)]}'
{
  "log": [
    {
      "commit": "a664b2d8555c659127bf8fe049a58449d394a707",
      "tree": "14771f4ab93a9dda98174f21e0361a77e2aebfa6",
      "parents": [
        "1ddd6db43a08cba56c7ee920800980862086f1c3"
      ],
      "author": {
        "name": "Andrea Arcangeli",
        "email": "aarcange@redhat.com",
        "time": "Thu Jan 13 15:47:17 2011 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 13 17:32:47 2011 -0800"
      },
      "message": "thp: madvise(MADV_NOHUGEPAGE)\n\nAdd madvise MADV_NOHUGEPAGE to mark regions that are not important to be\nhugepage backed.  Return -EINVAL if the vma is not of an anonymous type,\nor the feature isn\u0027t built into the kernel.  Never silently return\nsuccess.\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "ba76149f47d8c939efa0acc07a191237af900471",
      "tree": "162990f51dd24984f114cba14fc7169a3b54f0f1",
      "parents": [
        "79134171df238171daa4c024a42b77b401ccb00b"
      ],
      "author": {
        "name": "Andrea Arcangeli",
        "email": "aarcange@redhat.com",
        "time": "Thu Jan 13 15:46:58 2011 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 13 17:32:43 2011 -0800"
      },
      "message": "thp: khugepaged\n\nAdd khugepaged to relocate fragmented pages into hugepages if new\nhugepages become available.  (this is indipendent of the defrag logic that\nwill have to make new hugepages available)\n\nThe fundamental reason why khugepaged is unavoidable, is that some memory\ncan be fragmented and not everything can be relocated.  So when a virtual\nmachine quits and releases gigabytes of hugepages, we want to use those\nfreely available hugepages to create huge-pmd in the other virtual\nmachines that may be running on fragmented memory, to maximize the CPU\nefficiency at all times.  The scan is slow, it takes nearly zero cpu time,\nexcept when it copies data (in which case it means we definitely want to\npay for that cpu time) so it seems a good tradeoff.\n\nIn addition to the hugepages being released by other process releasing\nmemory, we have the strong suspicion that the performance impact of\npotentially defragmenting hugepages during or before each page fault could\nlead to more performance inconsistency than allocating small pages at\nfirst and having them collapsed into large pages later...  if they prove\nthemselfs to be long lived mappings (khugepaged scan is slow so short\nlived mappings have low probability to run into khugepaged if compared to\nlong lived mappings).\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    }
  ]
}