Lines Matching refs:huge

22   - Mark partially purged arena chunks as non-huge-page.  This improves
23     interaction with Linux's transparent huge page functionality.  (@jasone)
95   - Fix opt_zero-triggered in-place huge reallocation zeroing.  (@jasone)
188   - Attempt mmap-based in-place huge reallocation.  This can dramatically speed
189     up incremental huge reallocation.  (@jasone)
234   - Fix xallocx(..., MALLOCX_ZERO) to zero trailing bytes of huge allocations
279   - Fix chunk purge hook calls for in-place huge shrinking reallocation to
344   - Refactor huge allocation to be managed by arenas, so that arenas now
348     + The "stats.arenas.<i>.huge.allocated", "stats.arenas.<i>.huge.nmalloc",
349       "stats.arenas.<i>.huge.ndalloc", and "stats.arenas.<i>.huge.nrequests"
350       mallctls provide high level per arena huge allocation statistics.
393     reduces the cost of repeated huge allocation/deallocation, because it
408   - Implement in-place huge allocation growing and shrinking.
411     levels.  This resolves what was a concurrency bottleneck for per arena huge
413     which arenas own which huge allocations.
441   - Remove the "stats.huge.allocated", "stats.huge.nmalloc", and
442     "stats.huge.ndalloc" mallctls.
482   - Use dss allocation precedence for huge allocations as well as small/large
498   - Fix junk filling for mremap(2)-based huge reallocation.  This is only
548   - Fix huge deallocation to junk fill when munmap is disabled.
586     typically triggered by multiple threads concurrently deallocating huge
857   - Fix aligned huge reallocation (affected allocm()).
868   - Use Linux's mremap(2) for huge object reallocation when possible.