Date: Fri, 18 Apr 2008 21:32:28 -0700 From: Xin LI <delphij@delphij.net> To: "George V. Neville-Neil" <gnn@neville-neil.com> Cc: Chris Pratt <eagletree@hughes.net>, d@delphij.net, net@freebsd.org Subject: Re: zonelimit issues... Message-ID: <480975DC.3090600@delphij.net> In-Reply-To: <m2y77asixh.wl%gnn@neville-neil.com> References: <m2hcdztsx2.wl%gnn@neville-neil.com> <48087C98.8060600@delphij.net> <382258DB-13B8-4108-B8F4-157F247A7E4B@hughes.net> <m2y77asixh.wl%gnn@neville-neil.com>
next in thread | previous in thread | raw e-mail | index | archive | help
George V. Neville-Neil wrote: [snip] > I believe that a better solution is possible, but it will take more > careful study. One option is to start adding drain routines to UDP > that cause the protocol to drop packets under load, which is the > problem we're seeing. In our tests the server process cannot read > data fast enough to clear enough mbufs/clusters back to the system and > it gets stuck in a write() call. I'm not very sure, but in the past, the problem seems to be that for some reasons the sleep threads on zonelim were not being awaken any more, have you tried to adjust the nmbcluster sysctl (like a 2x increase) to see if the problem goes away? Cheers, -- Xin LI <delphij@delphij.net> http://www.delphij.net/ FreeBSD - The Power to Serve!
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?480975DC.3090600>