From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Ramsey Subject: Re: Phoronix article slaming BTRFS Date: Wed, 24 Jun 2009 02:47:32 +0000 (UTC) Message-ID: References: <2d23818a0906231026g6e4567fdv8eda3d6c4828ef4d@mail.gmail.com> <2d23818a0906231028t43d97e64t901610ca18e749d0@mail.gmail.com> <7a329d910906231920l49236acer404369643a2cf833@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii To: linux-btrfs@vger.kernel.org Return-path: List-ID: Wil Reichert gmail.com> writes: > > On Tue, Jun 23, 2009 at 6:27 PM, Mike Ramsey > comcast.net> wrote: > > Jaime sanchez gmail.com> writes: > > > >> [snip] > > I seriously doubt Phoronix has anything against btrfs, most likely > quite the opposite. I gave two possibilities, 1. Hatchet job i.e. malice with forethought 2. Just a poor effort I am not necessary favoring option 1. Regarding option 2, to err is human. Just admit it, correct it, and then don't repeat it. > My suggestion is either to show where their > benchmarks are in err, I did this, didn't I? 1. Vertex with write cache enabled; disabled would have seen a 2X improvement. 2. Error in libata > or come up with better benchmarks that > demonstrate btrfs in a more positive light. That is the ticket. I suggest that someone contact Tom's Hardware http://www.tomshardware.com/ And arrange to work with them to perform an honest benchmark. Head to head with Ext4 would work for me. :-) > Its quite possible > Phoronix would post updated benchmarks regarding the topic. They should either repeat the benchmark and do it right, or print a r etraction. BTW, thank you for your reply. I hope that none of the above sounded too harsh. The article was IMO damaging and needs to be countered. --Mike Ramsey [snip]