)]}'
{
  "commit": "3f2aa307c4d26b4ed6509d0a79e8254c9e07e921",
  "tree": "97514a19722ffe1f7a973868bf670177b671d3a5",
  "parents": [
    "61cbe54d9479ad98283b2dda686deae4c34b2d59"
  ],
  "author": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Thu Sep 10 20:34:48 2009 +0200"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Thu Sep 10 20:34:48 2009 +0200"
  },
  "message": "sched: Disable NEW_FAIR_SLEEPERS for now\n\nNikos Chantziaras and Jens Axboe reported that turning off\nNEW_FAIR_SLEEPERS improves desktop interactivity visibly.\n\nNikos described his experiences the following way:\n\n  \" With this setting, I can do \"nice -n 19 make -j20\" and\n    still have a very smooth desktop and watch a movie at\n    the same time.  Various other annoyances (like the\n    \"logout/shutdown/restart\" dialog of KDE not appearing\n    at all until the background fade-out effect has finished)\n    are also gone.  So this seems to be the single most\n    important setting that vastly improves desktop behavior,\n    at least here. \"\n\nJens described it the following way, referring to a 10-seconds\nxmodmap scheduling delay he was trying to debug:\n\n  \" Then I tried switching NO_NEW_FAIR_SLEEPERS on, and then\n    I get:\n\n    Performance counter stats for \u0027xmodmap .xmodmap-carl\u0027:\n\n         9.009137  task-clock-msecs         #      0.447 CPUs\n               18  context-switches         #      0.002 M/sec\n                1  CPU-migrations           #      0.000 M/sec\n              315  page-faults              #      0.035 M/sec\n\n    0.020167093  seconds time elapsed\n\n    Woot! \"\n\nSo disable it for now. In perf trace output i can see weird\ndelta timestamps:\n\n  cc1-9943  [001]  2802.059479616: sched_stat_wait: task: as:9944 wait: 2801938766276 [ns]\n\nThat nsec field is not supposed to be that large. More digging\nis needed - but lets turn it off while the real bug is found.\n\nReported-by: Nikos Chantziaras \u003crealnc@arcor.de\u003e\nTested-by: Nikos Chantziaras \u003crealnc@arcor.de\u003e\nReported-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nTested-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nLKML-Reference: \u003c4AA93D34.8040500@arcor.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "4569bfa7df9b9fee6f057e22aca18299d3c45f3b",
      "old_mode": 33188,
      "old_path": "kernel/sched_features.h",
      "new_id": "e2dc63a5815d5eb90975ce53efc283d5d5a70746",
      "new_mode": 33188,
      "new_path": "kernel/sched_features.h"
    }
  ]
}