)]}'
{
  "log": [
    {
      "commit": "b0d40c92adafde7c2d81203ce7c1c69275f41140",
      "tree": "f75a19dcd1a37aff23dc43323b58f014b1297c6b",
      "parents": [
        "12ad3ab66103e6582ca69c0c9de18b13487eaaef"
      ],
      "author": {
        "name": "Dave Chinner",
        "email": "dchinner@redhat.com",
        "time": "Fri Jul 08 14:14:42 2011 +1000"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Wed Jul 20 20:47:10 2011 -0400"
      },
      "message": "superblock: introduce per-sb cache shrinker infrastructure\n\nWith context based shrinkers, we can implement a per-superblock\nshrinker that shrinks the caches attached to the superblock. We\ncurrently have global shrinkers for the inode and dentry caches that\nsplit up into per-superblock operations via a coarse proportioning\nmethod that does not batch very well.  The global shrinkers also\nhave a dependency - dentries pin inodes - so we have to be very\ncareful about how we register the global shrinkers so that the\nimplicit call order is always correct.\n\nWith a per-sb shrinker callout, we can encode this dependency\ndirectly into the per-sb shrinker, hence avoiding the need for\nstrictly ordering shrinker registrations. We also have no need for\nany proportioning code for the shrinker subsystem already provides\nthis functionality across all shrinkers. Allowing the shrinker to\noperate on a single superblock at a time means that we do less\nsuperblock list traversals and locking and reclaim should batch more\neffectively. This should result in less CPU overhead for reclaim and\npotentially faster reclaim of items from each filesystem.\n\nSigned-off-by: Dave Chinner \u003cdchinner@redhat.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    }
  ]
}