- 19 Aug, 2009 15 commits
-
-
Lars Ellenberg authored
never observed, unlikely to be real. Still a coding bug. Signed-off-by:
Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by:
Lars Ellenberg <lars.ellenberg@linbit.com>
-
Philipp Reisner authored
drbd_uuid_compare(): Also undo the changes of last unsuccessful start of resync also on the peer's UUIDs Signed-off-by:
-
Philipp Reisner authored
Aditional errata to http://www.drbd.org/fileadmin/drbd/publications/drbd8.pdf 5 Data Generation UUIDs Algorithm: Rule 5a: Cs = H1p & H1s = H2p ==> Connection was lost before SyncUUID Packet came through. Become Sync target. Rule 7a: Cp = H1s & H1p = H2s ==> Connection was lost before SyncUUID Packet came through. Correct my UUIDs: B = H1 H1 = H2 H2 = 0 Become Sync source. Here are the relevant log lines, showing the issue: Aug 12 16:20:48 garcon1 kernel: [4941237.376998] drbd10: self 68CFBC7C5C0E6D4F:1C4BD1C2E7B77E75:F1812682E82B178A:3E381E47943D1E4B bits:85 flags:0 Aug 12 16:20:48 garcon1 kernel: [4941237.377003] drbd10: peer 1C4BD1C2E7B77E74:0000000000000000:F1812682E82B178A:3E381E47943D1E4B bits:0 flags:0 Aug 12 16:20:48 garcon1 kernel: [4941237.377006] drbd10: uuid_compare()=1 by rule 7 Aug 12 16:20:48 garcon1 kernel: [4941237.378131] drbd10: peer( Unknown -> Secondary ) conn( WFReportParams -> WFBitMapS ) pdsk( DUnknown -> UpToDate ) Aug 12 16:20:50 garcon1 kernel: [4941238.911877] drbd10: conn( WFBitMapS -> SyncSource ) pdsk( UpToDate -> Inconsistent ) Aug 12 16:20:50 garcon1 kernel: [4941238.911889] drbd10: Began resync as SyncSource (will sync 340 KB [85 bits set]). Aug 12 16:21:10 garcon1 kernel: [4941259.500053] drbd10: peer( Secondary -> Unknown ) conn( SyncSource -> NetworkFailure ) Aug 12 07:20:48 portman kernel: [11341861.890379] drbd10: self 1C4BD1C2E7B77E74:0000000000000000:F1812682E82B178A:3E381E47943D1E4B bits:0 flags:0 Aug 12 07:20:48 portman kernel: [11341861.890379] drbd10: peer 68CFBC7C5C0E6D4F:1C4BD1C2E7B77E75:F1812682E82B178A:3E381E47943D1E4B bits:85 flags:0 Aug 12 07:20:48 portman kernel: [11341861.890379] drbd10: uuid_compare()=-1 by rule 5 Aug 12 07:20:48 portman kernel: [11341861.890379] drbd10: peer( Unknown -> Primary ) conn( WFReportParams -> WFBitMapT ) pdsk( DUnknown -> UpToDate ) Aug 12 07:20:48 portman kernel: [11341862.146623] drbd10: conn( WFBitMapT -> WFSyncUUID ) Aug 12 07:21:10 portman kernel: [11341884.923517] drbd10: peer( Primary -> Unknown ) conn( WFSyncUUID -> NetworkFailure ) pdsk( UpToDate -> DUnknown ) Aug 12 16:21:34 garcon1 kernel: [4941283.720095] drbd10: self 68CFBC7C5C0E6D4F:6AA2B905AD177D20:1C4BD1C2E7B77E75:F1812682E82B178A bits:91 flags:0 Aug 12 16:21:34 garcon1 kernel: [4941283.720099] drbd10: peer 1C4BD1C2E7B77E74:0000000000000000:F1812682E82B178A:3E381E47943D1E4B bits:85 flags:0 Aug 12 16:21:34 garcon1 kernel: [4941283.720102] drbd10: uuid_compare()=2 by rule 8 Aug 12 16:21:34 garcon1 kernel: [4941283.720105] drbd10: Writing the whole bitmap, full sync required after drbd_sync_handshake. Aug 12 07:22:08 portman kernel: [11341943.908341] drbd10: self 1C4BD1C2E7B77E74:0000000000000000:F1812682E82B178A:3E381E47943D1E4B bits:85 