)]}' { "log": [ { "commit": "ea88eeac0cb8328014b53d80ca631e8dc0dc18dc", "tree": "de605c1d0e7ab1e342eedad47c56061b65a6b790", "parents": [ "848b81415c42ff3dc9a4204749087b015c37ef66", "a9add5d92b64ea57fb4c3b557c3891cdeb15fa0c" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 18 09:32:44 2012 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 18 09:32:44 2012 -0800" }, "message": "Merge tag \u0027md-3.8\u0027 of git://neil.brown.name/md\n\nPull md update from Neil Brown:\n \"Mostly just little fixes. Probably biggest part is AVX accelerated\n RAID6 calculations.\"\n\n* tag \u0027md-3.8\u0027 of git://neil.brown.name/md:\n md/raid5: add blktrace calls\n md/raid5: use async_tx_quiesce() instead of open-coding it.\n md: Use -\u003ecurr_resync as last completed request when cleanly aborting resync.\n lib/raid6: build proper files on corresponding arch\n lib/raid6: Add AVX2 optimized gen_syndrome functions\n lib/raid6: Add AVX2 optimized recovery functions\n md: Update checkpoint of resync/recovery based on time.\n md:Add place to update -\u003erecovery_cp.\n md.c: re-indent various \u0027switch\u0027 statements.\n md: close race between removing and adding a device.\n md: removed unused variable in calc_sb_1_csm.\n" }, { "commit": "0a19caabf01ac138bf3668786939e50ea4d9c8ac", "tree": "dc672faa83d44dbbb8097b367a35ce1cfba9c90f", "parents": [ "4f8c55c5ad491dbc7b52ce08bb702ca39ce944cf" ], "author": { "name": "majianpeng", "email": "majianpeng@gmail.com", "time": "Mon Nov 19 19:57:34 2012 +0800" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Dec 13 19:52:11 2012 +1100" }, "message": "md: Use -\u003ecurr_resync as last completed request when cleanly aborting resync.\n\nIf a resync is aborted cleanly, -\u003ecurr_resync is a reliable\nrecord of where we got up to.\nIf there was an error it is less reliable but we always know that\n-\u003ecurr_resync_completed is safe.\n\nSo add a flag MD_RECOVERY_ERROR to differentiate between these cases\nand set recovery_cp accordingly.\n\nSigned-off-by: Jianpeng Ma \u003cmajianpeng@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "eed8c02e680c04cd737e0a9cef74e68d8eb0cefa", "tree": "8bd2bd10b0c02bb8a579ca3fd4f1482e5335c747", "parents": [ "d33b98fc82b0908e91fb05ae081acaed7323f9d2" ], "author": { "name": "Lukas Czerner", "email": "lczerner@redhat.com", "time": "Fri Nov 30 11:42:40 2012 +0100" }, "committer": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Fri Nov 30 11:47:57 2012 +0100" }, "message": "wait: add wait_event_lock_irq() interface\n\nNew wait_event{_interruptible}_lock_irq{_cmd} macros added. This commit\nmoves the private wait_event_lock_irq() macro from MD to regular wait\nincludes, introduces new macro wait_event_lock_irq_cmd() instead of using\nthe old method with omitting cmd parameter which is ugly and makes a use\nof new macros in the MD. It also introduces the _interruptible_ variant.\n\nThe use of new interface is when one have a special lock to protect data\nstructures used in the condition, or one also needs to invoke \"cmd\"\nbefore putting it to sleep.\n\nAll new macros are expected to be called with the lock taken. The lock\nis released before sleep and is reacquired afterwards. We will leave the\nmacro with the lock held.\n\nNote to DM: IMO this should also fix theoretical race on waitqueue while\nusing simultaneously wait_event_lock_irq() and wait_event() because of\nlack of locking around current state setting and wait queue removal.\n\nSigned-off-by: Lukas Czerner \u003clczerner@redhat.com\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "7f7583d420231b9d09897afd57a957011b606a5b", "tree": "aa45d88b926bfc8e22f841b9ea83d338afa4c3ae", "parents": [ "1ed850f356a0a422013846b5291acff08815008b" ], "author": { "name": "Jianpeng Ma", "email": "majianpeng@gmail.com", "time": "Thu Oct 11 14:17:59 2012 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Oct 11 14:17:59 2012 +1100" }, "message": "Subject: [PATCH] md:change resync_mismatches to atomic64_t to avoid races\n\nNow that multiple threads can handle stripes, it is safer to\nuse an atomic64_t for resync_mismatches, to avoid update races.\n\nSigned-off-by: Jianpeng Ma \u003cmajianpeng@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "4ed8731d8e6bd2a88a30697fbf4f7e6e979a6c46", "tree": "3bb77592fa5a89b8e7f0ef84b8d7f53122bbd071", "parents": [ "57c67df48866d57b50d72eb198ffcc0cf7a6232d" ], "author": { "name": "Shaohua Li", "email": "shli@kernel.org", "time": "Thu Oct 11 13:34:00 2012 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Oct 11 13:34:00 2012 +1100" }, "message": "MD: change the parameter of md thread\n\nChange the thread parameter, so the thread can carry extra info. Next patch\nwill use it.\n\nSigned-off-by: Shaohua Li \u003cshli@fusionio.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "74018dc3063a2c729fc73041c0a9f03aac995920", "tree": "03f01bca3a2d9f7cf31785fbe74e9ab76bb0d4cd", "parents": [ "2a7d5559b346574057dce4672d1ed9aaa9d1e685" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jul 31 09:08:15 2012 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Tue Jul 31 09:08:15 2012 +0200" }, "message": "blk: pass from_schedule to non-request unplug functions.\n\nThis will allow md/raid to know why the unplug was called,\nand will be able to act according - if !from_schedule it\nis safe to perform tasks which could themselves schedule.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "9cbb17508808f8a6bdd83354b61e126ac4fa6fed", "tree": "bc797d1b5cd829751a333115e6e6d52799fb6df2", "parents": [ "0021b7bc045e4b0b85d8c53614342aaf84ca96a5" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jul 31 09:08:14 2012 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Tue Jul 31 09:08:14 2012 +0200" }, "message": "blk: centralize non-request unplug handling.\n\nBoth md and umem has similar code for getting notified on an\nblk_finish_plug event.\nCentralize this code in block/ and allow each driver to\nprovide its distinctive difference.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "0021b7bc045e4b0b85d8c53614342aaf84ca96a5", "tree": "1432761eec4c49bbacea55df083e73599e18ea1c", "parents": [ "01ff5dbc0925d11c8ad76eed3bdd02d0c7e1e0f5" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jul 31 09:08:14 2012 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Tue Jul 31 09:08:14 2012 +0200" }, "message": "md: remove plug_cnt feature of plugging.\n\nThis seemed like a good idea at the time, but after further thought I\ncannot see it making a difference other than very occasionally and\ntesting to try to exercise the case it is most likely to help did not\nshow any performance difference by removing it.\n\nSo remove the counting of active plugs and allow \u0027pending writes\u0027 to\nbe activated at any time, not just when no plugs are active.\n\nThis is only relevant when there is a write-intent bitmap, and the\nupdating of the bitmap will likely introduce enough delay that\nthe single-threading of bitmap updates will be enough to collect large\nnumbers of updates together.\n\nRemoving this will make it easier to centralise the unplug code, and\nwill clear the other for other unplug enhancements which have a\nmeasurable effect.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "6409bb05a9831f6af36a20b97cda13059c2ef1b6", "tree": "c997526bd60d3fb5cafea604e5b240c2479e20d9", "parents": [ "bf07bb7d5be813630d3530be274b3324f85e310c" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 22 13:55:07 2012 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 22 13:55:07 2012 +1000" }, "message": "md/bitmap: add new \u0027space\u0027 attribute for bitmaps.\n\nIf we are to allow bitmaps to be resized when the array is resized,\nwe need to know how much space there is.\n\nSo create an attribute to store this information and set appropriate\ndefaults.\n\nIt can be set more precisely via sysfs, or future metadata extensions\nmay allow it to be recorded.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "545c87957f4d53867b62921625f36df8c4b1bc08", "tree": "52dc839ac828f7742efbad83cfbe5f35f11a04d6", "parents": [ "96e67703e71f4b3cc32b747dbb6158ec74d01e19" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 22 13:54:30 2012 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 22 13:54:30 2012 +1000" }, "message": "md: dm-raid should call helper function to clear rdev.\n\ndm-raid currently open-codes the freeing of some members of\nand rdev. It is more maintainable to have it call common code\nfrom md.c which does this for all call-sites.\n\nSo remove free_disk_sb to md_rdev_clear, export it, and use it in\ndm-raid.c\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "c6563a8c38fde3c1c7fc925a10bde3ca20799301", "tree": "3916ae8247149a9dcf39ee1ca262f97be39071eb", "parents": [ "2c810cddc44d6f95cef75df3f07fc0850ff92417" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon May 21 09:27:00 2012 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon May 21 09:27:00 2012 +1000" }, "message": "md: add possibility to change data-offset for devices.\n\nWhen reshaping we can avoid costly intermediate backup by\nchanging the \u0027start\u0027 address of the array on the device\n(if there is enough room).\n\nSo as a first step, allow such a change to be requested\nthrough sysfs, and recorded in v1.x metadata.\n\n(As we didn\u0027t previous check that all \u0027pad\u0027 fields were zero,\n we need a new FEATURE flag for this.\n A (belatedly) check that all remaining \u0027pad\u0027 fields are\n zero to avoid a repeat of this)\n\nThe new data offset must be requested separately for each device.\nThis allows each to have a different change in the data offset.\nThis is not likely to be used often but as data_offset can be\nset per-device, new_data_offset should be too.\n\nThis patch also removes the \u0027acknowledged\u0027 arg to rdev_set_badblocks as\nit is never used and never will be. At the same time we add a new\narg (\u0027in_new\u0027) which is currently always zero but will be used more\nsoon.\n\nWhen a reshape finishes we will need to update the data_offset\nand rdev-\u003esectors. So provide an exported function to do that.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2c810cddc44d6f95cef75df3f07fc0850ff92417", "tree": "185b35ce06656a53327dd66343f0926aa5a910d7", "parents": [ "b5e1b8cee7ad58a15d2fa79bcd7946acb592602d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon May 21 09:27:00 2012 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon May 21 09:27:00 2012 +1000" }, "message": "md: allow a reshape operation to be reversed.\n\nCurrently a reshape operation always progresses from the start\nof the array to the end unless the number of devices is being\nreduced, in which case it progressed in the opposite direction.\n\nTo reverse a partial reshape which changes the number of devices\nyou can stop the array and re-assemble with the raid-disks numbers\nreversed and it will undo.\n\nHowever for a reshape that does not change the number of devices\nit is not possible to reverse the reshape in the middle - you have to\nwait until it completes.\n\nSo add a \u0027reshape_direction\u0027 attribute with is either \u0027forwards\u0027 or\n\u0027backwards\u0027 and can be explicitly set when delta_disks is zero.\n\nThis will become more important when we allow the data_offset to\nchange in a reshape. Then the explicit statement of what direction is\nbeing used will be more useful.\n\nThis can be enabled in raid5 trivially as it already supports\nreverse reshape and just needs to use a different trigger to request it.