Can anyone recommend a place to find out about currently supported hardware? The Hardware Howto doesn't seem to have been updated since 1999. I'm particularly interested in the Promise ATA100 hard drive controller, but I'm asking the question much more generally. Paul
Is this it? http://cdb.suse.de/cgi-bin/scdb?ID=98909444049&HTML=ENGLISH%2Fcdb_listtemplates%2Fshow_a.htm&INDEX=97083697451 The last update says 06.10.2000. The general answer would be http://cdb.suse.de/cdb_english.html HTH Anders On Saturday 05 May 2001 22:47, Paul Abrahams wrote:
Can anyone recommend a place to find out about currently supported hardware? The Hardware Howto doesn't seem to have been updated since 1999. I'm particularly interested in the Promise ATA100 hard drive controller, but I'm asking the question much more generally.
Paul
* Paul Abrahams (abrahams@acm.org) [010505 13:49]: }=}Can anyone recommend a place to find out about currently }=}supported hardware? The Hardware Howto doesn't seem to have }=}been updated since 1999. I'm particularly interested in }=}the Promise ATA100 hard drive controller, but I'm asking the }=}question much more generally. }=} }=}Paul Yep it's supported. The ATA100 controller that has my IBM Deskstar 30G which is /home is on this chipset. I have an Asus A7V which has ATA66 and ATA100 controller chipsets. It's cool. I have 3 devices on the ATA66 controllers and 2 on the Promise ATA100 controller..very sweet. :) umm..what else do you need to know :) -- Ben Rosenberg mailto:ben@whack.org ----- If two men agree on everything, you can be sure that only one of them is doing the thinking.
Ben Rosenberg wrote:
Yep it's supported. The ATA100 controller that has my IBM Deskstar 30G which is /home is on this chipset. I have an Asus A7V which has ATA66 and ATA100 controller chipsets. It's cool. I have 3 devices on the ATA66 controllers and 2 on the Promise ATA100 controller..very sweet. :)
umm..what else do you need to know :)
Since the controller is a separate card, once I connect my hard drive to it, the motherboard no longer sees it directly. So what if anything do I need to do to configure Linux prior to installing the card so that Linux will start properly? Paul
What mobo are you using. I know that you can set the kernel to boot offboard controllers. You might also have to make some bios changes. -----Original Message----- From: pwa@chmls06.mediaone.net [mailto:pwa@chmls06.mediaone.net]On Behalf Of Paul Abrahams Sent: Saturday, May 05, 2001 2051 To: SuSE listserve Subject: Re: [SLE] Info re supported hardware Ben Rosenberg wrote:
Yep it's supported. The ATA100 controller that has my IBM Deskstar 30G which is /home is on this chipset. I have an Asus A7V which has ATA66 and ATA100 controller chipsets. It's cool. I have 3 devices on the ATA66 controllers and 2 on the Promise ATA100 controller..very sweet. :)
umm..what else do you need to know :)
Since the controller is a separate card, once I connect my hard drive to it, the motherboard no longer sees it directly. So what if anything do I need to do to configure Linux prior to installing the card so that Linux will start properly? Paul -- To unsubscribe send e-mail to suse-linux-e-unsubscribe@suse.com For additional commands send e-mail to suse-linux-e-help@suse.com Also check the FAQ at http://www.suse.com/support/faq and the archives at http://lists.suse.com
Curtis Rey wrote: -----Original Message----- From: pwa@chmls06.mediaone.net [mailto:pwa@chmls06.mediaone.net]On Behalf Of Paul Abrahams Sent: Saturday, May 05, 2001 2051 To: SuSE listserve Subject: Re: [SLE] Info re supported hardware Ben Rosenberg wrote:
Yep it's supported. The ATA100 controller that has my IBM Deskstar 30G which is /home is on this chipset. I have an Asus A7V which has ATA66 and ATA100 controller chipsets. It's cool. I have 3 devices on the ATA66 controllers and 2 on the Promise ATA100 controller..very sweet. :)
umm..what else do you need to know :)
Since the controller is a separate card, once I connect my hard drive to it, the motherboard no longer sees it directly. So what if anything do I need to do to configure Linux prior to installing the card so that Linux will start properly?
What mobo are you using. I know that you can set the kernel to boot offboard controllers. You might also have to make some bios changes.
