)]}'
{
  "commit": "a08b159fc243dbfe415250466d24cfc5010deee5",
  "tree": "39bb59aaf183021e6d9b02ed26dc8a4930d00f0b",
  "parents": [
    "6751b71ea2c7ab8c0d65f01973a3fc8ea16992f4"
  ],
  "author": {
    "name": "Paul Mackerras",
    "email": "paulus@samba.org",
    "time": "Mon May 11 15:46:10 2009 +1000"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Mon May 11 12:10:53 2009 +0200"
  },
  "message": "perf_counter: don\u0027t count scheduler ticks as context switches\n\nThe context-switch software counter gives inflated values at present\nbecause each scheduler tick and each process-wide counter\nenable/disable prctl gets counted as a context switch.\n\nThis happens because perf_counter_task_tick, perf_counter_task_disable\nand perf_counter_task_enable all call perf_counter_task_sched_out,\nwhich calls perf_swcounter_event to record a context switch event.\n\nThis fixes it by introducing a variant of perf_counter_task_sched_out\nwith two underscores in front for internal use within the perf_counter\ncode, and makes perf_counter_task_{tick,disable,enable} call it.  This\nvariant doesn\u0027t record a context switch event, and takes a struct\nperf_counter_context *.  This adds the new variant rather than\nchanging the behaviour or interface of perf_counter_task_sched_out\nbecause that is called from other code.\n\n[ Impact: fix inflated context-switch event counts ]\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Corey Ashford \u003ccjashfor@linux.vnet.ibm.com\u003e\nLKML-Reference: \u003c18951.48034.485580.498953@drongo.ozlabs.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "a5bdc93ac4775d301aed2271d954207398f1983d",
      "old_mode": 33188,
      "old_path": "kernel/perf_counter.c",
      "new_id": "7373b96bc36cec9caa6b23a2cb48bf001f304db9",
      "new_mode": 33188,
      "new_path": "kernel/perf_counter.c"
    }
  ]
}