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "050b66152f87c79e8d66aed0e7996f9336462d5f", "tree": "44d100c2eadf2a56794e7b526abeb21d1019baa1", "parents": [ "ba13da47ffa202784355561f72160a41350e95cc" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 19 12:46:39 2012 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 19 12:46:39 2012 +1100" }, "message": "md/raid10: handle merge_bvec_fn in member devices.\n\nCurrently we don\u0027t honour merge_bvec_fn in member devices so if there\nis one, we force all requests to be single-page at most.\nThis is not ideal.\n\nSo enhance the raid10 merge_bvec_fn to check that function in children\nas well.\n\nThis introduces a small problem. There is no locking around calls\nthe -\u003emerge_bvec_fn and subsequent calls to -\u003emake_request. So a\ndevice added between these could end up getting a request which\nviolates its merge_bvec_fn.\n\nCurrently the best we can do is synchronize_sched(). This will work\nproviding no preemption happens. If there is preemption, we just\nhave to hope that new devices are largely consistent with old devices.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "dafb20fa34320a472deb7442f25a0c086e0feb33", "tree": "2ff501805f8a6d08119f1f1a7248f579d52e491b", "parents": [ "d6b42dcb995e6acd7cc276774e751ffc9f0ef4bf" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 19 12:46:39 2012 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 19 12:46:39 2012 +1100" }, "message": "md: tidy up rdev_for_each usage.\n\nmd.h has an \u0027rdev_for_each()\u0027 macro for iterating the rdevs in an\nmddev. However it uses the \u0027safe\u0027 version of list_for_each_entry,\nand so requires the extra variable, but doesn\u0027t include \u0027safe\u0027 in the\nname, which is useful documentation.\n\nConsequently some places use this safe version without needing it, and\nmany use an explicity list_for_each entry.\n\nSo:\n - rename rdev_for_each to rdev_for_each_safe\n - create a new rdev_for_each which uses the plain\n list_for_each_entry,\n - use the \u0027safe\u0027 version only where needed, and convert all other\n list_for_each_entry calls to use rdev_for_each.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2d78f8c451785f030ac1676a18691896b59c69d8", "tree": "4dfe69115b2ca2fb8be2a671e7c8399c3925fcb9", "parents": [ "b8321b68d1445f308324517e45fb0a5c2b48e271" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Dec 23 10:17:51 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Dec 23 10:17:51 2011 +1100" }, "message": "md: create externally visible flags for supporting hot-replace.\n\nhot-replace is a feature being added to md which will allow a\ndevice to be replaced without removing it from the array first.\n\nWith hot-replace a spare can be activated and recovery can start while\nthe original device is still in place, thus allowing a transition from\nan unreliable device to a reliable device without leaving the array\ndegraded during the transition. It can also be use when the original\ndevice is still reliable but it not wanted for some reason.\n\nThis will eventually be supported in RAID4/5/6 and RAID10.\n\nThis patch adds a super-block flag to distinguish the replacement\ndevice. If an old kernel sees this flag it will reject the device.\n\nIt also adds two per-device flags which are viewable and settable via\nsysfs.\n \"want_replacement\" can be set to request that a device be replaced.\n \"replacement\" is set to show that this device is replacing another\n device.\n\nThe \"rd%d\" links in /sys/block/mdXx/md only apply to the original\ndevice, not the replacement. We currently don\u0027t make links for the\nreplacement - there doesn\u0027t seem to be a need.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b8321b68d1445f308324517e45fb0a5c2b48e271", "tree": "3fc4c9b253435753d2154d9bd697a7869163c29a", "parents": [ "476a7abb9b00adfe6bf70e82800367319ab8078b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Dec 23 10:17:51 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Dec 23 10:17:51 2011 +1100" }, "message": "md: change hot_remove_disk to take an rdev rather than a number.\n\nSoon an array will be able to have multiple devices with the\nsame raid_disk number (an original and a replacement). So removing\na device based on the number won\u0027t work. So pass the actual device\nhandle instead.\n\nReviewed-by: Dan Williams \u003cdan.j.williams@intel.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b4fdcb02f1e39c27058a885905bd0277370ba441", "tree": "fd4cfd1994f21f44afe5e7904681fb5ac09f81b8", "parents": [ "044595d4e448305fbaec472eb7d22636d24e7d8c", "6dd9ad7df2019b1e33a372a501907db293ebcd0d" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Nov 04 17:06:58 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Nov 04 17:06:58 2011 -0700" }, "message": "Merge branch \u0027for-3.2/core\u0027 of git://git.kernel.dk/linux-block\n\n* \u0027for-3.2/core\u0027 of git://git.kernel.dk/linux-block: (29 commits)\n block: don\u0027t call blk_drain_queue() if elevator is not up\n blk-throttle: use queue_is_locked() instead of lockdep_is_held()\n blk-throttle: Take blkcg-\u003elock while traversing blkcg-\u003epolicy_list\n blk-throttle: Free up policy node associated with deleted rule\n block: warn if tag is greater than real_max_depth.\n block: make gendisk hold a reference to its queue\n blk-flush: move the queue kick into\n blk-flush: fix invalid BUG_ON in blk_insert_flush\n block: Remove the control of complete cpu from bio.\n block: fix a typo in the blk-cgroup.h file\n block: initialize the bounce pool if high memory may be added later\n block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown\n block: drop @tsk from attempt_plug_merge() and explain sync rules\n block: make get_request[_wait]() fail if queue is dead\n block: reorganize throtl_get_tg() and blk_throtl_bio()\n block: reorganize queue draining\n block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg()\n block: pass around REQ_* flags instead of broken down booleans during request alloc/free\n block: move blk_throtl prototypes to block/blk.h\n block: fix genhd refcounting in blkio_policy_parse_and_set()\n ...\n\nFix up trivial conflicts due to \"mddev_t\" -\u003e \"struct mddev\" conversion\nand making the request functions be of type \"void\" instead of \"int\" in\n - drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c}\n - drivers/staging/zram/zram_drv.c\n" }, { "commit": "5c04b426f2e8b46cfc7969a35b2631063a3c646c", "tree": "2d27d9f5d2fe5d5e8fbc01a467ec58bcb50235c1", "parents": [ "499337bb6511e665a236a6a947f819d98ea340c6", "899e3ee404961a90b828ad527573aaaac39f0ab1" ], "author": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Wed Oct 19 14:30:42 2011 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@kernel.dk", "time": "Wed Oct 19 14:30:42 2011 +0200" }, "message": "Merge branch \u0027v3.1-rc10\u0027 into for-3.2/core\n\nConflicts:\n\tblock/blk-core.c\n\tinclude/linux/blkdev.h\n\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n" }, { "commit": "84fc4b56db85cb9e05326424049973a2036c9940", "tree": "b8f942766ad620d63da92c24df56032168879253", "parents": [ "29d3247ea2274bca0d0b7f41fcf3b82e0a8bc44c" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:49:58 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:49:58 2011 +1100" }, "message": "md: rename \"mdk_personality\" to \"md_personality\"\n\n\"mdk\" doesn\u0027t mean anything any more.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2b8bf3451d1e3133ebc3998721d14013a6c27114", "tree": "6ad9afb9124d5eb865d513ec3f30259231075a8f", "parents": [ "fd01b88c75a718020ff77e7f560d33835e9b58de" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:48:23 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:48:23 2011 +1100" }, "message": "md: remove typedefs: mdk_thread_t -\u003e struct md_thread\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "fd01b88c75a718020ff77e7f560d33835e9b58de", "tree": "c455d5adefd58f3263dcf265bb8ba2024523b106", "parents": [ "3cb03002000f133f9f97269edefd73611eafc873" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:47:53 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:47:53 2011 +1100" }, "message": "md: remove typedefs: mddev_t -\u003e struct mddev\n\nHaving mddev_t and \u0027struct mddev_s\u0027 is ugly and not preferred\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "3cb03002000f133f9f97269edefd73611eafc873", "tree": "77fdb146666298b33aaeef0c05f082b6f82840fe", "parents": [ "50de8df4abca1b27dbf7b2f81a56451bd8b5a7d8" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:45:26 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 11 16:45:26 2011 +1100" }, "message": "md: removing typedefs: mdk_rdev_t -\u003e struct md_rdev\n\nThe typedefs are just annoying. \u0027mdk\u0027 probably refers to \u0027md_k.h\u0027\nwhich used to be an include file that defined this thing.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "7e841526263b3e0042a423513147dfd06c8e998d", "tree": "c576c1f968713c6f4ba020a8de744af757cbffe7", "parents": [ "2585f3ef8c7fffe750ef1feb2775023716d799a8" ], "author": { "name": "Wang Sheng-Hui", "email": "shhuiw@gmail.com", "time": "Wed Sep 21 15:37:46 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Sep 21 15:37:46 2011 +1000" }, "message": "trival: md_k.h should be md.h in the beginning comment of file md.h\n\nSigned-off-by: Wang Sheng-Hui \u003cshhuiw@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "01f96c0a9922cd9919baf9d16febdf7016177a12", "tree": "a877fe509c4ef0db5252b7192df56009c1d06d6f", "parents": [ "27a7b260f71439c40546b43588448faac01adb93" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Sep 21 15:30:20 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Sep 21 15:30:20 2011 +1000" }, "message": "md: Avoid waking up a thread after it has been freed.\n\nTwo related problems:\n\n1/ some error paths call \"md_unregister_thread(mddev-\u003ethread)\"\n without subsequently clearing -\u003ethread. A subsequent call\n to mddev_unlock will try to wake the thread, and crash.\n\n2/ Most calls to md_wakeup_thread are protected against the thread\n disappeared either by:\n - holding the -\u003emutex\n - having an active request, so something else must be keeping\n the array active.\n However mddev_unlock calls md_wakeup_thread after dropping the\n mutex and without any certainty of an active request, so the\n -\u003ethread could theoretically disappear.\n So we need a spinlock to provide some protections.\n\nSo change md_unregister_thread to take a pointer to the thread\npointer, and ensure that it always does the required locking, and\nclears the pointer properly.\n\nReported-by: \"Moshe Melnikov\" \u003cmoshe@zadarastorage.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\ncc: stable@kernel.org\n" }, { "commit": "5a7bbad27a410350e64a2d7f5ec18fc73836c14f", "tree": "3447cd62dbcbd77b4071e2eb7576f1d7632ef2d3", "parents": [ "c20e8de27fef9f59869c81c288ad6cf28200e00c" ], "author": { "name": "Christoph Hellwig", "email": "hch@infradead.org", "time": "Mon Sep 12 12:12:01 2011 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Mon Sep 12 12:12:01 2011 +0200" }, "message": "block: remove support for bio remapping from -\u003emake_request\n\nThere is very little benefit in allowing to let a -\u003emake_request\ninstance update the bios device and sector and loop around it in\n__generic_make_request when we can archive the same through calling\ngeneric_make_request from the driver and letting the loop in\ngeneric_make_request handle it.