[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: how to counteract slowdown


--On Monday, November 19, 2001 12:10:21 PM -0800 Andrew Morton <akpm zip com au> wrote:

Here's a top:

Thanks. All looks fairly normal, although I'd expect kjournald to be working harder.

Could you please try Neil's suggestion:

echo 40 0 0 0 60 300 60 0 0 > /proc/sys/vm/bdflush

which should smooth out the ext3 checkpointing and may indeed
help if the machine is stalled by large checkpoint writeout.

Sadly, no I can't. The machine is a production server :-(

It's been running with data=writeback and journal for the last six days without problems.

If it helps tracking down why the problem surfaces with data=ordered but not with data=writeback I'll ask the customer if another test run will be accepted by the users.

I only want to do testing on a production machine if it can not be avoided.


from the desk of Patrick C. F. Ernzer
Red Hat Europe

Attachment: pgp00009.pgp
Description: PGP signature

[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]