Date: Sat, 20 Oct 2012 21:58:03 +0300 From: Nikolay Denev <ndenev@gmail.com> To: "freebsd-hackers@freebsd.org Hackers" <freebsd-hackers@freebsd.org> Cc: Rick Macklem <rmacklem@uoguelph.ca>, Ivan Voras <ivoras@freebsd.org> Subject: Re: NFS server bottlenecks Message-ID: <BD7A192B-6208-4560-A955-A4B3C3563E5F@gmail.com> In-Reply-To: <C10B14C4-943E-47CC-B6A7-4596A2D11D73@gmail.com> References: <937460294.2185822.1350093954059.JavaMail.root@erie.cs.uoguelph.ca> <302BF685-4B9D-49C8-8000-8D0F6540C8F7@gmail.com> <k5gtdh$nc0$1@ger.gmane.org> <0857D79A-6276-433F-9603-D52125CF190F@gmail.com> <CAF-QHFUU0hhtRNK1_p9zks2w%2Be22bfWOtv%2BXaqgFqTiURcJBbQ@mail.gmail.com> <6DAAB1E6-4AC7-4B08-8CAD-0D8584D039DE@gmail.com> <23D7CB3A-BD66-427E-A7F5-6C9D3890EE1B@gmail.com> <CAF-QHFWY0drcrUpo7GGD1zQNSDWsEeB_LHAjEbUKrX2ovQHNxw@mail.gmail.com> <C10B14C4-943E-47CC-B6A7-4596A2D11D73@gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Oct 20, 2012, at 4:00 PM, Nikolay Denev <ndenev@gmail.com> wrote: >=20 > On Oct 20, 2012, at 3:11 PM, Ivan Voras <ivoras@freebsd.org> wrote: >=20 >> On 20 October 2012 13:42, Nikolay Denev <ndenev@gmail.com> wrote: >>=20 >>> Here are the results from testing both patches : = http://home.totalterror.net/freebsd/nfstest/results.html >>> Both tests ran for about 14 hours ( a bit too much, but I wanted to = compare different zfs recordsize settings ), >>> and were done first after a fresh reboot. >>> The only noticeable difference seems to be much more context = switches with Ivan's patch. >>=20 >> Thank you very much for your extensive testing! >>=20 >> I don't know how to interpret the rise in context switches; as this = is >> kernel code, I'd expect no context switches. I hope someone else can >> explain. >>=20 >> But, you have also shown that my patch doesn't do any better than >> Rick's even on a fairly large configuration, so I don't think there's >> value in adding the extra complexity, and Rick knows NFS much better >> than I do. >>=20 >> But there are a few things other than that I'm interested in: like = why >> does your load average spike almost to 20-ties, and how come that = with >> 24 drives in RAID-10 you only push through 600 MBit/s through the 10 >> GBit/s Ethernet. Have you tested your drive setup locally (AESNI >> shouldn't be a bottleneck, you should be able to encrypt well into >> Gbyte/s range) and the network? >>=20 >> If you have the time, could you repeat the tests but with a recent >> Samba server and a CIFS mount on the client side? This is probably = not >> important, but I'm just curious of how would it perform on your >> machine. >=20 > The first iozone local run finished, I'll paste just the result here, = and also the same test over NFS for comparison: > (This is iozone doing 8k sized IO ops, on ZFS dataset with = recordsize=3D8k) >=20 > NFS: > random = random bkwd record stride =20 > KB reclen write rewrite read reread read = write read rewrite read =20 > 33554432 8 4973 5522 2930 2906 2908 = 3886 =20 >=20 > Local: > random = random bkwd record stride =20 > KB reclen write rewrite read reread read = write read rewrite read =20 > 33554432 8 34740 41390 135442 142534 24992 = 12493 =20 >=20 >=20 > P.S.: I forgot to mention that the network is with 9K mtu. Here are the full results of the test on the local fs : http://home.totalterror.net/freebsd/nfstest/local_fs/ I'm now running the same test on NFS mount over the loopback interface = on the NFS server machine.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?BD7A192B-6208-4560-A955-A4B3C3563E5F>