[Lustre-devel] [RFC] "lctl readonly" modification proposal

Mikhail Pershin Mikhail.Pershin at Sun.COM
Wed Aug 20 12:42:39 PDT 2008

On Wed, 20 Aug 2008 21:39:13 +0400, Peter Braam <Peter.Braam at sun.com>  

> If I remember correctly the flush is only there to try to reduce  
> rollback.

Also to be sure that all before barrier is on disk, many test cases about  
recovery rely on the fact that operations before barrier are on disk. This  
is important with HARD failure case especially, without sync before  
barrier the operations before barrier may be lost and affect the tests.
I agree that syncless variant of barrier is needed but we also need  
barrier with sync depending on test case.

Mikhail Pershin
Staff Engineer
Lustre Group
Sun Microsystems, Inc.

More information about the lustre-devel mailing list