flags:0 Aug 12 07:22:08 portman kernel: [11341943.908390] drbd10: peer 68CFBC7C5C0E6D4F:6AA2B905AD177D20:1C4BD1C2E7B77E75:F1812682E82B178A bits:7864320 flags:0 Aug 12 07:22:08 portman kernel: [11341943.908437] drbd10: uuid_compare()=-2 by rule 6 Aug 12 07:22:08 portman kernel: [11341943.908461] drbd10: Writing the whole bitmap, full sync required after drbd_sync_handshake. Aug 12 07:22:08 portman kernel: [11341943.925199] drbd10: 30 GB (7864320 bits) marked out-of-sync by on disk bit-map. Aug 12 07:22:08 portman kernel: [11341943.925199] drbd10: peer( Unknown -> Primary ) conn( WFReportParams -> WFBitMapT ) pdsk( DUnknown -> UpToDate ) Aug 12 07:22:09 portman kernel: [11341944.896914] drbd10: conn( WFBitMapT -> WFSyncUUID ) Signed-off-by:
-
Lars Ellenberg authored
You do not NEED to hold the req_lock since 107a7ca67f9fffd0c0c94018f5a1f61a0afe7bf8 (2005-03-15). Since the drbd_pp_lock is not spin_lock_irqsave anymore, you MUST NOT hold the req_lock when trying to aquire the drbd_pp_lock. Signed-off-by:
-
Lars Ellenberg authored
fixes recently introduced potential spinlock deadlock. reduces the size of various critical sections. Signed-off-by:
-
Lars Ellenberg authored
2 seconds may be too small for high latency long distance medium packet loss links Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
Signed-off-by:
-
Lars Ellenberg authored
reporting comm_bm_set is more useful, it is used in the uuid_compare and after_sb comparisons. Signed-off-by:
-
Lars Ellenberg authored
If for some reason we get an unfortunately timed disconnect request, we could have leak a socket. Signed-off-by:
-
- 29 Jul, 2009 25 commits
-
-
Stephen Rothwell authored
bio_barrier() and bio_sync() are going away. Signed-off-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Rusty Russell authored
Any code which can be compiled on x86 should try to avoid cpumask_t (or even struct cpumask) declarations; we are heading towards struct cpumask being undefined if CONFIG_CPUMASK_OFFSTACK. The code is the same for CONFIG_CPUMASK_OFFSTACK=n. Signed-off-by:
Rusty Russell <rusty@rustcorp.com.au> Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
drbd_strings: Renamed the functions to the drbd_ namespace; export them from drbd.ko to drbd_trace.ko drbd_bitmap: set bits: do not trigger assert for aligned very last bit. Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
* Removed all calls to drbd_bm_recount_bits() * add missing recv_cnt accounting for diskless read * more efficiently set large areas of bitmap Signed-off-by:
-
Philipp Reisner authored
* drbd-8.3: Preparing the 8.3.2 release Fix a wronge use of kmap_atomic(..., KM_IRQ1) in the bitmap code [bugz 238] Added some missing statics remove an incorrect ASSERT Signed-off-by: -
Philipp Reisner authored
