Hello Daniel, I am following the tips from techforce.com.br blog, those recommend many tunning options to speed up write and read of small files. http://www.techforce.com.br/news/linux_blog/glusterfs_tuning_small_files Bellow the files: *glusterfsd.vol* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ volume posix type storage/posix option directory /data/export end-volume volume locks type features/locks subvolumes posix end-volume volume iothreads type performance/io-threads option thread-count 16 subvolumes locks end-volume volume writebehind type performance/write-behind option cache-size 1000MB option flush-behind off subvolumes iothreads end-volume volume brick type performance/io-cache option cache-size 2000MB option cache-timeout 1 subvolumes writebehind end-volume volume server-tcp type protocol/server option transport-type tcp option auth.addr.brick.allow * option transport.socket.listen-port 6996 option transport.socket.nodelay on subvolumes brick end-volume ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *glusterfs.vol* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ # TRANSPORT-TYPE tcp volume remote1 type protocol/client option transport-type tcp option remote-host remote1 option ping-timeout 10 option transport.socket.nodelay on option transport.remote-port 6996 option remote-subvolume brick end-volume volume remote3 type protocol/client option transport-type tcp option remote-host remote3 option ping-timeout 10 option transport.socket.nodelay on option transport.remote-port 6996 option remote-subvolume brick end-volume volume remote2 type protocol/client option transport-type tcp option remote-host remote2 option ping-timeout 10 option transport.socket.nodelay on option transport.remote-port 6996 option remote-subvolume brick end-volume volume remote4 type protocol/client option transport-type tcp option remote-host remote4 option ping-timeout 10 option transport.socket.nodelay on option transport.remote-port 6996 option remote-subvolume brick end-volume volume replicate1 type cluster/replicate subvolumes remote1 remote2 end-volume volume replicate2 type cluster/replicate subvolumes remote3 remote4 end-volume volume distribute type cluster/distribute subvolumes replicate1 replicate2 end-volume volume iocache type performance/io-cache option cache-size 1000MB option cache-timeout 1 subvolumes distribute end-volume volume writebehind type performance/write-behind option cache-size 500MB option flush-behind off subvolumes iocache end-volume volume quickread type performance/quick-read option cache-timeout 1 option max-file-size 256kB subvolumes writebehind end-volume volume iothreads type performance/io-threads option thread-count 16 subvolumes quickread end-volume ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <http://www.techforce.com.br/news/linux_blog/glusterfs_tuning_small_files>Thank you a lot On Wed, Sep 15, 2010 at 12:25 AM, Daniel Mons <daemons at kanuka.com.au> wrote: > On Tue, Sep 14, 2010 at 6:05 AM, Henrique Haas <henrique at dz6web.com> > wrote: > > My GlusterFS settings have used: > > Server: storage/posix, features/locks, performance/io-threads > > Client: 4 remote nodes > 2 Replicate > Write-Behind > IO-Threads > > QuickRead > >> Stat-Prefetch > > Are you able to share the config file with us? > > -Dan > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://gluster.org/cgi-bin/mailman/listinfo/gluster-users > -- Henrique Haas +55 (51) 3028.6602 www.dz6web.com