Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On 12/20/2011 09:37 AM, Philipp Reisner wrote: > Hi fellows, > > Once again I am proud to announce a new release: 8.4.1 > > I hope that we have the majority of regressions that where > introduced with the 8.4 effort identified and fixed now. > > The bug described by the first item of the changelog can only trigger > if you use multiple volumes. > > I advise every user of 8.4.0 to upgrade to 8.4.1, due to the possible > kernel OOPS (second item on the change log). > > New features > > * Read load balancing. > That might be of interest if you have a faster network between > your DRBD nodes in place, and want to benefit of the secondary's > IO bandwidth for reading. > > * Works with Linux-3.2 > It was actually tested with Linux-3.2-rc6, but since the merge > window closed long time ago, there is hope that it will also work > with the final Linux-3.2. > > > 8.4.1 (api:genl1/proto:86-100) > -------- > * Fixed a bug that might cause in kernel list corruption triggered by > simultaneous IO on multiple volumes in a single resource > * Fixed a bug that might cause a kernel OOPS in the worker thread while > the receiver tied to establish a connection (drbd-8.4.0 regression) > * Fixed an issue in the receiver that could cause connection triggered by > simultaneous IO on multiple volumes in a single resource > * Consider the discard-my-data flag for all volumes > * Fixed attaching to backing devices that do not support barriers/flushes, > when barriers/flushes are not disabled by the configuration. > (drbd-8.4.0 regression) > * Fixed a rare compatibility issue with DRBD's older than 8.3.7 > when negotiating the bio_size > * Fixed a rare race condition where an empty resync could stall with > if pause/unpause events happen in parallel > * Made the re-establishing of connections quicker, if it got a broken pipe > once. Previously there was a bug in the code caused it to waste the first > successful established connection after a broken pipe event. > * crm-fence-peer.sh: Can now deal with multiple DRBD instances being in > a master/slave group > * Optional load balancing for read requests: new keyword "read-balance" > > http://oss.linbit.com/drbd/8.4/drbd-8.4.1.tar.gz > http://git.drbd.org/?p=drbd-8.4.git;a=tag;h=drbd-8.4.1 > http://www.linbit.com/support/drbd-8.4.1/ > > Best, > Phil Congrats, folks! -- Digimer E-Mail: digimer at alteeve.com Freenode handle: digimer Papers and Projects: http://alteeve.com Node Assassin: http://nodeassassin.org "omg my singularity battery is dead again. stupid hawking radiation." - epitron