 | | | high context switching and high load averages slowing down sy stem | high context switching and high load averages slowing down sy stem 2005-08-01 - By BQ
Back
Tom,
On 7/29/05, Tom Sightler <ttsig@(protected)> wrote:
> Wow, that is a lot of context switches. There is also a high amount of
> system time with very little user time, that would imply that this is
> not an issue with high Oracle usage, unless it's a problem with the SGA
> and shared memory. Any information on what waits your Oracle system is
> reporting during these low performance periods that might give us a
> little clue.
Now that we're on this subject ... is there any way to check on what
does the system spend time, when we see a lot of system CPU%?
For example, I have a web+authentication server which, when under a
stress test spends a lot of time in system:
# sar
15:50:00 all 9.80 0.00 22.40 67.80
16:00:01 all 19.61 0.00 43.87 36.52
16:10:26 all 14.39 0.00 34.81 50.81
16:20:00 all 19.19 0.00 47.90 32.91
16:30:02 all 22.04 0.00 49.76 28.20
16:40:03 all 31.68 0.00 68.32 0.00
I'd like to find out what's going on here and if there is any way to
improve perfomance. The program is in house written so I could tell
developers what to do, if I had more information.
iostat and vmstat don't show anything strange, not a lot of disk IO
(we use tmpfs for temporary storage) and not a lot of context
switching.
Thanks,
BQ
--
Taroon-list mailing list
Taroon-list@(protected)
http://www.redhat.com/mailman/listinfo/taroon-list
Earn $52 per hosting referral at Lunarpages.
|
|
|