Messages in this thread | | | Date | Tue, 13 Jul 1999 17:13:28 -0700 | From | Nate Eldredge <> | Subject | Corruption bug in CPU, kernel or tar |
| |
I would send this to comp.os.linux.hardware as well, but my news server is broken :(
tar 1.12, Linux 2.2.10, and an AMD K6-3/450.
I'm chasing a bug which I found while doing a stress-test with `(tar x; tar d) &' times seventeen. It involves occasional corruption of an extracted file (every few days). I've only been able to inspect the file once, although the error apparently happened another time. In the case I found, the file, an MP3 of about 70MB, had 32 bytes in error, on a 32-byte boundary. Further investigation showed that the erroneous 32 bytes were also in libc.so.
This is suspicious as the K6-3 has cache lines of 32 bytes, and I have stepping 1. However, I should like to know if anyone can think of alternate explanations involving software problems. Is there anything in tar or the kernel that handles 32-byte chunks and might be able to cause such corruption? Alternatively, has anyone heard of similar problems with the K6-3?
The machine has 128MB of ECC memory, 20GB WD IDE hard disk, FIC motherboard with VIA chipset. All are brand new.
A CC by email would be appreciated if convenient.
TIA --
Nate Eldredge nate@cartsys.com
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |