topic Re: vmstat question in Operating System - HP-UX

vmstat question

Barry Deevey — Thu, 22 Feb 2001 12:10:50 GMT

Hi everybody,

I have recently increased the swap space on our 'D' class. I have noticed that the vmstat output is displaying quite a large number of blocked processes, this (I have read) could mean a disk throughput problem. Below is a sample of the vmstat output:

procs memory page faults cpu
r b w avm free re at pi po fr de sr in sy cs us sy id
0 300 0 47255 71082 6 5 0 0 0 0 0 476 2615 813 24 4 71
1 300 0 47240 71041 0 0 0 0 0 0 0 370 785 330 33 2 65
0 300 0 46476 71024 0 0 0 0 0 0 0 440 1543 466 25 3 71
2 298 0 46443 71024 0 0 0 0 0 0 0 401 1683 575 38 3 59

Due to my lack of experience, I'm not sure if it is actually exceeding an 'allowed' limit and if so, would it be possible for somebody to point me in the right direction as to what I need to do to resolve this problem??

Thanks for any help, it's greatly appreciated.

Best Regards,
Barry.

Re: vmstat question

MARTINACHE — Thu, 22 Feb 2001 13:06:06 GMT

Hi,

If Glance in installed, you can use it in order to find disk, network, ... bottlenecks.

Could you do these commands for more informations :

sar -v
swapinfo -tam
top

Ragards,

Patrice.

Re: vmstat question

Barry Deevey — Thu, 22 Feb 2001 13:12:03 GMT

Hi Patrice,

swapinfo -tam

Mb Mb Mb PCT START/ Mb
TYPE AVAIL USED FREE USED LIMIT RESERVE PRI NAME
dev 896 0 896 0% 0 - 1 /dev/vg00/lvol2
dev 1024 0 1024 0% 0 - 1 /dev/vg02/lvol2
dev 128 0 128 0% 0 - 1 /dev/vg00/lvol4
reserve - 852 -852
memory 766 135 631 18%
total 2814 987 1827 35% - 0 -

sar -v 5 5

13:10:48 text-sz ov proc-sz ov inod-sz ov file-sz ov
13:10:53 N/A N/A 383/1020 0 2942/2943 0 3651/4769 0
13:10:58 N/A N/A 383/1020 0 2943/2943 0 3651/4769 0
13:11:03 N/A N/A 383/1020 0 2943/2943 0 3651/4769 0
13:11:08 N/A N/A 383/1020 0 2943/2943 0 3651/4769 0
13:11:13 N/A N/A 383/1020 0 2943/2943 0 3651/4769 0

Does this help clarify the problem??

Thanks for your time,

Barry.

Re: vmstat question

Barry Deevey — Thu, 22 Feb 2001 13:56:56 GMT

Hello again Patrice,

Sorry I forgot the 'top' output:

Load averages: 0.63, 0.28, 0.24
384 processes: 379 sleeping, 5 running
Cpu states:
CPU LOAD USER NICE SYS IDLE BLOCK SWAIT INTR SSYS
0 0.73 72.0% 0.0% 5.7% 22.3% 0.0% 0.0% 0.0% 0.0%
1 0.53 81.5% 0.0% 3.9% 14.6% 0.0% 0.0% 0.0% 0.0%
--- ---- ----- ----- ----- ----- ----- ----- ----- -----
avg 0.63 76.7% 0.0% 4.7% 18.5% 0.0% 0.0% 0.0% 0.0%

Memory: 393320K (182040K) real, 426256K (200216K) virtual, 258000K free

Unfortunately we don't have glance installed.

Best Regards,
Barry