VIA silent disk corruption - likely fix
I've found the cause of silent disk corruption on my A7V motherboard, and it might affect all boards with the same North bridge (KT133 etc).
For some reason the IDE controller(s) was sometimes picking up stale data during bus master DMA to the drive. Assuming that there was no bug in the CPU it had to be the North bridge that was caching the stuff when it shouldn't have been. I assume the problem would also apply to other bus masters (SCSI, NIC etc).
Scanning the motherboard manual showed up a chipset setting "PCI master read caching" which I suspect is the culprit. According to the manual this defaults to "on" for Athlons and "off" for Durons (obviously other BIOSes / MB might treat this setting differently). Unfortunately my BIOS does not allow me to change this setting independently [1], I only have the choice of running the machine in "normal" or "optimal" configuration to alter this setting ("optimal" is the default).
In "normal" mode my machine is rock solid and I see no corruption, however "normal" mode also changes a lot of other settings (AGP speed, DRAM interleave etc). Anyone experiencing such corruption should look for a BIOS setting which disables this "feature".
If anyone out there has a BIOS which allows them to change just this one setting can they diff the "lspci -vvxxx" output with the setting off and then on so we can isolate which host bridge biti(s) control this feature. Maybe we can then add it to 'pci_quirks' and reduce the number of VIA corruption reports.
P.
[1] the BIOS appears to let you change the option but it defaults the option the moment you leave the "advanced settings" screen :-( -
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/
Quoted 22 lines · Peter Horton
I've found the cause of silent disk corruption on my A7V motherboard, and it might affect all boards with the same North bridge (KT133 etc).
For some reason the IDE controller(s) was sometimes picking up stale data during bus master DMA to the drive. Assuming that there was no bug in the CPU it had to be the North bridge that was caching the stuff when it shouldn't have been. I assume the problem would also apply to other bus masters (SCSI, NIC etc).
Scanning the motherboard manual showed up a chipset setting "PCI master read caching" which I suspect is the culprit. According to the manual this defaults to "on" for Athlons and "off" for Durons (obviously other BIOSes / MB might treat this setting differently). Unfortunately my BIOS does not allow me to change this setting independently [1], I only have the choice of running the machine in "normal" or "optimal" configuration to alter this setting ("optimal" is the default).
In "normal" mode my machine is rock solid and I see no corruption, however "normal" mode also changes a lot of other settings (AGP speed, DRAM interleave etc). Anyone experiencing such corruption should look for a BIOS setting which disables this "feature".
Quoted 5 lines
If anyone out there has a BIOS which allows them to change just this one setting can they diff the "lspci -vvxxx" output with the setting off and then on so we can isolate which host bridge biti(s) control this feature. Maybe we can then add it to '
pci_quirks' and reduce the number of VIA corruption reports.
It seem I have such an options,
named K7 CLK_CTL, under Advanced Setting, with two possible choise : Optimal or Default.
Here is the output of lspci with each of them,
I hope it will help.
Signature · 4 lines
-- -- Yoann http://www.mandrakesoft.com/~yoann/ An engineer from NVidia, while asking him to release cards specs said : "Actually, we do write our drivers without documentation."
Quoted 9 lines · Peter Horton
I've found the cause of silent disk corruption on my A7V motherboard, and it might affect all boards with the same North bridge (KT133 etc).
For some reason the IDE controller(s) was sometimes picking up stale data during bus master DMA to the drive. Assuming that there was no bug in the CPU it had to be the North bridge that was caching the stuff when it shouldn't have been. I assume the problem would also apply to other bus masters (SCSI, NIC etc).
Do you have a small test program to illustrate that bug? I have an A7V with PCI Master Read Caching enabled and haven't seen any corruption so far (which doesn't necessarily mean much). Or if you don't have a test program, how did you identify it's caching too much?
Also, are you using a Thunderbird or a Duron?
I'm using the 1003 Bios, which has proven to be the most stable so far. Which one do you use?
-Udo.
P.S. I seem to recall that later Bios Versions (>=1004) disable Master
Read Caching by default, so maybe Asus has also noticed something wrong with it.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
Please read the FAQ at http://www.tux.org/lkml/
Quoted 9 lines · Udo A. Steinberg
Quoted 2 lines · Peter Horton
I've found the cause of silent disk corruption on my A7V motherboard, and it might affect all boards with the same North bridge (KT133 etc).
Do you have a small test program to illustrate that bug? I have an A7V with PCI Master Read Caching enabled and haven't seen any corruption so far (which doesn't necessarily mean much). Or if you don't have a test program, how did you identify it's caching too much?
Also, are you using a Thunderbird or a Duron?
Just an extra data point here.
I have an A7V here also and I haven't seen anything wrong with my setup (but I'm using 2.2.18 + the IDE patches). Perhaps, I'm not hitting the bad cases or I'm not stressing the system enough. I'm using a Quantum lct15 drive here with UDMA/66 here. I have a Duron 600MHz and I remember that when I was setting the machine (after I bought it), I left everything in the default settings (so, the PCI Master Read Caching is disabled).
Quoted 2 lines
I'm using the 1003 Bios, which has proven to be the most stable so far. Which one do you use?
I also use 1003, but I have not tried anything else (for fear of something going wrong when I'm upgrading -- like a power outage). :-) []s, Roger...
Signature · 7 lines
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Rogerio Brito - [email protected] - http://www.ime.usp.br/~rbrito/ =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] Please read the FAQ at http://www.tux.org/lkml/
Quoted 2 lines · Peter Horton
I've found the cause of silent disk corruption on my A7V motherboard, and it might affect all boards with the same North bridge (KT133 etc).
...
Quoted 2 lines
[1] the BIOS appears to let you change the option but it defaults the option the moment you leave the "advanced settings" screen :-(
Is your BIOS current? Gigabyte 7ZXR BIOSes (F4) e. g. have exhibited not-so-different troubles (once you set a suspend timeout, you could not reset it lest you reloaded the entire BIOS anew; with American Megatrends' BIOS this means you lose ALL settings except your Standard CMOS setup), this problem is fixed in F5J (I did not bother to look for an official F5 release yet).
Signature · 5 lines
Matthias Andree - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] Please read the FAQ at http://www.tux.org/lkml/