Red Hat Bugzilla – Bug 131753
System response degrades under heavy i/o loads.
Last modified: 2013-03-06 00:57:30 EST
Description of problem:
The system becomes unresponsive during periods of heavy i/o.
This bug began life as service request 345034. I tried using and
ext2 filesystem in place of ext3 and (not unexpectedly) halved
i/o's but no real change in response time to commands from the
shell prompt, telnets into the system, etc. Am including the
original description of the service request:
Our application does large amounts of i/o (writes out 10GB to a file,
similar amounts from a local file). During these periods, any other
on the system becomes impossible (such as an ls, a remote login,
was wondering if you have any tuning recommendations that you could
I've checked through the support database, but didn't see anything.
been changing system parameters such as /proc/sys/vm/bdflush, using
along with old unix tricks like noatime on file systems, but haven't
gotten the right combination.
Version-Release number of selected component (if applicable):
Steps to Reproduce:
1.Run something that generates a heavy write load (such as the
2.Try to do an ls from a command prompt; try telneting to the
Response time to commands on the order of minutes
Response time to commands in the seconds range.
System is a Compaq Proliant DL380G3 with dual 3.06GHz Xeons with
9GB of memory writing to locally mounted SCSI drives.
Created attachment 103453 [details]
Test program used to reproduce problem
closing, as this appears (at least at the moment) to be a customer
request for VM tuning (tracking in IT48502) and not a VM bug, per se.