Well, I guess I'm not the only one who has ever had egg on his face
after posting a bug report.
Before posting the report, I had run memtest86 v2.5.1 for more than one
complete pass of the std tests and had concluded the memory was OK. On
a hunch, after a reply from Mark Hahn, I let it run all night; after 17
hours running all tests over 3+ passes, it recorded about 4000 errors.
These were clustered around 64MB and 135MB (64K and 4K holes,
respectively), and I think that adequately accounts for the problems I
was having on large file copies. The guy who sold me the hardware took
it all back and refunded my money rather than having to learn something
about linux, so I guess he didn't deserve the sale after all.
Thanks again to all who read and responded. Now I know to run multiple
passes on memtest before deciding things are OK....
Ken
-
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/