1950 with a PERC 6/i internal (RAID1 2x 136.13Gbyte SAS), PERC 6/e to an
MD1000 (RAID5 7x 698.13Gbyte SATA + hot spare), CentOS 5.4, attached as a
head-node to a beowulf, serving NFS over gigabit to 17 slaves.

Internal disks ST3146855SS rev S527
External disks ST3750640NS rev 3BKS3BKS

All has been fine for some time, but now I'm getting some really strange i/o
problems, that I was hoping somebody could advise on.

The machine's been trundling on just nicely, with perfectly reasonable
performance.  Reads are in the 100-140Mbyte/sec for the internal, and
300-360Mbytes/sec for the external.  Sequential writes are >100Mbytes/sec on
the internal, and >150Mbytes/sec on the external.

It's been happy for maybe 6 months.  I did update the kernel mid-november to
2.6.18-164.6.1.el5.  On friday, it went into a high load average state and was
timing out on logins  This would last for a couple of minutes.  Once that'd
passed, nothing was obviously wrong with the machine, no errors in any logs I
can find.  It's done it again over the weekend, and again today.  Load average
peaked at >100, so the machine was decidedly unhappy.

PERC firmware is 6.2.0-0013, driver is the default CentOS driver
00.00.04.08-RH2.

Watching the disk array this morning, it appeared that you'd get a period of
normal blinking activity lights, then it'd all go silent for maybe 5 seconds,
then solid on for a short while, then back to blinking.  This looked odd to
me.

Pointers as to where I should start looking?

jh

_______________________________________________
Linux-PowerEdge mailing list
[email protected]
https://lists.us.dell.com/mailman/listinfo/linux-poweredge
Please read the FAQ at http://lists.us.dell.com/faq

Reply via email to