lkml.org 
[lkml]   [1998]   [Jun]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Multiple swap partition uglies (fwd)
Hi James.

>>>> Rik - the problem is NOT with swapoff. Swapoff'ing one of the
>>>> drives actually solves the problem (ok it takes a while, but this
>>>> is no different from the performance I get _all the time_ when
>>>> swapping off two drives). The problem is with the 2 swap drive
>>>> setup. Sometimes, paging takes forever. When I swapoff one of the
>>>> drives, to revert to a 1 swap partition setup, the problem goes
>>>> away.

>>> Absolutely clear. You have 1 disk off of which the programs,
>>> libraries and other files are paged and is used for swap and
>>> another disk which is used for swap and not-often-used data.

>>> This means that the first disk will have to perform double
>>> duty, which can be very slow, especially when the swap partition
>>> is physically remote from the / and /usr partition.

>> I don't think that's the problem since I can reproduce it here, and on
>> my setup, neither of the swap partitions are sharing a drive with the
>> executables. Here's the system map for reference:

>> Q> /dev/hda => / /usr /usr/local /root
>> Q> /dev/hdb => /usr/doc /tmp (swap) /home
>> Q> /dev/hdc => /usr/src (swap) /home/ftp

>> It appears to be a bug that only shows itself when multiple swap
>> partitions have the same priority, since it doesn't appear when they
>> have different priorities, and this suggests that there's something up
>> with the round-robin algorithm referred to in the swapon/swapoff
>> manpages...

> Well I've got (from memory, I'm at work atm)...

> /dev/sda /usr swap pri=2
> /dev/sdb / swap pri=1
> /dev/sdc /boot swap pri=1

> Which seems is working fine.

Can you confirm that setup? If so, it narrows the conditions down
further - ALL swap partitions must have the SAME priority for the bug
to hit...

Best wishes from Riley.


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu

\
 
 \ /
  Last update: 2005-03-22 13:42    [W:0.087 / U:0.072 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site