This is the holy grail for lightweight synchronization of millions of small operations with heavy infrequent operations like garbage collection:https://docs.microsoft.com/en-us/windows/desktop/api/processthreadsapi/nf-processthreadsapi-flushprocesswritebuffers …
-
-
The Protocol on Intel x86 platform (QPI subset used on the rings) does take care of most of this, but it would be nice to have the OS informing this subsystem better. That could become in inform write combining.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Ah, nice! Could be used for non-GC epoch based reclamation too I guess I.e. instead of calling "delete" on objects from a MT queue, you attach it to the current epoch, then 2 epochs later they get deleted (this flush = per-thread "current epoch" index does not need to be atomic).
-
Probably only worth it if you have a ton of things that use the same epoch reclaimer system, which may in practice mean it's only nice for GC?
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.