UniPod speed tested

IDE and ethernet with a need for speed

Sequential byte access

There are various approaches used by software when saving and loading your information to and from storage media. The information can be saved as a stream of write operations, by saving one byte (or character) after another in a sequential manner. It's not terribly efficient, but it can be used when saving information that is being constantly updated or is generated 'on the fly'. The sequential byte access test investigates the interface's performance in this area and reports how much time each process took in centiseconds - where one centisecond is a hundredth of a second.

Block access

Another method of saving and loading information is to transfer the data in a block. This is more efficient, but requires the application to have all the information together beforehand. This is the preferred method when saving and loading large files like images and documents, so it gives a good indication of loading and saving speeds in the real world. The block access test investigates the interface's performance in this area and reports the transfer speed in kilobytes per second.

Links

Previous: Iyonix mobo spotted in the wild
Next: RISC OS Adjust Review

Discussion

What happens if you copy from the network to harddisc (on the podule) or vice versa? Does it go much slower, twice passing the podulebus, or doesn't it need to pass this bottleneck and it therefore faster? Or doesn't that really matter? jjvdgeer on 3/6/04 7:09AM [ Reply | Permalink | Report ]

I don't know who did the tests but it seems from the results that the Blitz was tested without DMA. With the drive described and DMA enabled block transfer speeds should be at least 50% higher. apdl on 3/6/04 7:40AM [ Reply | Permalink | Report ]

Yes, they probably should have mentioned that in the report, though they did say the computer was a "A RISC OS 4.39, StrongARM powered Kinetic RiscPC" The key word being 'Kinetic'... Rimmer on 3/6/04 8:30AM [ Reply | Permalink | Report ]

jjvdgeer: I've not tested it, but everything will have to go across the podule bus twice. All the network interface sees are just packets - doesn't know who they're for, what order they're in and can only buffer a few. All the working out where each packet goes is for the host to do. caliston2 on 3/6/04 9:16AM [ Reply | Permalink | Report ]

"The Unipod does offer IDE access that outperforms the internal IDE interface"... :cooldude: I'm told that the PC hard disks tend to wear out faster because it's system works the HD harder to retrieve both files/programmes and system instruction all from the HD. :rolleyes: As I understand, RISC OS is more 'Efficient' with it's instruction in Flash Rom, hence the HD doesn't need to work harder giving RISC OS HDs (generally speaking) a longer life span. Therefore, in the article statement I mentioned first, would a high performance IDE in this Unipod work the RISC OS HD faster, thus giving it a shorter life span? :blush: Finally, does a much larger memory (like the 192Mb RAM, 60GB HD in the article) installed on a computer, increase the :sparky: speed performance of the machine? Forgive my comments for I am not technically computer minded, :bowdown: just putting together info as I try to figure all this out! :wink: Cheers, Steve. Sawadee on 3/6/04 9:17AM [ Reply | Permalink | Report ]

David - I agree with your point; DMA is disabled with the Kinetic upgrade and the cards may perform differently on a DMA-enabled machine. I can see a case for repeating the tests on a DMA-enabled machine. I can aim to repeat this test when I've got the card and post the tests with DMA enabled; unfortunately my SA card is back in Notts and will take me a fortnight to do the test (unless someone wishes to post me instructions on how to temporarily turn a Kinetic into a normal SA card). Steve. Hard drive stress is a very difficult subject. It's not the throughput of data which would shorten drives significantly; drive temperature and number of power cycles are the major factors. Having said that, DO NOT use drives for much beyond their warranty period - the consequences of having a dead drive are catastrophic. Hope all that helps, Drew md0u80c9 on 3/6/04 11:06AM [ Reply | Permalink | Report ]

Might also be worth running the tests with an Arm710 card in the machine. I find that I can get much higher block transfers through the Blitz interface (in a DMA slot) than I can with a StrongArm card. Cheers! The Doctor on 3/6/04 3:14PM [ Reply | Permalink | Report ]

Whilst I agree that you probably would see a difference, my whole purpose was to demonstrate the effects on current hardware, and I wouldn't consider an Arm 700 RPC as 'current'. Also whilst this is attempting to look at 'real-world' values, it's not a 100% accurate performance indicator for all machines in all circumstances. Whilst I think the Unipod is excellent value for money, a second-hand SA card would add more to your machine for that money, so my advice to ARM 700 RPC users is simple: use the money on a SA first, and if you get the money again, come back for the Unipod if it suits your needs. If they desperately need, eg, USB or an NIC, then the choice of a Unipod would be obvious as it definitely offers the best value-for-money, but in those cases speed comparisons would be a moot point. md0u80c9 on 3/6/04 5:30PM [ Reply | Permalink | Report ]

