Re: Swap area: why not more than 128M each?

H. Peter Anvin (hpa@transmeta.com)
13 Mar 1998 21:02:08 GMT

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: C.J. Beyer: "3c595 vortex problems under high network loads"
Previous message: Dave Wreski: "Re: [OFFTOPIC]: Linux is losing to Macs in the RC5 effort!"
Maybe in reply to: Lagos Munoz Leonardo Alberto: "Swap area: why not more than 128M each?"

Followup to: <19980313204039.63413@lucifer.guardian.no>
By author: Alexander Kjeldaas <astor@guardian.no>
In newsgroup: linux.dev.kernel
>
> Not that I'm against large swapfiles or anything, but with 1GB+ of
> memory, putting 4GB of swap on one disk is not a good idea. On those
> systems you need to spread the swap on lots of disks to get reasonable
> swap-bandwidth/memory.
>

Depends on what you're doing. Some people use swap mostly for
"parking" processes in T state, as can happen if you're using LSF (a
commercial load-distribution system), for example. It can eat up a
*lot* of swap in no time.

-hpa

-- 
    PGP: 2047/2A960705 BA 03 D3 2C 14 A8 A8 BD  1E DF FE 69 EE 35 BD 74
    See http://www.zytor.com/~hpa/ for web page and full PGP public key
        I am Bahá'í -- ask me about it or see http://www.bahai.org/
   "To love another person is to see the face of God." -- Les Misérables

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

Next message: C.J. Beyer: "3c595 vortex problems under high network loads"
Previous message: Dave Wreski: "Re: [OFFTOPIC]: Linux is losing to Macs in the RC5 effort!"
Maybe in reply to: Lagos Munoz Leonardo Alberto: "Swap area: why not more than 128M each?"