diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2016-04-23 06:05:01 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2016-04-23 06:05:15 -0700 |
| commit | 2bc983b78c215765979a29a2e98b0cc01791c2d1 (patch) | |
| tree | dd39b724f90f6a70a28ee4fd06d1edf8aae743f2 | |
| parent | 00277a3f81bf023d4562da485f62efe5b5b30388 (diff) | |
| download | glibc-2bc983b78c215765979a29a2e98b0cc01791c2d1.tar glibc-2bc983b78c215765979a29a2e98b0cc01791c2d1.tar.gz glibc-2bc983b78c215765979a29a2e98b0cc01791c2d1.tar.bz2 glibc-2bc983b78c215765979a29a2e98b0cc01791c2d1.zip | |
Reduce number of mmap calls from __libc_memalign in ld.so
__libc_memalign in ld.so allocates one page at a time and tries to
optimize consecutive __libc_memalign calls by hoping that the next
mmap is after the current memory allocation.
However, the kernel hands out mmap addresses in top-down order, so
this optimization in practice never happens, with the result that we
have more mmap calls and waste a bunch of space for each __libc_memalign.
This change makes __libc_memalign to mmap one page extra. Worst case,
the kernel never puts a backing page behind it, but best case it allows
__libc_memalign to operate much much better. For elf/tst-align --direct,
it reduces number of mmap calls from 12 to 9.
* elf/dl-minimal.c (__libc_memalign): Mmap one extra page.
| -rw-r--r-- | ChangeLog | 4 | ||||
| -rw-r--r-- | elf/dl-minimal.c | 12 |
2 files changed, 9 insertions, 7 deletions
@@ -1,3 +1,7 @@ +2016-04-23 H.J. Lu <hongjiu.lu@intel.com> + + * elf/dl-minimal.c (__libc_memalign): Mmap one extra page. + 2016-04-23 Mike Frysinger <vapier@gentoo.org> * locale/programs/ld-time.c (time_finish): Set week_1stweek to 7 diff --git a/elf/dl-minimal.c b/elf/dl-minimal.c index 762e65b4d0..c8a8f8dc93 100644 --- a/elf/dl-minimal.c +++ b/elf/dl-minimal.c @@ -66,15 +66,13 @@ __libc_memalign (size_t align, size_t n) if (alloc_ptr + n >= alloc_end || n >= -(uintptr_t) alloc_ptr) { - /* Insufficient space left; allocate another page. */ + /* Insufficient space left; allocate another page plus one extra + page to reduce number of mmap calls. */ caddr_t page; size_t nup = (n + GLRO(dl_pagesize) - 1) & ~(GLRO(dl_pagesize) - 1); - if (__glibc_unlikely (nup == 0)) - { - if (n) - return NULL; - nup = GLRO(dl_pagesize); - } + if (__glibc_unlikely (nup == 0 && n != 0)) + return NULL; + nup += GLRO(dl_pagesize); page = __mmap (0, nup, PROT_READ|PROT_WRITE, MAP_ANON|MAP_PRIVATE, -1, 0); if (page == MAP_FAILED) |