\n\nNote that various drivers got the return value from -\u003emake_request and\nreturned non-zero values for errors.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nAcked-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "de393cdea66cbd63c90725663f400c76faf1b255", "tree": "6a2bf37bee98bf7de42856f904bd23c81e082f8e", "parents": [ "d7a9d443bc8a75a24873c0506f50051edfedc714" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md: make it easier to wait for bad blocks to be acknowledged.\n\nIt is only safe to choose not to write to a bad block if that bad\nblock is safely recorded in metadata - i.e. if it has been\n\u0027acknowledged\u0027.\n\nIf it hasn\u0027t we need to wait for the acknowledgement.\n\nWe support that using rdev-\u003eblocked wait and\nmd_wait_for_blocked_rdev by introducing a new device flag\n\u0027BlockedBadBlock\u0027.\n\nThis flag is only advisory.\nIt is cleared whenever we acknowledge a bad block, so that a waiter\ncan re-check the particular bad blocks that it is interested it.\n\nIt should be set by a caller when they find they need to wait.\nThis (set after test) is inherently racy, but as\nmd_wait_for_blocked_rdev already has a timeout, losing the race will\nhave minimal impact.\n\nWhen we clear \"Blocked\" was also clear \"BlockedBadBlocks\" incase it\nwas set incorrectly (see above race).\n\nWe also modify the way we manage \u0027Blocked\u0027 to fit better with the new\nhandling of \u0027BlockedBadBlocks\u0027 and to make it consistent between\nexternally managed and internally managed metadata. This requires\nthat each raidXd loop checks if the metadata needs to be written and\ntriggers a write (md_check_recovery) if needed. Otherwise a queued\nwrite request might cause raidXd to wait for the metadata to write,\nand only that thread can write it.\n\nBefore writing metadata, we set FaultRecorded for all devices that\nare Faulty, then after writing the metadata we clear Blocked for any\ndevice for which the Fault was certainly Recorded.\n\nThe \u0027faulty\u0027 device flag now appears in sysfs if the device is faulty\n*or* it has unacknowledged bad blocks. So user-space which does not\nunderstand bad blocks can continue to function correctly.\nUser space which does, should not assume a device is faulty until it\nsees the \u0027faulty\u0027 flag, and then sees the list of unacknowledged bad\nblocks is empty.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "d7a9d443bc8a75a24873c0506f50051edfedc714", "tree": "6255771f6cca87698dcc8eb11d62e7fc217b8d0b", "parents": [ "06f603851fa90bcd236328438278d4dc8b655495" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md: add \u0027write_error\u0027 flag to component devices.\n\nIf a device has ever seen a write error, we will want to handle\nknown-bad-blocks differently.\nSo create an appropriate state flag and export it via sysfs.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "d2eb35acfdccbe2a3622ed6cc441a5482148423b", "tree": "77600cab29fc9e1fd39d612773086a456fc32d88", "parents": [ "9f2f3830789a4c9c1af2d1437d407c43e05136e6" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:48 2011 +1000" }, "message": "md/raid1: avoid reading from known bad blocks.\n\nNow that we have a bad block list, we should not read from those\nblocks.\nThere are several main parts to this:\n 1/ read_balance needs to check for bad blocks, and return not only\n the chosen device, but also how many good blocks are available\n there.\n 2/ fix_read_error needs to avoid trying to read from bad blocks.\n 3/ read submission must be ready to issue multiple reads to\n different devices as different bad blocks on different devices\n could mean that a single large read cannot be served by any one\n device, but can still be served by the array.\n This requires keeping count of the number of outstanding requests\n per bio. This count is stored in \u0027bi_phys_segments\u0027\n 4/ retrying a read needs to also be ready to submit a smaller read\n and queue another request for the rest.\n\nThis does not yet handle bad blocks when reading to perform resync,\nrecovery, or check.\n\n\u0027md_trim_bio\u0027 will also be used for RAID10, so put it in md.c and\nexport it.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2699b67223aca6b1450fc2f72e40fada952afc85", "tree": "c84d0cbb763ad03cd770a218a37f0f1ec31118af", "parents": [ "34b343cff4354ab9864be83be88405fd53d928a0" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:47 2011 +1000" }, "message": "md: load/store badblock list from v1.x metadata\n\nSpace must have been allocated when array was created.\nA feature flag is set when the badblock list is non-empty, to\nensure old kernels don\u0027t load and trust the whole device.\n\nWe only update the on-disk badblocklist when it has changed.\nIf the badblocklist (or other metadata) is stored on a bad block, we\ndon\u0027t cope very well.\n\nIf metadata has no room for bad block, flag bad-blocks as disabled,\nand do the same for 0.90 metadata.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2230dfe4ccc3add340dc6d437965b2de1d269fde", "tree": "fc45b727ad2e1a148e7d20f327b45a3afc474e9d", "parents": [ "a519b26dbe6533416d21b552053b0bf687f878d7" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:46 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jul 28 11:31:46 2011 +1000" }, "message": "md: beginnings of bad block management.\n\nThis the first step in allowing md to track bad-blocks per-device so\nthat we can fail individual blocks rather than the whole device.\n\nThis patch just adds a data structure for recording bad blocks, with\nroutines to add, remove, search the list.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\n" }, { "commit": "3520fa4db7fc4ae1b0373dcecdaf720f620dab2d", "tree": "62c675a29c65f89ec15f4a52203e5e0f731c2aa5", "parents": [ "654e8b5abc0a793f0c029128db6e4804691a383e" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Wed Jul 27 11:00:37 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jul 27 11:00:37 2011 +1000" }, "message": "MD bitmap: Revert DM dirty log hooks\n\n\nRevert most of commit e384e58549a2e9a83071ad80280c1a9053cfd84c\n md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.\n\nMD should not need to use DM\u0027s dirty log - we decided to use md\u0027s\nbitmaps instead.\n\nKeeping the DIV_ROUND_UP clean-ups that were part of commit\ne384e58549a2e9a83071ad80280c1a9053cfd84c, however.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "5389042ffa36976caa45a79af16081d759001fa7", "tree": "eb303de141a50f41ccac438e734b65dbfe25825e", "parents": [ "a478a069b6adf186373a6648c54fc5f1d3c2f8eb" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jul 27 11:00:36 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jul 27 11:00:36 2011 +1000" }, "message": "md: change managed of recovery_disabled.\n\nIf we hit a read error while recovering a mirror, we want to abort the\nrecovery without necessarily failing the disk - as having a disk this\na read error is better than not having an array at all.\n\nCurrently this is managed with a per-array flag \"recovery_disabled\"\nand is only implemented for RAID1. For RAID10 we will need finer\ngrained control as we might want to disable recovery for individual\ndevices separately.\n\nSo push more of the decision making into the personality.\n\u0027recovery_disabled\u0027 is now a \u0027cookie\u0027 which is copied when the\npersonality want to disable recovery and is changed when a device is\nadded to the array as this is used as a trigger to \u0027try recovery\nagain\u0027.\n\nThis will allow RAID10 to get the control that it needs.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "36fad858a7404a9656122a9e560a224ae2a00979", "tree": "95f8a7a6b8dad6bb8d7c7735f7845888b5e702db", "parents": [ "8bda470e8ebde35f9349e98ecbce4dfb508a60fa" ], "author": { "name": "Namhyung Kim", "email": "namhyung@gmail.com", "time": "Wed Jul 27 11:00:36 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jul 27 11:00:36 2011 +1000" }, "message": "md: introduce link/unlink_rdev() helpers\n\nThere are places where sysfs links to rdev are handled\nin a same way. Add the helper functions to consolidate\nthem.\n\nSigned-off-by: Namhyung Kim \u003cnamhyung@gmail.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "9c81075f436f867f580c2edf2350c0898cffc9d0", "tree": "025ec9792e7f5700d9383ba15f953fb0d1f07ec9", "parents": [ "076f968b37f0232d883749da8f5031df5dea7ade" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Wed Jun 08 17:59:30 2011 -0500" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 09 11:41:36 2011 +1000" }, "message": "MD: support initial bitmap creation in-kernel\n\nAdd bitmap support to the device-mapper specific metadata area.\n\nThis patch allows the creation of the bitmap metadata area upon\ninitial array creation via device-mapper.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "076f968b37f0232d883749da8f5031df5dea7ade", "tree": "aa1c58756c3754abe657be36b4720a16d5c41858", "parents": [ "1ed7242e591af7e233234d483f12d33818b189d9" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Tue Jun 07 17:51:30 2011 -0500" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jun 08 15:11:31 2011 +1000" }, "message": "MD: add sync_super to mddev_t struct\n\nAdd the \u0027sync_super\u0027 function pointer to MD array structure (struct mddev_s)\n\nIf device-mapper (dm-raid.c) is to define its own on-disk superblock and be\nable to load it, there must still be a way for MD to initiate superblock\nupdates. The simplest way to make this happen is to provide a pointer in\nthe MD array structure that can be set by device-mapper (or other module)\nwith a function to do this. If the function has been set, it will be used;\notherwise, the method with be looked up via \u0027super_types\u0027 as usual.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "97658cdd3af7d01461874c93b89afa4a2465e7c6", "tree": "d4e2f930850eb3981307a3eec8c86399dcebf68a", "parents": [ "482c083492ddaa32ef5864bae3d143dc8bcdf7d1" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Apr 18 18:25:42 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Apr 18 18:25:42 2011 +1000" }, "message": "md: provide generic support for handling unplug callbacks.\n\nWhen an md device adds a request to a queue, it can call\nmddev_check_plugged.\nIf this succeeds then we know that the md thread will be woken up\nshortly, and -\u003eplug_cnt will be non-zero until then, so some\nprocessing can be delayed.\n\nIf it fails, then no unplug callback is expected and the make_request\nfunction needs to do whatever is required to make the request happen.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "482c083492ddaa32ef5864bae3d143dc8bcdf7d1", "tree": "75017fd1a51fe945c65b3600442ddaa20b636b1a", "parents": [ "af1db72d8b340f97ad12b60175afdef43e6f0e60" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Apr 18 18:25:42 2011 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Apr 18 18:25:42 2011 +1000" }, "message": "md - remove old plugging code.\n\nmd has some plugging infrastructure for RAID5 to use because the\nnormal plugging infrastructure required a \u0027request_queue\u0027, and when\ncalled from dm, RAID5 doesn\u0027t have one of those available.\n\nThis relied on the -\u003eunplug_fn callback which doesn\u0027t exist any more.\n\nSo remove all of that code, both in md and raid5. Subsequent patches\nwith restore the plugging functionality.