Hi,
I was diffing the OSDMap between a Jewel and Luminous cluster and found
the 'recovery_deletes' flag in the OSDMap.
Searching the internet I couldn't find much about this flag, except for
this Red Hat URL which is subscription only:
https://access.redhat.com/solutions/3200572
I looked through the source code and I found a few comments:
bool recovery_deletes = false; ///< whether the deletes are performed
during recovery instead of peering
#define CEPH_OSDMAP_RECOVERY_DELETES (1<<19) /* deletes performed during
recovery instead of peering */
Setting the flag is easy:
$ ceph osd set recovery_deletes
This means that deletes are performed during recovery and not during
peering, but what is to expect from this flag? Will it improve the
peering process and reduce the amount of blocked/slow I/O after a OSD boot?
Wido
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
