From: Adametz, Bluejay (bluejay@fujigreenwood.com)
Date: Thu Feb 20 2003 - 13:36:41 EST
Last Saturday a supposedly minor change was made to an application (custom
built plus an Oracle database) running on a DS10. Concurrently with that
change, the system CPU time shot up alarmingly. Clearly they changed
_something_ in the application that caused this, but, trying to be helpful
and also cover the OS end of things, is there any way to troubleshoot what's
causing this? Aside from killing processes and seeing when it stops?
Paging, disk, and network activity have been entirely normal. The only
metric I have that's off nominal is the CPU usage. Looking at processes with
relatively high user mode time (as shown by top) didn't lead us anywhere
obvious - the app folks say there's no way that process could be doing this.
Some quick data points are:
xxx# vmstat 2 10
Virtual Memory Statistics: (pagesize = 8192)
procs memory pages intr cpu
r w u act free wire fault cow zero react pin pout in sy cs us sy
id
3 250 30 43K 11K 7473 4G 265M 1G 45M 2G 1M 535 10K 2K 23 11
66
4 249 30 43K 11K 7473 1 16 17 0 28 0 2K 3K 12K 37 63
0
3 250 30 43K 11K 7473 2 0 1 0 1 0 2K 4K 15K 48 52
0
4 249 30 43K 11K 7473 207 0 207 0 0 0 2K 5K 13K 42 58
0
3 250 30 43K 11K 7473 0 0 0 0 0 0 2K 4K 15K 41 59
0
4 249 30 43K 11K 7473 211 0 207 0 0 0 2K 5K 13K 43 57
0
3 250 30 43K 11K 7473 0 0 0 0 0 0 2K 4K 14K 47 53
0
3 250 30 43K 11K 7473 1 0 0 0 0 0 2K 3K 13K 39 61
0
2 251 30 43K 11K 7473 207 0 207 0 0 0 2K 5K 15K 49 51
0
2 251 30 43K 11K 7473 0 0 0 0 0 0 2K 3K 12K 38 62
0
?
- Bluejay Adametz
Computing is the only field in which we consider
adding a wing to the building to be maintenance.
This archive was generated by hypermail 2.1.7 : Sat Apr 12 2008 - 10:49:08 EDT