[mythtv-users] System Load/Performance Question
beww at beww.org
Mon Feb 20 01:29:58 UTC 2006
On Feb 19, 2006, at 6:16 PM, Michael T. Dean wrote:
> On 02/19/2006 05:20 PM, Brian Wood wrote:
>> I know the "can this system do <blank> has been done to death here,
>> but I need some comparisons.
>> The system is an amd64 3700, running Gentoo 2.6.15, MythTV
>> 0.18.1,1.5GB RAM
>> We are talking strictly about SDTV here.
>> GeForce-5700 video card w/256MB.
>> nVidia 7676 drivers, no XvMC, MythTV compiled with OpenGL support
>> Recordings are going onto 2-250GB SATA drives configured Linux kernel
>> software RAID0, JFS filesystem.
>> Ring Buffer is going onto a UDMA 133 250GB single drive, JFS
>> filesystem, no other drive on the IDE channel, The OS is on another
>> partition of this drive.
>> If I have a recording happening on tuner 1, and am watching LiveTV
>> from tuner 2, and have a commercial flagging job happening, I get
>> digital breakup on the live picture, and occasional breakup in the
>> Without a flagging job running there is no breakup on liveTV or the
>> CPU usage shows about 30-35%, no swapping is happening.
>> The priority of the flagging job in MythSetup is set to "low".
>> vmstat shows "WA" as "1", and very occasionally "2"
>> So, my questions:
>> Is this normal, am I simply asking too much of the system?
>> Is it a disk IO problem? (I don't think it's a CPU problem)
>> Would putting the ringbuffer on the RAID system help?
>> Would moving to a SCSI disk system help?
>> Should I just run flagging jobs at other times?
>> Is having the ringbuffer on the same drive as the OS a bad idea?
>> Obviously I'd like to figure out what the weak link is in this system
>> that is causing the breakup, any ideas appreciated.
> Doesn't really answer your question except to say that something's
> messed up, but I've recorded 4 different shows via 4 PVR-250's with
> "near-real-time" mythcommflag job running while watching a
> previously-recorded show on a combined frontend/backend running on an
> AMD Athlon XP 2000+ with 512MB RAM, an NVIDIA GF4MX440 without
> XvMC, and
> 3 UDMA 100 disks on 2 IDE buses in an LVM group (no RAID) using ext3
> without any problems.
One obvious difference is that you are using LVM and no RAID, while I
am using RAID and no LVM. The other obvious difference is 32 vs. 64
bit, but that shouldn't matter. In fact, in each case the differences
between our systems *should* work in my favor)
I've read that LVM will slow things down, and that makes sense.
According to hdparm I can read from my RAID array twice as fast as
from a single drive, which again makes sense (non-cached reads that is).
Nonetheless, since it is the most obvious difference between our
setups, I may just try it without RAID to see what happens. I've
already tried EXT3 instead of JFS and that makes no apparent difference.
Thanks for the input, you've confirmed that something is not right.
More information about the mythtv-users