I'm using a Tyan S2390 motherboard. Do I need to rejigger the kernel before I take my computer apart to install the ATA controller? Paul
* Paul Abrahams [Sat, 05 May 2001 22:28:50 -0400]:
I'm using a Tyan S2390 motherboard. Do I need to rejigger the kernel before I take my computer apart to install the ATA controller?
Is there any reason why you want to move the drive to the offboard controller? It does depend on the hard disk, but only very few exceed UDMA33 speed and *none* exceed UDMA66. So if your onboard controller supports UDMA33, chances are very high that you will see no noticeable speedup by moving the disk. Even if a disk supports UDMA100, that does not mean that it actually can make use of the higher transfer speed. UDMA100 currently is nothing more then a marketing vehicle as there is *no* disk that even comes near UDMA66 speed. If this is the only disk you have or if you move all disks to the offboard controller, there is no need to reconfigure the kernel. Change /etc/fstab so that hda becomes hde and add this to your /etc/lilo.conf in the global section: disk=/dev/hde bios=0x80 To tell lilo that after booting hde is the first disk in the system. This is because Linux consistently names disks in the order they're attached: master on 1st channel: hda slave " : hdb master on 2nd channel: hdc slave " " " : hdd and so on, no matter if there are disks attached to a channel or not. The BIOS in contrast scans for available disks and numbers them in the order it finds them, beginning with 0x80h. Lilo by default thinks that hda will be the first disk, i.e. will be accessible as BIOS drive 0x80h. And of course rerun lilo after changing lilo.conf. -- Penguins to save the dinosaurs -- Handelsblatt on Linux for S/390
Philipp Thomas wrote:
* Paul Abrahams [Sat, 05 May 2001 22:28:50 -0400]:
I'm using a Tyan S2390 motherboard. Do I need to rejigger the kernel before I take my computer apart to install the ATA controller?
Is there any reason why you want to move the drive to the offboard controller? It does depend on the hard disk, but only very few exceed UDMA33 speed and *none* exceed UDMA66. So if your onboard controller supports UDMA33, chances are very high that you will see no noticeable speedup by moving the disk.
Even if a disk supports UDMA100, that does not mean that it actually can make use of the higher transfer speed.
UDMA100 currently is nothing more then a marketing vehicle as there is *no* disk that even comes near UDMA66 speed.
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me? Paul
Paul Abrahams wrote:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me?
From my experience the differences between ATA and UDMA are a matter of semantics. I do beleive that the marketing departments of the various HD makers use this term ad-hoc (though I have read that there is a difference from a technical standpoint) For example mobo makers refer to their IDE channels as UDMA and the HD makers will use both terms (ATA and UDMA).
Curtis Rey wrote:
Paul Abrahams wrote:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me?
From my experience the differences between ATA and UDMA are a matter of semantics. I do beleive that the marketing departments of the various HD makers use this term ad-hoc (though I have read that there is a difference from a technical standpoint) For example mobo makers refer to their IDE channels as UDMA and the HD makers will use both terms (ATA and UDMA).
So am I likely to gain anything by hooking my ATA100 hard drive to an ATA100 controller rather than hooking it directly to an UDMA 33/66 mobo? Paul
On Sun, May 06, 2001 at 01:22:35PM -0400, abrahams@acm.org wrote:
Curtis Rey wrote:
Paul Abrahams wrote:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me? From my experience the differences between ATA and UDMA are a matter of semantics. I do beleive that the marketing departments of the various HD makers use this term ad-hoc (though I have read that there is a difference from a technical standpoint) For example mobo makers refer to their IDE channels as UDMA and the HD makers will use both terms (ATA and UDMA). So am I likely to gain anything by hooking my ATA100 hard drive to an ATA100 controller rather than hooking it directly to an UDMA 33/66 mobo?
