)]}'
{
  "commit": "40a49e1b22c6af5b015f1ca057d8b88fb159a531",
  "tree": "b59a8bb36c0e66de9787f776a28c6e478e4da627",
  "parents": [
    "fd190b57aa1a4d55d051a97d661fb3e3ef5e299e"
  ],
  "author": {
    "name": "Barret Rhoden",
    "email": "brho@cs.berkeley.edu",
    "time": "Mon Aug 14 16:37:53 2017 -0400"
  },
  "committer": {
    "name": "Barret Rhoden",
    "email": "brho@cs.berkeley.edu",
    "time": "Fri Aug 25 14:41:49 2017 -0400"
  },
  "message": "vmm: Make the greedy 2LS pinning and optimistic\n\nThe greedy flag (-g) now causes the VMM 2LS to do the following:\n- Ask for N + 1 vcores, with N \u003d\u003d nr_guest_cores.\n- Assume all of those vcores are allocated (optimistic)\n- Never yield those vcores\n- All task threads run on vcore 0, including timer alarms\n- All other vcores run their respective guest thread or controller thread.\n  E.g. vcore 1 run GPC 0.\n\nWith this, guest cores are never rescheduled - they stay on the same vcore,\nand thus the same underlying pcore, since we never yield.\n\nNote that this assumes all vcores are allocated and remain that way.  So\nany preemptions will screw it up.  Fixing that is a much harder TODO.\n\nSigned-off-by: Barret Rhoden \u003cbrho@cs.berkeley.edu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "de1a75b5e3dc53d45839949e2d8a49d8f64f9518",
      "old_mode": 33188,
      "old_path": "user/vmm/sched.c",
      "new_id": "288b8d769bab1466f2758d8dc5622e815e9d4d6f",
      "new_mode": 33188,
      "new_path": "user/vmm/sched.c"
    }
  ]
}