[mythtv-users] VDPAU playback stuttering when XvMC playback is just fine?

[Dave Johansen]

On Thu, Apr 30, 2009 at 8:41 AM, Richard Shaw <hobbes1069 at gmail.com> wrote:
> On Thu, Apr 30, 2009 at 10:24 AM, Dave Johansen <davejohansen at gmail.com> wrote:
>> On Thu, Apr 30, 2009 at 6:48 AM, Richard Shaw <hobbes1069 at gmail.com> wrote:
>>> On Thu, Apr 30, 2009 at 7:35 AM, Keith Richie <disturbed1976 at gmail.com> wrote:
>>>> On Thu, Apr 30, 2009 at 1:38 AM, Jean-Yves Avenard <jyavenard at gmail.com> wrote:
>>>>> Hi
>>>>>
>>>>>
>>>>> On 30/04/2009, at 3:13 PM, Dave Johansen <davejohansen at gmail.com> wrote:
>>>>>
>>>>>> On Wed, Apr 29, 2009 at 10:09 PM, Jean-Yves Avenard <jyavenard at gmail.com>
>>>>>> wrote:
>>>>>>>
>>>>>>> Hi
>>>>>>>
>>>>>>> On 30/04/2009, at 2:42 PM, Dave Johansen <davejohansen at gmail.com> wrote:
>>>>>>>
>>>>>>>>>
>>>>>>>>
>>>>>>>> I will give this a try and see if it helps with the stuttering.
>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>> From your logs it's obvious you have issues with your machine not related
>>>>>>> to
>>>>>>> vdpau.
>>>>>>>
>>>>>>> Your PC seems to be IO bound for some reasons. Fix that first.
>>>>>>>
>>>>>>> I'm guessing the stream is corruted or interrupted
>>>>>>
>>>>>> How can I tell if my machine is IO bound?
>>>>>> And if so how do I tell what the bottleneck is?
>>>>>>
>>>>>>
>>>>>
>>>>> Look at the log you posted earlier. There are tons of messages regarding  IO
>>>>> bound issues, just google those
>>>>>
>>>>> There's not one single reason for those. Could be a kernel issue, could be
>>>>> your hard drive (on the backend) is dodgy.
>>>>>
>>>>> Just google for those error
>>>>> messages._______________________________________________
>>>>> mythtv-users mailing list
>>>>> mythtv-users at mythtv.org
>>>>> http://mythtv.org/cgi-bin/mailman/listinfo/mythtv-users
>>>>>
>>>>
>>>> IOBOUND errors are usually one of 2 things. Non optimal kernel
>>>> configuration, or you've reached the limit of your system.
>>>>
>>>> Check to make sure you don't have any non essential services running
>>>> in the background. Some distro's have those darned indexing utilities
>>>> ;)
>>>>
>>>> Try changing the kernel scheduler, analyze your slab/slub performance
>>>> (slabtop), and take a look at iostat.
>>>>
>>>> Running iostat -x will give you an output showing the utilization of
>>>> your drives (last column). If it is at or near 100%, you've reached
>>>> your limit.
>>>
>>> I had the same symptom but may not be the same problem. I used top and
>>> found I had a lot of IO waits then installed iotop and noticed that
>>> the data transfer rates were WAY below what the drive should be
>>> capable of. That's when I started suspecting the HD was going bad. A
>>> short SMART test said the drive was good but when I did the long SMART
>>> test it found lots of errors. Got a warranty replacement and all is
>>> fine again.
>>>
>>> Richard
>>
>> How do I run a SMART test?
>>
>> Dave
>
> Here[1] is what looks like a good tutorial.
>
> Richard
>
> [1] http://www.captain.at/howto-linux-smartmontools-smartctl.php

I ran the short test on my computer and it turned up no errors in the
log, so I just kicked off the long test and I'll see what happens with
that.

Also, I apologize for going slightly off-topic here, but my laptop has
been acting a little funny lately and so I ran the SMART test on it as
well, and it turned up this in the error log:

=== START OF READ SMART DATA SECTION ===
SMART Error Log Version: 1
ATA Error Count: 9092 (device log contains only the most recent five errors)
        CR = Command Register [HEX]
        FR = Features Register [HEX]
        SC = Sector Count Register [HEX]
        SN = Sector Number Register [HEX]
        CL = Cylinder Low Register [HEX]
        CH = Cylinder High Register [HEX]
        DH = Device/Head Register [HEX]
        DC = Device Command Register [HEX]
        ER = Error register [HEX]
        ST = Status register [HEX]
Powered_Up_Time is measured from power on, and printed as
DDd+hh:mm:SS.sss where DD=days, hh=hours, mm=minutes,
SS=sec, and sss=millisec. It "wraps" after 49.710 days.

Error 9092 occurred at disk power-on lifetime: 908 hours (37 days + 20 hours)
  When the command that caused the error occurred, the device was
active or idle.

  After command completion occurred, registers were:
  ER ST SC SN CL CH DH
  -- -- -- -- -- -- --
  40 51 18 38 5d 33 e0  Error: UNC 24 sectors at LBA = 0x00335d38 = 3366200

  Commands leading to the command that caused the error were:
  CR FR SC SN CL CH DH DC   Powered_Up_Time  Command/Feature_Name
  -- -- -- -- -- -- -- --  ----------------  --------------------
  25 00 18 38 5d 33 e0 00      00:11:13.304  READ DMA EXT
  25 00 08 38 5d 33 e0 00      00:11:07.344  READ DMA EXT
  25 00 08 38 5d 33 e0 00      00:11:01.377  READ DMA EXT
  25 00 17 38 5d 33 e0 00      00:10:56.088  READ DMA EXT
  25 00 18 38 5d 33 e0 00      00:10:51.055  READ DMA EXT

Can anyone tell me what that means or point me to a better resource
for me to tell what's going on with the hard drive in my laptop and if
there's something I can do to resolve the issue? Or is this is just a
warning sign before it dies?

Thanks,
Dave