AFAIK, ATA (AT Attachment) refers to the basic protocol by which the controller talks to the disk, whereas UDMA (Ultra-DMA) refers to the ability of the drive/controller combination to transfer data directly from the disk to the processor memory. I believe that the numbers (33/66/100) refers to the speed of the controller-drive bus. Therefore, if your drive is (for example) marked as ATA100 with UDMA, then it is UDMA100 compatible (i.e. the numbers can be placed after ATA or UDMA, and they mean the same thing). I believe that the correct way to say it is to put the speed after 'ATA', and put the UDMA separately, but, as usual, PC manufacturers seem to use the terms interchangeably. Anyway, as for whether it'll be faster, your PCI bus is limited to 33 MHz, 32 bit, and ATA is 16-bits wide, so an ATA66 card can (theoretically) saturate the PCI bus. There will be a slight performance advantage from ATA100, as the drive will be able to get data to the card faster, so will be able to ensure that the controller card never runs out of data to put on the PCI bus, but I don't think that the performance increase will be as much as you might hope for. Basically, latency for new accesses is determined more by the seek time of the drive (even the whizzy fast ones), and for large accesses, the data transfer rate will be limited by the PCI bus. Going from ATA33 to ATA66 will probably make a significant difference; from ATA66 to ATA100 won't. Sorry. Of course, I could be totally wrong... -- David Smith Tel: +44 (0)1454 462380 (direct) STMicroelectronics Fax: +44 (0)1454 617910 1000 Aztec West TINA (ST only): (065) 2380 Almondsbury Home: 01454 616963 BRISTOL Mobile: 07932 642724 BS32 4SQ Work Email: Dave.Smith@st.com Home Email: David.Smith@ds-electronics.co.uk
I believe Dave Smith is essentially correct about the issues. A person will see a reasonable and noticable increase in HDD response time more with drives that run at 7200rpms, combine this with a ATA/udma 66/100 drive and you will notice a difference. However, if you have a standard or 5400 rpm drive with ata/udma 66/100 then the increase in speed/performance will be minimal. The real increase comes from the seek-time and speed of the drive - 7200 rpms is the real ticket. Also the HDD buffers help because it will load/cache of data that is ready to go when called (e.g 2 or 4 MB HDD buffer/cache is better the 512KB - excuse my mixing of term "buffer" and "cache", can't remember the exact term for this feature - i believe it's a buffer but not sure). Cheers, Curtis Rey On Sunday 06 May 2001 13:14, Dave Smith wrote:
On Sun, May 06, 2001 at 01:22:35PM -0400, abrahams@acm.org wrote:
Curtis Rey wrote:
Paul Abrahams wrote:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me? From my experience the differences between ATA and UDMA are a matter of
semantics. I do beleive that the marketing departments of the various HD makers use this term ad-hoc (though I have read that there is a difference from a technical standpoint) For example mobo makers refer to their IDE channels as UDMA and the HD makers will use both terms (ATA and UDMA).
So am I likely to gain anything by hooking my ATA100 hard drive to an ATA100 controller rather than hooking it directly to an UDMA 33/66 mobo?
AFAIK, ATA (AT Attachment) refers to the basic protocol by which the controller talks to the disk, whereas UDMA (Ultra-DMA) refers to the ability of the drive/controller combination to transfer data directly from the disk to the processor memory. I believe that the numbers (33/66/100) refers to the speed of the controller-drive bus. Therefore, if your drive is (for example) marked as ATA100 with UDMA, then it is UDMA100 compatible (i.e. the numbers can be placed after ATA or UDMA, and they mean the same thing). I believe that the correct way to say it is to put the speed after 'ATA', and put the UDMA separately, but, as usual, PC manufacturers seem to use the terms interchangeably.
Anyway, as for whether it'll be faster, your PCI bus is limited to 33 MHz, 32 bit, and ATA is 16-bits wide, so an ATA66 card can (theoretically) saturate the PCI bus. There will be a slight performance advantage from ATA100, as the drive will be able to get data to the card faster, so will be able to ensure that the controller card never runs out of data to put on the PCI bus, but I don't think that the performance increase will be as much as you might hope for.
Basically, latency for new accesses is determined more by the seek time of the drive (even the whizzy fast ones), and for large accesses, the data transfer rate will be limited by the PCI bus. Going from ATA33 to ATA66 will probably make a significant difference; from ATA66 to ATA100 won't.
Sorry.
Of course, I could be totally wrong...
