Re: [PATCH 1/4] coredump: add an interface to control the core dump routine

From: Andrew Morton <akpm@linux-foundation.org>
To: David Howells <dhowells@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>,
	"Kawai, Hidehiro" <hidehiro.kawai.ez@hitachi.com>,
	kernel list <linux-kernel@vger.kernel.org>,
	Robin Holt <holt@sgi.com>, Alan Cox <alan@lxorguk.ukuu.org.uk>,
	Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>,
	sugita <yumiko.sugita.yf@hitachi.com>,
	Satoshi OSHIMA <soshima@redhat.com>,
	Hideo AOKI <haoki@redhat.com>
Subject: Re: [PATCH 1/4] coredump: add an interface to control the core dump routine
Date: Thu, 29 Mar 2007 14:17:15 -0700	[thread overview]
Message-ID: <20070329141715.71a6abae.akpm@linux-foundation.org> (raw)
In-Reply-To: <11911.1175195819@redhat.com>

On Thu, 29 Mar 2007 20:16:59 +0100
David Howells <dhowells@redhat.com> wrote:

> Pavel Machek <pavel@ucw.cz> wrote:
> 
> > > Userland core dumper is useful because it is relatively easy to be
> > > customized, but its reliability highly depends on the application
> > > programs.
> > 
> > Fix userland core dumper to be reliable, then.
> 
> I don't think it's that easy.  The userland core dumper, as I understand it,
> has to work *within* an application program (it's a library), thus the
> application program my scotch the core dumper in a couple of ways:

That's no longer necessarily true with the recently-added
dump-to-an-application feature:

core_pattern:
  ...
. If the first character of the pattern is a '|', the kernel will treat
  the rest of the pattern as a command to run.  The core dump will be
  written to the standard input of that program instead of to a file.

That's new in 2.6.20 (maybe .19?) so people probably don't know about it.