* drbd-8.3: (134 commits) Missing pices of the unaligned memory access stuff. possible fix for XEN crashes on disconnect fix regression: initial sync target hung in WFBitMapT fix a comment: there are no more ioctls. possible fix for XEN crashes on disconnect fix regression: initial sync target hung in WFBitMapT ... Removed compat code from lru_cache.h All STATIC -> static DRBD_ENABLE_FAULTS -> CONFIG_DRBD_FAULT_INJECTION * drbd-8.3: Fixed some errors/warnings when compiles without DBG_ALL_SYMBOLS (i.e. STATIC = static) Fixed a regression introduced with fb51e2eb1fac83839231499333bf683629388484 No longer include drbd_config.h directly, include drbd.h instead Got rid of drbd_config.h Support lru_cache as module Removing the drbd_buildtag.c file * drbd-8.3: Fixes for architectures that does not support unaligned memory accesses fix reading of the AL ring buffer sync handshake: fix detection of "unrelated" data - it was detected as "regular" split-brain * drbd-8.3: Preparing 8.3.2rc2 compat: 2.6.31 -- q->limits.* and accessor functions Signed-off-by: -
Philipp Reisner authored
Conflicts: lib/Kconfig
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
Moved lru_cache.c to ~linux/lib lru_cache - documentation update, type cast removal Using kmalloc() first, trying vmalloc() as fallback for the page anchors of the bitmap Making everything kernel-doc compliant rename mdev->bc to mdev->ldev (to match the recent change to get_ldev/put_ldev) make drbd thread t_lock irqsave - lockdep complained, and lockdep is right (theoretically) Signed-off-by:
-
Philipp Reisner authored
Improving a comment Call drbd_rs_cancel_all() and reset rs_pending when aborting resync due to detach. (Bugz 223) Allow detach of a SyncTarget node. (Bugz 221) rename inc_local -> get_ldev; inc_net -> get_net_conf; and corresponding dec_* -> put_* replace AL with activity log in comments drbd_md_sync_page_io: prepare for rw being more than just r/w direction remove outdated comment add comment: page_address allowed, preallocated with GFP_KERNEL renaming a few constants: _SECT -> _SECTOR_SIZE, _SIZE_B -> _SHIFT ... remove quite a few 'inline's from .c files replacing __attribute__((packed)) with __packed micro: comment spelling fix Allow pass-through options to drbdsetup also for the syncer subcommand dmsetup: ERR_PACKET_NR error message was missing Signed-off-by: -
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
2fcb72c00e0fb35120665943cbe7003739bd1009 get rid of unneccessary fsync_bdev 2721065e39000629e87296676fd077bb0970417b Merge branch 'drbd-8.2' into drbd-8.3 93edff9e37a122b5f2d23ed2baef0dfeef1c5a17 Merge branch 'drbd-8.0' into drbd-8.2 0fb44e5ef678346808a9ab06a259112af7814fc8 dead code removal 13bb2bb8dd3fddbae88a1fcba757b567208e3ae1 fix config/deconfig race 4c0505a621e8c06eeac9a7d831621ea949770fe2 need to hold req_lock for_drbd_set_state (recently introduced bogon) 590cb50f41337c39b7d8095991fa1d144dbc3fd7 remove unnecessary variable, fix comment formatting 73abcf4b8f53f26fa4a6d524916fba142342df33 make bm_lock message moreinformative; hunting configuration race condition 0efb38921eff65f7f05aa2e028833aea5ed5b8f4 adjust loglevel: some dev_dbg should rather be warn, or info at least 50ddc402f72ab5b4486e0efa912a16b6f3d3012a bitmap compression stats: output percentage saved, not 'factor' 1737021364ea6da4d08bd08e99d1083587d271d4 compressed bitmap: finally settle for _one_ encoding c63bd973e2d52baeceb425592af371bf8f4fe2cd introduce disable_sendpage module parameter a87458a4243968229b9db85e680d464aae3c9bd4 fix double send_cnt accounting of _drbd_no_send_page fallbacks Signed-off-by:
