Hello,
The most outstanding improvement is supporting thinly provisioned backing
devices with discard granularities larger than 128MiB. Here I mean with
supporting, that during a resync we make sure not to cause unnecessary
allocations in the backing block device, and merging the discard requests
for good resync performance.
Previously DRBD was only dealing with discard granularities of up to 1MiB.
The LVM tools create big chunksizes in thinpools for large pools. The
chunksize is then what determines the discard granularity. ZFS on the other
hand always stays with 8k, and it consumes too much space for its metadata
on large pools. The middle ground would be optimal. We will write an article
on these chunksize considerations. Also mentioning how to set these settings
with LVM-thin and ZFS.
On top of that, we have a bunch of fixes and lots of progress with upstream
kernel compatibility.
This is a release candidate, please help testing.
9.2.1-rc.1 (api:genl2/proto:110-121/transport:18)
--------
* fix spurious PingAck timeout, a regression of ack-processing in bottom
half
(introduced with 9.2.0)
* support merging of discards during resync even if the discard granularity
of the backing device is larger than 128MiB
* merged changes from the drbd-9.1 branch, including
- fix a race that could result in connection attempts getting aborted
with the message "sock_recvmsg returned -11"
- rate limit messages in case the peer can not write the backing storage
and it does not finish the necessary state transitions
- reduced the receive timeout during connecting to the intended 5 seconds
(ten times ping-ack timeout)
- losing the connection at a specific point in time during establishing
a connection could cause a transition to StandAlone; fixed that, so
that it keeps trying to connect
- fix a race that could lead to a fence-peer handler being called
unexpectedly when the fencing policy is changed at the moment before
promoting
9.1.12-rc.1 (api:genl2/proto:110-121/transport:17)
--------
* fix a race that could result in connection attempts getting aborted
with the message "sock_recvmsg returned -11"
* rate limit messages in case the peer can not write the backing storage
and it does not finish the necessary state transitions
* reduced the receive timeout during connecting to the intended 5 seconds
(ten times ping-ack timeout)
* losing the connection at a specific point in time during establishing
a connection could cause a transition to StandAlone; fixed that, so
that it keeps trying to connect
* fix a race that could lead to a fence-peer handler being called
unexpectedly when the fencing policy is changed at the moment before
promoting
https://pkg.linbit.com//downloads/drbd/9/drbd-9.1.12-rc.1.tar.gz
https://pkg.linbit.com//downloads/drbd/9/drbd-9.2.1-rc.1.tar.gz
https://github.com/LINBIT/drbd/commit/ff1a902fa721b0e8ca30a7a134b4308ecb0af90c
https://github.com/LINBIT/drbd/commit/e4966f94dc36c803a85f5e49b79428ef592beb83
_______________________________________________
Star us on GITHUB: https://github.com/LINBIT
drbd-user mailing list
drbd-user@lists.linbit.com
https://lists.linbit.com/mailman/listinfo/drbd-user
