fifteen seconds.  Anything else anyone would recommend
logging?

<<<



More information about the MIMEDefang mailing list