* Christoph Hellwig [2011-08-24 13:46]:
> On Mon, Aug 22, 2011 at 11:46:00AM -0500, Ryan Harper wrote:
> > So, I believe this is how it's happening.
> >
> > we start accounting on a write which is turned into a multiwrite via
> > virtio_blk_handle_write() which calls virtio_submit_multiwrite().
>
Am 25.08.2011 08:25, schrieb Christoph Hellwig:
> changes since V2:
> - fix the crash with non read/write/flush commands in virtio_blk
>pointed out by Ryan
> - address all review comments by Kevin
> changes since V1:
> - rebase to apply against the current qemu.git tree
>
>
> Note that thi
changes since V2:
- fix the crash with non read/write/flush commands in virtio_blk
pointed out by Ryan
- address all review comments by Kevin
changes since V1:
- rebase to apply against the current qemu.git tree
Note that this still includes the (unchanged) patch 1 that Kevin already
applie
On Mon, Aug 22, 2011 at 11:46:00AM -0500, Ryan Harper wrote:
> So, I believe this is how it's happening.
>
> we start accounting on a write which is turned into a multiwrite via
> virtio_blk_handle_write() which calls virtio_submit_multiwrite().
>
> Then when the multiwrite completes, we invoke v
* Christoph Hellwig [2011-08-22 10:37]:
> On Mon, Aug 22, 2011 at 10:29:11AM -0500, Ryan Harper wrote:
> > (gdb) frame 0
> > #0 0x004200c1 in bdrv_acct_done (bs=0x12310b0, cookie=0x1c68810)
> > at /root/git/qemu/block_int.h:239 239 bs->nr_bytes[cookie->type] +=
> > cookie->bytes
Am 22.08.2011 00:25, schrieb Christoph Hellwig:
> changes since V1:
> - rebase to apply against the current qemu.git tree
Applied patch 1, commented on patch 2. The third one looks good, but
doesn't apply without the other one.
Kevin
On Mon, Aug 22, 2011 at 10:29:11AM -0500, Ryan Harper wrote:
> (gdb) frame 0
> #0 0x004200c1 in bdrv_acct_done (bs=0x12310b0, cookie=0x1c68810) at
> /root/git/qemu/block_int.h:239 239 bs->nr_bytes[cookie->type] +=
> cookie->bytes;
> (gdb) p *cookie
> $3 = {bytes = 720575897597378
* Christoph Hellwig [2011-08-22 10:16]:
> On Mon, Aug 22, 2011 at 09:59:16AM -0500, Ryan Harper wrote:
> > * Christoph Hellwig [2011-08-21 17:27]:
> > > changes since V1:
> > > - rebase to apply against the current qemu.git tree
> >
> >
> > Testing on tip + this series with:
> >
> > ./configu
On Mon, Aug 22, 2011 at 09:59:16AM -0500, Ryan Harper wrote:
> * Christoph Hellwig [2011-08-21 17:27]:
> > changes since V1:
> > - rebase to apply against the current qemu.git tree
>
>
> Testing on tip + this series with:
>
> ./configure --enable-debug --enable-kvm --enable-io-thread
> --targ
* Christoph Hellwig [2011-08-21 17:27]:
> changes since V1:
> - rebase to apply against the current qemu.git tree
Testing on tip + this series with:
./configure --enable-debug --enable-kvm --enable-io-thread
--target-list=x86_64-softmmu
x86_64-softmmu/qemu-system-x86_64 --enable-kvm -L pc-bi
On Mon, Aug 22, 2011 at 12:25:47AM +0200, Christoph Hellwig wrote:
> changes since V1:
> - rebase to apply against the current qemu.git tree
Reviewed-by: Stefan Hajnoczi
changes since V1:
- rebase to apply against the current qemu.git tree
On Fri, Aug 12, 2011 at 06:50:57AM +0100, Stefan Hajnoczi wrote:
> I do see the drawbacks of leaving accounting in block.c on every
> request. For example, we'll fetch the timestamp for internal requests
> as well as external requests from hardware emulation. Due to memory
> mapping and bounce bu
On Fri, Aug 12, 2011 at 6:14 AM, Stefan Hajnoczi wrote:
> This change requires that callers manage the accounting cookie. I
> think this belongs in block.c to make the life of callers easier.
>
> Today block.c doesn't track requests and pretty much lets the
> BlockDriver control the BlockDriverAI
This change requires that callers manage the accounting cookie. I
think this belongs in block.c to make the life of callers easier.
Today block.c doesn't track requests and pretty much lets the
BlockDriver control the BlockDriverAIOCB. But the request metadata
(timestamp, operation type, number
16 matches
Mail list logo
