Date: Mon, 11 Apr 2011 04:59:41 +0700 From: Eugene Grosbein <egrosbein@rdtc.ru> To: Przemyslaw Frasunek <przemyslaw@frasunek.com> Cc: freebsd-net@freebsd.org Subject: Re: mpd5/Netgraph issues after upgrading to 7.4 Message-ID: <4DA2284D.2060804@rdtc.ru> In-Reply-To: <4DA216D8.9090009@frasunek.com> References: <4D947756.6050808@freebsd.lublin.pl> <4D9F6C71.1040209@frasunek.com> <4DA171BA.9000507@frasunek.com> <4DA1E39C.9090300@rdtc.ru> <4DA216D8.9090009@frasunek.com>
index | next in thread | previous in thread | raw e-mail
On 11.04.2011 03:45, Przemyslaw Frasunek wrote: >> Use command "vmstat -z|egrep 'ITEM|NetGraph'" and check FAILURES column. >> If you see non-zero values there, you need to increase netgraph memory limits >> net.graph.maxdata and net.graph.maxalloc using /boot/loader.conf. > > Thanks, indeed it helped a lot. I also noticed that other zones have > non-zero failure counters: > > UMA Slabs: 64, 0, 2666, 1051, 128676, > 127 > 128 Bucket: 524, 0, 1455, 316, 82489, > 97401821 > g_bio: 132, 0, 0, 3190, 11471737, > 3 > ata_request: 192, 0, 0, 1880, 2905852, > 378 > rtentry: 124, 0, 2513, 1765, 802803, > 132 > pffrent: 16, 5075, 175, 3073, 48983719, > 6 > pffrag: 48, 0, 39, 3081, 15699916, > 216 > > I'm quite anxious about "ata_request" failures. In general, you should not worry about failures here - they are transient and normal. Afaik, that's only mpd that cannot gracefully recover from such errors (it should). So, increasing mentioned tunnables is only workaround from mpd's deficiency. Eugene Grosbeinhome | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4DA2284D.2060804>