Hello On Tue, 2006-02-28 at 00:14 +0100, Pierre Etchemaïté wrote: > Hi all, > > I have a question that didn't occur to me until a power failure (eh)... > > When a journalized file system like reiserfs 3 runs on top on a > software raid volume, does the volume give enough (and correct) > feedback so that the file system can still guarantee that its metadata > will be in a consistant state after a power failure/crash/you name it ? > > If all disks go back online ? If some don't (but below redundancy > amount, of course) ? > > In short, beside disks resynching, is a fsck also necessary ? >
It should not be. I believe that journal replaying on mount is enough. Does your experience contradict that?
