Archived from groups: alt.comp.periphs.videocards.nvidia (More info?)
"J. Clarke" <jclarke@nospam.invalid> wrote in message
news:ciuj5411vem@news3.newsguy.com...
> Chip wrote:
>
> >
> > "J. Clarke" <jclarke@nospam.invalid> wrote in message
> > news:cithok02vi2@news1.newsguy.com...
> >> PRIVATE1964 wrote:
> >>
> >> >>
> >> >>And that's the only real benefit of SATA that I can see that is
> >> >>inherent in its being serial--that narrow cable is a lot easier to
> >> >>route.
> >> >
> >> > Here's a question for you that will keep me from having to search on
> >> > related to SATA. I plan on getting a new serial hard drive soon.
> >> >
> >> > I'm using a NF7-S with serial connections.
> >> > What is the maximum throughput for a hard drive connected to the
serial
> >> > connection.
> >> >
> >> > Is that connection spec'd for 150Mb/sec? I've read that the serial
> > drives
> >> > that are out now are not "true native" serial drives so there is no
way
> >> > they could ever hit 150Mb/sec.
> >> >
> >> > What can you tell me about this please.
> >>
> >> There is no drive in the world that can fill a 100 MB/sec pipe. WD
> > Raptors
> >> have a maximum sustained transfer rate of 72 MB/sec, 7K400s max at
62.1,
> >> Cheetah X15s max at 86. The limit is the bits per track and the
> > rotational
> >> speed, not the interface. So it doesn't matter whether the interface
can
> >> hit 150 or 133 or 100.
> >
> > ... apart from the burst speed which with drives with 16MB cache now can
> > be a significant factor, especially with video editing applications
(where
> > the
> > caching algorithms have a better chance because of the big files). 16MB
> > bursting at 150MB/s is not insigificant.
>
> I fail to see how it makes a difference with video editing, where you are
> trying to stream several gigabytes of data.
But you are not. You don't load "several gigabytes of data" into memory and
*then* start processing it. True, the data comes in large chunks - but not
gigabytes. Its processed piece by piece.
>
> How much real-world difference do you see between a drive with a 16 meg
> cache and an otherwise identical drive with a 2 meg cache?
"Some"?
>
> >> With PATA and two drives per channel, it's possible for both drives
> > together
> >> to fill a 150 MB/sec channel but SATA allows only one per channel so
> > that's
> >> not an issue.
> >>
> >> In any case, some use a bridge chip, others don't. IIRC Seagate is not
> >> using a bridge chip. I don't recall what WD is doing, but their
Raptors
> >> outperform any SATA drive from any other manufacturer, although the
> > Hitachi
> >> 7K250 and 7K400 come close, so whether they're using a bridge chip or
not
> >> clearly doesn't make any real-world difference.
> >
> > The Raptors have a bridge chip too. They are basically SCSI drives with
> > an adapter chip on them.
>
> I see. So you are claiming that they have a SCSI interface bridged to
SATA?
Yes. I am not sure to what extent the SCSI interface remains in tact. But
I know they are not "native" SATA drives, i.e. they are something else with
a bridge chip. And the "something else" was originally a 37Gb or 74GB SCSI
drive.
> Or are you just saying that being constructed to the same quality
standards
> as server-grade drives somehow makes them have a different interface?
Nope. See above.
Chip
"J. Clarke" <jclarke@nospam.invalid> wrote in message
news:ciuj5411vem@news3.newsguy.com...
> Chip wrote:
>
> >
> > "J. Clarke" <jclarke@nospam.invalid> wrote in message
> > news:cithok02vi2@news1.newsguy.com...
> >> PRIVATE1964 wrote:
> >>
> >> >>
> >> >>And that's the only real benefit of SATA that I can see that is
> >> >>inherent in its being serial--that narrow cable is a lot easier to
> >> >>route.
> >> >
> >> > Here's a question for you that will keep me from having to search on
> >> > related to SATA. I plan on getting a new serial hard drive soon.
> >> >
> >> > I'm using a NF7-S with serial connections.
> >> > What is the maximum throughput for a hard drive connected to the
serial
> >> > connection.
> >> >
> >> > Is that connection spec'd for 150Mb/sec? I've read that the serial
> > drives
> >> > that are out now are not "true native" serial drives so there is no
way
> >> > they could ever hit 150Mb/sec.
> >> >
> >> > What can you tell me about this please.
> >>
> >> There is no drive in the world that can fill a 100 MB/sec pipe. WD
> > Raptors
> >> have a maximum sustained transfer rate of 72 MB/sec, 7K400s max at
62.1,
> >> Cheetah X15s max at 86. The limit is the bits per track and the
> > rotational
> >> speed, not the interface. So it doesn't matter whether the interface
can
> >> hit 150 or 133 or 100.
> >
> > ... apart from the burst speed which with drives with 16MB cache now can
> > be a significant factor, especially with video editing applications
(where
> > the
> > caching algorithms have a better chance because of the big files). 16MB
> > bursting at 150MB/s is not insigificant.
>
> I fail to see how it makes a difference with video editing, where you are
> trying to stream several gigabytes of data.
But you are not. You don't load "several gigabytes of data" into memory and
*then* start processing it. True, the data comes in large chunks - but not
gigabytes. Its processed piece by piece.
>
> How much real-world difference do you see between a drive with a 16 meg
> cache and an otherwise identical drive with a 2 meg cache?
"Some"?
>
> >> With PATA and two drives per channel, it's possible for both drives
> > together
> >> to fill a 150 MB/sec channel but SATA allows only one per channel so
> > that's
> >> not an issue.
> >>
> >> In any case, some use a bridge chip, others don't. IIRC Seagate is not
> >> using a bridge chip. I don't recall what WD is doing, but their
Raptors
> >> outperform any SATA drive from any other manufacturer, although the
> > Hitachi
> >> 7K250 and 7K400 come close, so whether they're using a bridge chip or
not
> >> clearly doesn't make any real-world difference.
> >
> > The Raptors have a bridge chip too. They are basically SCSI drives with
> > an adapter chip on them.
>
> I see. So you are claiming that they have a SCSI interface bridged to
SATA?
Yes. I am not sure to what extent the SCSI interface remains in tact. But
I know they are not "native" SATA drives, i.e. they are something else with
a bridge chip. And the "something else" was originally a 37Gb or 74GB SCSI
drive.
> Or are you just saying that being constructed to the same quality
standards
> as server-grade drives somehow makes them have a different interface?
Nope. See above.
Chip