)]}'
{
  "commit": "78ac07b0d2b09b1ccb7a41a2e25f71d60b652920",
  "tree": "9dfa659eccd1865c6c5e5b71591689775a8fd7ca",
  "parents": [
    "a0e90acc657990511c83bc69965bfd3c63386d45"
  ],
  "author": {
    "name": "Andreas Mohr",
    "email": "andi@lisas.de",
    "time": "Sun Nov 21 12:09:32 2010 +0100"
  },
  "committer": {
    "name": "Takashi Iwai",
    "email": "tiwai@suse.de",
    "time": "Mon Nov 22 10:56:53 2010 +0100"
  },
  "message": "ALSA: azt3328: period bug fix (for PA), add missing ACK on stop timer\n\n. Fix PulseAudio \"ALSA driver bug\" issue\n  (if we have two alternated areas within a 64k DMA buffer, then max\n  period size should obviously be 32k only).\n  Back references:\n   http://pulseaudio.org/wiki/AlsaIssues\n   http://fedoraproject.org/wiki/Features/GlitchFreeAudio\n. In stop timer function, need to supply ACK in the timer control byte.\n. Minor log output correction\n\nWhen I did my first PA testing recently, the period size bug resulted\nin quite precisely observeable half-period-based playback distortion.\n\nPA-based operation is quite a bit more underrun-prone (despite its\nzero-copy optimizations etc.) than raw ALSA with this rather spartan\nsound hardware implementation on my puny Athlon.\n\nNote that even with this patch, azt3328 still doesn\u0027t work for both\ncases yet, PA tsched\u003d0 and tsched\n(on tsched\u003d0 it will playback tiny fragments of periods, leading to tiny\nstuttering sounds with some pauses in between, whereas with\ntimer-scheduled operation playback works fine - minus some quite increased\nunderrun trouble on PA vs. ALSA, that is).\n\nSigned-off-by: Andreas Mohr \u003candi@lisas.de\u003e\nSigned-off-by: Takashi Iwai \u003ctiwai@suse.de\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "4679ed83a43b8687402b7efca98ed47a0518ac98",
      "old_mode": 33188,
      "old_path": "sound/pci/azt3328.c",
      "new_id": "2f3cacbd5528da80cccca5791147d6f516dcdf82",
      "new_mode": 33188,
      "new_path": "sound/pci/azt3328.c"
    }
  ]
}