On 20.02.20 08:21, Vladimir Sementsov-Ogievskiy wrote:
> 17.02.2020 16:38, Max Reitz wrote:
>> On 27.11.19 19:08, Vladimir Sementsov-Ogievskiy wrote:
[...]
>>> + if (!block_copy_wait_one(s, start, bytes)) {
>>> + /* No dirty bits and nothing to wait: the whole request
>>> is don
17.02.2020 16:38, Max Reitz wrote:
On 27.11.19 19:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, it will
disturb other parallel block_copy requests for no reason.
Let's i
On 27.11.19 19:08, Vladimir Sementsov-Ogievskiy wrote:
> Currently, block_copy operation lock the whole requested region. But
> there is no reason to lock clusters, which are already copied, it will
> disturb other parallel block_copy requests for no reason.
>
> Let's instead do the following:
>
On 30/01/2020 20:09, Vladimir Sementsov-Ogievskiy wrote:
30.01.2020 19:24, Andrey Shinkevich wrote:
On 30/01/2020 16:45, Vladimir Sementsov-Ogievskiy wrote:
29.01.2020 23:05, Andrey Shinkevich wrote:
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operati
30.01.2020 19:24, Andrey Shinkevich wrote:
On 30/01/2020 16:45, Vladimir Sementsov-Ogievskiy wrote:
29.01.2020 23:05, Andrey Shinkevich wrote:
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to
On 30/01/2020 16:45, Vladimir Sementsov-Ogievskiy wrote:
29.01.2020 23:05, Andrey Shinkevich wrote:
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, i
30.01.2020 18:53, Andrey Shinkevich wrote:
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, it will
disturb other parallel block_copy requests for no reas
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, it will
disturb other parallel block_copy requests for no reason.
Let's instead do the following:
Lock
29.01.2020 23:05, Andrey Shinkevich wrote:
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, it will
disturb other parallel block_copy requests for no reas
On 27/11/2019 21:08, Vladimir Sementsov-Ogievskiy wrote:
> Currently, block_copy operation lock the whole requested region. But
> there is no reason to lock clusters, which are already copied, it will
> disturb other parallel block_copy requests for no reason.
>
> Let's instead do the following:
Currently, block_copy operation lock the whole requested region. But
there is no reason to lock clusters, which are already copied, it will
disturb other parallel block_copy requests for no reason.
Let's instead do the following:
Lock only sub-region, which we are going to operate on. Then, after
11 matches
Mail list logo