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "25985edcedea6396277003854657b5f3cb31a628", "tree": "f026e810210a2ee7290caeb737c23cb6472b7c38", "parents": [ "6aba74f2791287ec407e0f92487a725a25908067" ], "author": { "name": "Lucas De Marchi", "email": "lucas.demarchi@profusion.mobi", "time": "Wed Mar 30 22:57:33 2011 -0300" }, "committer": { "name": "Lucas De Marchi", "email": "lucas.demarchi@profusion.mobi", "time": "Thu Mar 31 11:26:23 2011 -0300" }, "message": "Fix common misspellings\n\nFixes generated by \u0027codespell\u0027 and manually reviewed.\n\nSigned-off-by: Lucas De Marchi \u003clucas.demarchi@profusion.mobi\u003e\n" }, { "commit": "f0b4f7e2f29af678bd9af43422c537dcb6008603", "tree": "dfc2aa18bbf8411a499ef8117a5e15490eb44728", "parents": [ "93b270f76e7ef3b81001576860c2701931cdc78b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Feb 24 17:26:41 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Feb 24 17:26:41 2011 +1100" }, "message": "md: Fix - again - partition detection when array becomes active\n\nRevert\n b821eaa572fd737faaf6928ba046e571526c36c6\nand\n f3b99be19ded511a1bf05a148276239d9f13eefa\n\nWhen I wrote the first of these I had a wrong idea about the\nlifetime of \u0027struct block_device\u0027. It can disappear at any time that\nthe block device is not open if it falls out of the inode cache.\n\nSo relying on the \u0027size\u0027 recorded with it to detect when the\ndevice size has changed and so we need to revalidate, is wrong.\n\nRather, we really do need the \u0027changed\u0027 attribute stored directly in\nthe mddev and set/tested as appropriate.\n\nWithout this patch, a sequence of:\n mknod / open / close / unlink\n\n(which can cause a block_device to be created and then destroyed)\nwill result in a rescan of the partition table and consequence removal\nand addition of partitions.\nSeveral of these in a row can get udev racing to create and unlink and\nother code can get confused.\n\nWith the patch, the rescan is only performed when needed and so there\nare no races.\n\nThis is suitable for any stable kernel from 2.6.35.\n\nReported-by: \"Wojcik, Krzysztof\" \u003ckrzysztof.wojcik@intel.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nCc: stable@kernel.org\n" }, { "commit": "f21e9ff7f77d41ceca4e1e5ee5a4efa5ad7a5e40", "tree": "c6bf9c0457ae891505983c1493bf15856e815c5b", "parents": [ "50da08409654e036c4c964a473567a61a654cb83" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jan 31 12:10:09 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jan 31 12:10:09 2011 +1100" }, "message": "md: Remove the AllReserved flag for component devices.\n\nThis flag is not needed and is used badly.\n\nDevices that are included in a native-metadata array are reserved\nexclusively for that array - and currently have AllReserved set.\nThey all are bd_claimed for the rdev and so cannot be shared.\n\nDevices that are included in external-metadata arrays can be shared\namong multiple arrays - providing there is no overlap.\nThese are bd_claimed for md in general - not for a particular rdev.\n\nWhen changing the amount of a device that is used in an array we need\nto check for overlap. This currently includes a check on AllReserved\nSo even without overlap, sharing with an AllReserved device is not\nallowed.\nHowever the bd_claim usage already precludes sharing with these\ndevices, so the test on AllReserved is not needed. And in fact it is\nwrong.\n\nAs this is the only use of AllReserved, simply remove all usage and\ndefinition of AllReserved.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "a6ff7e089c7fca813c956ccbed824087e89a3a49", "tree": "6537f72a2431c30601736676e9b1f89a7f1fe52e", "parents": [ "ccebd4c4159462c96397ae9af9c667bb394d7b70" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Fri Jan 14 09:14:34 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Jan 14 09:14:34 2011 +1100" }, "message": "md: separate meta and data devs\n\nAllow the metadata to be on a separate device from the\ndata.\n\nThis doesn\u0027t mean the data and metadata will by on separate\nphysical devices - it simply gives device-mapper and userspace\ntools more flexibility.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "ccebd4c4159462c96397ae9af9c667bb394d7b70", "tree": "04554f0e7607d906c6b09f31a995fca0dd40c5b5", "parents": [ "57b2caa394393f8870ed41bdcc38a7542593018f" ], "author": { "name": "Jonathan Brassow", "email": "jbrassow@redhat.com", "time": "Fri Jan 14 09:14:33 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Jan 14 09:14:33 2011 +1100" }, "message": "md-new-param-to_sync_page_io\n\nAdd new parameter to \u0027sync_page_io\u0027.\n\nThe new parameter allows us to distinguish between metadata and data\noperations. This becomes important later when we add the ability to\nuse separate devices for data and metadata.\n\nSigned-off-by: Jonathan Brassow \u003cjbrassow@redhat.com\u003e\n" }, { "commit": "0ca69886a8273ac1350143d562280bfcbe4760dc", "tree": "98acbe1e5682e4455bf7d2e7a9413b5a3fd43b2a", "parents": [ "067032bc628598606056412594042564fcf09e22" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Jan 14 09:14:33 2011 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Fri Jan 14 09:14:33 2011 +1100" }, "message": "md: Ensure no IO request to get md device before it is properly initialised.\n\nWhen an md device is in the process of coming on line it is possible\nfor an IO request (typically a partition table probe) to get through\nbefore the array is fully initialised, which can cause unexpected\nbehaviour (e.g. a crash).\n\nSo explicitly record when the array is ready for IO and don\u0027t allow IO\nthrough until then.\n\nThere is no possibility for a similar problem when the array is going\noff-line as there must only be one \u0027open\u0027 at that time, and it is busy\noff-lining the array and so cannot send IO requests. So no memory\nbarrier is needed in md_stop()\n\nThis has been a bug since commit 409c57f3801 in 2.6.30 which\nintroduced md_make_request. Before then, each personality would\nregister its own make_request_fn when it was ready.\nThis is suitable for any stable kernel from 2.6.30.y onwards.\n\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReported-by: \"Hawrylewicz Czarnowski, Przemyslaw\" \u003cprzemyslaw.hawrylewicz.czarnowski@intel.com\u003e\n" }, { "commit": "a167f663243662aa9153c01086580a11cde9ffdc", "tree": "886e64787421bbf17a1eab7853d67258b598f050", "parents": [ "2b193363ef68667ad717a6723165e0dccf99470f" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Oct 26 18:31:13 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Oct 28 17:36:15 2010 +1100" }, "message": "md: use separate bio pool for each md device.\n\nbio_clone and bio_alloc allocate from a common bio pool.\nIf an md device is stacked with other devices that use this pool, or under\nsomething like swap which uses the pool, then the multiple calls on\nthe pool can cause deadlocks.\n\nSo allocate a local bio pool for each md array and use that rather\nthan the common pool.\n\nThis pool is used both for regular IO and metadata updates.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2b193363ef68667ad717a6723165e0dccf99470f", "tree": "bd45d5186f0edf2b546c4503d794b479d126ad1f", "parents": [ "1c4588e9c19cae6209a28c9da2f16a18a610b935" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Oct 27 15:16:40 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Oct 28 17:36:11 2010 +1100" }, "message": "md: change type of first arg to sync_page_io.\n\nCurrently sync_page_io takes a \u0027bdev\u0027.\nEvery caller passes \u0027rdev-\u003ebdev\u0027.\nWe will soon want another field out of the rdev in sync_page_io,\nSo just pass the rdev instead of the bdev out of it.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "fa251f89903d73989e2f63e13d0eaed1e07ce0da", "tree": "3f7fe779941e3b6d67754dd7c44a32f48ea47c74", "parents": [ "dd3932eddf428571762596e17b65f5dc92ca361b", "cd07202cc8262e1669edff0d97715f3dd9260917" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Oct 19 09:13:04 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Oct 19 09:13:04 2010 +0200" }, "message": "Merge branch \u0027v2.6.36-rc8\u0027 into for-2.6.37/barrier\n\nConflicts:\n\tblock/blk-core.c\n\tdrivers/block/loop.c\n\tmm/swapfile.c\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "e9c7469bb4f502dafc092166201bea1ad5fc0fbf", "tree": "04202b0bb88623d3005c909eaafcb280778902da", "parents": [ "7bc9fddab074d6bb630344e1969e28d20b140621" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Sep 03 11:56:18 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Sep 10 12:35:38 2010 +0200" }, "message": "md: implment REQ_FLUSH/FUA support\n\nThis patch converts md to support REQ_FLUSH/FUA instead of now\ndeprecated REQ_HARDBARRIER. In the core part (md.c), the following\nchanges are notable.\n\n* Unlike REQ_HARDBARRIER, REQ_FLUSH/FUA don\u0027t interfere with\n processing of other requests and thus there is no reason to mark the\n queue congested while FLUSH/FUA is in progress.\n\n* REQ_FLUSH/FUA failures are final and its users don\u0027t need retry\n logic. Retry logic is removed.\n\n* Preflush needs to be issued to all member devices but FUA writes can\n be handled the same way as other writes - their processing can be\n deferred to request_queue of member devices. md_barrier_request()\n is renamed to md_flush_request() and simplified accordingly.\n\nFor linear, raid0 and multipath, the core changes are enough. raid1,\n5 and 10 need the following conversions.\n\n* raid1: Handling of FLUSH/FUA bio\u0027s can simply be deferred to\n request_queues of member devices. Barrier related logic removed.\n\n* raid5: Queue draining logic dropped. FUA bit is propagated through\n biodrain and stripe resconstruction such that all the updated parts\n of the stripe are written out with FUA writes if any of the dirtying\n writes was FUA. preread_active_stripes handling in make_request()\n is updated as suggested by Neil Brown.\n\n* raid10: FUA bit needs to be propagated to write clones.\n\nlinear, raid0, 1, 5 and 10 tested.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReviewed-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "070dc6dd7103b6b3f7e4d46e754354a5c15f366e", "tree": "173e72d08b2070d496c203a6d5156b9a2ad2808c", "parents": [ "bd52b746262c8d77e73903d6608014fb2fcdcd9d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Aug 30 17:33:34 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Aug 30 18:06:21 2010 +1000" }, "message": "md: resolve confusion of MD_CHANGE_CLEAN\n\nMD_CHANGE_CLEAN is used for two different purposes and this leads to\nconfusion.\nOne of the purposes is largely mirrored by MD_CHANGE_PENDING which is\nnot used for anything else, so have MD_CHANGE_PENDING take over that\npurpose fully.\n\nThe two purposes are:\n 1/ tell md_update_sb that an update is needed and that it is just a\n clean/dirty transition.\n 2/ tell user-space that an transition from clean to dirty is pending\n (something wants to write), and tell te kernel (by clearin the\n flag) that the transition is OK.\n\nThe first purpose remains wit MD_CHANGE_CLEAN, the second is moved\nfully to MD_CHANGE_PENDING.\n\nThis means that various places which conditionally set or cleared\nMD_CHANGE_CLEAN no longer need to be conditional.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "3d30701b58970425e1d45994d6cb82f828924fdd", "tree": "8b14cf462628bebf8548c1b8c205a674564052d1", "parents": [ "8cbd84f2dd4e52a8771b191030c374ba3e56d291", "fd8aa2c1811bf60ccb2d5de0579c6f62aec1772d" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Aug 10 15:38:19 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Aug 10 15:38:19 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://neil.brown.name/md\n\n* \u0027for-linus\u0027 of git://neil.brown.name/md: (24 commits)\n md: clean up do_md_stop\n md: fix another deadlock with removing sysfs attributes.