Compression is defined per pool and is independent of the replication type. You can choose depending on IO pattern. I use compression only on data pools. Meta data is usually small random IO and not very suited for compression, which might increase latency. In particular, when meta data is on SSD. Best regards, Frank _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |