)]}'
{
  "log": [
    {
      "commit": "69e51b449d383e97b1b9f890f8378c96e9e17346",
      "tree": "650123fa4f08e8fa7f348a4ca875c59c129e5d84",
      "parents": [
        "e384e58549a2e9a83071ad80280c1a9053cfd84c"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue Jun 01 19:37:35 2010 +1000"
      },
      "committer": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Mon Jul 26 13:21:34 2010 +1000"
      },
      "message": "md/bitmap:  separate out loading a bitmap from initialising the structures.\n\ndm makes this distinction between -\u003ectr and -\u003eresume, so we need to\ntoo.\n\nAlso get the new bitmap_load to clear out the bitmap first, as this is\nmost consistent with the dm suspend/resume approach\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\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": "e555190d82c0f58e825e3cbd9e6ebe2e7ac713bd",
      "tree": "ea9c8e548c4d5eb5fc903bab05af3bda4192ed00",
      "parents": [
        "d754c5ae1ff76b20d3ecde8ad666d7865eada8ae"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Wed Mar 31 11:21:44 2010 +1100"
      },
      "committer": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue May 18 15:27:57 2010 +1000"
      },
      "message": "md/raid1: delay reads that could overtake behind-writes.\n\nWhen a raid1 array is configured to support write-behind\non some devices, it normally only reads from other devices.\nIf all devices are write-behind (because the rest have failed)\nit is possible for a read request to be serviced before a\nbehind-write request, which would appear as data corruption.\n\nSo when forced to read from a WriteMostly device, wait for any\nwrite-behind to complete, and don\u0027t start any more behind-writes.\n\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n"
    },
    {
      "commit": "696fcd535b5a8cfc0617e9cf1d9d69a13895cc1e",
      "tree": "b9f55833c83a41a6e047f0de82b17d9753ad0542",
      "parents": [
        "ee8b81b03dffa1c0075553d01c557714aedb85a1"
      ],
      "author": {
        "name": "Paul Clements",
        "email": "paul.clements@steeleye.com",
        "time": "Mon Mar 08 16:02:37 2010 +1100"
      },
      "committer": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue May 18 15:27:46 2010 +1000"
      },
      "message": "md: expose max value of behind writes counter\n\nKeep track of the maximum number of concurrent write-behind requests\nfor an md array and exposed this number in sysfs at\n   md/bitmap/max_backlog_used\n\nWriting any value to this file will clear it.\n\nThis allows userspace to be involved in tuning bitmap/backlog.\n\nSigned-off-by: Paul Clements \u003cpaul.clements@steeleye.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": "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": "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": "ef740c372dfd80e706dbf955d4e4aedda6c0c148",
      "tree": "8d9ef9db346ee1ba319a125c9de83cdde049510d",
      "parents": [
        "2a40a8aed083d988df6822bb9b1b08fb7ce21e1d"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.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 headers out of include/linux/raid/\n\nMove the headers with the local structures for the disciplines and\nbitmap.h into drivers/md/ so that they are more easily grepable for\nhacking and not far away.  md.h is left where it is for now as there\nare some uses from the outside.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: NeilBrown \u003cneilb@suse.de\u003e\n"
    },
    {
      "commit": "a0da84f35b25875870270d16b6eccda4884d61a7",
      "tree": "3c092bcef7a8c8704054b02197156e1c803306b2",
      "parents": [
        "0e13fe23a00ad88c737d91d94a050707c6139ce4"
      ],
      "author": {
        "name": "Neil Brown",
        "email": "neilb@notabene.brown",
        "time": "Sat Jun 28 08:31:22 2008 +1000"
      },
      "committer": {
        "name": "Neil Brown",
        "email": "neilb@notabene.brown",
        "time": "Sat Jun 28 08:31:22 2008 +1000"
      },
