Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Hi
We are using DRBD to mail server shared storage, recently I feel the server
is very slow, so I use iostat tools to monitoring disk status, when mail
queue more than 10, the "await" value of parameter is very high. As below:
avg-cpu: %user %nice %system %iowait %steal %idle
0.12 0.00 0.12 0.00 0.00 99.75
avg-cpu: %user %nice %system %iowait %steal %idle
0.42 0.00 0.25 7.49 0.00 91.84
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz
avgqu-sz await svctm %util
sda 0.00 6752.00 0.00 308.00 0.00 44467.00 144.37
142.56 433.49 3.25 100.10
sda1 0.00 6701.00 0.00 285.00 0.00 40424.00 141.84
134.80 427.90 3.51 100.10
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 0.00 0.00 3.00 0.00 3.00 1.00
0.16 53.00 53.00 15.90
sda4 0.00 51.00 0.00 20.00 0.00 4040.00 202.00
7.60 570.15 46.80 93.60
drbd0 0.00 0.00 0.00 57.00 0.00 456.00 8.00
160.15 5144.61 17.58 100.20
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz
avgqu-sz await svctm %util
sda 0.00 548.51 0.00 234.65 0.00 5548.51 23.65
20.97 92.11 4.22 99.11
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 0.00 0.00 51.49 0.00 51.49 1.00
0.99 19.13 19.17 98.71
sda4 0.00 548.51 0.00 183.17 0.00 5497.03 30.01
19.98 112.62 5.38 98.61
drbd0 0.00 0.00 0.00 717.82 0.00 5742.57 8.00
1092.35 1621.75 1.38 99.11
avg-cpu: %user %nice %system %iowait %steal %idle
0.25 0.00 0.29 0.00 0.00 99.46
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz
avgqu-sz await svctm %util
sda 0.00 885.00 0.00 228.00 0.00 8498.00 37.27
26.45 112.99 4.39 100.10
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 0.00 0.00 50.00 0.00 50.00 1.00
0.99 19.70 19.86 99.30
sda4 0.00 885.00 0.00 178.00 0.00 8448.00 47.46
25.46 139.20 5.59 99.50
drbd0 0.00 0.00 0.00 1060.00 0.00 8480.00 8.00
2345.33 1761.36 0.94 100.10
Can I improve the performance of DRBD?
The following is my drbd.conf configration:
global {
# minor-count 64;
# dialog-refresh 5; # 5 seconds
# disable-ip-verification;
usage-count no;
}
common {
protocol C;
disk {
on-io-error detach;
#size 454G;
no-disk-flushes;
no-md-flushes;
}
net {
sndbuf-size 512k;
# timeout 60; # 6 seconds (unit = 0.1 seconds)
# connect-int 10; # 10 seconds (unit = 1 second)
# ping-int 10; # 10 seconds (unit = 1 second)
# ping-timeout 5; # 500 ms (unit = 0.1 seconds)
max-buffers 8000;
unplug-watermark 1024;
max-epoch-size 8000;
# ko-count 4;
# allow-two-primaries;
cram-hmac-alg "sha1";
shared-secret "hdhwXes23sYEhart8t";
after-sb-0pri disconnect;
after-sb-1pri disconnect;
after-sb-2pri disconnect;
rr-conflict disconnect;
# data-integrity-alg "md5";
# no-tcp-cork;
}
syncer {
rate 120M;
al-extents 517;
}
}
resource data {
on mail1.domain.com {
device /dev/drbd0;
disk /dev/sda4;
address 192.168.8.62:7788;
meta-disk /dev/sda3 [0];
}
on mail2.domain.com {
device /dev/drbd0;
disk /dev/sda4;
address 192.168.8.63:7788;
meta-disk /dev/sda3 [0];
}
}
Please help me. Thanks.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20151119/9af266b3/attachment.htm>