> On 18 Apr 2025, at 21:55, Eric Blake wrote:
>
> On Fri, Apr 18, 2025 at 05:24:36PM +0300, Nir Soffer wrote:
>> Testing with qemu-nbd shows that computing a hash of an image via
>> qemu-nbd is 5-7 times faster with this change.
>>
>
>> +++ b/io/channel-socket.c
>> @@ -410,6 +410,19 @@ qio_ch
This should be changed also on the client side.
The libnbd part is here:
https://gitlab.com/nbdkit/libnbd/-/merge_requests/21
We may want to change also the nbd client code used in qemu-img. I can look at
this later.
> On 18 Apr 2025, at 17:24, Nir Soffer wrote:
>
> Testing with qemu-nbd sho
> On 18 Apr 2025, at 17:50, Philippe Mathieu-Daudé wrote:
>
> Hi Nir,
>
> On 18/4/25 16:24, Nir Soffer wrote:
>> Testing with qemu-nbd shows that computing a hash of an image via
>> qemu-nbd is 5-7 times faster with this change.
>> Tested with 2 qemu-nbd processes:
>> $ ./qemu-nbd-after -
On Fri, Apr 18, 2025 at 05:24:36PM +0300, Nir Soffer wrote:
> Testing with qemu-nbd shows that computing a hash of an image via
> qemu-nbd is 5-7 times faster with this change.
>
> +++ b/io/channel-socket.c
> @@ -410,6 +410,19 @@ qio_channel_socket_accept(QIOChannelSocket *ioc,
> }
> #endif
Hi Nir,
On 18/4/25 16:24, Nir Soffer wrote:
Testing with qemu-nbd shows that computing a hash of an image via
qemu-nbd is 5-7 times faster with this change.
Tested with 2 qemu-nbd processes:
$ ./qemu-nbd-after -r -t -e 0 -f raw -k /tmp/after.sock
/var/tmp/bench/data-10g.img &
$ ./qe