      "message": "Improve setting of \"events_cleared\" for write-intent bitmaps.\n\nWhen an array is degraded, bits in the write-intent bitmap are not\ncleared, so that if the missing device is re-added, it can be synced\nby only updated those parts of the device that have changed since\nit was removed.\n\nThe enable this a \u0027events_cleared\u0027 value is stored. It is the event\ncounter for the array the last time that any bits were cleared.\n\nSometimes - if a device disappears from an array while it is \u0027clean\u0027 -\nthe events_cleared value gets updated incorrectly (there are subtle\nordering issues between updateing events in the main metadata and the\nbitmap metadata) resulting in the missing device appearing to require\na full resync when it is re-added.\n\nWith this patch, we update events_cleared precisely when we are about\nto clear a bit in the bitmap.  We record events_cleared when we clear\nthe bit internally, and copy that to the superblock which is written\nout before the bit on storage.  This makes it more \"obviously correct\".\n\nWe also need to update events_cleared when the event_count is going\nbackwards (as happens on a dirty-\u003eclean transition of a non-degraded\narray).\n\nThanks to Mike Snitzer for identifying this problem and testing early\n\"fixes\".\n\nCc:  \"Mike Snitzer\" \u003csnitzer@gmail.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\n"
    },
    {
      "commit": "6bcfd601861cce45ca73ac1d714f1286b6b3f0d4",
      "tree": "175173d057e10dd006d6dbd033395977aff55dd9",
      "parents": [
        "03de250a269bfa8e6a9e6ccb4a1dbce19dae8a61"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@lst.de",
        "time": "Fri May 23 13:04:34 2008 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sat May 24 09:56:09 2008 -0700"
      },
      "message": "md: kill file_path wrapper\n\nKill the trivial and rather pointless file_path wrapper around d_path.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "8311c29d40235062a843f4a8e8a70a44af6fe4c9",
      "tree": "c869143fae8f135646300d1bac6639af5bb30dd7",
      "parents": [
        "a35e63efa1fb18c6f20f38e3ddf3f8ffbcf0f6e7"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue Mar 04 14:29:30 2008 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Tue Mar 04 16:35:17 2008 -0800"
      },
      "message": "md: reduce CPU wastage on idle md array with a write-intent bitmap\n\nOn an md array with a write-intent bitmap, a thread wakes up every few seconds\nand scans the bitmap looking for work to do.  If the array is idle, there will\nbe no work to do, but a lot of scanning is done to discover this.\n\nSo cache the fact that the bitmap is completely clean, and avoid scanning the\nwhole bitmap when the cache is known to be clean.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "b47490c9bc73d0b34e4c194db40de183e592e446",
      "tree": "8334581aff7aa0b199df04c6f9d707c1902ad14f",
      "parents": [
        "66c811e99322767bad5db4368de93aac604f02a2"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Wed Feb 06 01:39:50 2008 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Wed Feb 06 10:41:18 2008 -0800"
      },
      "message": "md: Update md bitmap during resync.\n\nCurrently an md array with a write-intent bitmap does not updated that bitmap\nto reflect successful partial resync.  Rather the entire bitmap is updated\nwhen the resync completes.\n\nThis is because there is no guarentee that resync requests will complete in\norder, and tracking each request individually is unnecessarily burdensome.\n\nHowever there is value in regularly updating the bitmap, so add code to\nperiodically pause while all pending sync requests complete, then update the\nbitmap.  Doing this only every few seconds (the same as the bitmap update\ntime) does not notciably affect resync performance.\n\n[snitzer@gmail.com: export bitmap_cond_end_sync]\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: \"Mike Snitzer\" \u003csnitzer@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "5ebf2c1260705a2ce51ad19af33059f08211579d",
      "tree": "a710660aaa499f17239f62328e75cb7159da4d3b",
      "parents": [
        "4d936ec1fdc1541cd6d59d21ddb8b9386e2fcc4c"
      ],
      "author": {
        "name": "Adrian Bunk",
        "email": "bunk@kernel.org",
        "time": "Tue Oct 16 23:30:52 2007 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Wed Oct 17 08:43:03 2007 -0700"
      },
      "message": "bitmap.h: remove dead artifacts\n\nbitmap_active() no longer exists and BITMAP_ACTIVE is no longer used.\n\nSigned-off-by: Adrian Bunk \u003cbunk@kernel.org\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "4ad1366376bfef32ec0ffa12d1faa483d6f330bd",
      "tree": "87a9c864ec5ebd446f6c99f3298bc7638efa8f1e",
      "parents": [
        "f0d76d70bc77b9b11256a3a23e98e80878be1578"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue Jul 17 04:06:13 2007 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Tue Jul 17 10:23:15 2007 -0700"
      },
