Re: PROBLEM: 2.6.6 grinds to a halt with moderate I/O

From: Philippe Gramoullé
Date: Wed Jun 16 2004 - 02:44:53 EST



Hello Micah,

Could you give more information on the Megaraid part of your setup ?

Are the i/o made on a disk/partition controlled by the megaraid ?

If no, does the same behavior occur on a plain scsi disk ?

If yes, what kind of RAID level do you use ? how many disks ?

Could you give megaraid firmware information as well as logical volume settings regarding
read,write and cache policy.

Also, is it a regression over previous kernels, like 2.6.5 or even earlier kernels ?

I've been using 2.6.3-mm3 for weeks now with DELL hardware and a megaraid controller
doing intensive i/o around the clock without any problems. The box has been just rock solid.

Thanks,

Philippe

On Tue, 15 Jun 2004 10:47:45 -0500
Micah Anderson <micah@xxxxxxxxxx> wrote:

|
| Following the format from REPORTING-BUGS please see the below information.
| I unfortunately cannot subscribe to the list, but will follow the thread. I
| have searched high and low, read a number of threads somewhat tangential to
| this problem, and asked a few times in #kernelnewbies before I got to my
| wits end and now will try here. I really appreciate any insight anyone has,
| and will be happy to provide more information or additional tests
| [snip]
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/