------------------------------------------------------------------- Thu Jan 9 10:59:39 UTC 2014 - lmb@suse.com - submit discard/trim/unmap bios with a single (but empty) biovec (bnc#857231) ------------------------------------------------------------------- Mon Oct 14 11:35:12 UTC 2013 - lmb@suse.com - Update to drbd-8.4.4 - fix potential deadlock when concurrently fencing and establishing a connection - fix potential distributed deadlock during verify or resync - fix decoding of bitmap vli rle for device sizes > 64 TB - fix for deadlock when using automatic split-brain-recovery - only fail empty flushes if no good data is reachable - avoid to shrink max_bio_size due to peer re-configuration - fix resume-io after reconnect with broken fence-peer handler - fix too large bursts for very slow resync rates - don't let application IO throttle resync to a stall - Fixed a hole in the challenge-response implementation - Fixed a theoretical IO deadlock (Only triggers with unusual small AL i.e. 7) - Fixed attaching to disks with fixed size external meta-data (bnc#833764) - drbd: fix NULL pointer deref in module init error path (bnc#825657) - Fixed a crash when the connection broke at a very exact point in time while a graceful disconnect executes - Support for REQ_DISCARD - Allow parallel promote/demote - Allow online changing of al-stripes and al-stripe-size with the resize command ------------------------------------------------------------------- Tue Mar 19 09:21:48 UTC 2013 - lpechacek@suse.com - Build RT KMPs for SP3 ------------------------------------------------------------------- Mon Feb 18 14:31:16 CET 2013 - ro@suse.de - add # needssslcertforbuild to specfile header ------------------------------------------------------------------- Mon Feb 11 14:35:06 UTC 2013 - mmarek@suse.cz - Set $BRP_PESIGN_FILES in the %install section so that modules are signed in the buildservice (fate#314552). ------------------------------------------------------------------- Fri Feb 8 17:00:00 UTC 2013 - lmb@suse.com - Do not end up in Unconnected state if the connection breaks at a certain point during the handshake (was introduced with 8.3.12) - Closed a race condition between promoting and connection handshake, that could lead to an inconsistent view of the peer's UUIDS - Fixed a race condition that could lead to a full sync, if connection breaks at a certain point while starting a regular resync - Fixed a list corruption for read requests that complete with an error after they were aborted - Fixed a kernel panic if the device size was an exact multiple of 128MiB - Fixed a potential memory allocation during deadlock online resize - Improve the handling of read-errors: Make sure that sectors that had a read error are overwritten with data from the peer on the next resync - Expose the data-generation-uuids through /sys/block/drbdXX/drbd/ - Fixed a potential protocol error and resulting disconnect/reconnect, when a disk fails on the secondary node. (Introduced with 8.4.2) - Do not fail empty flushed on diskless, primary node - Non blocking queuing of AL-updates; This change significantly improves the number of IOPs in case the workload does not fit into the configured AL size. - Fixed a memory leak of 336 byte per attach/detach cycle - Fix a potential null-pointer deference when configuring invalid resync after dependencies ------------------------------------------------------------------- Wed Nov 21 14:44:04 UTC 2012 - lmb@novell.com - Disable build of rt flavor for SLE HA 11 SP3. ------------------------------------------------------------------- Fri Nov 16 03:42:42 UTC 2012 - xli@suse.com - Update drbd to latest upstream release drbd-8.4.2 (FATE#313824) - Fixed IO resuming after connection was established before fence peer handler returned - Fixed an issue in the state engine that could cause state lockup with multiple volumes - Write all pages of the bitmap if it gets moved during an online resize operation. (This issue was introduced with 8.3.10) - Fixed a race condition could cause DRBD to go through a NetworkFailure state during disconnect - Fixed a race condition in the disconnect code path that could lead to a BUG() (introduced with 8.4.0) - Fixed a write ordering problem on SyncTarget nodes for a write to a block that gets resynced at the same time. The bug can only be triggered with a device that has a firmware that actually reorders writes to the same block (merged from 8.3.13) - Fixed a potential deadlock during restart of conflicting writes - Disable the write ordering method "barrier" by default, since