\n md: move revalidate_disk() back outside open_mutex\n md/raid10: fix deadlock with unaligned read during resync\n md/bitmap: separate out loading a bitmap from initialising the structures.\n md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.\n md/bitmap: optimise scanning of empty bitmaps.\n md/bitmap: clean up plugging calls.\n md/bitmap: reduce dependence on sysfs.\n md/bitmap: white space clean up and similar.\n md/raid5: export raid5 unplugging interface.\n md/plug: optionally use plugger to unplug an array during resync/recovery.\n md/raid5: add simple plugging infrastructure.\n md/raid5: export is_congested test\n raid5: Don\u0027t set read-ahead when there is no queue\n md: add support for raising dm events.\n md: export various start/stop interfaces\n md: split out md_rdev_init\n md: be more careful setting MD_CHANGE_CLEAN\n md/raid5: ensure we create a unique name for kmem_cache when mddev has no gendisk\n ...\n" }, { "commit": "bb4f1e9d0e2ef93de8e36ca0f5f26625fcd70b7d", "tree": "7c7edc0d5fa2b5702358f11396d52d07183708c0", "parents": [ "147e0b6a639ac581ca3bf627bedc3f4a6d3eca66" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Sun Aug 08 21:18:03 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Sun Aug 08 21:21:27 2010 +1000" }, "message": "md: fix another deadlock with removing sysfs attributes.\n\nMove the deletion of sysfs attributes from reconfig_mutex to\nopen_mutex didn\u0027t really help as a process can try to take\nopen_mutex while holding reconfig_mutex, so the same deadlock can\nhappen, just requiring one more process to be involved in the chain.\n\nI looks like I cannot easily use locking to wait for the sysfs\ndeletion to complete, so don\u0027t.\n\nThe only things that we cannot do while the deletions are still\npending is other things which can change the sysfs namespace: run,\ntakeover, stop. Each of these can fail with -EBUSY.\nSo set a flag while doing a sysfs deletion, and fail run, takeover,\nstop if that flag is set.\n\nThis is suitable for 2.6.35.x\n\nCc: stable@kernel.org\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "7b6d91daee5cac6402186ff224c3af39d79f4a0e", "tree": "b1518cf0b6c301178e0a320f80610cd5b3aa7625", "parents": [ "33659ebbae262228eef4e0fe990f393d1f0ed941" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Sat Aug 07 18:20:39 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Sat Aug 07 18:20:39 2010 +0200" }, "message": "block: unify flags for struct bio and struct request\n\nRemove the current bio flags and reuse the request flags for the bio, too.\nThis allows to more easily trace the type of I/O from the filesystem\ndown to the block driver. There were two flags in the bio that were\nmissing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I\u0027ve\nrenamed two request flags that had a superflous RW in them.\n\nNote that the flags are in bio.h despite having the REQ_ name - as\nblkdev.h includes bio.h that is the only way to go for now.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "e384e58549a2e9a83071ad80280c1a9053cfd84c", "tree": "805619143612ddc8cc71a45dd4522393c23a576f", "parents": [ "ef4256733506f2459a0c436b62267d22a3f0cec6" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:34 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 13:21:34 2010 +1000" }, "message": "md/bitmap: prepare for storing write-intent-bitmap via dm-dirty-log.\n\nThis allows md/raid5 to fully work as a dm target.\n\nNormally md uses a \u0027filemap\u0027 which contains a list of pages of bits\neach of which may be written separately.\ndm-log uses and all-or-nothing approach to writing the log, so\nwhen using a dm-log, -\u003efilemap is NULL and the flags normally stored\nin filemap_attr are stored in -\u003elogattrs instead.\n\n\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b63d7c2e29bf9cc94989806f2df0cfca4976b830", "tree": "fdb82527ca458769d3c7381375873931bfb23b19", "parents": [ "5ff5afffe6527543866a47ffab12769427283917" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:33 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 13:21:32 2010 +1000" }, "message": "md/bitmap: clean up plugging calls.\n\n1/ use md_unplug in bitmap.c as we will soon be using bitmaps under\n arrays with no queue attached.\n\n2/ Don\u0027t bother plugging the queue when we set a bit in the bitmap.\n The reason for this was to encourage as many bits as possible to\n get set before we unplug and write stuff out.\n However every personality already plugs the queue after\n bitmap_startwrite either directly (raid1/raid10) or be setting\n STRIPE_BIT_DELAY which causes the queue to be plugged later\n (raid5).\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "ac2f40be46ce6ab3bec4c8c297d6923f941741ce", "tree": "f1abc7d627edaaf450dbff3e68a902ff667a3c92", "parents": [ "9f7c2220017771253d7d10b3cc017cb79eeac0fb" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:31 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 13:07:22 2010 +1000" }, "message": "md/bitmap: white space clean up and similar.\n\nFixes some whitespace problems\nFixed some checkpatch.pl complaints.\nReplaced kmalloc ... memset(0), with kzalloc\nFixed an unlikely memory leak on an error path.\nReformatted a number of \u0027if/else\u0027 sets, sometimes\nreplacing goto with an else clause.\nRemoved some old comments and commented-out code.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "252ac5221a71be72b7e7c7b7482af91e9c962e8c", "tree": "cb9542b1391dabc136ce0052eb28948e77a6e2e5", "parents": [ "2ac8740151b082f045e58010eb92560c3a23a0e9" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:29 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 12:53:08 2010 +1000" }, "message": "md/plug: optionally use plugger to unplug an array during resync/recovery.\n\nIf an array doesn\u0027t have a \u0027queue\u0027 then md_do_sync cannot\nunplug it.\nIn that case it will have a \u0027plugger\u0027, so make that available\nto the mddev, and use it to unplug the array if needed.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "2ac8740151b082f045e58010eb92560c3a23a0e9", "tree": "39bff686e28f033339c6d1cf47042b6dc1586c2f", "parents": [ "11d8a6e3719519fbc0e2c9d61b6fa931b84bf813" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:29 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 12:53:08 2010 +1000" }, "message": "md/raid5: add simple plugging infrastructure.\n\nmd/raid5 uses the plugging infrastructure provided by the block layer\nand \u0027struct request_queue\u0027. However when we plug raid5 under dm there\nis no request queue so we cannot use that.\n\nSo create a similar infrastructure that is much lighter weight and use\nit for raid5.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "768a418db102bb6aa6064e6090892b5c21ff1f9e", "tree": "2f33acbf0ca542f43c8014201b539ae8f461ee5c", "parents": [ "390ee602a142a93f2c7eb7bffee8e277058b8e0a" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 11:49:55 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 12:52:27 2010 +1000" }, "message": "md: add support for raising dm events.\n\ndm uses scheduled work to raise events to user-space.\nSo allow md device to have work_structs and schedule them on an error.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "390ee602a142a93f2c7eb7bffee8e277058b8e0a", "tree": "33a23748dd5ff4ea76b34ed3e458c6da91185376", "parents": [ "e8bb9a839a26f076379e9cb9f46a879d210156f1" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:27 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 12:52:27 2010 +1000" }, "message": "md: export various start/stop interfaces\n\nexport entry points for starting and stopping md arrays.\nThis will be used by a module to make md/raid5 work under\ndm.\nAlso stop calling md_stop_writes from md_stop, as that won\u0027t\nwork well with dm - it will want to call the two separately.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "e8bb9a839a26f076379e9cb9f46a879d210156f1", "tree": "4da184e861cc5fea4967089711dfdc4fbb175f43", "parents": [ "676e42d896ab6967859fabbb06f4e11b9615cbcf" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:26 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Jul 26 12:52:27 2010 +1000" }, "message": "md: split out md_rdev_init\n\nThis functionality will be needed separately in a subsequent patch, so\nsplit it into it\u0027s own exported function.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "00bcb4ac7ee7e557a491b614219142cea0ef16f4", "tree": "992cfa1d0e653aa3de8f0865c5e1a5a0fee4f935", "parents": [ "d0c6f6258478e1dba532bf7c28e2cd6e1047d3a4" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 01 19:37:23 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Jul 21 13:27:53 2010 +1000" }, "message": "md: reduce dependence on sysfs.\n\nWe will want md devices to live as dm targets where sysfs is not\nvisible. So allow md to not connect to sysfs.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "e93f68a1fc6244c05ad8fae28e75835ec74ab34e", "tree": "d282978aac8f6fcec512be2a6e61287bbb6241b1", "parents": [ "0544a21db02c1d8883158fd6f323364f830a120a" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Jun 15 09:36:03 2010 +0100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 24 13:33:24 2010 +1000" }, "message": "md: fix handling of array level takeover that re-arranges devices.\n\nMost array level changes leave the list of devices largely unchanged,\npossibly causing one at the end to become redundant.\nHowever conversions between RAID0 and RAID10 need to renumber\nall devices (except 0).\n\nThis renumbering is currently being done in the -\u003erun method when the\nnew personality takes over. However this is too late as the common\ncode in md.c might already have invalidated some of the devices if\nthey had a -\u003eraid_disk number that appeared to high.\n\nMoving it into the -\u003etakeover method is too early as the array is\nstill active at that time and wrong -\u003eraid_disk numbers could cause\nconfusion.\n\nSo add a -\u003enew_raid_disk field to mdk_rdev_s and use it to communicate\nthe new raid_disk number.\nNow the common code knows exactly which devices need to be renumbered,\nand which can be invalidated, and can do it all at a convenient time\nwhen the array is suspend.\nIt can also update some symlinks in sysfs which previously were not be\nupdated correctly.\n\nReported-by: Maciej Trela \u003cmaciej.trela@intel.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "a8707c08f4f718bb0ed65499d3f43201f6e41455", "tree": "8fc3ea9ea924ebc4f28012c11f3c1e70ad60bcb2", "parents": [ "7b0bb5368a7195606eca475d9f4e291ab7227052" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 09:28:43 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 15:28:01 2010 +1000" }, "message": "md: simplify updating of event count to sometimes avoid updating spares.\n\nWhen updating the event count for a simple clean \u003c-\u003e dirty transition,\nwe try to avoid updating the spares so they can safely spin-down.\nAs the event_counts across an array must be +/- 1, this means\ndecrementing the event_count on a dirty-\u003eclean transition.\nThis is not always safe and we have to avoid the unsafe time.\nWe current do this with a misguided idea about it being safe or\nnot depending on whether the event_count is odd or even. This\napproach only works reliably in a few common instances, but easily\nfalls down.