[8551] in Info-AFS_Redistribution
Re: [OpenAFS] OpenAFS Project List
daemon@ATHENA.MIT.EDU (Nathan Neulinger)
Wed Mar 14 08:05:27 2001
Message-ID: <3AAF6B14.BFB8DFCA@umr.edu>
Date: Wed, 14 Mar 2001 06:59:00 -0600
From: Nathan Neulinger <nneul@umr.edu>
MIME-Version: 1.0
CC: info-afs@transarc.com, openafs-info@openafs.org
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
> I seem to recall that results of some performance tests were posted here
> or on openafs-devel in the not-too-distant past. The performance problems
> with vos dump appear to be primarily in the dump process itself, _not_ in
> the network transfer.
I don't get that... What is so horrible about the dump process that it
can reduce a disk capable of 35 MB/sec sustained reads down to 3.5
MB/sec dumps? Something must be screwy with that. There was just a note
in info-afs from someone using a EMC/Clarion array, and you can be sure
that does at least 35 MB/sec... (well, for as much as they cost, I
certainly hope they can beat 35)
He was saying that butc based backups are extremely fast, whereas 'vos
dump' backups are really slow. What is butc doing differently? Does butc
not generate the equivalent of a vos dump internally?
-- Nathan
------------------------------------------------------------
Nathan Neulinger EMail: nneul@umr.edu
University of Missouri - Rolla Phone: (573) 341-4841
CIS - Systems Programming Fax: (573) 341-4216
