Date: Fri, 02 May 2008 11:50:22 -0700 From: gnn@freebsd.org To: Andrew Snow <andrew@modulus.org> Cc: Alfred Perlstein <alfred@freebsd.org>, freebsd-current@freebsd.org Subject: Re: Some odd behaviour of vmstat and vmtotal... Message-ID: <m27ieck0b5.wl%gnn@neville-neil.com> In-Reply-To: <48195384.5030204@modulus.org> References: <m2lk2ultc1.wl%gnn@neville-neil.com> <20080501045736.GU30325@elvis.mu.org> <48195384.5030204@modulus.org>
next in thread | previous in thread | raw e-mail | index | archive | help
At Thu, 01 May 2008 15:22:12 +1000, Andrew Snow wrote: > > > > In deploying 7.0 at work we were finding a persistent problem when > > running "vmstat 1" on systems. The problem shows up as a 10ms "pause" > > in processing, usually packet stamping and forwarding by a user level > > process. > > Thats interesting. I once did some quick and dirty profiling of vmtotal > and found it runs extremely quickly. Are you running on slow machines > (embedded perhaps)? Or do you have a situation where you perhaps have > alot more VM objects created than normal? I can't think of a good > example where this would be the case.. > Doing a buildworld will cause you to see this. It's all about how many vm objects are on the list. Best, George
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?m27ieck0b5.wl%gnn>