Date: Sun, 1 Sep 2013 22:11:14 +0300 From: Mikolaj Golub <trociny@FreeBSD.org> To: "Sam Fourman Jr." <sfourman@gmail.com> Cc: FreeBSD FS <freebsd-fs@freebsd.org> Subject: Re: NFS on ZFS pure SSD pool Message-ID: <20130901191113.GC15654@gmail.com> In-Reply-To: <CAOFF%2BZ02Z%2BAezgQ9WufbB40P00qDL2i3iqpAfJUfbMfJ-gSeTw@mail.gmail.com> References: <CAOFF%2BZ2C26V3Ktuvj5RFwGN%2BH657OPXm796TqA54xOpQj1TVFg@mail.gmail.com> <258054624.15907722.1377905324980.JavaMail.root@uoguelph.ca> <20130901181630.GB15654@gmail.com> <CAOFF%2BZ02Z%2BAezgQ9WufbB40P00qDL2i3iqpAfJUfbMfJ-gSeTw@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, Sep 01, 2013 at 02:28:45PM -0400, Sam Fourman Jr. wrote: > > BTW, I noticed that nfsd sets listen backlog to 5. Isn't it a bit low > > for servers that might have hundreds clients? > > > > is there a sysctl to increase the listen backlog for nfsd? No. It is hardcoded to 5 in nfsd.c. If it had been set to -1 instead, the system default would have been used and could be tuned (kern.ipc.soacceptqueue). But my note was just an observation and I am not sure this makes any difference in your case, without seeing netstat output. -- Mikolaj Golub
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20130901191113.GC15654>