disk contention problem?

From: utkanbir (hopehope_123_at_yahoo.com)
Date: 05/28/04 

Date: 28 May 2004 04:22:31 -0700

Hi Gurus,

This is iostat -x 5 output of my redhat linux , itanium , ( 8 gb.ram ,
4 cpu) , emc disk array (raid s) , and oracle 9.2.0.2 rac ,
datawarehouse:

avg-cpu: %user %nice %sys %idle
         123.75 0.00 32.15 868.10

Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz
await svctm %util
sdq 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sda 0.00 0.60 0.00 1.40 0.00 16.00 11.43 0.02
11.02 6.00 0.86
sda1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sda2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sda3 0.00 0.60 0.00 0.60 0.00 9.60 16.00 0.01
10.09 9.77 0.60
sda4 0.00 0.00 0.00 0.80 0.00 6.40 8.00 0.01
11.72 9.03 0.74
sdb 0.00 0.60 0.00 1.40 0.00 16.00 11.43 0.02
12.97 6.00 0.86
sdb1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdb2 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdb3 0.00 0.60 0.00 0.60 0.00 9.60 16.00 0.01
14.00 14.00 0.86
sdb4 0.00 0.00 0.00 0.80 0.00 6.40 8.00 0.01
12.45 8.54 0.70
sdc 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdd 70.00 7.00 2.00 3.00 72.00 10.00 16.40 0.00
 0.90 0.86 0.44
sdd1 70.00 7.00 2.00 3.00 72.00 10.00 16.40 0.00
 0.86 0.86 0.44
sde 101.00 139.40 3.00 122.60 104.00 7605.20 61.38 0.57
  4.53 1.01 13.04
sde1 101.00 139.40 3.00 122.60 104.00 7605.20 61.38 0.57
  4.53 1.01 13.04
sdf 68.00 0.00 4.00 2.00 72.00 2.00 12.33 0.01
 0.78 0.62 0.38
sdf1 68.00 0.00 4.00 2.00 72.00 2.00 12.33 0.01
 0.81 0.65 0.40
sdg 70.00 7163.80 2.00 134.20 72.00 7298.00 54.11 0.69
   5.07 1.00 13.96
sdg1 70.00 7163.80 2.00 134.20 72.00 7298.00 54.11 0.69
   5.07 1.00 13.94
sdh 15604.80 0.00 442.00 2.00 29755.20 2.00 67.02
15.38 34.76 2.20 100.00
sdh1 15604.80 0.00 442.00 2.00 29755.20 2.00 67.02
15.38 34.76 2.20 100.00
sdi 70.00 0.00 2.00 2.00 72.00 2.00 18.50 0.00
 0.78 0.73 0.30
sdi1 70.00 0.00 2.00 2.00 72.00 2.00 18.50 0.00
 0.73 0.73 0.30
sdj 70.00 0.00 2.00 2.00 72.00 2.00 18.50 0.00
 0.98 0.98 0.40
sdj1 70.00 0.00 2.00 2.00 72.00 2.00 18.50 0.00
 0.93 0.98 0.40
sdk 67.80 1.40 4.20 2.40 72.00 3.80 11.48 0.00
 0.77 0.65 0.44
sdk1 67.80 1.40 4.20 2.40 72.00 3.80 11.48 0.01
 0.77 0.65 0.44
sdl 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdl1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdm 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00
sdm1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
 0.00 0.00 0.00

The list has two lines:
sdh 15604.80 0.00 442.00 2.00 29755.20 2.00 67.02
15.38 34.76 2.20 100.00
sdh1 15604.80 0.00 442.00 2.00 29755.20 2.00 67.02
15.38 34.76 2.20 100.00

, these disks are 100percent utilized , how can go deeper to
understand the cause?(For instance is 67.02 a great value?)

Kind Regards,
hope

Relevant Pages

  • Poor performance on cp on kernel 2.6.27.7-9-xen (openSUSE 11.1)
    ... machine that basically has two test disks, ... PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND ... Now why doesn't Linux have 100 "%util" reported by iostat when I copy ... sdd: 4 disks in RAID-5 ...
    (Linux-Kernel)
  • Re: Configuring storage with Disk Management
    ... Kind regards, ... >disks. ... One of the servers in my company is being moved to a ... >>disks through the Disk Management tool. ...
    (microsoft.public.win2000.file_system)
  • Re: process doing all the disk i/o
    ... avgrq-sz avgqu-sz await svctm %util ... As you can see a couple disks are at 100% utilization. ... The lsof and fuser commands would show you what processes ...
    (comp.os.linux.misc)