Date: Sat, 1 Feb 2014 11:05:52 -0500 (EST) From: Rick Macklem <rmacklem@uoguelph.ca> To: J David <j.david.lists@gmail.com> Cc: freebsd-net@freebsd.org, Garrett Wollman <wollman@freebsd.org> Subject: Re: Terrible NFS performance under 9.2-RELEASE? Message-ID: <1966386250.1241234.1391270752429.JavaMail.root@uoguelph.ca> In-Reply-To: <CABXB=RQDDn2AW0tU4hb9mS5hN5B52VFcCGiicv0SCkMB7SEKAg@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
J David wrote: > On Fri, Jan 31, 2014 at 6:16 PM, Rick Macklem <rmacklem@uoguelph.ca> > wrote: > > You can certainly try "-o rsize=61440,wsize=61440" (assuming a 4K > > page size) > > for the mount, if you'd like. > > This has previously been tested with all 4k steps between 16k and > 32k. > All of them perform worse than > > With 61440, NFS fails outright on the random read test: > > $ iozone -e -I -s 1g -r 4k -i 0 -i 2 > > Iozone: Performance Test of File I/O > > Version $Revision: 3.420 $ > > Compiled for 64 bit mode. > > Build: freebsd > > [...] > > Include fsync in write timing > > O_DIRECT feature enabled > > File size set to 1048576 KB > > Record Size 4 KB > > Command line used: iozone -e -I -s 1g -r 4k -i 0 -i 2 > > Output is in Kbytes/sec > > Time Resolution = 0.000005 seconds. > > Processor cache size set to 1024 Kbytes. > > Processor cache line size set to 32 bytes. > > File stride size set to 17 * record size. > > random > random bkwd record stride > > KB reclen write rewrite read reread read > write read rewrite read fwrite frewrite fread freread > > 1048576 4 24688 23891 > > Error reading block at 1073729536 > > read: Bad file descriptor > > > Upon using the -w option, which leaves the file intact on exit, it's > possible to see that it's not even 1gig in length: > > $ ls -aln iozone.tmp > > -rw-r----- 1 1000 0 1073709056 Feb 1 01:18 iozone.tmp > > > It's 32k short, which is a pretty surprising result. > Ok, I knew that non-powers of 2 could result in problems. I thought they only occurred when the size wasn't an exact multiple of page size, but it seems there are non-power of 2 problems. rick > Thanks! > _______________________________________________ > freebsd-net@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-net > To unsubscribe, send any mail to > "freebsd-net-unsubscribe@freebsd.org" >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1966386250.1241234.1391270752429.JavaMail.root>