Date: Tue, 13 Jan 2009 08:24:20 -0600 From: "Weldon Godfrey" <wgodfrey@ena.com> To: <linimon@FreeBSD.org>, <freebsd-bugs@FreeBSD.org> Subject: RE: kern/130313: [nfs] -n option appears to have no effect, only one master and one server Message-ID: <A7B0A9F02975A74A845FE85D0B95B8FA0C305830@misex01.ena.com> In-Reply-To: <200901091925.n09JPnJ3084977@freefall.freebsd.org> References: <200901091925.n09JPnJ3084977@freefall.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
FYI. Our suspicion that it was needing to spawn more processes was correct. We noticed these sysctl tunables: vfs.nfsrv.minthreads: 4 vfs.nfsrv.maxthreads: 4 vfs.nfsrv.threads: 4 We manually changed vfs.nfsrv.maxthreads to 200 and now it is varying from 7 to 25 and the client delays stopped. The I compared the snapshot of 8-CURRENT and although we have 1.35 of nfsd, some of he upgrades in sys/nfsserver that is in CVS with the same comment is not on our snapshot so the issue of ignoreing -n may not be an issue with HEAD right now, but we are available to test this, sorry. Thanks! Weldon -----Original Message----- From: linimon@FreeBSD.org [mailto:linimon@FreeBSD.org]=20 Sent: Friday, January 09, 2009 1:26 PM To: Weldon Godfrey; linimon@FreeBSD.org; freebsd-bugs@FreeBSD.org Subject: Re: kern/130313: [nfs] -n option appears to have no effect, only one master and one server Synopsis: [nfs] -n option appears to have no effect, only one master and one server State-Changed-From-To: open->closed State-Changed-By: linimon State-Changed-When: Fri Jan 9 19:25:37 UTC 2009 State-Changed-Why:=20 Already documented. http://www.freebsd.org/cgi/query-pr.cgi?pr=3D130313
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?A7B0A9F02975A74A845FE85D0B95B8FA0C305830>