Instead of iterating over object->memq to free pages, use a callback in VM_RADIX_PCTRIE_RECLAIM_CALLBACK to do it.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG FreeBSD src repository
- Lint
Lint Not Applicable - Unit
Tests Not Applicable
Event Timeline
Comment Actions
So the point here is to move us away from needing memq at all, correct? Taking this patch by itself, I am not seeing a performance benefit (different from your other recent uses of PCTRIE_RECLAIM_CALLBACK).
I'm not against this, I just want to make sure I understand.
sys/vm/vm_object.c | ||
---|---|---|
880 | Nitpick: I'd suggest choosing a name that more closely associates this with vm_object_terminate_pages, or at least doesn't read as very generic, because this routine can only be used from vm_object_terminate_pages, as it obviously doesn't do the normal cleanup. E.g. it reads as generic as vm_object_page_remove, but actually is specialized. |
Comment Actions
@alc suggested this, so I did it. Now, asked if he'd like to see memq replaced by pctrie iterators, he seems unenthusiastic.