search for: 25tb

On Wed, May 6, 2015 2:46 pm, m.roth at 5-cent.us wrote: > Alessandro Baggi wrote: >> I list, >> I'm new with backup ops and I'm searching a good system to accomplish >> this >> work. I know that on centos there are bacula and amanda but they are >> too >> tape oriented. Another is that they are very powerfull but more complex. >> I >>

...a replicated pool of SSDs, and messages stored in a replicated pool of HDDs (under a Cache Tier with a pool of SSDs). All using cephfs / filestore backend. Currently there are 3 clusters running dovecot 2.2.34 and ceph Jewel (10.2.9-4). - ~25K users from a few thousands of domains per cluster - ~25TB of email data per cluster - ~70GB of dovecot INDEX [meta]data per cluster - ~100MB of cephfs metadata per cluster Our goal is to build a single ceph cluster for storage that could expand in capacity, be highly available and perform well enough. I know, that's what everyone wants. Cephfs is...

...drbd for disaster recovery. I keep 12+ months of monthly full backups, and 30+ days of daily incrementals. The deduplicated and compressed backups of all this take all of 4800GB, containing 9.1 million files and 4369 directories. The full backups WOULD have taken 68TB and the incrementals 25TB without dedup. I'm very happy with it. its a 'pull' based backup, no agents are required for the clients... it can use a variety of methods, I mostly use rsync-over-ssh, all you need to configure is a ssh key so the backup server's backuppc user can connect to the target via ss...

...*.chifrator*/*.cpderksu*/*.cry/*.crypto/*.darkness/*.dyatel*/*.enc*/*.gruzin*/*.hb15/*.help*/*.kraken/*.locked/*.nalog*/*.nochance/*.oplata*/*.oshit/*.pizda*/*.relock*/*.troyancoder*/*.encrypted/*.ccc/*.xyz/*.aaa/*.abc/*.eee/*.exx/.zzz/*.mkv/*.asp/*.cgi/*.vv/*.vvv/*.MICRO/ [ELELE] path = /media/25tb/opi/dergimac/Elele browseable = yes writeable = yes valid users = @__renkayrim, at __foto_arsiv, at _mac_elele,@"Domain Admins" write list = @_mac_elele ------------------------------------------- Internet uzerinden iletişimde zamaninda, guvenli, hatasiz ve viruslerden arindirilmis...

...of SSDs). > >>> All using cephfs / filestore backend. > >>> > >>> Currently there are 3 clusters running dovecot 2.2.34 and ceph Jewel > >>> (10.2.9-4). > >>> - ~25K users from a few thousands of domains per cluster > >>> - ~25TB of email data per cluster > >>> - ~70GB of dovecot INDEX [meta]data per cluster > >>> - ~100MB of cephfs metadata per cluster > >>> > >>> Our goal is to build a single ceph cluster for storage that could > expand > >> in > >>&gt...

...er recovery. I keep 12+ months of monthly full backups, and 30+ > days of daily incrementals. The deduplicated and compressed backups of > all this take all of 4800GB, containing 9.1 million files and 4369 > directories. The full backups WOULD have taken 68TB and the > incrementals 25TB without dedup. > > I'm very happy with it. > > its a 'pull' based backup, no agents are required for the clients... it > can use a variety of methods, I mostly use rsync-over-ssh, all you need > to configure is a ssh key so the backup server's backuppc user can &gt...

...ages stored > in a replicated pool of HDDs (under a Cache Tier with a pool of SSDs). > All using cephfs / filestore backend. > > Currently there are 3 clusters running dovecot 2.2.34 and ceph Jewel > (10.2.9-4). > - ~25K users from a few thousands of domains per cluster > - ~25TB of email data per cluster > - ~70GB of dovecot INDEX [meta]data per cluster > - ~100MB of cephfs metadata per cluster > > Our goal is to build a single ceph cluster for storage that could expand in > capacity, be highly available and perform well enough. I know, that's what &g...

...ted pool of HDDs (under a Cache Tier with a pool of SSDs). > > All using cephfs / filestore backend. > > > > Currently there are 3 clusters running dovecot 2.2.34 and ceph Jewel > > (10.2.9-4). > > - ~25K users from a few thousands of domains per cluster > > - ~25TB of email data per cluster > > - ~70GB of dovecot INDEX [meta]data per cluster > > - ~100MB of cephfs metadata per cluster > > > > Our goal is to build a single ceph cluster for storage that could expand > in > > capacity, be highly available and perform well enoug...

Hello, Thanks to "partner" on IRC who told me about this (quite big) problem. Apparently in a distributed setup once a brick fills up you start getting write failures. Is there a way to work around this? I would have thought gluster would check for free space before writing to a brick. It's very easy to test, I created a distributed volume from 2 uneven bricks and started to