Welcome, Guest. Please login or register.

Author Topic: A4091 performance  (Read 5348 times)

Description:

0 Members and 1 Guest are viewing this topic.

Offline DamionTopic starter

Re: A4091 performance
« Reply #14 from previous page: November 26, 2012, 09:18:35 AM »
Hi Dan,

Quote from: danbeaver;716378
Does the bus speed mean that much to what you do?  Could you use a UWSCSI controller instead?  A USB external drive gets 5 MB/s on a Deneb, would that help you out, or a FastATA card with one of the upper range PIO modes?

Actually, the performance of the 4091 is more than enough for what I need to do (casual tinkering, games, demos, etc). Filesystem operations are just as zippy as my accelerators with SCSI, so the system feels similarly responsive. And the CPU use is negligible compared to IDE, or even the Fastlane. The real challenge here was simply figuring out whether or not the 4091 was performing at its best, which (tinkering with the hardware) accounts for a majority of the fun for me. An MK3 with UWSCSI would be ideal, but maybe too easy... LOL!

I have a DENEB installed, it's a nice, useful piece of hardware. Unfortunately I had one major problem - read errors when transferring files between devices on the DENEB. For example, copying MP3s between a flashdrive and the internal storage inevitably resulted in an unrecoverable failure. I was unable to resolve this after many countless hours trying, and could replicate the fault on a number of different systems (2000, 3000 and 4000) and hardware/software configurations. Copying between accelerator SCSI (or internal IDE) and the DENEB worked fine. Accelerator SCSI wasn't an option on my A4K/CSMK2, since it's clocked at 66MHz.

Also - CPU usage with the DENEB in DMA mode is similar to the Fastlane; it sacrifices quite a bit in that department for the sake of a higher transfer rate. This also explains why the DENEB works in DMA mode with Buster 9 in conjunction with the Fastlane and its Buster 9 "workaround" - there really isn't the same kind of efficient DMA going on like you have with the 4091 or accelerator SCSI... But hey, it's potentially faster, more compatible, and at least it works!

I have to say I'm 100% satisfied with the current setup, MK2 Cyberstorm@66MHz, DENEB + Melody 1200 Pro, A4066 ethernet, and the 4091. (The 4091 has an AztecMonster SCSI ->CF adapter and 16GB SanDisk onboard.) I've successfully transferred a ton of files between the 4091 and DENEB, and had the system up for a few days now with no crashes or resets. Aside from easy USB access, flashrom for custom kickstart+modules, and providing a clockport for the Melody, the DENEB also serves an additional useful purpose: without it, the 4091 refuses to see attached drives so long as the ethernet board is installed. Plop in the DENEB, and everything works just fine. :pint:

Quote
You should do some tests of the A3000 SCSI.

Incidentally, I did a bit of that this evening, with both the stock '030 and a few different accelerators in the mix. I get 3.8 MB/s from an old Quantum Fireball with some 80% CPU free. The Fastlane in the same setup will do 7 MB/s (with a fast enough drive), but it eats all available CPU time. Buster 11 mode (which, btw, works reliably only on my A3000 sans accelerator) yields ~5 MB/s and still sucks massive CPU.
« Last Edit: November 26, 2012, 05:12:59 PM by Damion »
 

Offline Zac67

  • Hero Member
  • *****
  • Join Date: Nov 2004
  • Posts: 2890
    • Show only replies by Zac67
Re: A4091 performance
« Reply #15 on: November 26, 2012, 06:33:25 PM »
I guess with the Fastlane saturating the internal bus (including Z3 overhead from Buster) it just stalls the stock CPU. An accelerator board with RAM might solve this problem. One with onboard SCSI could boost SCSI performance significantly but there are only a few fast-wide and ultra-wide adapters around.
 

Offline DamionTopic starter

Re: A4091 performance
« Reply #16 on: November 26, 2012, 07:46:21 PM »
Quote from: Zac67;716446
I guess with the Fastlane saturating the internal bus (including Z3 overhead from Buster) it just stalls the stock CPU.


Makes sense, the CPU is locked out rather than being utilized, as the SCSI controller is still doing all the work. So it's still technically DMA (if I have that correct).

Quote
An accelerator board with RAM might solve this problem.


When the Fastlane's Buster 11 mode works long enough to run RSCP, it does perform about as well as the 4091, even a touch better. Problem is it locks up on both the 3000 and 4000, with several different accelerators, unless the datacache is disabled - which then cuts CPU availability almost back the levels of Buster 9 mode. Regardless, 7 MB/s on a stock 3000 over Zorro isn't too shabby, IMHO.
 

Offline Zac67

  • Hero Member
  • *****
  • Join Date: Nov 2004
  • Posts: 2890
    • Show only replies by Zac67
Re: A4091 performance
« Reply #17 on: November 26, 2012, 09:11:22 PM »
Quote
Regardless, 7 MB/s on a stock 3000 over Zorro isn't too shabby, IMHO.
True.

The problem with adding accelerator RAM may be that CPU caching breaks data integrity. Since the CPU then lives on another bus apart from mainboard RAM it can't see (bus snooping) what addresses are written to by DMA - stale cache entries need to be invalidated.

This is not a problem which can't be solved (through proper OS and driver support or clever driver support w/o the OS) but it's unsolved on the Amiga afaik. :( The only workaround is to turn off caches altogether (ouch) or flush caches after each DMA operation (a bit less painful but still). :-/
 

Offline ChaosLord

  • Hero Member
  • *****
  • Join Date: Nov 2003
  • Posts: 2608
    • Show only replies by ChaosLord
    • http://totalchaoseng.dbv.pl/news.php
Re: A4091 performance
« Reply #18 on: November 26, 2012, 11:09:54 PM »
Its not hard to fix any broken drivers as long as you find a programmer who is interested in the subject and can get the source code.

You could prob even get RedSkullDC to do it without source code.

RedSkullDC> I donno anything about hard drive drivers.

Don't worry :)

You just need to flush the cache after loading some DMA data.  Problem solved.  Presto!  (That is the simple explanation).  I think there may be a fancier more elegant thing you can do with the MMU but this is outside my realm.

Thor can explain anything about these cache coherency problems to any competent haxx0r and we can get this problem fixed.  Thor hangs out on the Natami forums and is easily reached there.  Put "Cache Coherency" or "MMU" in the title of your forum post and he is 512% likely to read it and teach you all the magic spells u need to know. :)
Wanna try a wonderfull strategy game with lots of handdrawn anims,
Magic Spells and Monsters, Incredible playability and lastability,
English speech, etc. Total Chaos AGA
 

Offline danbeaver

Hijacking the A4091 performance Thread
« Reply #19 on: November 27, 2012, 01:23:26 AM »
Damion,

I get the same fornicating errors on large transfers from a. USB thumb device; I have tweaked the Poseidon settings to no avail. I think the Fat95 file system has issues with thumb drives on large transfers. Small chunks go fine; DOS copying does better than WB, and so on. Of I format the thumb in an FFS or so and use it like an Amiga drive, then I get better transfers before errors. What I do not understand is how CF cards (at least everyone I've tried) work so dern well in FAT mode, Amiga modes and over SCSI to card reader, USB to card reader and IDE connections. I get errors on large transfers on the USB bus, but only rarely on DOS shell copies.

When I use an external USB HDD I never see any problems.

"There are more things in heaven and earth, Horatio,
Than are dreamt of in your philosophy. "