-
Philipp Reisner authored
9b8b170585e2959d552b0ba592b649d758b933b8 Merge branch 'drbd-8.3' into drbd-8.3-cleanups 1922274c822b34cf4b66843819ccfed97e1da4f1 Improvements to drbd_nl_net_conf() * Removing macros * Fixed the code for 1a59b007715215697968cfaed3f2f159d262c030 Removing a workaround for bugs in blk_queue_stack_limits() in older kernels 56d788e4fa7a4809fc41f8c17a02032fb8793080 Merge branch 'drbd-8.3' into drbd-8.3-cleanups a95b4cfb595ced59ca6d2b26d450fd7e5e08fec8 The coding style guide says: Constants are ALL_CAPS 84cc8259557954b39fa8b0c57931b08cdc3df3f6 Merge branch 'drbd-8.2' into drbd-8.3 555b9f742cce70430a5769a35128ee3fa06fa9f4 Merge branch 'drbd-8.0' into drbd-8.2 f96e2776b2e49ef992d43a624d7c6be7d0610bfa Removing CamelCase from structs, enums and unions 727aca1fcc001381ab6f0a7229fa7db54b9431ea Removing '#if 0' code 546cbdec6779e997a37eac0d3762f4e0a3a390f2 Changing the remaining constants to UPPER_CASE only 57e478a0d328405ed97c3bada9d617e5d21a3868 Merge branch 'drbd-8.3' into drbd-8.3-cleanups 23b99bfb4ceca5a00c180620ac3f6db91edf7f85 Andi does not want to get it CC, he prefers to pick it off LKML d362ab639c966107670f4b375cbff757314f5cba Changing the remaining constants to UPPER_CASE only 6fe98c4f0302a28174dd3a852e72fbc6a0caa45e Merge branch 'drbd-8.2' into drbd-8.3 ff327744475ffc66795fc49dcdc232b21589185e Changing the remaining constants to UPPER_CASE only 185392bf5ce63936a5c424b97e38512ab4bcfdb7 Merge branch 'drbd-8.0' into drbd-8.2 5f87618f7272e9ef92b17b2b7c36dcc1c3d59031 Making all constants UPPER_CASE only 2ebf5224634bf5fda709fb54b43a5de6e3c10bee Adding explicit numbers to the return codes to user space Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
* Moving BUG_ON() as suggested by Nikanth Karthikesan * Removing our ERR, drbd_WARN, INFO, ALERT macros, using the kernel standard dev_err, dev_warn etc.. instead suggested by Bart Van Assche Signed-off-by:
-
Philipp Reisner authored
Signed-off-by:
-
Philipp Reisner authored
782b1ed1e3582393381e1f3f1cb80020f027ca06 Merge branch 'drbd-8.0' into drbd-8.3 80de0d362ffd9906412ce7b602db7c9cd550b678 Adjusted the drbd_congested() function to work on kernels >= 2.6.30 f484da549b3375ef7e7d9d08d5bf2c95745c8eaa Correct exapnsion of "device minor %d" statements for upper resources. 4cecefe99336e911425e390f115cf32a9036679f Fixed the res_by_minor() function 10d77c7a0d08257a19f8d67fdda3af71bf415b1d Do not do state changes on unconfigured devices (bugz 214) 706b35dc7ada32cf9cc47d331733514a52c5a820 double :: typo 3ced685cd6ae4179d77e09945a4951f4c997d2db Merge branch 'drbd-8.2' into drbd-8.3 70339fe8d52ee93696aa975b9ed14cbaa61d0e0c Merge branch 'drbd-8.0' into drbd-8.2 864141476a52d5e174dcbb03fa9f98b6da6f9689 Fixing the error code path in case the bitmap allocation failes. 8126b2adf618924c1d00407bd56b8b4f3976e198 Fault injection for the bitmap allocation c091e4513f805f9a2118f01ee87e6ec7a419126a proc/drbd: catch uninitialized congestion flag d30881451c988619e243d6294a899139eed1183d Preparing 8.0.16 Signed-off-by:
-
