Hi all,

 

I created a case with HP about disk performance on my master server. I got
the answer that my server is trashing and perhaps have memory leak problems.

These are some numbers from my disks (sar -d). I have tried to increase scsi
queue depth, but nothing helps. HP said that it must be an extremely intense
oracle database on this disk, but its not, is my netbackup disk.

 device   %busy   avque   r+w/s  blks/s  avwait  avserv

 c16t0d1   97.70  312.67    1573   19467  232.55    4.52

 c16t0d1  100.00  649.81     834    6651  681.50    9.99

 c16t0d1  100.00  854.77    1112    8896  751.81    6.03

 

 

HP also pointed out that I have some processes that might have memory leak
problems. Those processes is bpsched.. I got this back from HP: (from top)

CPU   TTY    PID    USERNAME PRI NI   SIZE    RES   STATE    TIME %WCPU
%CPU COMMAND

 0         ?   21867             root     192 20 17280K  5040K run
0:01        17.98    3.98 bpsched


 1         ?   21867             root     213 20 20928K  8692K run
0:06       58.86    23.16 bpsched


 1         ?   21867             root     148 20 21312K  9076K sleep
0:07       51.48    27.16 bpsched
 

This process seems to have a memory leak since the size field keeps
increasing and the cpu usage is high

 

 

1.      Does anyone else have these numbers against disk on the master
server? My master don't have these values all the time, but from now and
then it peaks at these numbers and sometimes higher.
2.      Do bpsched have a memory leak or is just how it works?

 

 

Our environment:

HPUX 11.11

NBU 5.1 MP5

 

Thanks and regards,

Hampus Lind
Rikspolisstyrelsen
National Police Board
Tel dir: +46 (0)8 - 401 99 43
Tel mob: +46 (0)70 - 217 92 66
E-mail:  <mailto:hampus.lind at rps.police.se> hampus.lind at rps.police.se

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: 
http://mailman.eng.auburn.edu/pipermail/veritas-bu/attachments/20061027/a0501c15/attachment.html