)]}'
{
  "commit": "13e12d14e2dccc7995b8f15a5678a338ab4e6a8c",
  "tree": "d0fc2752fc71d30710a909516d5317b2c7bb8b96",
  "parents": [
    "95f4efb2d78661065aaf0be57f5bf00e4d2aea1d"
  ],
  "author": {
    "name": "Linus Torvalds",
    "email": "torvalds@linux-foundation.org",
    "time": "Wed Jun 08 15:18:19 2011 -0700"
  },
  "committer": {
    "name": "Linus Torvalds",
    "email": "torvalds@linux-foundation.org",
    "time": "Wed Jun 08 15:18:19 2011 -0700"
  },
  "message": "vfs: reorganize \u0027struct inode\u0027 layout a bit\n\nThis tries to make the \u0027struct inode\u0027 accesses denser in the data cache\nby moving a commonly accessed field (i_security) closer to other fields\nthat are accessed often.\n\nIt also makes \u0027i_state\u0027 just an \u0027unsigned int\u0027 rather than \u0027unsigned\nlong\u0027, since we only use a few bits of that field, and moves it next to\nthe existing \u0027i_flags\u0027 so that we potentially get better structure\nlayout (although depending on config options, i_flags may already have\npacked in the same word as i_lock, so this improves packing only for the\ncase of spinlock debugging)\n\nOut \u0027struct inode\u0027 is still way too big, and we should probably move\nsome other fields around too (the acl fields in particular) for better\ndata cache access density.  Other fields (like the inode hash) are\nlikely to be entirely irrelevant under most loads.\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "646a1836152a9f980b4f76f85ee51d36f9e914b2",
      "old_mode": 33188,
      "old_path": "include/linux/fs.h",
      "new_id": "1c777878f1ea5d375be6f04f3364ac2fb9d6c8ba",
      "new_mode": 33188,
      "new_path": "include/linux/fs.h"
    }
  ]
}