      "message": "md: change bitmap_unplug and others to void functions\n\nbitmap_unplug only ever returns 0, so it may as well be void.  Two callers try\nto print a message if it returns non-zero, but that message is already printed\nby bitmap_file_kick.\n\nwrite_page returns an error which is not consistently checked.  It always\ncauses BITMAP_WRITE_ERROR to be set on an error, and that can more\nconveniently be checked.\n\nWhen the return of write_page is checked, an error causes bitmap_file_kick to\nbe called - so move that call into write_page - and protect against recursive\ncalls into bitmap_file_kick.\n\nbitmap_update_sb returns an error that is never checked.\n\nSo make these \u0027void\u0027 and be consistent about checking the bit.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "ab6085c795a71b6a21afe7469d30a365338add7a",
      "tree": "d9d901ea1c3401906553ef9e684a1094a1b3083a",
      "parents": [
        "787f17feb204ed1c6331892fb8124b80dc9fe288"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Wed May 23 13:58:10 2007 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Wed May 23 20:14:14 2007 -0700"
      },
      "message": "md: don\u0027t write more than is required of the last page of a bitmap\n\nIt is possible that real data or metadata follows the bitmap without full page\nalignment.\n\nSo limit the last write to be only the required number of bytes, rounded up to\nthe hard sector size of the device.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "da6e1a32fb8d7539a27f699c8671f64d7fefd0cc",
      "tree": "8faa7713ad1333b30d8ba668627251dbc1e0b4ad",
      "parents": [
        "aaf68cfbf2241d24d46583423f6bff5c47e088b3"
      ],
      "author": {
        "name": "Neil Brown",
        "email": "neilb@suse.de",
        "time": "Thu Feb 08 14:20:37 2007 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@woody.linux-foundation.org",
        "time": "Fri Feb 09 09:25:47 2007 -0800"
      },
      "message": "[PATCH] md: avoid possible BUG_ON in md bitmap handling\n\nmd/bitmap tracks how many active write requests are pending on blocks\nassociated with each bit in the bitmap, so that it knows when it can clear\nthe bit (when count hits zero).\n\nThe counter has 14 bits of space, so if there are ever more than 16383, we\ncannot cope.\n\nCurrently the code just calles BUG_ON as \"all\" drivers have request queue\nlimits much smaller than this.\n\nHowever is seems that some don\u0027t.  Apparently some multipath configurations\ncan allow more than 16383 concurrent write requests.\n\nSo, in this unlikely situation, instead of calling BUG_ON we now wait\nfor the count to drop down a bit.  This requires a new wait_queue_head,\nsome waiting code, and a wakeup call.\n\nTested by limiting the counter to 20 instead of 16383 (writes go a lot slower\nin that case...).\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "4f2e639af4bd5e152fc79256e333643d3dd6c10f",
      "tree": "1adf32d929c552d7e4b24475baa45c6108436f79",
      "parents": [
        "1c05b4bc22cd640d3a534bd2851a8413d5df3709"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Sat Oct 21 10:24:09 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Sat Oct 21 13:35:05 2006 -0700"
      },
      "message": "[PATCH] md: endian annotations for the bitmap superblock\n\nAnd a couple of bug fixes found by sparse.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "9b1d1dac181d8c1b9492e05cee660a985d035a06",
      "tree": "af12b1eaac4e0f7f3528ec26a223faeabed35845",
      "parents": [
        "76186dd8b73d2b7b9b4c8629b89c845e97009801"
      ],
      "author": {
        "name": "Paul Clements",
        "email": "paul.clements@steeleye.com",
        "time": "Tue Oct 03 01:15:49 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Tue Oct 03 08:04:17 2006 -0700"
      },
      "message": "[PATCH] md: new sysfs interface for setting bits in the write-intent-bitmap\n\nAdd a new sysfs interface that allows the bitmap of an array to be dirtied.\nThe interface is write-only, and is used as follows:\n\necho \"1000\" \u003e /sys/block/md2/md/bitmap\n\n(dirty the bit for chunk 1000 [offset 0] in the in-memory and on-disk\nbitmaps of array md2)\n\necho \"1000-2000\" \u003e /sys/block/md1/md/bitmap\n\n(dirty the bits for chunks 1000-2000 in md1\u0027s bitmap)\n\nThis is useful, for example, in cluster environments where you may need to\ncombine two disjoint bitmaps into one (following a server failure, after a\nsecondary server has taken over the array).  By combining the bitmaps on\nthe two servers, a full resync can be avoided (This was discussed on the\nlist back on March 18, 2005, \"[PATCH 1/2] md bitmap bug fixes\" thread).\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "d785a06a0b9d0cd86b3cc1bf8e236e62af7b47ed",
