Re: kern/47702: coredumping big programs freeze NFS during dump

[Martin Husemann <martin%duskware.de@localhost>]

The following reply was made to PR kern/47702; it has been noted by GNATS.

From: Martin Husemann <martin%duskware.de@localhost>
To: gnats-bugs%NetBSD.org@localhost
Cc: 
Subject: Re: kern/47702: coredumping big programs freeze NFS during dump
Date: Thu, 28 Mar 2013 16:48:30 +0100

 On Thu, Mar 28, 2013 at 03:15:00PM +0000, reinoud%NetBSD.org@localhost wrote:
 > Shouldn't it be possible to have the process write out the data beginning 
 > with
 > the pages that are in memory, freeing them ASAP and then, using demand
 > swapping, write out the other pages/info?
 
 The core is written sequentially, by calling back from the exec pack to
 coredump_write() with exec format specific chunks of data (for elf: sections).
 
 It all ends up in a vn_rdwr(UIO_WRITE,...) call.
 
 There is no reason any of these pages should be wired into kernel space,
 so even if the order of pages is not optimized for the resident ones first,
 already written ones should be elligible for recycling.
 
 Are you sure the the NFS server is not doing something wrong/slow here
 and the problem is not the client?
 
 Btw: there are several ways to move the coredumps out of your homedir,
 the two most simple ones are to not start firefox from ~ or to set
 kern.defcorename = /tmp/%n.core.
 
 Martin