Date: Wed, 29 Sep 2010 16:32:10 +0300 From: Andriy Gapon <avg@icyb.net.ua> To: Attilio Rao <attilio@freebsd.org> Cc: Ryan Stone <rstone@sandvine.com>, FreeBSD Current <current@freebsd.org>, Ed Maste <emaste@sandvine.com> Subject: Re: [PATCH] Netdump for review and testing -- preliminary version Message-ID: <4CA33FDA.4020001@icyb.net.ua> In-Reply-To: <AANLkTikA5OUYD1A9pqCqVEZ5qk%2BVECq8x-fnRXnpp0KE@mail.gmail.com> References: <AANLkTikA5OUYD1A9pqCqVEZ5qk%2BVECq8x-fnRXnpp0KE@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
on 28/09/2010 20:39 Attilio Rao said the following: > In order to work into an "up and running" system (meant as with all > the devices in place) the netdump handler hooks as a pre-sync handler > (differently from other dumping routines). It however suffers some I actually like this idea. I think that regular dump should also be done at that time. Shouldn't we try to dump memory as early as possible, so that as little of it as possible is modified? (Not that I like sync-on-panic option at all) > problems typical of other dumping mechanism. For example, on DDB > entering unlocked version of polling handler is used, in order to > reduce the risk of deadlocks during inspections*. That reflects, among > the netdump methods, the existence of 2 versions of polling hooks, > where the "unlocked" is meant as reducing locking as much as possible. -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4CA33FDA.4020001>