)]}'
{
  "commit": "aa373cf550994623efb5d49a4d8775bafd10bbc1",
  "tree": "64b14d1f5491f436a8b3ea5c32edecde5c255285",
  "parents": [
    "71927e84e0aebfbe5a91565c3b207af25a4e9162"
  ],
  "author": {
    "name": "Jan Kara",
    "email": "jack@suse.cz",
    "time": "Thu Jan 13 15:45:47 2011 -0800"
  },
  "committer": {
    "name": "Linus Torvalds",
    "email": "torvalds@linux-foundation.org",
    "time": "Thu Jan 13 17:32:32 2011 -0800"
  },
  "message": "writeback: stop background/kupdate works from livelocking other works\n\nBackground writeback is easily livelockable in a loop in wb_writeback() by\na process continuously re-dirtying pages (or continuously appending to a\nfile).  This is in fact intended as the target of background writeback is\nto write dirty pages it can find as long as we are over\ndirty_background_threshold.\n\nBut the above behavior gets inconvenient at times because no other work\nqueued in the flusher thread\u0027s queue gets processed.  In particular, since\ne.g.  sync(1) relies on flusher thread to do all the IO for it, sync(1)\ncan hang forever waiting for flusher thread to do the work.\n\nGenerally, when a flusher thread has some work queued, someone submitted\nthe work to achieve a goal more specific than what background writeback\ndoes.  Moreover by working on the specific work, we also reduce amount of\ndirty pages which is exactly the target of background writeout.  So it\nmakes sense to give specific work a priority over a generic page cleaning.\n\nThus we interrupt background writeback if there is some other work to do.\nWe return to the background writeback after completing all the queued\nwork.\n\nThis may delay the writeback of expired inodes for a while, however the\nexpired inodes will eventually be flushed to disk as long as the other\nworks won\u0027t livelock.\n\n[fengguang.wu@intel.com: update comment]\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Dave Chinner \u003cdavid@fromorbit.com\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nCc: Jan Engelhardt \u003cjengelh@medozas.de\u003e\nCc: Jens Axboe \u003caxboe@kernel.dk\u003e\n\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "482de0a92ca771319742eeb119b166816b79b485",
      "old_mode": 33188,
      "old_path": "fs/fs-writeback.c",
      "new_id": "9e72d04e706e06dfd0885432cec6dc20e15374c8",
      "new_mode": 33188,
      "new_path": "fs/fs-writeback.c"
    }
  ]
}