Bas Verhoeven schrieb:

After doing some testing with a quick custom script (see [1]),
downloading the same file over and over from a remote server, I indeed
noticed that a lot of the downloads would indeed be written to disk in a
corrupted state: the SHA1 sums for each file were different, although
they were all downloading the same file.

testing your script from / get errors
Run #277 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #278 94ebed967308edd4e01885a06a691825060d6b51 current
Run #279 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #280 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #281 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #282 f51f9dc9e1b54a4299042b8d54f5934998444040 current
Run #283 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
testing from /tmp/ramtmp everthing is fine
Run #1 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #2 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #3 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #4 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #5 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #6 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
Run #7 b82cabbb4145f1ddcedb70ec05894ea54c3f1fba current
booting from debian bigmem kernel everything is fine too.
greets Holm
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users