From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Sat, 11 Feb 2017 12:43:56 +0100 From: Wouter Verhelst To: Josef Bacik Cc: Alex Bligh , axboe@kernel.dk, linux-block@vger.kernel.org, kernel-team@fb.com, "nbd-general@lists.sourceforge.net" Subject: Re: [Nbd] [PATCH] nbd: set the logical and physical blocksize properly Message-ID: <20170211114356.qr2atsx4ewcjfbes@grep.be> References: <1486750004-2988-1-git-send-email-jbacik@fb.com> <59F046CB-9EE6-4E45-A06D-3F352218E91B@alex.org.uk> <1486763262.4094.12.camel@fb.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 In-Reply-To: <1486763262.4094.12.camel@fb.com> List-ID: On Fri, Feb 10, 2017 at 04:47:42PM -0500, Josef Bacik wrote: > On Fri, 2017-02-10 at 21:07 +0100, Alex Bligh wrote: > > > > > > On 10 Feb 2017, at 19:06, Josef Bacik wrote: > > > > > > We noticed when trying to do O_DIRECT to an export on the server > > > side > > > that we were getting requests smaller than the 4k sectorsize of the > > > device.��This is because the client isn't setting the logical and > > > physical blocksizes properly for the underlying device.��Fix this > > > up by > > > setting the queue blocksizes and then calling bd_set_size. > > Interesting. Some input into the info extension (re blocksizes) would > > definitely be appreciated. > > > > What do you mean? �Right now the client is just calling�NBD_SET_BLKSIZE > with 4k blocksize since all of our devices are 4k drives. �Thanks, He's talking about , which is a protocol extension that hasn't been implemented yet but would be relevant to this patch. -- < ron> I mean, the main *practical* problem with C++, is there's like a dozen people in the world who think they really understand all of its rules, and pretty much all of them are just lying to themselves too. -- #debian-devel, OFTC, 2016-02-12