\n\nSo instead, simply keep internal state concerning whether it is safe\nor not, and always assume it is not safe when an array is first\nassembled.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "21a52c6d05c15f862797736393915bfa8cd40ee9", "tree": "44ffb633d209457979177a52132761a368fcb976", "parents": [ "cca9cf90c504d98644ace52c474770970729f0eb" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Apr 01 15:02:13 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 15:27:55 2010 +1000" }, "message": "md: pass mddev to make_request functions rather than request_queue\n\nWe used to pass the personality make_request function direct\nto the block layer so the first argument had to be a queue.\nBut now we have the intermediary md_make_request so it makes\nat lot more sense to pass a struct mddev_s.\nIt makes it possible to have an mddev without its own queue too.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b821eaa572fd737faaf6928ba046e571526c36c6", "tree": "0db462a3c7da3dbf42d28e2483a27d78839b4589", "parents": [ "49ce6cea85fb8d25ee59486c919406e9cecf1762" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 29 11:18:15 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 15:27:53 2010 +1000" }, "message": "md: remove -\u003echanged and related code.\n\nWe set -\u003echanged to 1 and call check_disk_change at the end\nof md_open so that bd_invalidated would be set and thus\npartition rescan would happen appropriately.\n\nNow that we call revalidate_disk directly, which sets bd_invalidates,\nthat indirection is no longer needed and can be removed.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "c0cc75f84e0e413bce2dcabea74ef418da45c7c1", "tree": "f5723fbd0f5828cadaeec650abb8066ad52fad71", "parents": [ "7b92813c3c0b6990f14838e3985fb385d2655d0c" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 22 10:28:51 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 15:27:47 2010 +1000" }, "message": "md: discard StateChanged device flag.\n\nThis was needed when sysfs files could only be \u0027notified\u0027\nfrom process context. Now that we have sys_notify_direct,\nwe can call it directly from an interrupt.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "ee8b81b03dffa1c0075553d01c557714aedb85a1", "tree": "95ba42aad6fb632699cd9e60d700d05ff96bc889", "parents": [ "964147d5c86d63be79b442c30f3783d49860c078" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Mar 08 16:02:36 2010 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue May 18 15:27:45 2010 +1000" }, "message": "md: remove some dead fields from mddev_s\n\nThese fields have never been used.\ncommit 4b6d287f627b5fb6a49f78f9e81649ff98c62bb7\nadded them, but also added identical files to bitmap_super_s,\nand only used the latter.\n\nSo remove these unused fields.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "a64c876fd357906a1f7193723866562ad290654c", "tree": "077fcdab730d40227585025bf15bf8e027949a29", "parents": [ "b6eb127d274385d81ce8dd45c98190f097bce1b4" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Apr 14 17:15:37 2010 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon May 17 14:45:40 2010 +1000" }, "message": "md: manage redundancy group in sysfs when changing level.\n\nSome levels expect the \u0027redundancy group\u0027 to be present,\nothers don\u0027t.\nSo when we change level of an array we might need to\nadd or remove this group.\n\nThis requires fixing up the current practice of overloading -\u003eprivate\nto indicate (when -\u003epers \u003d\u003d NULL) that something needs to be removed.\nSo create a new -\u003eto_remove to fill that role.\n\nWhen changing levels, we may need to add or remove attributes. When\nchanging RAID5 -\u003e RAID6, we both add and remove the same thing. It is\nimportant to catch this and optimise it out as the removal is delayed\nuntil a lock is released, so trying to add immediately would cause\nproblems.\n\n\nCc: stable@kernel.org\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "1e50915fe0bbf7a46db0fa7e1e604d3fc95f057d", "tree": "7a722ad6f56c61a6173493f1cd44d809c8b1bd8d", "parents": [ "67b8dc4b06b0e97df55fd76e209f34f9a52e820e" ], "author": { "name": "Robert Becker", "email": "Rob.Becker@riverbed.com", "time": "Mon Dec 14 12:49:58 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "raid: improve MD/raid10 handling of correctable read errors.\n\nWe\u0027ve noticed severe lasting performance degradation of our raid\narrays when we have drives that yield large amounts of media errors.\nThe raid10 module will queue each failed read for retry, and also\nwill attempt call fix_read_error() to perform the read recovery.\nRead recovery is performed while the array is frozen, so repeated\nrecovery attempts can degrade the performance of the array for\nextended periods of time.\n\nWith this patch I propose adding a per md device max number of\ncorrected read attempts. Each rdev will maintain a count of\nread correction attempts in the rdev-\u003eread_errors field (not\nused currently for raid10). When we enter fix_read_error()\nwe\u0027ll check to see when the last read error occurred, and\ndivide the read error count by 2 for every hour since the\nlast read error. If at that point our read error count\nexceeds the read error threshold, we\u0027ll fail the raid device.\n\nIn addition in this patch I add sysfs nodes (get/set) for\nthe per md max_read_errors attribute, the rdev-\u003eread_errors\nattribute, and added some printk\u0027s to indicate when\nfix_read_error fails to repair an rdev.\n\nFor testing I used debugfs-\u003efail_make_request to inject\nIO errors to the rdev while doing IO to the raid array.\n\nSigned-off-by: Robert Becker \u003cRob.Becker@riverbed.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "ece5cff0da9e696c360fff592cb5f51b6419e4d6", "tree": "1c5cab0e89ae466be9edb476ceb91e5c898fafa6", "parents": [ "624ce4f5658fa3e0303c1217bba2706142fe7568" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:56 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: Support write-intent bitmaps with externally managed metadata.\n\nIn this case, the metadata needs to not be in the same\nsector as the bitmap.\nmd will not read/write any bitmap metadata. Config must be\ndone via sysfs and when a recovery makes the array non-degraded\nagain, writing \u0027true\u0027 to \u0027bitmap/can_clear\u0027 will allow bits in\nthe bitmap to be cleared again.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "43a705076e51c5af21ec4260a35699775ea298f5", "tree": "ff8e161d841c41992dbbcca2a844816411941c3c", "parents": [ "72e02075a33f739e21430262f71da8e82db9dbb3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:55 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: support updating bitmap parameters via sysfs.\n\nA new attribute directory \u0027bitmap\u0027 in \u0027md\u0027 is created which\ncontains files for configuring the bitmap.\n\u0027location\u0027 identifies where the bitmap is, either \u0027none\u0027,\nor \u0027file\u0027 or \u0027sector offset from metadata\u0027.\nWriting \u0027location\u0027 can create or remove a bitmap.\nAdding a \u0027file\u0027 bitmap this way is not yet supported.\n\u0027chunksize\u0027 and \u0027time_base\u0027 must be set before \u0027location\u0027\ncan be set.\n\n\u0027chunksize\u0027 can be set before creating a bitmap, but is\ncurrently always over-ridden by the bitmap superblock.\n\n\u0027time_base\u0027 and \u0027backlog\u0027 can be updated at any time.\n\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Andre Noll \u003cmaan@systemlinux.org\u003e\n" }, { "commit": "72e02075a33f739e21430262f71da8e82db9dbb3", "tree": "04a87a16751b714fe0fb41f28ccc54af9f820de1", "parents": [ "f6af949c5672115313cc3c976d85b0533f607d7e" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:55 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: factor out parsing of fixed-point numbers\n\nsafe_delay_store can parse fixed point numbers (for fractions\nof a second). We will want to do that for another sysfs\nfile soon, so factor out the code.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "f6af949c5672115313cc3c976d85b0533f607d7e", "tree": "6d00471bd4ee7c3aee67f9ad4c0a3023109b88e0", "parents": [ "9cd30fdc33cde9ae4ac55a1ccbbb89f3f7b9b2f2" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:54 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: support bitmap offset appropriate for external-metadata arrays.\n\nFor md arrays were metadata is managed externally, the kernel does not\nknow about a superblock so the superblock offset is 0.\nIf we want to have a write-intent-bitmap near the end of the\ndevices of such an array, we should support sector_t sized offset.\nWe need offset be possibly negative for when the bitmap is before\nthe metadata, so use loff_t instead.\n\nAlso add sanity check that bitmap does not overlap with data.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "42a04b5078ce73a32f85762551d5703c5bd646a1", "tree": "3ef384933cd33d000516c292712da9a99e273360", "parents": [ "c3d9714e88c8685cf9bc837c3241fc005f95fb82" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:53 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: move offset, daemon_sleep and chunksize out of bitmap structure\n\n... and into bitmap_info. These are all configuration parameters\nthat need to be set before the bitmap is created.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "c3d9714e88c8685cf9bc837c3241fc005f95fb82", "tree": "dd11e16ec911983bb7452bb4fb092769ba612e3b", "parents": [ "709ae4879ae33628ded276ce7da8cd5acfec476b" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:52 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:51:41 2009 +1100" }, "message": "md: collect bitmap-specific fields into one structure.\n\nIn preparation for making bitmap fields configurable via sysfs,\nstart tidying up by making a single structure to contain the\nconfiguration fields.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "a2826aa92e2e14db372eda01d333267258944033", "tree": "9cdd3329205bf480a4782705a3db1738e3faae44", "parents": [ "efa593390e70b0e3c39f6b2dca8876b6b1461e41" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:49 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:49 2009 +1100" }, "message": "md: support barrier requests on all personalities.\n\nPreviously barriers were only supported on RAID1. This is because\nother levels requires synchronisation across all devices and so needed\na different approach.\nHere is that approach.\n\nWhen a barrier arrives, we send a zero-length barrier to every active\ndevice. When that completes - and if the original request was not\nempty - we submit the barrier request itself (with the barrier flag\ncleared) and then submit a fresh load of zero length barriers.\n\nThe barrier request itself is asynchronous, but any subsequent\nrequest will block until the barrier completes.\n\nThe reason for clearing the barrier flag is that a barrier request is\nallowed to fail. If we pass a non-empty barrier through a striping\nraid level it is conceivable that part of it could succeed and part\ncould fail. That would be way too hard to deal with.\nSo if the first run of zero length barriers succeed, we assume all is\nsufficiently well that we send the request and ignore errors in the\nsecond run of barriers.\n\nRAID5 needs extra care as write requests may not have been submitted\nto the underlying devices yet. So we flush the stripe cache before\nproceeding with the barrier.