it is not possible for a driver to find out if it works reliably since 2.6.36 - All fixes that went into 8.3.13 - Removed a null pointer access when using on-congestion policy on a diskless device - In case of a graceful detach under IO load, wait for the outstanding IO. (As opposed to aborting IOs as a forcefully detach does) - Reinstate disabling AL updates with invalidate-remote (8.4.0 regression) - Reinstate the 'disk-barrier no', 'disk-flushes no', and 'disk-drain no' switches (8.4.0 regression) - Backported the request code from DRBD-9. Improves handling of many corner cases. - Support FLUSH/FUA bio flags - Made the establishing of connections faster - New option 'al-updates no' to disable writing transactions into the activity log. It is use full if you prefer a full sync after a primary crash, for improved performance of a spread out random write work load - Expose the data generation identifies via sysfs - "--stop" option for online verify to specify a stop sector ------------------------------------------------------------------- Mon Jun 18 12:46:31 UTC 2012 - lmb@novell.com - Build RT kernel modules again for SLE HA 11 SP2 (FATE#313534) ------------------------------------------------------------------- Thu Feb 2 05:17:20 UTC 2012 - tserong@suse.com - Update to drbd-8.4.1 release - 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" ------------------------------------------------------------------- Tue Sep 6 11:24:32 UTC 2011 - mmarek@suse.cz - Add appropriate include for prefetch users. ------------------------------------------------------------------- Tue Sep 6 08:41:49 UTC 2011 - mmarek@suse.cz - drbd: Fix build on bigendian. ------------------------------------------------------------------- Tue Jul 12 15:34:34 UTC 2011 - lmb@novell.com - Enforce application of activity log after primary crash in user space - Features from drbd-8.3: Allow detach from frozen backing devices with the new --force option; configurable timeout for backing devices by the new disk-timeout option - Fixes from drbd-8.3: fixes for >16TiB support, fixed bit_size negotiation with drbd < 8.3.7 - Fixed state transitions in case attach fails ------------------------------------------------------------------- Fri Jul 1 15:28:37 UTC 2011 - lmb@novell.com - Disable build of rt kernel modules for SLE HA 11 SP2. ------------------------------------------------------------------- Fri Jul 1 13:11:59 UTC 2011 - lmb@novell.com - Update to drbd 8.4.0rc3. ------------------------------------------------------------------- Tue Mar 1 11:44:20 UTC 2011 - lmb@novell.com - Fix module loading on s390x (bnc#674302). ------------------------------------------------------------------- Wed Feb 16 10:39:09 UTC 2011 - lmb@novell.com - Build modules for the realtime kernel. ------------------------------------------------------------------- Tue Feb 8 21:17:32 UTC 2011 - lmb@novell.com - Fix compile on ppc64/s390x. ------------------------------------------------------------------- Mon Jan 31 09:05:07 UTC 2011 - lmb@novell.com - Update to drbd 8.3.10 - On 64bit architectures allow device sizes up to one petabyte - Fixed on-no-data-accessible for Primary, SyncTarget nodes (Bugz 332) - Progress bar for online verify - Optionally use the resync speed control loop code for the online verify process as well - Added code to detect false positives when using data-integrity-alg - New config option on-congestion and new connection states ahead and behind - Reduced IO latencies during resync, bitmap exchange and temporal states - Fix for possible deadlock on IO error during resync - Fixed a race condition between adding and removing network configuration. - Fixed spurious full syncs that could happen after an empty resync and concurrent connection loss. - Fixed spurious full syncs that happened when connection got lost while one node was in WFSyncUUID state (Bugz 318) - Fixed a race in the meta-data update code path, that could lead to forgotten updates to the meta-data. That in fact could lead to unexpected behavior at the next connect - Fixed potential deadlock on detach - Fixed potential data divergence after multiple failures - Implicitly create unconfigured devices which are referenced in sync-after dependencies. - Resource agent (ocf:linbit:drbd): Updates for latest pacemaker versions (bnc#649824). - Allow BIO sizes of up to 128kByte (bnc#657479). - New configuration keyword on-no-data-accessible. Possible values io-error, and suspend-io. The default is "io-error", which matches the previous behavior. - If the fencing policy