      "tree": "7a238aedb0facb5c207a0477296e78b9ef7d551b",
      "parents": [
        "acc55e220166a5ad898e66ad6153fd62eaaac76d"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Mon Jun 26 00:27:48 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Mon Jun 26 09:58:38 2006 -0700"
      },
      "message": "[PATCH] md/bitmap: change md/bitmap file handling to use bmap to file blocks\n\nIf md is asked to store a bitmap in a file, it tries to hold onto the page\ncache pages for that file, manipulate them directly, and call a cocktail of\noperations to write the file out.  I don\u0027t believe this is a supportable\napproach.\n\nThis patch changes the approach to use the same approach as swap files.  i.e.\nbmap is used to enumerate all the block address of parts of the file and we\nwrite directly to those blocks of the device.\n\nswapfile only uses parts of the file that provide a full pages at contiguous\naddresses.  We don\u0027t have that luxury so we have to cope with pages that are\nnon-contiguous in storage.  To handle this we attach buffers to each page, and\nstore the addresses in those buffers.\n\nWith this approach the pagecache may contain data which is inconsistent with\nwhat is on disk.  To alleviate the problems this can cause, md invalidates the\npagecache when releasing the file.  If the file is to be examined while the\narray is active (a non-critical but occasionally useful function), O_DIRECT io\nmust be used.  And new version of mdadm will have support for this.\n\nThis approach simplifies a lot of code:\n - we no longer need to keep a list of pages which we need to wait for,\n   as the b_endio function can keep track of how many outstanding\n   writes there are.  This saves a mempool.\n - -EAGAIN returns from write_page are no longer possible (not sure if\n    they ever were actually).\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "0b79ccf0cdd9f59e5f99017e1a5d23da336544b2",
      "tree": "8688d9810fcba1e24abce726eaf35ff32f6b58d9",
      "parents": [
        "d7375ab324971e7acbea9f02a0269ae7348f4147"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Mon Jun 26 00:27:44 2006 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Mon Jun 26 09:58:38 2006 -0700"
      },
      "message": "[PATCH] md/bitmap: remove bitmap writeback daemon\n\nmd/bitmap currently has a separate thread to wait for writes to the bitmap\nfile to complete (as we cannot get a callback on that action).\n\nHowever this isn\u0027t needed as bitmap_unplug is called from process context and\nwaits for the writeback thread to do it\u0027s work.  The same result can be\nachieved by doing the waiting directly in bitmap_unplug.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "bd926c63b7a6843d3ce2728396c0891e54fce5c4",
      "tree": "38f7083a733e9b31efe69616c5fa3448c74c1320",
      "parents": [
        "b2d444d7ad975d555bb919601bcdc0e58975a40e"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@suse.de",
        "time": "Tue Nov 08 21:39:32 2005 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Wed Nov 09 07:56:38 2005 -0800"
      },
      "message": "[PATCH] md: make md on-disk bitmaps not host-endian\n\nCurrent bitmaps use set_bit et.al and so are host-endian, which means\nnot-portable.  Oops.\n\nDefine a new version number (4) for which bitmaps are little-endian.\n\nSigned-off-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "4b6d287f627b5fb6a49f78f9e81649ff98c62bb7",
      "tree": "7b6cbc6a997e25a7fb6185da7129e539c4ffda8b",
      "parents": [
        "8ddf9efe6708f3674f0ddfeb6425fd27bea109a2"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Fri Sep 09 16:23:47 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Fri Sep 09 16:39:10 2005 -0700"
      },
      "message": "[PATCH] md: add write-behind support for md/raid1\n\nIf a device is flagged \u0027WriteMostly\u0027 and the array has a bitmap, and the\nbitmap superblock indicates that write_behind is allowed, then write_behind is\nenabled for WriteMostly devices.\n\nWrite requests will be acknowledges as complete to the caller (via b_end_io)\nwhen all non-WriteMostly devices have completed the write, but will not be\ncleared from the bitmap until all devices complete.\n\nThis requires memory allocation to make a local copy of the data being\nwritten.  If there is insufficient memory, then we fall-back on normal write\nsemantics.\n\nSigned-Off-By: Paul Clements \u003cpaul.clements@steeleye.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "6b8b3e8a8b3e62b4209eaa36697e3c9df457e196",
      "tree": "8b537e5b358cbe93cd8e8ea54a9281d56a7ce205",
