On Mon, Jan 10, 2022 at 7:02 AM Peter Zijlstra wrote:
> Can we start by describing the actual problem?
Of course. Sorry, I didn't realize Jaegeuk was going to move so
quickly with this patch :)
We have a few thousand traces from internal Android devices where
large numbers of threads throughout
On Mon, Jan 10, 2022 at 8:15 PM Waiman Long wrote:
> That is not how rwsem works. A reader which fails to get the lock
> because it is write-locked will remove its reader count before going to
> sleep. So the reader count will be zero eventually. Of course, there is
> a short period of time where
On Wed, Jan 12, 2022 at 6:06 AM Peter Zijlstra wrote:
> *urgh*... so you're making the worst case less likely but fundamentally
> you don't change anything.
>
> If one of those low prio threads manages to block while holding
> cp_rwsem your checkpoint thread will still block for a very long time.
Hi Linus,
On Tue, Mar 22, 2022 at 10:50 AM Linus Torvalds
wrote:
>
> Even when people get the semantics and memory ordering right (which is
> not always the case, but at least the f2fs code uses real lock
> primitives - just oddly - and should thus be ok), it invariably tends
> to be a sign of so
