Rebalance with old bricks almost full

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hello,

we have a setup with few bricks which were almost full. We added new ones and started rebalance process. We are using older version of Gluster 3.2.7 because we have mixed rdma/tcp setup. When we started the rebalance there was abouth 25% free space on the old bricks. However, since the volume is being used constantly we have a situation where old bricks are near cluster.min-free-disk limit (currently set to 50GB), while the new one have bunch of disk free (e.g. some old bricks are 100% used, while new ones are at 65% or 8TB disk free).

Could someone please clarify/advise:
- what will happen if rebalance process tries to push data to a brick which space is below cluster.min-free-disk limit? will gluster place this data automagically to one of free bricks? or will the data be lost? - what is the recommendation in this situation - should I stop the rebalance and let gluster automatically place files to non-full bricks?

Thanks in advance,
--
Emir Imamagic
SRCE - University of Zagreb University Computing Centre, www.srce.unizg.hr
Emir.Imamagic@xxxxxxx, tel: +385 1 616 5809, fax: +385 1 616 5559
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users




[Index of Archives]     [Gluster Development]     [Linux Filesytems Development]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux