From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mike Snitzer Subject: Re: [PATCH 08/10] dm-integrity: add a bitmap mode Date: Wed, 8 May 2019 13:25:33 -0400 Message-ID: <20190508172533.GA29488@redhat.com> References: <20190429125746.036036640@debian-a64.vm> <20190507185154.GB24320@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com To: Mikulas Patocka Cc: Ondrej Kozina , Heinz Mauelshagen , dm-devel@redhat.com, Alasdair G Kergon , Milan Broz List-Id: dm-devel.ids On Wed, May 08 2019 at 12:46pm -0400, Mikulas Patocka wrote: > > > On Tue, 7 May 2019, Mike Snitzer wrote: > > > On Mon, Apr 29 2019 at 8:57am -0400, > > Mikulas Patocka wrote: > > > > > Add a new bitmap mode for dm-integrity. > > > > > > Signed-off-by: Mikulas Patocka > > > > This patch header needs much more detail. > > > > Can you please be as informative and detailed as possible about what > > this new bitmap mode is (what constraints it has, where it is expected > > to be useful, etc)? Also, if you have them, provide some benchmarks > > that showcase its benefits. > > > > Thanks, > > Mike > > The patch adds the documentation to the file > "Documentation/device-mapper/dm-integrity.txt", so it can be also used as > a patch header. For example: > > "This patch introduces an alternative mode of operation whete dm-integrity > uses bitmap instead of a journal. If a bit in the bitmap is 1, the > corresponding region's data and integrity tags are not synchronized - if > the machine crashes, the unsynchronized regions will be recalculated. The > bitmap mode is faster than the journal mode, because we don't have to > write the data twice, but it is also less reliable, because if data > corruption happens when the machine crashes, it may not be detected." > > Benchmark - on an SSD connected to a SATA300 port, when doing large linear > writes with dd. > > buffered I/O: > raw device throughput - 245MB/s > dm-integrity with journaling - 120MB/s > dm-integrity with bitmap - 238MB/s > > direct I/O with 1MB block size: > raw device throughput - 248MB/s > dm-integrity with journaling - 123MB/s > dm-integrity with bitmap - 223MB/s Great, thanks.