Re: IDE hdd faster than sata? How come?
Also you have to consider that many of the first and some of the second
generation SATA drives are simply pata drives with bridge chips. The
bridge chips reduce max bandwidth. You are also not going to be able to
use things like commang queueing that SATA makes avalible with these
dirves.
most of the ATA133 drives were only as fast as the better ATA100 drives.
It seems like one of the main reasons for the speed increases is for
marketing purposes.
On Tue, 2005-10-25 at 11:23 +0300, koray wrote:
> Hi all,
>
> I think you look from the wrong side to the matter.SATA is a
> bus/protocol and the disk you use on this bus is a standart IDE disk.
> The advantage of this protocol is it can make "transfer rate" up to
> 150MB/s.But the main question is "can your sata disk read/write data up
> to 150MB/s?". Next level of SATA disks will perform better speeds and
> they will be able to produce I/O near 150MB/s.But now, RPM, platter
> densities etc. are nearly same.So it doesnt mean a SATA disk is faster
> than an PATA disk (both are IDE disks).Think about:
> you have an ISA based 56k modem and a PCI based 56K modem.Which one is
> faster? I hope i could tell what i meaned.
>
>
> Regards
> Koray Kusat
>
>
> Ron Johnson wrote:
> > On Mon, 2005-10-24 at 22:43 -0200, Bruno Buys wrote:
> >
> >>Ron Johnson wrote:
> >>
> >>
> >>>On Mon, 2005-10-24 at 18:25 -0200, Bruno Buys wrote:
> >>>
> >>>
> >>>
> >>>>How good is hdparm benchmark for sata? What am I missing here?
> >>>>
> >>>>
> >>>>frank:/home/bruno# hdparm -Tt /dev/sda
> >>>>
> >>>>/dev/sda:
> >>>>Timing cached reads: 2368 MB in 2.00 seconds = 1183.00 MB/sec
> >>>>Timing buffered disk reads: 170 MB in 3.01 seconds = 56.56 MB/sec
> >>>>
> >>>>
> >>>>frank:/home/bruno# hdparm -Tt /dev/hda
> >>>>
> >>>>/dev/hda:
> >>>>Timing cached reads: 2352 MB in 2.00 seconds = 1176.18 MB/sec
> >>>>Timing buffered disk reads: 180 MB in 3.03 seconds = 59.47 MB/sec
> >>>>
> >>>>
> >>>>IDE disk is SAMSUNG SP0802N, FwRev=TK200-04. 80GB. udma5.
> >>>>Sata is SAMSUNG SP0812C SATA 80GB.
> >>>>
> >>>>
> >>>>The only thing I found was in samsung website "The drive comes defaulted
> >>>>to udma100. To enable udma133 refer to www.samsung.com.br". So far,
> >>>>www.samsung.com.br gives me nothing.
> >>>>
> >>>>Does anybody have a clue?
> >>>>
> >>>>
> >>>
> >>>Was it a quiet system, with nothing else running at that moment?
> >>>
> >>>
> >>>
> >>
> >>I guess. There was no X and DE running. I run hdparm a few times, with
> >>similar results. But since it fails to talk to the sata disk for lots of
> >>other commands, i'm begining to suspect this benchmark feature...
> >>I also tested the jumpers, but they are irrelevant for the sata disk.
> >
> >
> > On my system, the SATA drive is sightly faster, but that's just it:
> > slightly. On your system, it's 4.9% slower. Maybe the drivers for
> > your SATA aren't up to snuff? Maybe that Samsung SATA drive has
> > ineffcient microcode...
> >
> > Abit KV-81
> > IDE - via82cxxx
> > SATA - sata_via
> > hda - WD 2500JB-00GVA0 - IDE 250GB
> > sda - Maxtor 7L300S0 - SATA
> >
> > # hdparm -Tt /dev/hda
> >
> > /dev/hda:
> > Timing cached reads: 2392 MB in 2.00 seconds = 1194.99 MB/sec
> > Timing buffered disk reads: 174 MB in 3.03 seconds = 57.43 MB/sec
> > root@haggis:~# hdparm -Tt /dev/hda
> >
> > # hdparm -Tt /dev/sda
> >
> > /dev/sda:
> > Timing cached reads: 2408 MB in 2.00 seconds = 1202.98 MB/sec
> > HDIO_DRIVE_CMD(null) (wait for flush complete) failed: Inappropriate
> > ioctl for device
> > Timing buffered disk reads: 184 MB in 3.01 seconds = 61.12 MB/sec
> > HDIO_DRIVE_CMD(null) (wait for flush complete) failed: Inappropriate
> > ioctl for device
> >
>
>
Reply to: