* Re: Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
@ 2002-03-29 22:18 David Härdeman
0 siblings, 0 replies; 6+ messages in thread
From: David Härdeman @ 2002-03-29 22:18 UTC (permalink / raw)
To: linux-kernel
Hi,
First off, I'd like to thank Andre Hedrick for the link to:
http://www.tecchannel.de/hardware/817/index.html
It was very helpful in making me understand why the performance of my
newly bought Adaptec 2400A IDE-Raid card sucked so badly in combination
with my VIA KT133 based board.
I have done some testing (on the Win platform since that's where the
patches to remedy this situation are available) that shows quite nicely
how the PCI bus gets totally overrun by transfer rates in excess of
approximately 74MB/s and instead slows down.
Short summary
=============
Expected rate Experienced rate
84MB/s
50MB/s
80MB/s
64MB/s
74MB/s
74MB/s
(If someone is very interested, mail me and I can publish some transfer
rate graphs online)
I just have a few questions:
1) Is there any efforts made to add the "hacks" that VIA has put into
their (win only patch) at:
http://www.viaarena.com/?PageID=66#raid
into the kernel? Does VIA give out specs what the patch does?
2) Has anyone had any experiences with the VIA KT333 chipset? Does it
have the same numerous problems that the KT133/266 seem to have?
3) Could someone recommend another non-VIA chipset to use instead that
they've had good experiences with? (since I am going to buy a new
motherboard to remedy this situation)
Thanks in advance and please CC me any answers since I'm not on the list.
Regards,
David
david@2gen.com
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
@ 2002-03-26 13:15 Nicholas Berry
0 siblings, 0 replies; 6+ messages in thread
From: Nicholas Berry @ 2002-03-26 13:15 UTC (permalink / raw)
To: kschad, <
I've got one system roughly similar to yours, RAID 5 , but scsi, not ata.
The CPU is also a 1400MHz Athlon.
My lspci:
00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
00:09.0 Ethernet controller: Lite-On Communications Inc LNE100TX [Linksys EtherFast 10/100] (rev 25)
00:0a.0 SCSI storage controller: Adaptec 7899A (rev 01)
00:0a.1 SCSI storage controller: Adaptec 7899A (rev 01)
00:0b.0 SCSI storage controller: Adaptec AIC-7881U
00:0c.0 Ethernet controller: Bridgecom, Inc: Unknown device 0985 (rev 11)
00:11.0 ISA bridge: VIA Technologies, Inc. VT8233 PCI to ISA Bridge
00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
00:11.2 USB Controller: VIA Technologies, Inc. UHCI USB (rev 18)
00:11.3 USB Controller: VIA Technologies, Inc. UHCI USB (rev 18)
00:11.4 USB Controller: VIA Technologies, Inc. UHCI USB (rev 18)
00:11.5 Multimedia audio controller: VIA Technologies, Inc. AC97 Audio Controller (rev 10)
01:00.0 VGA compatible controller: ATI Technologies Inc Rage 128 PF
It would hang exactly as you described. It's a test system, and things change so fast I never got around to tracking the problem down. However, it's now running 2.4.19-pre4 and hasn't hung for days (since 2.4.19-pre4 was installed).
Nik
>>> Kai-Boris Schad <kschad@correo.e-technik.uni-ulm.de> 03/26/02 06:27AM >>>
> Hi !
> I have problems with PC mainboard using the Via VT8367 [KT266] chipset.
> lspci shows the configuration:
> lspci
> 00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
> 00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
> 00:0c.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139 (rev 10)
> 00:0e.0 Unknown mass storage controller: Promise Technology, Inc. 20268 (rev
> 01)00:0f.0 Unknown mass storage controller: Promise Technology, Inc. 20268
> (rev 01)00:11.0 ISA bridge: VIA Technologies, Inc. VT8233 PCI to ISA Bridge
> 00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
> 01:00.0 VGA compatible controller: ATI Technologies Inc Rage XL AGP (rev 27)
>
>The CPU is a 1400MHz Athlon.
> We use this system for a software Raid 5. If we produce heavy load on the
> disks and network the system hangs. There is no log of errors at all. We
> tried to change the network card form a 3com to a rtl83xx. The system remains
> a litle longer stable but crashes then too. We also tried to have the
> harddisks on seperate ide channels but this didn't solve the crashs.
> It seems to be something with the dma, because if we disable the dma of the
> harddisks the system is stable. Does anybody also recognise this problem ?
> Is there any solution for this effect ?
>
> Thanks a lot
>
> Kai
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
^ permalink raw reply [flat|nested] 6+ messages in thread
* Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
@ 2002-03-26 11:27 Kai-Boris Schad
2002-03-26 13:44 ` Alan Cox
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Kai-Boris Schad @ 2002-03-26 11:27 UTC (permalink / raw)
To: linux-kernel
Hi !
I have problems with PC mainboard using the Via VT8367 [KT266] chipset.
lspci shows the configuration:
lspci
00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
00:0c.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139 (rev 10)
00:0e.0 Unknown mass storage controller: Promise Technology, Inc. 20268 (rev
01)00:0f.0 Unknown mass storage controller: Promise Technology, Inc. 20268
(rev 01)00:11.0 ISA bridge: VIA Technologies, Inc. VT8233 PCI to ISA Bridge
00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
01:00.0 VGA compatible controller: ATI Technologies Inc Rage XL AGP (rev 27)
The CPU is a 1400MHz Athlon.
We use this system for a software Raid 5. If we produce heavy load on the
disks and network the system hangs. There is no log of errors at all. We
tried to change the network card form a 3com to a rtl83xx. The system remains
a litle longer stable but crashes then too. We also tried to have the
harddisks on seperate ide channels but this didn't solve the crashs.
It seems to be something with the dma, because if we disable the dma of the
harddisks the system is stable. Does anybody also recognise this problem ?
Is there any solution for this effect ?
Thanks a lot
Kai
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
2002-03-26 11:27 Kai-Boris Schad
@ 2002-03-26 13:44 ` Alan Cox
2002-03-26 15:57 ` Mark Cooke
2002-03-26 20:31 ` Andre Hedrick
2 siblings, 0 replies; 6+ messages in thread
From: Alan Cox @ 2002-03-26 13:44 UTC (permalink / raw)
To: kschad; +Cc: linux-kernel
> harddisks on seperate ide channels but this didn't solve the crashs.
> It seems to be something with the dma, because if we disable the dma of the
> harddisks the system is stable. Does anybody also recognise this problem ?
> Is there any solution for this effect ?
I have a large count "via plus lots of disks hangs my computer" mails. I
have a very small count of non via plus lots of disks ..
I don't think its the VIA IDE drivers either - similar reports are seen when
people are doing it with plug in promise cards.
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
2002-03-26 11:27 Kai-Boris Schad
2002-03-26 13:44 ` Alan Cox
@ 2002-03-26 15:57 ` Mark Cooke
2002-03-26 20:31 ` Andre Hedrick
2 siblings, 0 replies; 6+ messages in thread
From: Mark Cooke @ 2002-03-26 15:57 UTC (permalink / raw)
To: Kai-Boris Schad; +Cc: linux-kernel
Hi,
I saw similar issues with a KT133A-RAID board. The latest BIOS from
ABit appear to have helped fix this problem here, as does the VIA fix
to register 0x55.
Before this, I was seeing hard freezes when using software raid-5 too.
I still see a very occasional glitch where the machine appears to get
stuck doing a repeated bus-master transfer. The last occurance was a
hard loop with the sound card repeating the same ~ 0.5 seconds over
and over, but the machine was entirely frozen, with no sysrq / network
activity.
My lspci:
00:00.0 Host bridge: VIA Technologies, Inc. VT8363/8365 [KT133/KM133] (rev 03)
00:01.0 PCI bridge: VIA Technologies, Inc. VT8363/8365 [KT133/KM133 AGP]
00:07.0 ISA bridge: VIA Technologies, Inc. VT82C686 [Apollo Super South] (rev 40)
00:07.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
00:07.2 USB Controller: VIA Technologies, Inc. UHCI USB (rev 1a)
00:07.3 USB Controller: VIA Technologies, Inc. UHCI USB (rev 1a)
00:07.4 Bridge: VIA Technologies, Inc. VT82C686 [Apollo Super ACPI] (rev 40)
00:08.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8029(AS)
00:0b.0 Ethernet controller: 3Com Corporation 3c905B 100BaseTX [Cyclone] (rev 30)
00:0f.0 Multimedia audio controller: Trident Microsystems 4DWave DX (rev 02)
00:11.0 Multimedia video controller: Brooktree Corporation Bt848 TV with DMA push (rev 12)
00:13.0 Unknown mass storage controller: HighPoint Technologies, Inc. HPT366/370 UltraDMA 66/100 IDE Controller (rev 04)
01:00.0 VGA compatible controller: nVidia Corporation NV11 DDR (rev b2)
and also from the startup dmesg, the message about the memory write
queue, which is known to cause corruption and freezes if it's not
done:
Disabling VIA memory write queue: [55] 89->09
I'm using 2.4.19-pre3 with AlanC's pre4 patch ontop of that with good
success. You might try one of the very latest kernels as the via fix
was pretty recent.
I would say that my experience with this via chipset has put me off
their product for future purchases.
The read performance of my raid-5 partition is only around 50MB/sec,
when the individual drives all produce 40MB/sec, and this does seem
very strongly dependent on the PCI options in the BIOS.
It is still well below the 60-80MB/sec I was hoping to see. (Based
approximately on total theoretical pci bandwidth * 66% for my 3 disk
raid-5 setup, with each disk on an individual chain.) Note I did
isolate the raid-5 from causing problems by monitoring the overall
transfer rates running parallel read tests against each disk, as well
as an overall read test against the md device. Virtually no
throughput difference.
Note there is a windows-only patch available on viaarena.com that
claims to really improve PCI burst transfer bandwidth, but my attempts
to contact the author for details of what that patch actually does
have so far gone unanswered.
PrePatch: http://www.tecchannel.de/hardware/817/5.html
Via Patch: http://www.viaarena.com/?PageID=66#raid
Post Patch: http://www.tecchannel.de/hardware/817/11.html
Cheers,
Mark
On Tue, 26 Mar 2002, Kai-Boris Schad wrote:
> Hi !
>
> I have problems with PC mainboard using the Via VT8367 [KT266] chipset.
> lspci shows the configuration:
> lspci
> 00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
> 00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
> 00:0c.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139 (rev 10)
> 00:0e.0 Unknown mass storage controller: Promise Technology, Inc. 20268 (rev
> 01)00:0f.0 Unknown mass storage controller: Promise Technology, Inc. 20268
> (rev 01)00:11.0 ISA bridge: VIA Technologies, Inc. VT8233 PCI to ISA Bridge
> 00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
> 01:00.0 VGA compatible controller: ATI Technologies Inc Rage XL AGP (rev 27)
>
> The CPU is a 1400MHz Athlon.
> We use this system for a software Raid 5. If we produce heavy load on the
> disks and network the system hangs. There is no log of errors at all. We
> tried to change the network card form a 3com to a rtl83xx. The system remains
> a litle longer stable but crashes then too. We also tried to have the
> harddisks on seperate ide channels but this didn't solve the crashs.
> It seems to be something with the dma, because if we disable the dma of the
> harddisks the system is stable. Does anybody also recognise this problem ?
> Is there any solution for this effect ?
>
> Thanks a lot
>
> Kai
>
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
--
+-------------------------------------------------------------------------+
Mark Cooke The views expressed above are mine and are not
Systems Programmer necessarily representative of university policy
University Of Birmingham URL: http://www.sr.bham.ac.uk/~mpc/
+-------------------------------------------------------------------------+
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load
2002-03-26 11:27 Kai-Boris Schad
2002-03-26 13:44 ` Alan Cox
2002-03-26 15:57 ` Mark Cooke
@ 2002-03-26 20:31 ` Andre Hedrick
2 siblings, 0 replies; 6+ messages in thread
From: Andre Hedrick @ 2002-03-26 20:31 UTC (permalink / raw)
To: Kai-Boris Schad; +Cc: linux-kernel
This is an identical problem I am seeing w/ VIA and any add on card.
Everybody and their brother is attempting NAS with cheap VIA boards and
addon cards and they go south and die.
http://www.tecchannel.de/hardware/817/index.html
This is one of the better explaination why :-/
Regards,
Andre Hedrick
LAD Storage Consulting Group
On Tue, 26 Mar 2002, Kai-Boris Schad wrote:
> Hi !
>
> I have problems with PC mainboard using the Via VT8367 [KT266] chipset.
> lspci shows the configuration:
> lspci
> 00:00.0 Host bridge: VIA Technologies, Inc. VT8367 [KT266]
> 00:01.0 PCI bridge: VIA Technologies, Inc. VT8367 [KT266 AGP]
> 00:0c.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139 (rev 10)
> 00:0e.0 Unknown mass storage controller: Promise Technology, Inc. 20268 (rev
> 01)00:0f.0 Unknown mass storage controller: Promise Technology, Inc. 20268
> (rev 01)00:11.0 ISA bridge: VIA Technologies, Inc. VT8233 PCI to ISA Bridge
> 00:11.1 IDE interface: VIA Technologies, Inc. Bus Master IDE (rev 06)
> 01:00.0 VGA compatible controller: ATI Technologies Inc Rage XL AGP (rev 27)
>
> The CPU is a 1400MHz Athlon.
> We use this system for a software Raid 5. If we produce heavy load on the
> disks and network the system hangs. There is no log of errors at all. We
> tried to change the network card form a 3com to a rtl83xx. The system remains
> a litle longer stable but crashes then too. We also tried to have the
> harddisks on seperate ide channels but this didn't solve the crashs.
> It seems to be something with the dma, because if we disable the dma of the
> harddisks the system is stable. Does anybody also recognise this problem ?
> Is there any solution for this effect ?
>
> Thanks a lot
>
> Kai
>
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2002-03-29 22:20 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-03-29 22:18 Kernel 2.4.17 with VT8367 [KT266] crashes on heavy ide load togeter with heavy network load David Härdeman
-- strict thread matches above, loose matches on Subject: below --
2002-03-26 13:15 Nicholas Berry
2002-03-26 11:27 Kai-Boris Schad
2002-03-26 13:44 ` Alan Cox
2002-03-26 15:57 ` Mark Cooke
2002-03-26 20:31 ` Andre Hedrick
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox