SCIENTIFIC-LINUX-USERS Archives

April 2013

SCIENTIFIC-LINUX-USERS@LISTSERV.FNAL.GOV

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Orion Poplawski <[log in to unmask]>
Reply To:
Orion Poplawski <[log in to unmask]>
Date:
Sat, 6 Apr 2013 08:44:37 -0600
Content-Type:
text/plain
Parts/Attachments:
text/plain (29 lines)
On 04/05/2013 07:32 PM, Bill Maidment wrote:
> After switching back to the older kernel, I can confirm that the swap
> usage has returned to normal, even during the backup time 6am-8am. (See
> attached graph)
>
> I'm wondering if this has anything to do with NUMA, which sometimes
> prefers to use swap rather than memory that is slightly slower than the
> currently used memory.
>
> I am using a single Phenom II 955 processor (quad core) on an ASUS
> M4N68T motherboard and SL6.4 upgraded from 6.3

Switching back fixed it for me too.  Max swap usage reduced from 100% to 
25%, all dumps completed on time.  I suppose NUMA could be a factor, 
this is a Xeon L5520 system.  I haven't seen this large swap usage on my 
other older hardware, although I only have the one machine writing 
backups to local disk, remote machines send the backup via the network 
to this host.

I've filed https://bugzilla.redhat.com/show_bug.cgi?id=949166


-- 
Orion Poplawski
Technical Manager                     303-415-9701 x222
NWRA/CoRA Division                    FAX: 303-415-9702
3380 Mitchell Lane                  [log in to unmask]
Boulder, CO 80301              http://www.cora.nwra.com

ATOM RSS1 RSS2