lkml.org 
[lkml]   [2003]   [Jun]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
Subject[VM] writes starve reads in 2.5.72-bk1
load:                           gzipping a 128M file, with "gzip file"
CPU: p3-500
physical RAM installed: 256M
kernel: 2.5.72-bk1
drive: one 10krpm IBM
controller: DAC960PL RAID controller

0 1 9384 3960 33640 116184 0 0 1280 4096 1022 122 63 7 0 30
1 0 9384 4016 33220 116568 0 0 1792 0 1096 122 81 7 0 12
1 0 9384 3624 33156 117112 0 0 2048 0 1036 119 92 8 0 0
1 1 9384 4856 32024 116876 0 0 1024 11432 1092 145 48 5 2 44
0 2 9384 4632 32024 117164 0 0 128 7288 1120 208 8 2 0 90
0 2 9384 4072 32024 117676 0 0 256 9172 1149 224 12 2 0 86
1 0 9384 3624 31516 118684 0 0 896 944 1146 145 38 4 0 58
1 0 9384 3288 30916 119764 0 0 2048 0 1031 117 92 8 0 0
1 0 9384 4128 30620 119228 0 0 1920 92 1062 160 92 7 1 0
1 0 9384 3960 30208 120120 0 0 2048 0 1033 115 93 7 0 0
procs -----------memory---------- ---swap-- -----io---- --system-- ----cpu----
r b swpd free buff cache si so bi bo in cs us sy id wa
problem as i see it:

although the drive is mostly idle since the cpu is too slow to max it out,
reads are starved during bursts of gzipped data writeouts,
causing gzip to spend its time on sleeping on request completion.

regards, Samium Gromoff
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:46    [from the cache]
©2003-2011 Jasper Spaans