On Wed, Nov 11, 2026 at 11:25 AM shihao zhong <[email protected]> wrote: > > Hi Xuneng, > > Thanks for reviewing this patch. > > > The diganose of the problem seems good to me. The fix is small and > > helps to mitigate the stall. > > Yes, so I think we can start from the existing patch and get it backpatched.
Make sense. I'll look into this one. > > A more ideal fix seems to be more > > event-driven -- let the late pinners cancel themselves. > > If I understand correctly, you are referring to changing the PINBuffer logic > where the backend sees BM_PIN_COUNT_WAITER and cancels itself? > > I am not sure if that is the best approach as PinBuffer is in the hot path. Honestly, I don't have a concrete idea of how to do this for now. Just a natural thought of keeping the stall causers away instead of asking them to leave repeatedly. -- Regards, Xuneng Zhou HighGo Software Co., Ltd.
