[mythtv-users] RE: mythfrontend setup for around $300 ??

[Eni Gma]

Robert Kulagowski wrote:

> 
>-----BEGIN PGP SIGNED MESSAGE-----
>Hash: SHA1
>
>  
>
>>The nice thing about this setup is that you aren't limited to the 1
>>IDE  connection that the Pundit is limited to.  If you added a
>>DVD-ROM to the  pundit, all of a sudden, your HD can only be
>>accessed at ATA-33 speeds.  
>>    
>>
>
>Umm, I _have_ a Pundit, and I'm certainly not seeing my hard drive
>being accessed at ATA-33 speeds, and it's on the same cable as a DVD:
>
>[root at livingroom home]# hdparm -tT /dev/hdb
>
>/dev/hdb:
> Timing buffer-cache reads:   128 MB in  0.33 seconds =387.88 MB/sec
> Timing buffered disk reads:  64 MB in  1.36 seconds = 47.06 MB/sec
>
>Jun  8 14:48:25 livingroom kernel: hdb: 234441648 sectors (120034 MB)
>w/8192KiB Cache, CHS=14593/255/63, UDMA(100)
>Jun  8 14:48:25 livingroom kernel: hda: ATAPI 48X DVD-ROM drive,
>512kB Cache, UDMA(33)
>  
>

Those are some very odd numbers (at least the buffer-cache reads).  The 
maximum bandwidth for standard PCI is 132 MB/s (32 
bit*33mhz/8/1000/1000).  AFAIK, the Pundit does not have PCI-66 or 
PCI-X.  I would suspect that you are hitting memory cache rather than 
the actual disk cache, or hdparm has a bug.  At any rate, it certainly 
does look like you can add a secondary optical drive without slowing 
your primary drive down.  

Hmm, after reading the hdparm man page it does indeed look like the test 
is to the Linux buffer cache, and not the disk cache as I presumed. 
 That number looks about right for DDR memory.  Just for kicks, here are 
my numbers using regular SDRAM on a 1ghz Athlon with a 4 and 8 disk 
RAID-5, respectively:

[root at gabbo2 v-9.0]# hdparm -tT /dev/md[0-1]

/dev/md0:
 Timing buffer-cache reads:   128 MB in  0.61 seconds =209.84 MB/sec
 Timing buffered disk reads:  64 MB in  1.06 seconds = 60.38 MB/sec

/dev/md1:
 Timing buffer-cache reads:   128 MB in  0.62 seconds =206.45 MB/sec
 Timing buffered disk reads:  64 MB in  0.96 seconds = 66.67 MB/sec


It just seems to me the 'T' test is misleading, since it does not 
actually touch the IDE bus.  You would still get the same numbers for it 
if your drive was running at UDMA-33.


>  
>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: /pipermail/attachments/20030610/b6f0ce8a/attachment.htm