Il 22/02/2013 11:59, Juan Quintela ha scritto:
> Paolo Bonzini wrote:
>> Some state is shared between the block migration code and its AIO
>> callbacks. Once block migration will run outside the iothread,
>> the block migration code and the AIO callbacks will be able to
>> run concurrently. Prot
Paolo Bonzini wrote:
> Some state is shared between the block migration code and its AIO
> callbacks. Once block migration will run outside the iothread,
> the block migration code and the AIO callbacks will be able to
> run concurrently. Protect the critical sections with a separate
> lock. Do
Il 18/02/2013 15:33, Orit Wasserman ha scritto:
>> @@ -199,6 +222,7 @@ static void blk_mig_read_cb(void *opaque, int ret)
>>
>> block_mig_state.submitted--;
>> block_mig_state.read_done++;
>> +blk_mig_unlock();
>> assert(block_mig_state.submitted >= 0);
> Shouldn't the assert b
On 02/15/2013 07:46 PM, Paolo Bonzini wrote:
> Some state is shared between the block migration code and its AIO
> callbacks. Once block migration will run outside the iothread,
> the block migration code and the AIO callbacks will be able to
> run concurrently. Protect the critical sections with
Some state is shared between the block migration code and its AIO
callbacks. Once block migration will run outside the iothread,
the block migration code and the AIO callbacks will be able to
run concurrently. Protect the critical sections with a separate
lock. Do the same for completed_sectors,