\n\nNote that the second set of zero-length barriers are submitted\nimmediately after the original request is submitted. Thus when\na personality finds mddev-\u003ebarrier to be set during make_request,\nit should not return from make_request until the corresponding\nper-device request(s) have been queued.\n\nThat will be done in later patches.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nReviewed-by: Andre Noll \u003cmaan@systemlinux.org\u003e\n" }, { "commit": "aa5cbd103887011b4830355f88fb055f9ad2d556", "tree": "92ef7c80999c6d0bfc6fef9a9cd3e4a75ee16c06", "parents": [ "f40542532e96dda5506eb76badea322f2ae4731c" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:46 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Dec 14 12:49:46 2009 +1100" }, "message": "md/bitmap: protect against bitmap removal while being updated.\n\nA write intent bitmap can be removed from an array while the\narray is active.\nWhen this happens, all IO is suspended and flushed before the\nbitmap is removed.\nHowever it is possible that bitmap_daemon_work is still running to\nclear old bits from the bitmap. If it is, it can dereference the\nbitmap after it has been freed.\n\nSo introduce a new mutex to protect bitmap_daemon_work and get it\nbefore destroying a bitmap.\n\nThis is suitable for any current -stable kernel.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\nCc: stable@kernel.org\n" }, { "commit": "3fa841d7e7266f6fcc1b3885b905f5153ba897d8", "tree": "7afa971a10eddcf52787340ea43fa1e910b5805b", "parents": [ "0da3c6194ec2f32617b272df4505a1cf022faea5" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Sep 23 18:10:29 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Wed Sep 23 18:10:29 2009 +1000" }, "message": "md: report device as congested when suspended\n\nThis should writeback from coming when the device is temporarily\nsuspended.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "411c94038594b2a3fd123d09bdec3fe2500e383d", "tree": "44b991786c7f4806b1b88f40439945b3835b6292", "parents": [ "786d8ca341a30296264bc6cebac52d37b0851647" ], "author": { "name": "Anand Gadiyar", "email": "gadiyar@ti.com", "time": "Tue Jul 07 15:24:23 2009 +0530" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Mon Sep 21 15:14:54 2009 +0200" }, "message": "trivial: fix typo \"for for\" in multiple files\n\ntrivial: fix typo \"for for\" in multiple files\n\nSigned-off-by: Anand Gadiyar \u003cgadiyar@ti.com\u003e\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\n" }, { "commit": "c8c00a6915a2e3d10416e8bdd3138429beb96210", "tree": "ecf06a9e2b08edefe707da450b52a69f818ec7d6", "parents": [ "7b2aa037e878c939676675969983284a02958ae3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Aug 10 12:50:52 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Aug 10 12:50:52 2009 +1000" }, "message": "Remove deadlock potential in md_open\n\nA recent commit:\n commit 449aad3e25358812c43afc60918c5ad3819488e7\n\nintroduced the possibility of an A-B/B-A deadlock between\nbd_mutex and reconfig_mutex.\n\n__blkdev_get holds bd_mutex while calling md_open which takes\n reconfig_mutex,\ndo_md_run is always called with reconfig_mutex held, and it now\n takes bd_mutex in the call the revalidate_disk.\n\nThis potential deadlock was not caught by lockdep due to the\nuse of mutex_lock_interruptible_nexted which was introduced\nby\n commit d63a5a74dee87883fda6b7d170244acaac5b05e8\ndo avoid a warning of an impossible deadlock.\n\nIt is quite possible to split reconfig_mutex in to two locks.\nOne protects the array data structures while it is being\nreconfigured, the other ensures that an array is never even partially\nopen while it is being deactivated.\nIn particular, the second lock prevents an open from completing\nbetween the time when do_md_stop checks if there are any active opens,\nand the time when the array is either set read-only, or when -\u003epers is\nset to NULL. So we can be certain that no IO is in flight as the\narray is being destroyed.\n\nSo create a new lock, open_mutex, just to ensure exclusion between\n\u0027open\u0027 and \u0027stop\u0027.\n\nThis avoids the deadlock and also avoids the lockdep warning mentioned\nin commit d63a5a74d\n\nReported-by: \"Mike Snitzer\" \u003csnitzer@gmail.com\u003e\nReported-by: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "ac5e7113e74872928844d00085bd47c988f12728", "tree": "dabce6a99c2af9f00b33660f6b2d906cce836764", "parents": [ "95fc17aac45300f45968aacd97a536ddd8db8101" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Mon Aug 03 10:59:47 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Mon Aug 03 10:59:47 2009 +1000" }, "message": "md: Push down data integrity code to personalities.\n\nThis patch replaces md_integrity_check() by two new public functions:\nmd_integrity_register() and md_integrity_add_rdev() which are both\npersonality-independent.\n\nmd_integrity_register() is called from the -\u003erun and -\u003ehot_remove\nmethods of all personalities that support data integrity. The\nfunction iterates over the component devices of the array and\ndetermines if all active devices are integrity capable and if their\nprofiles match. If this is the case, the common profile is registered\nfor the mddev via blk_integrity_register().\n\nThe second new function, md_integrity_add_rdev() is called from the\n-\u003ehot_add_disk methods, i.e. whenever a new device is being added\nto a raid array. If the new device does not support data integrity,\nor has a profile different from the one already registered, data\nintegrity for the mddev is disabled.\n\nFor raid0 and linear, only the call to md_integrity_register() from\nthe -\u003erun method is necessary.\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "0894cc3066aaa3e75a99383c0d25feebf9b688ac", "tree": "651664e6b288e36dc9553443e334e650139851c8", "parents": [ "8190e754e0723de7cecb80bdd9eb93911dfa04a1" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Thu Jun 18 08:49:23 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:49:23 2009 +1000" }, "message": "md: Move check for bitmap presence to personality code.\n\nIf the superblock of a component device indicates the presence of a\nbitmap but the corresponding raid personality does not support bitmaps\n(raid0, linear, multipath, faulty), then something is seriously wrong\nand we\u0027d better refuse to run such an array.\n\nCurrently, this check is performed while the superblocks are examined,\ni.e. before entering personality code. Therefore the generic md layer\nmust know which raid levels support bitmaps and which do not.\n\nThis patch avoids this layer violation without adding identical code\nto various personalities. This is accomplished by introducing a new\npublic function to md.c, md_check_no_bitmap(), which replaces the\nhard-coded checks in the superblock loading functions.\n\nA call to md_check_no_bitmap() is added to the -\u003erun method of each\npersonality which does not support bitmaps and assembly is aborted\nif at least one component device contains a bitmap.\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "8190e754e0723de7cecb80bdd9eb93911dfa04a1", "tree": "6fbd0edd64cb767b9421103301e198804c3aa40b", "parents": [ "13f2682b7216ebebd72b3d5868fe7fccec91a92d" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:48:58 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:48:58 2009 +1000" }, "message": "md: remove chunksize rounding from common code.\n\nIt is easiest to round sizes to multiples of chunk size in\nthe personality code for those personalities which care.\nThose personalities now do the rounding, so we can\nremove that function from common code.\n\nAlso remove the upper bound on the size of a chunk, and the lower\nbound on the size of a device (1 chunk), neither of which really buy\nus anything.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "50ac168a6e0a061bf5346d53aa9e7beb94c97527", "tree": "4f1eff67793bd8349a1995c921a63e9512be7818", "parents": [ "597a711b69cfff95c4b8f6069037e7ad3fc71f56" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:47:55 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:47:55 2009 +1000" }, "message": "md: merge reconfig and check_reshape methods.\n\nThe difference between these two methods is artificial.\nBoth check that a pending reshape is valid, and perform any\naspect of it that can be done immediately.\n\u0027reconfig\u0027 handles chunk size and layout.\n\u0027check_reshape\u0027 handles raid_disks.\n\nSo make them just one method.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "597a711b69cfff95c4b8f6069037e7ad3fc71f56", "tree": "8c2cfa4c1223827a560de2f14da426d4822151c4", "parents": [ "01ee22b496c41384eaa6dcae983c86d8bc32fbb8" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:47:42 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:47:42 2009 +1000" }, "message": "md: remove unnecessary arguments from -\u003ereconfig method.\n\nPassing the new layout and chunksize as args is not necessary as\nthe mddev has fields for new_check and new_layout.\n\nThis is preparation for combining the check_reshape and reconfig\nmethods\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "664e7c413f1e90eceb0b2596dd73a0832faec058", "tree": "72ea827a0f2a493766d3ea1fd14909c756aa4496", "parents": [ "9d8f0363623b3da12c43007cf77f5e1a4e8a5964" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Thu Jun 18 08:45:27 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:45:27 2009 +1000" }, "message": "md: Convert mddev-\u003enew_chunk to sectors.\n\nA straight-forward conversion which gets rid of some\nmultiplications/divisions/shifts. The patch also introduces a couple\nof new ones, most of which are due to conf-\u003echunk_size still being\nrepresented in bytes. This will be cleaned up in subsequent patches.\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "9d8f0363623b3da12c43007cf77f5e1a4e8a5964", "tree": "0fee53971a397ade209dd36c4f1ed50db6450faf", "parents": [ "fbb704efb784e2c8418e34dc3013af76bdd58101" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Thu Jun 18 08:45:01 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Thu Jun 18 08:45:01 2009 +1000" }, "message": "md: Make mddev-\u003echunk_size sector-based.\n\nThis patch renames the chunk_size field to chunk_sectors with the\nimplied change of semantics. Since\n\n\tis_power_of_2(chunk_size) \u003d is_power_of_2(chunk_sectors \u003c\u003c 9)\n\t\t\t\t \u003d is_power_of_2(chunk_sectors)\n\nthese bits don\u0027t need an adjustment for the shift.\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "63fe08177f92ce21929df8af6361491b98ad12cd", "tree": "7d6f5aa9251f3120e0911483463e14e1137ed81c", "parents": [ "b0cbc861a3c05e634520b049b5cc27ad6febb51f" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Apr 14 12:01:53 2009 +1000" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Apr 14 12:01:53 2009 +1000" }, "message": "md: tiny md.h cleanups\n\n- update inclusion guard and make sure it covers the whole file\n - remove superflous #ifdef CONFIG_BLOCK\n - make sure all required headers are included so that new users aren\u0027t\n required to include others before\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "cea9c22800773cecb1d41f4a6139f9eb6a95368b", "tree": "d070d22390b86768fefb8ba04c64d74993ed28e9", "parents": [ "7ec0547838976d088dfb9cb0adb073e6e8a15aa3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 15:15:05 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 15:15:05 2009 +1100" }, "message": "md: add explicit method to signal the end of a reshape.\n\nCurrently raid5 (the only module that supports restriping)\nnotices that the reshape has finished be sync_request being\ngiven a large value, and handles any cleanup them.