Date: Mon, 3 Apr 2006 00:40:12 +0100 (BST) From: Robert Watson <rwatson@FreeBSD.org> To: John Birrell <jb@cimlogic.com.au> Cc: current@FreeBSD.org Subject: Re: HEADS UP: socket and pcb reference changes entering tree today Message-ID: <20060403003428.X76562@fledge.watson.org> In-Reply-To: <20060402230012.GA24758@what-creek.com> References: <20060317141627.W2181@fledge.watson.org> <20060329100839.V19236@fledge.watson.org> <20060401102918.P79188@fledge.watson.org> <20060401170554.R82503@fledge.watson.org> <20060402233436.P76562@fledge.watson.org> <20060402230012.GA24758@what-creek.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, 2 Apr 2006, John Birrell wrote: > I've just updated a current system which also serves as a (socket based) > backup system for a remotely hosted web site with LOTS of file updates. The > update went without a hitch and the system seems to work fine AFAICT. > > I guess that sounds like a bit of an anti-climax, but there really isn't > anything to report. Sorry. 8-) > > Perhaps I just don't know what to look for. Shrug. Well, other than the normal array of panics and bad network behavior, I'm particularly interested in possible memory leaks in the TCP and socket code. Generally speaking, I find the following useful for keeping an eye on it: vmstat -z | head -1 ; vmstat -z | grep -i tcp ; vmstat -z | grep -i socket Of course, because a lot of events and tear-downs in the network stack are asynchronous anyway, you have to watch for the leaks over a longer run time rather than the short term. Finally, I had some reports of additional connection resets from Kris during his testing, which may be tricky to track down if they still exist. Robert N M Watson
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060403003428.X76562>