      "parents": [
        "e3b9703e27aab3839dcdb76b00d98428b67d25b0"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Thu Aug 04 12:53:35 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Thu Aug 04 13:00:54 2005 -0700"
      },
      "message": "[PATCH] md: make sure md bitmap updates are flushed when array is stopped.\n\nThe recent change to never ignore the bitmap, revealed that the bitmap isn\u0027t\nbegin flushed properly when an array is stopped.\n\nWe call bitmap_daemon_work three times as there is a three-stage pipeline for\nflushing updates to the bitmap file.\n\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "6a806c510de490318846b53bbfec463d02ca274b",
      "tree": "7018abfd9db7856708bc2c578f48c30eab8855b1",
      "parents": [
        "a1287ba1ba810aae1f8b81e32560d5d3bf3ff9f0"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Fri Jul 15 03:56:35 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@g5.osdl.org",
        "time": "Fri Jul 15 09:54:51 2005 -0700"
      },
      "message": "[PATCH] md/raid1: clear bitmap when fullsync completes\n\nWe need to be careful differentiating between a resync of a complete array,\nin which we can clear the bitmap, and a resync of a degraded array, in\nwhich we cannot.\n\nThis patch cleans all that up.\n\nCc: Paul Clements \u003cpaul.clements@steeleye.com\u003e\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "a654b9d8f851f4ca02649d5825cbe6c608adb10c",
      "tree": "747301647f619a9f1dd48f4d6be96b5e35d2484c",
      "parents": [
        "3d310eb7b3df1252e8595d059d982b0a9825a137"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Tue Jun 21 17:17:27 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@ppc970.osdl.org",
        "time": "Tue Jun 21 19:07:47 2005 -0700"
      },
      "message": "[PATCH] md: allow md intent bitmap to be stored near the superblock.\n\nThis provides an alternate to storing the bitmap in a separate file.  The\nbitmap can be stored at a given offset from the superblock.  Obviously the\ncreator of the array must make sure this doesn\u0027t intersect with data....\nAfter is good for version-0.90 superblocks.\n\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "77ad4bc706fe6c52ab953f31c287a6af712d080c",
      "tree": "6823261d0e111a93c5190ebb1f2ecd8c4905a559",
      "parents": [
        "bfb39fba4e8cdda091f9ebee29fbb8331c4bb605"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Tue Jun 21 17:17:21 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@ppc970.osdl.org",
        "time": "Tue Jun 21 19:07:45 2005 -0700"
      },
      "message": "[PATCH] md: enable the bitmap write-back daemon and wait for it.\n\nCurrently we don\u0027t wait for updates to the bitmap to be flushed to disk\nproperly.  The infrastructure all there, but it isn\u0027t being used....\n\nA separate kernel thread (bitmap_writeback_daemon) is needed to wait for each\npage as we cannot get callbacks when a page write completes.\n\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    },
    {
      "commit": "32a7627cf3a35396a8e834faf34e38ae9f3b1309",
      "tree": "3fe7764f5d8e39d835a397e1099358d924b02981",
      "parents": [
        "57afd89f98a990747445f01c458ecae64263b2f8"
      ],
      "author": {
        "name": "NeilBrown",
        "email": "neilb@cse.unsw.edu.au",
        "time": "Tue Jun 21 17:17:14 2005 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@ppc970.osdl.org",
        "time": "Tue Jun 21 19:07:43 2005 -0700"
      },
      "message": "[PATCH] md: optimised resync using Bitmap based intent logging\n\nWith this patch, the intent to write to some block in the array can be logged\nto a bitmap file.  Each bit represents some number of sectors and is set\nbefore any update happens, and only cleared when all writes relating to all\nsectors are complete.\n\nAfter an unclean shutdown, information in this bitmap can be used to optimise\nresync - only sectors which could be out-of-sync need to be updated.\n\nAlso if a drive is removed and then added back into an array, the recovery can\nmake use of the bitmap to optimise reconstruction.  This is not implemented in\nthis patch.\n\nCurrently the bitmap is stored in a file which must (obviously) be stored on a\nseparate device.\n\nThe patch only provided infrastructure.  It does not update any personalities\nto bitmap intent logging.\n\nMd arrays can still be used with no bitmap file.  This patch has minimal\nimpact on such arrays.\n\nSigned-off-by: Neil Brown \u003cneilb@cse.unsw.edu.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n"
    }
  ]
}