肖力
2012-Nov-06 01:38 UTC
[Gluster-users] I am very confused about strip Stripe what way it hold space?
I have 4 dell 2970 server , three server harddisk is 146Gx6 ,one hard disk is 72Gx6: each server mount info is /dev/sda4 on /exp1 type xfs (rw) /dev/sdb1 on /exp2 type xfs (rw) /dev/sdc1 on /exp3 type xfs (rw) /dev/sdd1 on /exp4 type xfs (rw) /dev/sde1 on /exp5 type xfs (rw) /dev/sdf1 on /exp6 type xfs (rw) I create a gluster volume have 4 stripe gluster volume create test-volume3 stripe 4 transport tcp \ 172.16.20.231:/exp4 \ 172.16.20.232:/exp4 \ 172.16.20.233:/exp4 \ 172.16.20.235:/exp4 \ then i mount volume on client 172.16.20.230 mount -t glusterfs 192.168.106.231:/test-volume3 /gfs3 and i dd 10G file in gfs3 dd if=/dev/zero of=/gfs3/3 bs=1M count=10240 10240+0 records in 10240+0 records out 10737418240 bytes (11 GB) copied, 119.515 s, 89.8 MB/s I am very confused about this [root at node231 ~]# du -hs /exp4 10G /exp4 [root at node232 ~]# du -hs /exp4 10G /exp4 [root at node233 ~]# du -hs /exp4 10G /exp4 [root at node235 ~]# du -hs /exp4 10G /exp4 i understand Stripe 4 should hold 1/4 space on each brick,why is 10G on each brick? can someone explain it,think you. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20121106/d1e801cb/attachment.html>
Brian Foster
2012-Nov-06 12:34 UTC
[Gluster-users] I am very confused about strip Stripe what way it hold space?
On 11/05/2012 08:38 PM, ?? wrote:> I have 4 dell 2970 server , three server harddisk is 146Gx6 ,one hard > disk is 72Gx6: > > each server mount info is > //dev/sda4 on /exp1 type xfs (rw)/ > //dev/sdb1 on /exp2 type xfs (rw)/ > //dev/sdc1 on /exp3 type xfs (rw)/ > //dev/sdd1 on /exp4 type xfs (rw)/ > //dev/sde1 on /exp5 type xfs (rw)/ > //dev/sdf1 on /exp6 type xfs (rw)/ > > I create a gluster volume have 4 stripe > /gluster volume create test-volume3 stripe 4 transport tcp \/ > /172.16.20.231:/exp4 \/ > /172.16.20.232:/exp4 \/ > /172.16.20.233:/exp4 \/ > /172.16.20.235:/exp4 \/ > > then i mount volume on client 172.16.20.230 > /mount -t glusterfs 192.168.106.231:/test-volume3 /gfs3/ > and i dd 10G file in gfs3 > /dd if=/dev/zero of=/gfs3/3 bs=1M count=10240/ > /10240+0 records in/ > /10240+0 records out/ > /10737418240 bytes (11 GB) copied, 119.515 s, 89.8 MB/s/ > I am very confused about this > /[root at node231 ~]# du -hs /exp4/ > /10G /exp4/ > /[root at node232 ~]# du -hs /exp4/ > /10G /exp4/ > /[root at node233 ~]# du -hs /exp4/ > /10G /exp4/ > /[root at node235 ~]# du -hs /exp4/ > /10G /exp4/ > i *understand **Stripe 4 should hold 1/4 space on each brick,why is 10G > on each brick?* > *can someon e explain it,think you.* >The default stripe data layout conflicts with XFS default speculative preallocation behavior. XFS preallocates space beyond the end of files and the stripe translator continuously seeks past this space, making it permanent. You can address this by 1.) enabling the cluster.stripe-coalesce translator option in gluster or 2.) setting the allocsize mount option (i.e., allocsize=128k) in XFS. Note that using the latter option will increase the likelihood of fragmentation on the backend filesystem. Brian> > > > > > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users >
肖力
2012-Nov-07 01:51 UTC
[Gluster-users] I am very confused about strip Stripe what way it hold space?
thks a lot,i test it,and it work! xiao li ? 2012-11-06 20:34:55?"Brian Foster" <bfoster at redhat.com> ???>On 11/05/2012 08:38 PM, ?? wrote: >> I have 4 dell 2970 server , three server harddisk is 146Gx6 ,one hard >> disk is 72Gx6: >> >> each server mount info is >> //dev/sda4 on /exp1 type xfs (rw)/ >> //dev/sdb1 on /exp2 type xfs (rw)/ >> //dev/sdc1 on /exp3 type xfs (rw)/ >> //dev/sdd1 on /exp4 type xfs (rw)/ >> //dev/sde1 on /exp5 type xfs (rw)/ >> //dev/sdf1 on /exp6 type xfs (rw)/ >> >> I create a gluster volume have 4 stripe >> /gluster volume create test-volume3 stripe 4 transport tcp \/ >> /172.16.20.231:/exp4 \/ >> /172.16.20.232:/exp4 \/ >> /172.16.20.233:/exp4 \/ >> /172.16.20.235:/exp4 \/ >> >> then i mount volume on client 172.16.20.230 >> /mount -t glusterfs 192.168.106.231:/test-volume3 /gfs3/ >> and i dd 10G file in gfs3 >> /dd if=/dev/zero of=/gfs3/3 bs=1M count=10240/ >> /10240+0 records in/ >> /10240+0 records out/ >> /10737418240 bytes (11 GB) copied, 119.515 s, 89.8 MB/s/ >> I am very confused about this >> /[root at node231 ~]# du -hs /exp4/ >> /10G /exp4/ >> /[root at node232 ~]# du -hs /exp4/ >> /10G /exp4/ >> /[root at node233 ~]# du -hs /exp4/ >> /10G /exp4/ >> /[root at node235 ~]# du -hs /exp4/ >> /10G /exp4/ >> i *understand **Stripe 4 should hold 1/4 space on each brick,why is 10G >> on each brick?* >> *can someon e explain it,think you.* >> > >The default stripe data layout conflicts with XFS default speculative >preallocation behavior. XFS preallocates space beyond the end of files >and the stripe translator continuously seeks past this space, making it >permanent. > >You can address this by 1.) enabling the cluster.stripe-coalesce >translator option in gluster or 2.) setting the allocsize mount option >(i.e., allocsize=128k) in XFS. Note that using the latter option will >increase the likelihood of fragmentation on the backend filesystem. > >Brian > >> >> >> >> >> >> >> _______________________________________________ >> Gluster-users mailing list >> Gluster-users at gluster.org >> http://supercolony.gluster.org/mailman/listinfo/gluster-users >> >-------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20121107/5cc35435/attachment.html>