Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
I have a drbd (drbd 0.7.19) setup on Centos 3.7 with software raid Everything is Ok but I have hundreds of messages of this type in the log file Jul 24 11:49:31 mail01 kernel: raid5: switching cache buffer size, 4096 --> 512 Jul 24 11:49:31 mail01 kernel: raid5: switching cache buffer size, 512 --> 4096 Jul 24 11:49:31 mail01 kernel: raid5: switching cache buffer size, 4096 --> 512 Jul 24 11:49:31 mail01 kernel: raid5: switching cache buffer size, 512 --> 4096 Jul 24 11:49:31 mail01 kernel: raid5: switching cache buffer size, 0 --> 4096 The messages are much more frequent on the primary node, but occasionally I also see them on the secondary node I understand that this continous switching reduces performance quite a lot. Can anyone suggest why this is happening? my drbd.conf file: resource r0 { protocol C; incon-degr-cmd "echo '!DRBD! pri on incon-degr' | wall ; sleep 60 ; halt -f"; startup { degr-wfc-timeout 15; # 2 minutes. } disk { on-io-error detach; } net { max-buffers 4096; } syncer { rate 70M; group 1; al-extents 257; } on mail01.domain.loc { device /dev/drbd0; disk /dev/md3; address 10.3.0.1:7788; meta-disk internal; } on mail02.domain.loc { device /dev/drbd0; disk /dev/md3; address 10.3.0.2:7788; meta-disk internal; } } -- ------------------------------------------------------------------------ /Ove Fredrik Thoresen / <mailto:othoresen at yayamedia.it>othoresen at yayamedia dot it