Hi All,
Hope this is the correct forum for asking my questions. Pl forgive
me if it is otherwise.
I am facing severe reliability issues with the following environment:
OS: MANDRIVA 2006
KERNEL : 2.6.12-12mdksmp
RAID CARD: INTEL SRCS16
KERNEL MODULE: megaraid_mbox
DISKS (these are 400 GB units) I am using:
HITACHI ATA HDS724040KLSA80
SEAGATE ATA ST3400832AS
After I setup the hardware RAID, it seems to work ok (the read/write
performance is very poor though) but after a few days, the RAID disk
collapses with the following errors in /var/log/messages:
Feb 4 05:49:58 archive kernel: scsi2 (0:0): rejecting I/O to offline device
Feb 4 05:49:58 archive kernel: EXT3-fs error (device sdc1): ext3_readdir: directory #1464833 contains a hole at offset 4096
My questions:
a) Has anyone in this list tried this CARD+DISK combination and if so what
are the experiences ?
b) What am I possibly doing wrong ? I am using the same disks on a different
system which has onboard SATA support. I have 8 such ports and I have
configured a software RAID5 on that one. It seems to be quite stable and
also the I/O thruput seems to be at least twice that of the hardware
RAID5 configuration.
Pl try and share any information/suggestion you may have on this.
--ajit
-
: send the line "unsubscribe linux-scsi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
