drbd-9.3.3-rc.1 and drbd-9.2.19-rc.1

drbd-9.3.3-rc.1 and drbd-9.2.19-rc.1

[Philipp Reisner]

Hi,

With the upcoming release, we are fixing a surprisingly large number of
bugs across the board. All of the issues are related to unusual
timings. An example is the resize that could lock up when a write on a
remote peer switched an activity log extent on the resizing machine at
the "wrong time".
The other large fix is that DRBD around the scenario
when a diskless primary gets isolated from all storage servers at once,
and the storage servers get isolated from each other at the same
moment. E.g. a network switch failure.

This is a release candidate. Please help test it.

I'm planning the final release for Monday, June 29.


9.3.3-rc.1 (api:genl2/proto:86-101,118-124/transport:21)
--------
 * Support adding and removing paths on established lb-tcp connections
 * Fix a page-reference leak on TLS connections by copying instead of
   referencing pages when sending
 * Reject paths that would make incoming connections ambiguous
 * All fixes from 9.2.19
  - Fix silent data divergence when a diskless primary creates a new
    current UUID that a peer never received (e.g. switch failure);
    the optimistic UUID is now confirmed via the data stream before
    being relied upon
  - Reconcile two peers holding the same current UUID but still carrying
    out-of-sync bits toward each other, instead of silently dropping the
    divergence
  - Fix a list corruption crash when freeing a peer_req that was
    still linked on the send_oos list
  - Fix an AB-BA deadlock between online resize and activity-log
    transactions
  - Fix a use-after-free of the TCP listener during connection setup
  - Fix a list corruption crash and assertion failures when a peer
    disconnects while online-verify requests are still in flight
  - Fix several races during connection teardown that could crash or
    hang (ack_sender requeue, pending ping work, in-progress lb-tcp
    connect)
  - Abort a two-phase-commit on peers when the target connection fails
    to prepare
  - Added max_parallel_resyncs module parameter to cap how many
    volumes may resync (or verify) in parallel
  - Fix multiple RDMA transport bugs hit during racing teardown: a
    NULL pointer dereference, a self-deadlock, and a cm object leak
  - Fix bogus resync speed/ETA reported in /proc/drbd when the
    out-of-sync amount grows
  - Do not throttle a resync that is losing ground to ongoing writes

https://pkg.linbit.com//downloads/drbd/9/drbd-9.3.3-rc.1.tar.gz
https://github.com/LINBIT/drbd/commit/40a5c7792f0791838c87fa74cc0ad91c49421200

https://pkg.linbit.com//downloads/drbd/9/drbd-9.2.19-rc.1.tar.gz
https://github.com/LINBIT/drbd/commit/e0f5483477fd0a56886d11143103cf3b5a069735

cheers,
 Philipp