Copying gluster-devel@ From: Brian Taber <btaber@xxxxxxxxxxxxx> Date: Oct 15, 2007 3:59 AM Subject: Re: Performance To: Anand Avati <avati@xxxxxxxxxxxxx> Now there's a beautiful thing.... NFS Write: time dd if=/dev/zero bs=65536 count=15625 of=/shared/1Gb.file 1024000000 bytes (1.0 GB) copied, 62.9818 seconds, 16.3 MB/s Gluster Write: time dd if=/dev/zero bs=65536 count=15625 of=/mnt/glusterfs/1Gb.file 1024000000 bytes (1.0 GB) copied, 41.74 seconds, 24.5 MB/s NFS Read: time dd if=/shared/1Gb.file bs=65536 count=15625 of=/dev/zero 1024000000 bytes (1.0 GB) copied, 44.4734 seconds, 23.0 MB/s Gluster Read: time dd if=/mnt/glusterfs/1Gb.file bs=65536 count=15625 of=/dev/zero 1024000000 bytes (1.0 GB) copied, 42.1526 seconds, 24.3 MB/s this test is performed within a VMWare virtual machine, so network speed isn't as good. I tried it from outsite, 1000MB network: NFS Write: time dd if=/dev/zero bs=65536 count=15625 of=/shared/1Gb.file 1024000000 bytes (1.0 GB) copied, 27.619 seconds, 37.1 MB/s Gluster Write: time dd if=/dev/zero bs=65536 count=15625 of=/mnt/glusterfs/1Gb.file 1024000000 bytes (1.0 GB) copied, 11.1978 seconds, 91.4 MB/s NFS Read: time dd if=/shared/1Gb.file bs=65536 count=15625 of=/dev/zero 1024000000 bytes (1.0 GB) copied, 43.5323 seconds, 23.5 MB/s Gluster Read: time dd if=/mnt/glusterfs/1Gb.file bs=65536 count=15625 of=/dev/zero 1024000000 bytes (1.0 GB) copied, 30.6922 seconds, 33.4 MB/s > Brian, > block size of 1kb is too small and expensive, especially for network or > fuse based filesystems. Please try with a larger block size like 64kb. > > avati > > On 10/14/07, Brian Taber <btaber@xxxxxxxxxxxxx> wrote: >> >> I am new to ClusterFS and I am looking for a replacement for my NFS >> setup. >> I have configured a clusterfs server on top of a raid 5 array on 4 SATA >> hard drives. Directly I can get a speed of 72.3 MB/s weh I do a: >> >> dd if=/dev/zero bs=1024 count=1000000 of=/data/1Gb.file >> >> If I do the same test over NFSv3 I get performance of 14.1 MB/s >> >> If I do the same test over the gluster mount, I get perfromance of >> 3.6MB/s >> >> Am I doing something wrong here? How can I increase my performance to >> the >> same or beyond my current NFS? >> >> I setup the server with this config: >> >> volume brick-ns >> type storage/posix >> option directory /gluster-ns >> end-volume >> >> volume brick >> type storage/posix >> option directory /data/gluster >> end-volume >> >> volume iothreads1 #iothreads can give performance a boost >> type performance/io-threads >> option thread-count 8 >> subvolumes brick >> end-volume >> >> volume server >> type protocol/server >> subvolumes iothreads1 brick-ns >> option transport-type tcp/server # For TCP/IP transport >> option auth.ip.iothreads1.allow 192.168.* >> option auth.ip.brick-ns.allow 192.168.* >> end-volume >> >> >> and setup a client with: >> >> volume client1-ns >> type protocol/client >> option transport-type tcp/client >> option remote-host 192.168.200.201 >> option remote-subvolume brick-ns >> end-volume >> >> volume client1 >> type protocol/client >> option transport-type tcp/client >> option remote-host 192.168.200.201 >> option remote-subvolume iothreads1 >> end-volume >> >> volume bricks >> type cluster/unify >> subvolumes client1 >> option namespace client1-ns >> option scheduler alu >> option alu.limits.min-free-disk 60GB # Stop creating >> files >> when free-space lt 60GB >> option alu.limits.max-open-files 10000 >> option alu.order >> disk-usage:read-usage:write-usage:open-files-usage:disk-speed-usage >> option alu.disk-usage.entry-threshold 2GB # Units in KB, MB >> and >> GB are allowed >> option alu.disk-usage.exit-threshold 60MB # Units in KB, MB >> and >> GB are allowed >> option alu.open-files-usage.entry-threshold 1024 >> option alu.open-files-usage.exit-threshold 32 >> option alu.stat-refresh.interval 10sec >> end-volume >> >> volume writebehind #writebehind improves write performance a lot >> type performance/write-behind >> option aggregate-size 131072 # in bytes >> subvolumes bricks >> end-volume >> >> >> When trying the >> >> >> >> _______________________________________________ >> Gluster-devel mailing list >> Gluster-devel@xxxxxxxxxx >> http://lists.nongnu.org/mailman/listinfo/gluster-devel >> > > > > -- > It always takes longer than you expect, even when you take into account > Hofstadter's Law. > > -- Hofstadter's Law > -- It always takes longer than you expect, even when you take into account Hofstadter's Law. -- Hofstadter's Law