-- David Smith Tel: +44 (0)1454 462380 (direct) STMicroelectronics Fax: +44 (0)1454 617910 1000 Aztec West TINA (ST only): (065) 2380 Almondsbury Home: 01454 616963 BRISTOL Mobile: 07932 642724 BS32 4SQ Work Email: Dave.Smith@st.com Home Email: David.Smith@ds-electronics.co.uk
Curtis Rey wrote:
I believe Dave Smith is essentially correct about the issues. A person will see a reasonable and noticable increase in HDD response time more with drives that run at 7200rpms, combine this with a ATA/udma 66/100 drive and you will notice a difference. However, if you have a standard or 5400 rpm drive with ata/udma 66/100 then the increase in speed/performance will be minimal. The real increase comes from the seek-time and speed of the drive - 7200 rpms is the real ticket. Also the HDD buffers help because it will load/cache of data that is ready to go when called (e.g 2 or 4 MB HDD buffer/cache is better the 512KB - excuse my mixing of term "buffer" and "cache", can't remember the exact term for this feature - i believe it's a buffer but not sure).
My drive is a 7200RPM Maxtor ATA100 30GB model, so I assume from what you say that I'd realize the benefits of an ATA100 controller. When my system boots up, one of the messages I see is: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx Since the mobo claims 33/66, should I be inserting the override? How would that decision be affected by the presence of an ATA100 PCI controller? Paul
* Paul Abrahams (abrahams@acm.org) [010506 15:25]: }=}Curtis Rey wrote: }=} }=}> I believe Dave Smith is essentially correct about the issues. A person will }=}> see a reasonable and noticable increase in HDD response time more with drives }=}> that run at 7200rpms, combine this with a ATA/udma 66/100 drive and you will }=}> notice a difference. However, if you have a standard or 5400 rpm drive with }=}> ata/udma 66/100 then the increase in speed/performance will be minimal. The }=}> real increase comes from the seek-time and speed of the drive - 7200 rpms is }=}> the real ticket. Also the HDD buffers help because it will load/cache of }=}> data that is ready to go when called (e.g 2 or 4 MB HDD buffer/cache is }=}> better the 512KB - excuse my mixing of term "buffer" and "cache", can't }=}> remember the exact term for this feature - i believe it's a buffer but not }=}> sure). }=} }=}My drive is a 7200RPM Maxtor ATA100 30GB model, so I assume from what you say }=}that I'd realize the benefits of an ATA100 controller. }=} }=}When my system boots up, one of the messages I see is: }=} }=} Assuming 33MHz system bus speed for PIO modes; override with idebus=xx }=} }=}Since the mobo claims 33/66, should I be inserting the override? How would }=}that decision be affected by the presence of an ATA100 PCI controller? Nope, they all do this. It has something to do with IDE vs ISA or so I was told by Andre Hedrick..the guy who writes 99% of the IDE code in the kernel. Mine says it too...even though I have 2 drives on the ATA66 controller and 1 on the ATA100 Promise controller. It was the same message when I had my K6-III mb. -- Ben Rosenberg mailto:ben@whack.org ----- If two men agree on everything, you can be sure that only one of them is doing the thinking.
Ben Rosenberg wrote:
* Paul Abrahams (abrahams@acm.org) [010506 15:25]:
}=}When my system boots up, one of the messages I see is: }=} }=} Assuming 33MHz system bus speed for PIO modes; override with idebus=xx }=} }=}Since the mobo claims 33/66, should I be inserting the override? How would }=}that decision be affected by the presence of an ATA100 PCI controller?
Nope, they all do this.
They all do what? I'm confused.
It has something to do with IDE vs ISA or so I was told by Andre Hedrick..the guy who writes 99% of the IDE code in the kernel. Mine says it too...even though I have 2 drives on the ATA66 controller and 1 on the ATA100 Promise controller. It was the same message when I had my K6-III mb.
So did you insert the override, Ben? Paul
Paul, }=}They all do what? I'm confused. The kernel gives the 33mhz output for every mb is what I ment. }=}So did you insert the override, Ben? Yes, I use hdparm. It seems to work quite well. You can enable it in YaST2 if you have 7.1 and it seems to work pretty well. My IBM Deskstar that replaced the Maxtor that died works quite well..is very fast. -- Ben Rosenberg mailto:ben@whack.org ----- If two men agree on everything, you can be sure that only one of them is doing the thinking.
On Sun, 6 May 2001 15:48:16 -0700
Ben Rosenberg
Yes, I use hdparm. It seems to work quite well. You can enable it in YaST2 if you have 7.1 and it seems to work pretty well. My IBM Deskstar that replaced the Maxtor that died works quite well..is very fast.
