2 Feb
2023
2 Feb
'23
3:56 p.m.
On Thu Feb 2 15:45:11 2023 +0000, Jinoh Kang wrote:
This array is intended to be accessed atomically by multiple threads, but a substantial number of elements reside in a cache line (assuming 64 byte cache line size). This results in false sharing, which may impact performance compared to purely threaded heaps. A possible solution is to have an array of slots per each affinity. This will also reduce the frequency of affinity groups running out.
-- https://gitlab.winehq.org/wine/wine/-/merge_requests/1628#note_22841