Thanks Peter! Am 11.07.2020 um 06:13 schrieb Peter Woodman:
in the meanwhile, you can turn on compression in your mon's rocksdb tunables and make things slightly less scary, something like: mon_rocksdb_options = write_buffer_size=33554432,compression=kLZ4Compression,level_compaction_dynamic_level_bytes=true,bottommost_compression=kLZ4HCCompression,max_background_jobs=4,max_subcompactions=2
I check the cluster the next day (around 10 hours after my mail) and it seems that the store.db size grew to almost 400GiB and then started to drop to ~8GiB again. It's now been at this level for 24 hours so it seems to have fixed itself.
Regards, Michael _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