\n\nThis patch changes it so md_check_recovery calls into an\nexplicit finish_reshape method as well.\n\nThe clean-up from sync_request can do things that need to be\ndone promptly, typically things local to the raid5_conf_t\nstructure.\n\nThe \"finish_reshape\" method is called under the mddev_lock\nso it can do things involving reconfiguring the device.\n\nThis allows us to get rid of md_set_array_sectors_locked, which\nwould have caused a deadlock if you tried to stop and array\nwhile a reshape was happening.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "b522adcde9c4d3fb7b579cfa9160d8bde7744be8", "tree": "4208e3dcec3ebdfa6ad9bc153f76129400532717", "parents": [ "1f403624bde3c678a166984b1e6a727a0ce06f2b" ], "author": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 31 15:00:31 2009 +1100" }, "committer": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 31 15:00:31 2009 +1100" }, "message": "md: \u0027array_size\u0027 sysfs attribute\n\nAllow userspace to set the size of the array according to the following\nsemantics:\n\n1/ size must be \u003c\u003d to the size returned by mddev-\u003epers-\u003esize(mddev, 0, 0)\n a) If size is set before the array is running, do_md_run will fail\n if size is greater than the default size\n b) A reshape attempt that reduces the default size to less than the set\n array size should be blocked\n2/ once userspace sets the size the kernel will not change it\n3/ writing \u0027default\u0027 to this attribute returns control of the size to the\n kernel and reverts to the size reported by the personality\n\nAlso, convert locations that need to know the default size from directly\nreading -\u003earray_sectors to \u003cpers\u003e_size. Resync/reshape operations\nalways follow the default size.\n\nFinally, fixup other locations that read a number of 1k-blocks from\nuserspace to use strict_blocks_to_sectors() which checks for unsigned\nlong long to sector_t overflow and blocks to sectors overflow.\n\nReviewed-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: Dan Williams \u003cdan.j.williams@intel.com\u003e\n" }, { "commit": "1f403624bde3c678a166984b1e6a727a0ce06f2b", "tree": "b66ed37091e825bcde1cd0d333d4ebba86772805", "parents": [ "80c3a6ce4ba4470379b9e6a4d9bcd9d2ee26ae03" ], "author": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 31 14:59:03 2009 +1100" }, "committer": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 31 14:59:03 2009 +1100" }, "message": "md: centralize -\u003earray_sectors modifications\n\nGet personalities out of the business of directly modifying\n-\u003earray_sectors. Lays groundwork to introduce policy on when\n-\u003earray_sectors can be modified.\n\nReviewed-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: Dan Williams \u003cdan.j.williams@intel.com\u003e\n" }, { "commit": "80c3a6ce4ba4470379b9e6a4d9bcd9d2ee26ae03", "tree": "de88622f05a7e681ac7bff7714e8f2d8953b66ac", "parents": [ "93ed05e2a56b5ee06c0100a169433b11c4aa5d0b" ], "author": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 17 18:10:40 2009 -0700" }, "committer": { "name": "Dan Williams", "email": "dan.j.williams@intel.com", "time": "Tue Mar 31 14:57:49 2009 +1100" }, "message": "md: add \u0027size\u0027 as a personality method\n\nIn preparation for giving userspace control over -\u003earray_sectors we need\nto be able to retrieve the \u0027default\u0027 size, and the \u0027anticipated\u0027 size\nwhen a reshape is requested. For personalities that do not reshape emit\na warning if anything but the default size is requested.\n\nIn the raid5 case we need to update -\u003eprevious_raid_disks to make the\nnew \u0027default\u0027 size available.\n\nReviewed-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: Dan Williams \u003cdan.j.williams@intel.com\u003e\n" }, { "commit": "245f46c2c221ef09c7db892f0e3fc2149be42052", "tree": "be7e6f4b7b65b682c43e59ef17f7ed580bc8a82b", "parents": [ "409c57f3801701dfee27a28103dda4831306cb20" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:39:39 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:39:39 2009 +1100" }, "message": "md: add -\u003etakeover method to support changing the personality managing an array\n\nImplement this for RAID6 to be able to \u0027takeover\u0027 a RAID5 array. The\nnew RAID6 will use a layout which places Q on the last device, and\nthat device will be missing.\nIf there are any available spares, one will immediately have Q\nrecovered onto it.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "409c57f3801701dfee27a28103dda4831306cb20", "tree": "430c8e4ebe879b27250e061dc1a1171b12aaadf0", "parents": [ "e0cf8f045b2023b0b3f919ee93eb94345f648434" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:39:39 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:39:39 2009 +1100" }, "message": "md: enable suspend/resume of md devices.\n\nTo be able to change the \u0027level\u0027 of an md/raid array, we need to\nsuspend the device so that no requests are active - then move some\npointers around etc.\n\nThe code already keeps counts of active requests and the -\u003equiesce\nfunction can be used to wait until those counts hit zero.\nHowever the quiesce function blocks new requests once they are all\nready \u0027inside\u0027 the personality module, and that is too late if we want\nto replace the personality modules.\n\nSo make all md requests come in through a common md_make_request\nfunction that keeps track of how many requests have entered the\nmodules but may not yet be on the internal reference counts.\nAllow md_make_request to be blocked when we want to suspend the\ndevice, and make it possible to wait for all those in-transit requests\nto be added to internal lists so that -\u003equiesce can wait for them.\n\nThere is still a problem that when a request completes, we drop the\nref count inside the personality code so there is a short time between\nwhen the refcount hits zero, and when the personality code is no\nlonger being used.\nThe personality code never blocks (schedule or spinlock) between\ndropping the refcount and exiting the routine, so this should be safe\n(as put_module calls synchronize_sched() before unmapping the module\ncode).\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "dd8ac336c13fd8afdb082ebacb1cddd5cf727889", "tree": "0baa8111d7406774525a1053be461135257d73d2", "parents": [ "58c0fed400603a802968b23ddf78f029c5a84e41" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: Represent raid device size in sectors.\n\nThis patch renames the \"size\" field of struct mdk_rdev_s to\n\"sectors\" and changes this field to store sectors instead of\nblocks.\n\nAll users of this field, linear.c, raid0.c and md.c, are fixed up\naccordingly which gets rid of many multiplications and divisions.\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "58c0fed400603a802968b23ddf78f029c5a84e41", "tree": "474fcb9775bb07f39ebb7802fb9b51d69222dcbb", "parents": [ "575a80fa4f623141e9791e41879d87800fb6d862" ], "author": { "name": "Andre Noll", "email": "maan@systemlinux.org", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: Make mddev-\u003esize sector-based.\n\nThis patch renames the \"size\" field of struct mddev_s to \"dev_sectors\"\nand stores the number of 512-byte sectors instead of the number of\n1K-blocks in it.\n\nAll users of that field, including raid levels 1,4-6,10, are adjusted\naccordingly. This simplifies the code a bit because it allows to get\nrid of a couple of divisions/multiplications by two.\n\nIn order to make checkpatch happy, some minor coding style issues\nhave also been addressed. In particular, size_store() now uses\nstrict_strtoull() instead of simple_strtoull().\n\nSigned-off-by: Andre Noll \u003cmaan@systemlinux.org\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "97e4f42d62badb0f9fbc27c013e89bc1336a03bc", "tree": "04cc809702a6b080c417c4ddf605642bbf7de521", "parents": [ "43b2e5d86d8bdd77386226db0bc961529492c043" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: occasionally checkpoint drive recovery to reduce duplicate effort after a crash\n\nVersion 1.x metadata has the ability to record the status of a\npartially completed drive recovery.\nHowever we only update that record on a clean shutdown.\nIt would be nice to update it on unclean shutdowns too, particularly\nwhen using a bitmap that removes much to the \u0027sync\u0027 effort after an\nunclean shutdown.\n\nOne complication with checkpointing recovery is that we only know\nwhere we are up to in terms of IO requests started, not which ones\nhave completed. And we need to know what has completed to record\nhow much is recovered. So occasionally pause the recovery until all\nsubmitted requests are completed, then update the record of where\nwe are up to.\n\nWhen we have a bitmap, we already do that pause occasionally to keep\nthe bitmap up-to-date. So enhance that code to record the recovery\noffset and schedule a superblock update.\nAnd when there is no bitmap, just pause 16 times during the resync to\ndo a checkpoint.\n\u002716\u0027 is a fairly arbitrary number. But we don\u0027t really have any good\nway to judge how often is acceptable, and it seems like a reasonable\nnumber for now.\n\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "43b2e5d86d8bdd77386226db0bc961529492c043", "tree": "601a885b1410324678cf319eee77cc54a02f2cf3", "parents": [ "bff61975b3d6c18ee31457cc5b4d73042f44915f" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: move md_k.h from include/linux/raid/ to drivers/md/\n\nIt really is nicer to keep related code together..\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "bff61975b3d6c18ee31457cc5b4d73042f44915f", "tree": "3aff48088b35172e74f56ae54f0b53e76a0c2150", "parents": [ "92022950c6b1bb3da90b2976b20271cdfd98b8a3" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: move lots of #include lines out of .h files and into .c\n\nThis makes the includes more explicit, and is preparation for moving\nmd_k.h to drivers/md/md.h\n\nRemove include/raid/md.h as its only remaining use was to #include\nother files.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "92022950c6b1bb3da90b2976b20271cdfd98b8a3", "tree": "5405257242ddcadef6e90ea597289558de4e03f2", "parents": [ "8b2b5c217c20b5460218ab8731295f2e46c7dd29" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:33:13 2009 +1100" }, "message": "md: move most content from md.h to md_k.h\n\nThe extern function definitions are kernel-internal definitions, so\nthey belong in md_k.h\n\nThe MD_*_VERSION values could reasonably go in a number of places,\nbut md_u.h seems most reasonable.\n\nThis leaves almost nothing in md.h. It will go soon.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" }, { "commit": "8b2b5c217c20b5460218ab8731295f2e46c7dd29", "tree": "f5da8b06b3d2a53e80c31e0c0aa386e381b3a841", "parents": [ "ef740c372dfd80e706dbf955d4e4aedda6c0c148" ], "author": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:27:03 2009 +1100" }, "committer": { "name": "NeilBrown", "email": "neilb@suse.de", "time": "Tue Mar 31 14:27:03 2009 +1100" }, "message": "md: move LEVEL_* definition from md_k.h to md_u.h\n\n.. as they are part of the user-space interface.\nAlso move MdpMinorShift into there so we can remove duplication.\n\nLastly move mdp_major in. It is less obviously part of the user-space\ninterface, but do_mounts_md.c uses it, and it is acting a bit like\nuser-space.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n" } ], "next": "eea1bf384e05b5ab747f8530c4fba9e9e6907fff" }