From mboxrd@z Thu Jan 1 00:00:00 1970 From: Oleg Drokin Subject: Re: [BK] ReiserFS file write bug fix for 2.4 Date: Fri, 13 Sep 2002 09:05:40 +0400 Message-ID: <20020913090540.A4723@namesys.com> References: <5.1.1.6.2.20020912183504.01d24f60@pop.tvnet.hu> Mime-Version: 1.0 Return-path: list-help: list-unsubscribe: list-post: Errors-To: flx@namesys.com Content-Disposition: inline In-Reply-To: <5.1.1.6.2.20020912183504.01d24f60@pop.tvnet.hu> List-Id: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Newsmail Cc: reiserfs-list@namesys.com Hello! On Thu, Sep 12, 2002 at 06:40:10PM +0100, Newsmail wrote: > > The mount option (-o alloc=prealloc min=4:preallocsize=9) only or better > > a "reformat"? > > Those mount options are no longer needed starting from 2.4.20-pre6. > > They are default. Reformat is not needed, but all the blocks allocated by > > old allocator will remain at their old places of course. > I use 2.4.20-pre4 without these mount options. So apparently reiserfs is > much slower than the optimal am I right? (if my memory is good this is > about some speed optimization right?). It depends on kind of workloads you have. But in general - yes, it is somewhat slower and if you have massive parallel writers, on-disk blocks layout is suboptimal. You should use above mount options (alloc=preallocmin=4:preallocsize=9) or upgrade to 2.4.19-pre7 (of that's not our yet, then to whatever is the current state of Marcelo's bk repository is ). Bye, Oleg