[clug] finding source of high wait states
jm
jeffm at ghostgun.com
Mon Sep 21 00:06:56 MDT 2009
I've got a machine which is suffering from high CPU wait states. The
load on the machine is sitting around 15 and it's spending about 60-90%
of time in the wait state. This is normally assoicated with I/O of some
form. I'm guessing disk. Is there someway to track down which program(s)
are causing this, which files are being accessed, is there any i/o
errors (checked logs including dmesg and don't see any), etc?
Normally I use iostat, but I came across dstat recently. Here's example
output for this machine:
$dstat -D total,sda,sdb,sdc,sdd
----total-cpu-usage---- -dsk/total----dsk/sda-----dsk/sdb-----dsk/sdc-----dsk/sdd-- -net/total- ---paging-- ---system--
usr sys idl wai hiq siq| read writ: read writ: read writ: read writ: read writ| recv send| in out | int csw
15 3 20 61 0 1|3118k 3957k:3112k 654k:6684B 3303k: 105B 79B: 19B 79B| 0 0 |3701B 4301B| 601 1596
6 1 7 84 1 1| 968k 1920k: 960k 672k:8192B 1248k: 0 0 : 0 0 |3191B 39k| 0 0 | 494 2617
13 3 6 77 0 1| 912k 920k: 896k 204k: 16k 716k: 0 0 : 0 0 |6183B 64k| 0 0 | 491 2130
22 2 7 68 0 0| 880k 1504k: 872k 496k:8192B 1008k: 0 0 : 0 0 | 24k 80k| 0 0 | 603 2157
1 1 6 92 0 0| 996k 1640k: 992k 500k:4096B 1140k: 0 0 : 0 0 |2509B 52k| 0 0 | 476 2133
6 2 5 87 0 0| 952k 2720k: 940k 1072k: 12k 1648k: 0 0 : 0 0 |2782B 49k| 0 0 | 465 1977
20 1 5 74 0 0| 880k 968k: 872k 228k:8192B 740k: 0 0 : 0 0 |3684B 30k| 0 0 | 449 1860
10 2 8 79 0 1| 920k 2008k: 916k 716k:4096B 1292k: 0 0 : 0 0 |1874B 41k| 0 0 | 467 2081
6 1 7 86 0 0| 864k 2160k: 848k 824k: 16k 1336k: 0 0 : 0 0 |2193B 30k| 0 0 | 433 1840
2 0 3 91 2 2| 316k 2872k: 308k 1064k:8192B 1808k: 0 0 : 0 0 | 18k 36k| 0 0 | 747 2234
2 2 0 94 0 2| 0 3060k: 0 1664k: 0 1396k: 0 0 : 0 0 | 92k 45k| 0 0 | 857 4393
7 1 3 88 0 1| 680k 2540k: 676k 1188k:4096B 1352k: 0 0 : 0 0 |5998B 45k| 0 0 | 593 3203
Jeff.
More information about the linux
mailing list