[Gluster-users] Performance question

[Shehjar Tikoo]

Joe Julian wrote:
> I'm using an unpatched fuse 2.7.4-1 and glusterfs 2.0.2-1 with the 
> following configs and have this result which surprised me:
> 
> # dd if=/dev/zero of=foo bs=512k count=1024 1024+0 records in 1024+0 
> records out 536870912 bytes (537 MB) copied, 14.1538 seconds, 37.9 
> MB/s # dd if=/dev/zero of=foo bs=512k count=1024 1024+0 records in 
> 1024+0 records out 536870912 bytes (537 MB) copied, 24.4553 seconds, 
> 22.0 MB/s
> 
> Why is it slower if the file exists? Should it be?

It is nearly impossible to tell from the difference between these
two runs of dd. We can help better if there are more data points
for us to look at.

Once you have figures averaged from more than a few runs and if you
still see a drop, we'd much appreciate if you file a performance bug
with your findings at:

http://bugs.gluster.com

Thanks
Shehjar


> 
> 
> ############# Servers ############# volume posix0 type storage/posix
>  option directory /cluster/0 end-volume
> 
> volume locks0 type features/locks subvolumes posix0 end-volume
> 
> volume brick0 type performance/io-threads option thread-count 8 
> subvolumes locks0 end-volume
> 
> volume posix1 type storage/posix option directory /cluster/1 
> end-volume
> 
> volume locks1 type features/locks subvolumes posix1 end-volume
> 
> volume brick1 type performance/io-threads option thread-count 8 
> subvolumes locks1 end-volume
> 
> volume posix2 type storage/posix option directory /cluster/2 
> end-volume
> 
> volume locks2 type features/locks subvolumes posix2 end-volume
> 
> volume brick2 type performance/io-threads option thread-count 8 
> subvolumes locks2 end-volume
> 
> volume posix3 type storage/posix option directory /cluster/3 
> end-volume
> 
> volume locks3 type features/locks subvolumes posix3 end-volume
> 
> volume brick3 type performance/io-threads option thread-count 8 
> subvolumes locks3 end-volume
> 
> volume server type protocol/server option transport-type tcp 
> subvolumes brick0 brick1 brick2 brick3 option auth.addr.brick0.allow 
> * option auth.addr.brick1.allow * option auth.addr.brick2.allow * 
> option auth.addr.brick3.allow * end-volume
> 
> ################ Client ################ volume ewcs2_cluster0 type 
> protocol/client option transport-type tcp option remote-host 
> ewcs2.ewcs.com option remote-subvolume brick0 end-volume volume 
> ewcs2_cluster1 type protocol/client option transport-type tcp option 
> remote-host ewcs2.ewcs.com option remote-subvolume brick1 end-volume
>  volume ewcs2_cluster2 type protocol/client option transport-type tcp
>  option remote-host ewcs2.ewcs.com option remote-subvolume brick2 
> end-volume volume ewcs2_cluster3 type protocol/client option 
> transport-type tcp option remote-host ewcs2.ewcs.com option 
> remote-subvolume brick3 end-volume
> 
> volume ewcs4_cluster0 type protocol/client option transport-type tcp
>  option remote-host ewcs4.ewcs.com option remote-subvolume brick0 
> end-volume volume ewcs4_cluster1 type protocol/client option 
> transport-type tcp option remote-host ewcs4.ewcs.com option 
> remote-subvolume brick1 end-volume volume ewcs4_cluster2 type 
> protocol/client option transport-type tcp option remote-host 
> ewcs4.ewcs.com option remote-subvolume brick2 end-volume volume 
> ewcs4_cluster3 type protocol/client option transport-type tcp option 
> remote-host ewcs4.ewcs.com option remote-subvolume brick3 end-volume
> 
> volume ewcs7_cluster0 type protocol/client option transport-type tcp
>  option remote-host ewcs7.ewcs.com option remote-subvolume brick0 
> end-volume volume ewcs7_cluster1 type protocol/client option 
> transport-type tcp option remote-host ewcs7.ewcs.com option 
> remote-subvolume brick1 end-volume volume ewcs7_cluster2 type 
> protocol/client option transport-type tcp option remote-host 
> ewcs7.ewcs.com option remote-subvolume brick2 end-volume volume 
> ewcs7_cluster3 type protocol/client option transport-type tcp option 
> remote-host ewcs7.ewcs.com option remote-subvolume brick3 end-volume
> 
> volume repl1 type cluster/replicate subvolumes ewcs2_cluster0 
> ewcs4_cluster0 ewcs7_cluster0 end-volume
> 
> volume repl2 type cluster/replicate subvolumes ewcs2_cluster1 
> ewcs4_cluster1 ewcs7_cluster1 end-volume
> 
> volume repl3 type cluster/replicate subvolumes ewcs2_cluster2 
> ewcs4_cluster2 ewcs7_cluster2 end-volume
> 
> volume repl4 type cluster/replicate subvolumes ewcs2_cluster3 
> ewcs4_cluster3 ewcs7_cluster3 end-volume
> 
> volume distribute type cluster/distribute subvolumes repl1 repl2 
> repl3 repl4 end-volume
> 
> volume writebehind type performance/write-behind option 
> aggregate-size 128KB option cache-size 1MB subvolumes distribute 
> end-volume
> 
> volume ioc type performance/io-cache option cache-size 512MB 
> subvolumes writebehind end-volume
> 
> #######################
> 
> mount -t glusterfs /etc/glusterfs/glusterfs-client.vol /mnt/gluster
> 
> 
> 
> _______________________________________________ Gluster-users mailing
>  list Gluster-users at gluster.org 
> http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
>