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 <jbacik@xxxxxx> 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 <https://github.com/NetworkBlockDevice/nbd/blob/extension-info/doc/proto.md#block-size-constraints>, 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
