[mythtv-users] Heavy load troubles

[Brian Foddy]

On Wed, 24 Dec 2003, David Rees wrote:

> Brian Foddy wrote:
> 
> > Since Thanksgiving, I built up a new machine, a single 3Ghz xeon,
> > 1GB ram, the same scsi matched 10K disks (now 4) in raid0, Nvidia FX5600,
> > and the same 3 tuner cards.  By all reasonable comparisons, the new
> > machine is many times the machine as the old.  I intentionally
> > overbuilt to handle a pcHDTV card, which is currently installed
> > in a test machine until this get more stable.
> 
> Out of curiosity, what motherboard are you using, and what NVidia drivers?

The motherboard is an Asus PC-DL, it has 5 std PCI slots, agp, but no
pci-x type slots.  The scsi is a 2940u2w card in a pci slot.  This board
uses the P4 Canterwood chipset on Xeons, gives faster memory than
std Xeons (333 vs 266).  Generally, I've been very happy with it.

I'm using the 4496 Nvidia driver.

> 
> > Over the past month, I have seen almost all the following symptoms
> > starting with Myth .12+ cvs, .13 release, back to .12 release,
> > and now .13+ cvs from Dec 17.  I've upgraded several ivtv versions
> > and am now using the 1125a release recommended for .13.  The machine
> > is running Mandrake 9.2 (2.4.22mdk_smp) with current patches, and is 
> > dedicated to myth so there are no other jobs running.
> 
> I've had issues with the 1125a release hanging very similarly to what 
> you've described.  I've only got one PVR-250 in my machine.  Try the 
> CVS-LATEST tarball on the ivtv website that has been working very well 
> for me the last few days.

I've noticed they have remerged their cvs tree again, so I'll try that
tonight.

> 
> > 4.  Looking at "top" and xosview while running the 3 shows and playing
> > one of them, I notice a very strange cpu load behavior, its not
> > consistant, not even close.  Even using my old low-quality settings,
> > there is an aproximately 4 minute cycle where the cpu load slowly goes from
> > almost nothing up to 80-100%, followed by a sharp drop back to 5-10%
> > again.  About 4 minutes later the cycle repeats.  Changing recording quality
> > (even dramatically, 640x480 mpeg at 4500) doesn't change the behavior, 
> > only the cycle period and the cpu starting level.  Top shows the backend
> > and X server taking most of the cpu during the peak.
> 
> Do you have automatic transcoding turned on?  What is using up the CPU?

No, I think I have auto transcoding and commercial detection turned off.
And they don't run while against a still-recording file do they?
What exactly is using it?  I can't tell.  But by watching it more closely
last night I can say
A.  Its a backend thread.
B.  It definately cycles on some semi-regular period, usually 3-4 minutes.
C.  It only does it when the backend is recording, not sure if it does it
    when its recording but not playing.
D.  It will do it with even 1 PVR recording in progress.
E.  Both top and xosview agree, the cpu gets very busy then suddenly drops 
    to almost 0, even if there is a software encoding going on,
    stays low for a couple minutes, then gradually grows again.

> 
> > 3.  I normally run the backend as root, to activate the renice
> > logic of the card reading thread to -10.  
> > I've even tried changing the source to make that
> > reniced thread a real-time process (SCHED_RR).  No apparent help.
> 
> Shouldn't be necessary.

I agree, but I was willing to try anything that might help.
So far, I havent made a correlation between the bttv error I described
and the cycling cpu.  Its a case there are a lot of things going on,
its tough to get a true cause/effect, but I'll keep watching it.

Brian