Re: [SLUG] HDD transfer rate

From: Levi Bard (levi@bard.sytes.net)
Date: Mon May 24 2004 - 11:16:27 EDT


Scott Piper wrote:

> Here are my results with -t -T
>
> /dev/hda:
> Timing buffer-cache reads: 1892 MB in 2.00 seconds = 945.67 MB/sec
> Timing buffered disk reads: 172 MB in 3.04 seconds = 56.66 MB/sec
>
>
> and then without options
> /dev/hda:
> multcount = 16 (on)
> IO_support = 1 (32-bit)
> unmaskirq = 1 (on)
> using_dma = 1 (on)
> keepsettings = 0 (off)
> readonly = 0 (off)
> readahead = 256 (on)
> geometry = 65535/16/63, sectors = 240121728, start = 0
>
> and finally with the -i option
>
> /dev/hda:
>
> Model=Maxtor 6Y120P0, FwRev=YAR41BW0, SerialNo=Y3JGZRCE
> Config={ Fixed }
> RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
> BuffType=DualPortCache, BuffSize=7936kB, MaxMultSect=16, MultSect=16
> CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=240121728
> IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
> PIO modes: pio0 pio1 pio2 pio3 pio4
> DMA modes: mdma0 mdma1 mdma2
> UDMA modes: udma0 udma1 udma2 udma3 udma4 udma5 *udma6
> AdvancedPM=yes: disabled (255) WriteCache=enabled
> Drive conforms to: (null):
>
> * signifies the current active mode
>
>
> I'm using kernel 2.6.4 and Debian unstable. It looks like I have
> quite a bit more readahead than you do. The drive has an 8mb buffer.

I'm also using debian/unstable, and I've got kernels 2.4.25 and 2.6.6 on it.
OK, here's mine with the readahead set to 255:
(kernel 2.4.25)
/dev/hda:
 Timing buffer-cache reads: 2768 MB in 2.00 seconds = 1384.00 MB/sec
 Timing buffered disk reads: 78 MB in 3.05 seconds = 25.57 MB/sec

 multcount = 16 (on)
 IO_support = 1 (32-bit)
 unmaskirq = 1 (on)
 using_dma = 1 (on)
 keepsettings = 0 (off)
 readonly = 0 (off)
 readahead = 255 (on)
 geometry = 14596/255/63, sectors = 234493056, start = 0

--

(kernel 2.6.6) /dev/hda: Timing buffer-cache reads: 2624 MB in 2.00 seconds = 1310.23 MB/sec Timing buffered disk reads: 72 MB in 3.07 seconds = 23.47 MB/sec

multcount = 16 (on) IO_support = 1 (32-bit) unmaskirq = 1 (on) using_dma = 1 (on) keepsettings = 0 (off) readonly = 0 (off) readahead = 256 (on) geometry = 16383/255/63, sectors = 234493056, start = 0 --

Here's the drive specs: Model=SAMSUNG SP1213N, FwRev=TL100-24, SerialNo=0642J1FWB18403 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs } RawCHS=16383/16/63, TrkSize=34902, SectSize=554, ECCbytes=4 BuffType=DualPortCache, BuffSize=8192kB, MaxMultSect=16, MultSect=16 CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=234493056 IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120} PIO modes: pio0 pio1 pio2 pio3 pio4 DMA modes: mdma0 mdma1 mdma2 UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 AdvancedPM=no WriteCache=enabled Drive conforms to: (null):

So, by increasing the read-ahead, I can get quite a bit of improvement in the buffer-cache read, but none in the disk read. I wonder if the difference between mine and yours (scott's) is due to the udma6/udma5 mode difference?

----------------------------------------------------------------------- This list is provided as an unmoderated internet service by Networked Knowledge Systems (NKS). Views and opinions expressed in messages posted are those of the author and do not necessarily reflect the official policy or position of NKS or any of its employees.



This archive was generated by hypermail 2.1.3 : Fri Aug 01 2014 - 18:54:57 EDT