really strange ext4 behavior

Michał Piotrowski mkkp4x4 at
Tue Feb 15 16:41:28 UTC 2011

W dniu 15 lutego 2011 00:21 użytkownik Eric Sandeen
<sandeen at> napisał:
> There is no real best-practice tuning without workload details;
> without that, "defaults" is best practice.  :)
> (except for ext3, where, for data integrity with a volatile writeback
> cache, defaults + barriers=1, since that safe default was never accepted upstream)

Thanks, I enabled barriers on all my ext3 fs'es. (I use ecryptfs in
certain dirs, so it is difficult
to recover data for them :))

> -Eric

Best regards,

More information about the devel mailing list