[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
GC: cons sweeping and cons block size
|
From: |
Jonathan Yavner |
|
Subject: |
GC: cons sweeping and cons block size |
|
Date: |
Tue, 3 Jul 2007 16:22:09 -0400 |
|
User-agent: |
KMail/1.9.5 |
> malloc()'ing 1K-aligned 1K-block is cheaper than 4K-aligned 4K-block,
> and the latter allocation probably tends to a higher heap
> fragmentation.
On some systems, large malloc blocks go directly to MMAP_ANONYMOUS and
so fragmentation worries are eliminated. I don't see any support for
direct use of mmap() in gmalloc.c, though. Should we consider it?
OS-specific code is needed -- Windoze calls it VirtualAlloc(), while
MacOS calls it vm_alloc().