Bug 214826 - Poor performance under heavy i/o:
Summary: Poor performance under heavy i/o:
Keywords:
Status: CLOSED WONTFIX
Alias: None
Product: Red Hat Enterprise Linux 4
Classification: Red Hat
Component: kernel
Version: 4.0
Hardware: x86_64
OS: Linux
medium
high
Target Milestone: ---
: ---
Assignee: Brian Maly
QA Contact: Brian Brock
URL: http://www.turkeyforum.com/satforum/
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2006-11-09 17:21 UTC by Bulent Tekcan
Modified: 2008-09-25 06:12 UTC (History)
2 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2008-09-25 06:12:18 UTC
Target Upstream Version:
Embargoed:


Attachments (Terms of Use)

Description Bulent Tekcan 2006-11-09 17:21:12 UTC
Poor performance under heavy i/o:


2.6.9-42.0.3.ELsmp #1 SMP Mon Sep 25 17:24:31 EDT 2006 x86_64 x86_64 x86_64 
GNU/Linux

Our sites high traffic on theplanet,we have a Dual Opteron 4GB ram.Under high 
traffic this error occured.

Nov 9 17:22:23 imagine su(pam_unix)[5976]: session closed for user root 
Nov 9 17:22:46 imagine kernel: warning: many lost ticks. 
Nov 9 17:22:46 imagine kernel: Your time source seems to be instable or some 
driver is hogging interupts 
Nov 9 17:22:46 imagine kernel: rip __do_softirq+0x4d/0xd0


How reproducible:
I cannot reproduce,because only under higf traffic this error occured.After 
this problem my system unstable load goes high,and cpu %2 to 80 jumping.

Comment 2 Brian Maly 2007-02-08 21:41:07 UTC
What timesource is being used here (dmesg|grep time)? Does the error go away if
a different timesource is used?



Can you try booting with each of the following boot args (one at a time) and see
if any make a difference: acpi_irq_balance, noirqbalance and idle=poll



Note You need to log in before you can comment on or make changes to this bug.