My experience with UniPod shows the IDE is slower with DMA on and the ethernet only gets about half the rate quoted above as it keeps stalling. Clearly YMMV. STD are aware of the issues, however. Here's hoping for the new firmware soon! Even ignoring the ethernet, the USB and IDE on one podule provide a good space saving and nice new features. If STD ever release the developer docs for the addon features and parallel port we may also see it really become _the_ podule to have (after ViewFinder ) imj on 3/6/04 7:06PM [ Reply | Permalink | Report ]

I was looking at the picture (no plate? how on earth do you screw this podule in? ) and saw the internal USB header. Read the text. Are you limited to 2 USB ports internal *and* external? Does !MassFS now support USB mass storage devices properly? i.e. could you fit a CDRW + card reader or a floppy + card reader to a Risc PC now? I am curious epistaxsis@work on 3/6/04 8:13PM [ Reply | Permalink | Report ]

There is a plate - it's removed upon shipping, and you screw it on when you take it out the box. Epistaxis - you are limited to two interfaces TOTAL, ie. two external, or one internal and one external. I have not played with this, and you will have to wait for STD to provide information re this. IMJ - I didn't find any experience with it stalling, despite regular use, so hopefully this is a firmware issue. md0u80c9 on 3/6/04 8:23PM [ Reply | Permalink | Report ]

Epistaxis: Yep, MassFS works very nicely. Connect the device and up pop drive icons on the iconbar. Super. Been using it with a flash drive and smartmedia reader from my camera. md0u80c9: I've had beta firmware since Wakefield, no improvement :unhappy: :crybaby:, but we live in hope. imj on 3/6/04 10:40PM [ Reply | Permalink | Report ]

md0u80c9: thanks for the clarification epistaxsis@work on 3/6/04 10:44PM [ Reply | Permalink | Report ]

Drew. It was pointed out to me that PC Hard Disks (tend) to wear faster, I think they mean one factor is that the PC HD is used by the machine a more than a RISC OS machine does. (I personally wouldn't know - but others say to me these things). :unhappy: Other major factors as you pointed out - such as temperature, an obvious point I was not aware of as to the importance of cooler running RISC OS machine (not forgetting QUIETER)! Also from what you are suggesting, it really pays to renew your Hard Drive before it ages or is due to 'run to the ground' (die!). Thanks! :cooldude: Steve Sawadee on 4/6/04 8:28AM [ Reply | Permalink | Report ]

Whilst it's logical to suggest the more you use it, the quicker it wears out, AIUI this isn't the case with normal running of desktop drives. Power cycling is the major issue; the more you power cycle the drive, the quicker it dies. From the drive, I fished out the number of power cycles my drive has done in just a few months - it was astonishing. FWIW, I also learnt that in my RISC OS box on the top slice, my drive runs at a toasty 47 degrees. I actually cut it down (from 51 degrees) with Unipod. That's not due to anything clever - merely the fact that with it I got a rounded IDE cable in, and removed a USB card, NIC and IDE card and replaced it with a single board, so more air throughput was possible. Those figures are presumed to be correct, but the software used is still in development. However, as I've said, the take-home message is NEVER use old drives for anything other than non-essential storage (NOT BACKUPS, because when you come to reach for your backup...) or doorstops - otherwise you ask for what you get. md0u80c9 on 4/6/04 11:39AM [ Reply | Permalink | Report ]

I have got my backups networked on two other RISC OS computers. But I'm noting the importance of keeping these machine cool. With 11 RISC OS machines in two adequately sized small rooms and up to 20 children working on the at times, the doors and the windows are open to vetilate air circulation and this cooling may help the Hard Disk life? Not to forget, I must keep the school's water heater tap valves down to a minimum during winter as well. :blush: The (PC)computer room in the next building however, gets so hot in the warmer summer days I sweat easily (many others complain about the computer sauna room). Almost 3 years old, a number of the new PC's have had HD and other major problems already. Our school needs airconditioning for the main computer room, what's an ideal temperature for about 30 computers in an old design classroom just big enough for them? :cooldude: Cheers, Steve. Sawadee on 4/6/04 12:17PM [ Reply | Permalink | Report ]

