On Aug 7, 2009, at 23:31 PM, Reimundo Heluani wrote:
There is a corruption issue with ext3 and ext4, that we have seen on
some test boxes. Upstream is aware.
Is this an issue on NSF servers? that's the only thing I could find
online and it's been around since 2.6.28.9.
R.
Hello,
The issue has been around for a while:
http://lkml.org/lkml/2009/3/24/415
The 2.6.30 kernel now has data=guarded mode that can be used instead
of data=ordered for ext3.
I think the default could have been data=writeback which is pretty
much insane.
You can follow a nice history of what has been going on.
http://kerneltrap.org/node/7534
William
_______________________________________________
Clfs-dev mailing list
[email protected]
http://lists.cross-lfs.org/listinfo.cgi/clfs-dev-cross-lfs.org