Hi, I did some searching on this theme a while ago. Here are three posts from the kernel list I found useful. Geoff On Wed, 24 Jan 2001 dmeyer@dmeyer.net wrote:
The kernel always says:
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
at boot time. How would I know if it's safe to say idebus=66? The documentation is fairly vague on this.
When the manual for your mainboard states that clock settings for setting up your CPU creates a change in the normal idebus=33MHz of any other value, then you are probablely safe. Since all 32-bit PCI busses run at 33MHz, as last thought and reported, it should not be needed to change. If I recall the idebus=XX primary use was for VLB/ISA/EISA systems, but I have been wrong before. Chers, Andre Hedrick On Wed, May 24, 2000 at 12:33:37PM -0700, Dr. Kelsey Hudson wrote:
You didn't read that error message well enough. :)
Look, you can pass a kernel parameter on boot with the
idebus=33
option to tell it to go to UDMA/33 instead of UDMA/66. You didn't read that error message well enough. :) (in fact, maybe it's not your fault, but the massage is a little bit missleading...) idebus doesn't set UDMA speed, it sets the system bus speed that is used in ide timing calculations. From ide.c: /* * ide_system_bus_speed() returns what we think is the system VESA/PCI * bus speed (in MHz). This is used for calculating interface PIO timings. * The default is 40 for known PCI systems, 50 otherwise. * The "idebus=xx" parameter can be used to override this value. * The actual value to be used is computed/displayed the first time through. */ Jan
Camm Maguire
Greetings! The above chipset is reported as supporting ATA-66 under linux at www.linux-ide.org. But the specs at via's website indicate that this is a UltraDMA33 chipset. I may not be understanding my terms correctly, but can one set 'idebus=66' with this chipset under linux with the current ide patch?
No. That idebus parameter is to tell the kernel the ACTUAL PCI bus speed which is the same clock that the IDE interface uses, if you set it to 66 while your PCI is at 33, strange things may happen. I never checked what actually happens, but among the possible outcomes are: slow disk data loss no transfer at all, IDE resets Don't do it. Set idebus to your actual bus speed as per your mainboard jumpers (or switches or other settings). It should be 33, if you're overclocking, it might be 37 or 40 but this renders your entire hardware unstable. -- Matthias Andree _________________________________________________________ Do You Yahoo!? Get your free @yahoo.com address at http://mail.yahoo.com
* Paul Abrahams [Sun, 06 May 2001 10:20:38 -0400]:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me?
Yes, they're used interchangeably. BTW, what hard drive is it exactly? But just try to run 'hdparm -tT /dev/<your disk>' (and please post the output :). If you get Numbers below 66 MB/sec (and *no* currently available hard disk even comes near that), it won't get any faster when connected to a ATA100 controller. So if you've bought the controller for higher speed, you've wasted your money. But at least you've now got two more ATA channels, so you can run four ATA devices as master on their own channel. Running ATA devices as master on their own channel is always the best way to attach them as that will give you the most speed when talking to them in parallel (like installing from CD) and will avoid trouble. -- Penguins to save the dinosaurs -- Handelsblatt on Linux for S/390
Philipp Thomas wrote:
* Paul Abrahams [Sun, 06 May 2001 10:20:38 -0400]:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me?
Yes, they're used interchangeably. BTW, what hard drive is it exactly? But just try to run 'hdparm -tT /dev/<your disk>' (and please post the output :). If you get Numbers below 66 MB/sec (and *no* currently available hard disk even comes near that), it won't get any faster when connected to a ATA100 controller.
Well, there are two numbers, one above 66MB/sec and one below: root@suillus:/aux/home/pwa > hdparm -tT /dev/hda /dev/hda: Timing buffer-cache reads: 128 MB in 1.10 seconds =116.36 MB/sec Timing buffered disk reads: 64 MB in 2.03 seconds = 31.53 MB/sec I'll see what happens when I attach the controller.
So if you've bought the controller for higher speed, you've wasted your money. But at least you've now got two more ATA channels, so you can run four ATA devices as master on their own channel. Running ATA devices as master on their own channel is always the best way to attach them as that will give you the most speed when talking to them in parallel (like installing from CD) and will avoid trouble.