Sawadee: Can a RISC OS machine with a UNIPod boot from a USB-stick? Yes, than you can stop using Hard Disks. > what's an ideal temperature for about 30 computers in an old design classroom just big enough for them? Too cold for the students : 10-15 'C (the lower the beter) egel on 4/6/04 1:54PM [ Reply | Permalink | Report ]

Like beer, they work better cold. But obviously not sub-zero, as like beer, they can freeze . md0u80c9 on 4/6/04 8:58PM [ Reply | Permalink | Report ]

BEER!! Now we're talking English (not tech jargon). I'm an Aussie, chilled beer's the one and I clearly understand the point about sub-zero and computers now. But not a problem understanding those tips in terms of beer, we Aussies chill and care for our beer with utmost pride and care. :acorn: Like one of the Acorn !Sibelius7 "Tips of the Day", it says 'don't water your computer'. So I don't think I'll chill my computer (like beer) on ICE!! :cooldude: 'Reply to egel:' Obviously as you suggest, the cooler the better - with ideal being maybe 10 - 15C ? In the summer months here in New Zealand, a computer room that has virtually no cooling apart from a couple of ceiling fans and not to forget the massive body heat created here, your ideally suggested temperature is sadly about half what we experience at times!! I can see our ICT computer teacher submitting a :bowdown: BIG ask for airconditioning after the huge millions spent on our school the past four years. But then again I would image the airconditioning may not outweigh the costs over years of repairs to overheated computers (and overheated children and teachers!). Some of the points in the article were interesting about allowing (if possible) airflow around the components in the computer. Now would this argue a point against the thought of buying a compact slimline computer case?? :rolleyes: Cheers, Steve Sawadee on 5/6/04 3:48AM [ Reply | Permalink | Report ]

sawadee: If you're worried about heat you could get some teeny weeny fans mounted in the ventilation slots in front of the Hard Disk - set to blow over the drive. The RiscPC never did pressurise too well - especially once you went beyond a couple of slices... epistaxsis@work on 5/6/04 2:41PM [ Reply | Permalink | Report ]

Re: Air Condtioning Sometimes, "rapid air extraction" is all that's needed, (i.e. rather than "air conditioning", which may be cheeper and more environmentally friendly. i.e. Simply suck the hot air out rather than try to cool it down. martin on 6/6/04 12:04AM [ Reply | Permalink | Report ]

jlavallin on 6/6/04 1:46AM [ Reply | Permalink | Report ]

If an airflow is sufficient, then I have just about that in the summer months when I open windows and doors, there is a decent draft flow through my clasroom area. But as for the computer room, maybe a few of it's useless large lower windows replaced with decent ones that open enough for a good draft with extra fans??? Airflow in a room is often sufficient when you think about it. Thanks, Steve. Sawadee on 6/6/04 7:28AM [ Reply | Permalink | Report ]

Re RiscPC cooling [link] I've done this mod on all of the RiscPC's I have owned. On a two slice machine with only podules in the second slice and a PC card on the motherboard, I blanked off the cooling slots on the top slice thus forcing air out only via the slots in the bottom slice. The machine became more stable in hot weather as a result of these changes. My A3010 used to crash a lot in summer when the ambient temp went above 25'C blahsnr on 7/6/04 10:37AM [ Reply | Permalink | Report ]

Could you provide some pictures on how to do that blahsnr? In fact, thinking about it - Ian's just posted the combo-drive how-to. Why not spruce up your page with some piccies, and it could go onto the Drobe hardware archive??? md0u80c9 on 15/6/04 2:55PM [ Reply | Permalink | Report ]

Has Andrew got his RPC back yet ? I'd love to see the DMA-enabled results .. especially now STD are selling them again ! JohnB on 15/7/04 8:57AM [ Reply | Permalink | Report ]

Not the RPC that was the problem - I needed the SA card. Now I've got that and...the drive dies. Under warranty, so I'm waiting for it to get back. Will post - I often need prompting though as I'm a little snowed at the moment. BTW - any ideas how to turn a Kinetic into a SA? md0u80c9 on 15/7/04 5:45PM [ Reply | Permalink | Report ]

A jumper setting on the kinetic will make it a normal SA card. micken on 17/8/04 3:53PM [ Reply | Permalink | Report ]

Please login before posting a comment. Use the form on the right to do so or create a free account.

Search the archives

Today's featured article

From the BBC Micro, little Acorns grew : The Guardian reports

 Discuss this. Published: 8 Mar 2001

Random article

One-Step Compilation
Automatic building in action for RISC OS
 4 comments, latest by mrchocky on 3/3/05 8:00PM. Published: 3 Mar 2005

Useful links