Date: Mon, 11 Apr 2011 09:49:32 +0400 From: Gleb Smirnoff <glebius@FreeBSD.org> To: Przemyslaw Frasunek <przemyslaw@frasunek.com> Cc: freebsd-net@FreeBSD.org, Eugene Grosbein <egrosbein@rdtc.ru> Subject: Re: mpd5/Netgraph issues after upgrading to 7.4 Message-ID: <20110411054932.GU84445@FreeBSD.org> In-Reply-To: <4DA23090.8060206@frasunek.com> References: <4D947756.6050808@freebsd.lublin.pl> <4D9F6C71.1040209@frasunek.com> <4DA171BA.9000507@frasunek.com> <4DA1E39C.9090300@rdtc.ru> <4DA23090.8060206@frasunek.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Apr 11, 2011 at 12:34:56AM +0200, Przemyslaw Frasunek wrote: P> > Use command "vmstat -z|egrep 'ITEM|NetGraph'" and check FAILURES column. P> > If you see non-zero values there, you need to increase netgraph memory limits P> > net.graph.maxdata and net.graph.maxalloc using /boot/loader.conf. P> P> Unfortunately, increasing net.graph.maxdata & net.graph.maxalloc didn't P> solved EPERM problems on netgraph control sockets. It is still appearing P> every few hours, but failure counters are zero: IMO, any kind of memory allocation code (malloc, uma, netgraph item allocator) never return EPERM, they return ENOMEM or ENOBUFS. So, there is a bug somewhere else. -- Totus tuus, Glebius.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20110411054932.GU84445>