Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-07-08 Thread Kevin Wolf
Am 06.07.2016 um 04:04 hat Eric Blake geschrieben: > On 06/21/2016 11:54 PM, Fam Zheng wrote: > > On Mon, 06/20 17:39, Eric Blake wrote: > >> We have max_transfer documented in BlockLimits, but while we > >> honor it during pwrite_zeroes, we were blindly ignoring it > >> during pwritev and preadv,

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-07-05 Thread Eric Blake
On 06/21/2016 11:54 PM, Fam Zheng wrote: > On Mon, 06/20 17:39, Eric Blake wrote: >> We have max_transfer documented in BlockLimits, but while we >> honor it during pwrite_zeroes, we were blindly ignoring it >> during pwritev and preadv, leading to multiple drivers having >> to implement fragmentat

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-22 Thread Stefan Hajnoczi
On Tue, Jun 21, 2016 at 04:05:22PM -0600, Eric Blake wrote: > On 06/21/2016 04:23 AM, Stefan Hajnoczi wrote: > > On Mon, Jun 20, 2016 at 05:39:24PM -0600, Eric Blake wrote: > >> We have max_transfer documented in BlockLimits, but while we > >> honor it during pwrite_zeroes, we were blindly ignoring

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-22 Thread Stefan Hajnoczi
On Tue, Jun 21, 2016 at 12:43:08PM +0200, Kevin Wolf wrote: > Am 21.06.2016 um 12:23 hat Stefan Hajnoczi geschrieben: > > On Mon, Jun 20, 2016 at 05:39:24PM -0600, Eric Blake wrote: > > > We have max_transfer documented in BlockLimits, but while we > > > honor it during pwrite_zeroes, we were blind

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-21 Thread Fam Zheng
On Mon, 06/20 17:39, Eric Blake wrote: > We have max_transfer documented in BlockLimits, but while we > honor it during pwrite_zeroes, we were blindly ignoring it > during pwritev and preadv, leading to multiple drivers having > to implement fragmentation themselves. This series moves > fragmentat

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-21 Thread Eric Blake
On 06/21/2016 04:23 AM, Stefan Hajnoczi wrote: > On Mon, Jun 20, 2016 at 05:39:24PM -0600, Eric Blake wrote: >> We have max_transfer documented in BlockLimits, but while we >> honor it during pwrite_zeroes, we were blindly ignoring it >> during pwritev and preadv, leading to multiple drivers having

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-21 Thread Kevin Wolf
Am 21.06.2016 um 12:23 hat Stefan Hajnoczi geschrieben: > On Mon, Jun 20, 2016 at 05:39:24PM -0600, Eric Blake wrote: > > We have max_transfer documented in BlockLimits, but while we > > honor it during pwrite_zeroes, we were blindly ignoring it > > during pwritev and preadv, leading to multiple dr

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-21 Thread Stefan Hajnoczi
On Mon, Jun 20, 2016 at 05:39:24PM -0600, Eric Blake wrote: > We have max_transfer documented in BlockLimits, but while we > honor it during pwrite_zeroes, we were blindly ignoring it > during pwritev and preadv, leading to multiple drivers having > to implement fragmentation themselves. This seri

Re: [Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-20 Thread Eric Blake
On 06/20/2016 05:39 PM, Eric Blake wrote: > We have max_transfer documented in BlockLimits, but while we > honor it during pwrite_zeroes, we were blindly ignoring it > during pwritev and preadv, leading to multiple drivers having > to implement fragmentation themselves. This series moves > fragmen

[Qemu-devel] [PATCH 0/5] Auto-fragment large transactions at the block layer

2016-06-20 Thread Eric Blake
We have max_transfer documented in BlockLimits, but while we honor it during pwrite_zeroes, we were blindly ignoring it during pwritev and preadv, leading to multiple drivers having to implement fragmentation themselves. This series moves fragmentation to the block layer, then fixes the NBD driver