[Lustre-discuss] tuning max_sectors

Götz Waschk goetz.waschk at gmail.com
Fri Apr 17 04:08:34 PDT 2009


Hi everyone,

on starting an OST I get this message in the log:

Lustre: zn_atlas-OST0000: underlying device cciss/c1d0p1 should be
tuned for larger I/O requests: max_sectors = 1024 could be up to
max_hw_sectors=2048

/dev/cciss/c1d0p1 is a RAID6 on a HP Smart Array P800 controller with
12 750 GB SATA drives. The stripe size is 128 KB according to the
hpacucli script.

The OST was created with
mkfs.lustre --fsname=zn_atlas --ost --mkfsoptions="-E stride=32 -E
stripe-width=320 -J device=/dev/vg00/j-ost0 -i 1048576"
--mgsnode=192.168.224.2 at o2ib1,141.34.218.7 at tcp0 /dev/cciss/c1d0p1

What can I do?


Regards, Götz Waschk



More information about the lustre-discuss mailing list