That's good to know. Paul
* Paul Abrahams [Sun, 06 May 2001 20:15:31 -0400]:
Well, there are two numbers, one above 66MB/sec and one below:
root@suillus:/aux/home/pwa > hdparm -tT /dev/hda
/dev/hda: Timing buffer-cache reads: 128 MB in 1.10 seconds =116.36 MB/sec Timing buffered disk reads: 64 MB in 2.03 seconds = 31.53 MB/sec
I'll see what happens when I attach the controller.
Yeah, I should've told you to use only -t, as that one tests the drive. The other tests the speed of the buffer cache. The second line is the interesting (BTW, repeat the timing a few times as that'll make the values more reliable) and it shows that the transfer rate is even below the ATA33 speed. I'll bet the numbers for buffered disk reads won't be significantly higher when you attach the drive to the ATA100 controller. BTW, for testing new hard disks I'd recommend ftp://ftp.heise.de/pub/ct/ctsi/h2bench.zip . This is a DOS program that'll overwrite the whole disk, so it can only be used for a fresh disk. But otherwise it's the best free program I've found in many years. c't is one of Germany's oldest (first issue was 12/83) computer magazines and IMO the best we have. A bit like the old Byte of the eighties. -- Penguins to save the dinosaurs -- Handelsblatt on Linux for S/390
On Sun, May 06, 2001 at 08:15:31PM -0400, abrahams@acm.org wrote:
Philipp Thomas wrote:
* Paul Abrahams [Sun, 06 May 2001 10:20:38 -0400]:
My hard drive claims to be ATA100; the motherboard claims UDMA 33/66 IDE. I'll admit that I know nothing of the relationship between ATA and UDMA, but I had assumed that the numbers were comparable, especially since most hard drives seem to be ATA66. Can you enlighten me?
Yes, they're used interchangeably. BTW, what hard drive is it exactly? But just try to run 'hdparm -tT /dev/<your disk>' (and please post the output :). If you get Numbers below 66 MB/sec (and *no* currently available hard disk even comes near that), it won't get any faster when connected to a ATA100 controller.
Well, there are two numbers, one above 66MB/sec and one below:
root@suillus:/aux/home/pwa > hdparm -tT /dev/hda
/dev/hda: Timing buffer-cache reads: 128 MB in 1.10 seconds =116.36 MB/sec
You won't improve much on this. Normal PCI is 32-bit, 33 MHz. As they say, 'you do the maths'. Unless things have moved on and we actually have 66 MHz PCI machines around? Does anyone know about this? Of course, the moment you plug in a 33 MHz card, the whole bus will slow down to 33 MHz anyway, so even if there are 66 MHz machines around, they'll probably be slowed down by one or more of the cards plugged in to them.
Timing buffered disk reads: 64 MB in 2.03 seconds = 31.53 MB/sec
Limited by the physical disk itself; again, you won't improve on this much. You'll get a slightly lower latency because the data can come down the 100 MHz ATA bus faster, but compared to the latency of the drive, the bus latency is peanuts.
I'll see what happens when I attach the controller.
So if you've bought the controller for higher speed, you've wasted your money. But at least you've now got two more ATA channels, so you can run four ATA devices as master on their own channel. Running ATA devices as master on their own channel is always the best way to attach them as that will give you the most speed when talking to them in parallel (like installing from CD) and will avoid trouble.
That's good to know.
Paul
-- To unsubscribe send e-mail to suse-linux-e-unsubscribe@suse.com For additional commands send e-mail to suse-linux-e-help@suse.com Also check the FAQ at http://www.suse.com/support/faq and the archives at http://lists.suse.com
-- David Smith Tel: +44 (0)1454 462380 (direct) STMicroelectronics Fax: +44 (0)1454 617910 1000 Aztec West TINA (ST only): (065) 2380 Almondsbury Home: 01454 616963 BRISTOL Mobile: 07932 642724 BS32 4SQ Work Email: Dave.Smith@st.com Home Email: David.Smith@ds-electronics.co.uk
participants (7)
-
Anders Johansson
-
Ben Rosenberg
-
Curtis Rey
-
Dave Smith
-
Paul Abrahams
-
Philipp Thomas
-
quintaq@yahoo.co.uk