is set to resource-and-stonith, the primary node will creates the new current UUID _after_ the fencing handler returned. (Before it did immediately) - Rewrote the resync speed control loop code. New configuration parameters c-plan-ahead, c-fill-target, c-delay-target, c-max-rate, c-min-rate. - Disable activity log updates when all blocks of an unconnected device is are out of sync. That can be activated by using "invalidate-remote" on an unconnected primary. - Improved IPv6 support: link local addresses - Improved resync speed display in /proc/drbd ------------------------------------------------------------------- Wed Jul 21 09:24:40 UTC 2010 - lmb@novell.com - Update drbd to 8.3.8.1; all patches are upstream now (bnc#622647) - Do not expose failed local READs to upper layers - Fixed a potential Oops in the disconnect code - Fixed a race condition that could cause DRBD to consider the peers disk as Inconstent after resync instead of UpToDate - Fixed a reace condition that could cause DRBD to consider the peers disk as Outdated instead of Inconsistent during resync - Disallow to start a resync with invalidate / invalidate-remote when the source disk is not UpToDate - Forcing primary works now also for Consistent, not only for Outdated and Inconsistent - Improved robustness against corrupt or malicous sector addresses when receiving data - Gave the receiving code the ability to use multiple BIOs for writing a single data packet; now DRBD works with BIOs up to 32kByte also on LVM devices; from now on the use_bmbv config option does nothing - New command check-resize, that allows DRBD to detect offline resizing and to move internal meta-data accordingly - Added a control loop, that allows DRBD to find auto tune the resync speed, on connections with large queues (drbd-proxy) ------------------------------------------------------------------- Tue Apr 13 11:56:04 UTC 2010 - lmb@novell.com - drbd: Do not expose failed local reads to upper layers, but retry remotely (bnc#596101) ------------------------------------------------------------------- Tue Apr 6 12:01:41 UTC 2010 - lmb@novell.com - fix regression: attach while connected failed ------------------------------------------------------------------- Mon Mar 29 10:19:59 UTC 2010 - lmb@novell.com - drbd: fix max_segment_size initialization - drbd: null dereference bug - drbdadm: fix potential access after free - snapshot-resync-target handler: fix endless loop in option parsing - drbd: fix NULL pointer dereference on 4k hard sect size - drbd: fix broken state change after split-brain attach while connected - fix segfault in drbdadm parser - fix unit of rs_same_csums accounting - drbd_disconnect: grab meta.socket mutex as well - add missing drbd command names to avoid in error messages - Reduce the time an empty resync takes usually - Make sure we do not send state updates during an empty resync [Bugz 271] - Forcing primary should also work for Consistent disks [Bugz 266] - drbd: fix al-to-on-disk-bitmap for 4k logical_block_size - Removed that mystical UTF character, trailing white space, and trailing semicolon - drbd: Do not upgrade state to Outdated if already Inconsistent [Bugz 277] ------------------------------------------------------------------- Mon Jan 25 16:28:12 UTC 2010 - lmb@novell.com - Fix drbd-kmp spec file to build proper version and remove reference to deleted patch. ------------------------------------------------------------------- Fri Jan 22 11:38:02 UTC 2010 - lmb@novell.com - New upstream release 8.3.7 - Silenced an assert. Could trigger after changing write ordering. - Fixed a race condition between detach and ongoing IO. Very hard to trigger, caused an OOPS in make_request/drbd_make_request. - Fixed a regression in the resync handshake code introduced before 8.3.3. That bug causes DRBD to block during the initial handshake when a partial resync is not possible but a full resync is necessary. Happens very rarely. - Do not drop into StandAlone mode when connection is lost during authentication. - Corrected a null test in the authentication code. - Following Linux upstream changes in 2.6.32. ------------------------------------------------------------------- Fri Dec 11 13:17:33 CET 2009 - mmarek@suse.cz - Fixed kmp package name (bnc#562259). ------------------------------------------------------------------- Thu Nov 8 10:04:24 CET 2009 - phil@linbit.com - New upstream release 8.3.6-1. ------------------------------------------------------------------- Thu Oct 27 12:30:41 CET 2009 - phil@linbit.com - New upstream release 8.3.5-1.