Hi Liu,
On Wed, Mar 22, 2017 at 1:40 AM, Liu Bo wrote:
> On Sun, Mar 19, 2017 at 07:18:59PM +0200, Alex Lyakas wrote:
>> We have a commit_root_sem, which is a read-write semaphore that protects the
>> commit roots.
>> But it is also used to protect the list of caching block
On Sun, Mar 19, 2017 at 07:18:59PM +0200, Alex Lyakas wrote:
> We have a commit_root_sem, which is a read-write semaphore that protects the
> commit roots.
> But it is also used to protect the list of caching block groups.
>
> As a result, while doing "slow" caching, the following issue is seen:
This sounds reasonable to me, I'll look at it more when I'm on the ground and
can look at the code and see for sure. Thanks,
Josef
Sent from my iPhone
> On Mar 19, 2017, at 1:19 PM, Alex Lyakas wrote:
>
> We have a commit_root_sem, which is a read-write semaphore
We have a commit_root_sem, which is a read-write semaphore that protects the
commit roots.
But it is also used to protect the list of caching block groups.
As a result, while doing "slow" caching, the following issue is seen:
Some of the caching threads are scanning the extent tree with