lkml.org 
[lkml]   [2010]   [Nov]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: 2.6.36 io bring the system to its knees
Date
Hello, 

On Sun, 31 Oct 2010 09:51:32 +0800, Wu Fengguang wrote:
> It may also help to lower the dirty ratio.
>
> echo 5 > /proc/sys/vm/dirty_ratio
>
> Memory pressure + heavy write can easily hurt responsiveness.
>
> - eats up to 20% (the default value for dirty_ratio) memory with dirty
> pages and hence increase the memory pressure and number of swap IO

My experience has been different with that. Wouldn't it make more sense
to _increase_ dirty_ratio (to 50 lets say) and at the same time decrease
dirty_background_ratio? That way writing to disk starts early, but the
related apps stall waiting for I/O only when dirty_ratio is reached.


Thanks,
Dimitris

>
> - the file copy makes the device write congested and hence makes
> pageout() easily blocked in get_request_wait()
>
> As a result every application may be slowed down by the heavy swap IO
> when page fault as well as being blocked when allocating memory (which
> may go into direct reclaim and then call pageout()).
>
> Thanks,
> Fengguang




\
 
 \ /
  Last update: 2010-11-01 21:27    [W:0.151 / U:0.012 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site