From 87750d1db4bc73933e92d862ff73d10d06ff4f5d Mon Sep 17 00:00:00 2001 From: Sebastien Dugue Date: Wed, 29 Jul 2009 11:45:55 -0700 Subject: [PATCH] Use mmap(MAP_ANONYMOUS) to allocate queue buffers Internal buffers for QPs, CQs, SRQs etc. are allocated with mlx4_alloc_buf(), which rounds the buffer's size to the page size and then allocates page aligned memory using posix_memalign(). However, this allocation is quite wasteful on architectures using 64K pages (ia64 for example) because we then hit glibc's MMAP_THRESHOLD malloc parameter and chunks are allocated using mmap. Thus we end up allocating: (requested size rounded to the page size) + (page size) + (malloc overhead) rounded internally to the page size. So for example, if we request a buffer of page_size bytes, we end up consuming 3 pages. In short, for each buffer we allocate, there is an overhead of 2 pages. This is quite visible on large clusters where the number of QPs can reach several thousands. This patch replaces the call to posix_memalign() in mlx4_alloc_buf() with a direct call to mmap(). Signed-off-by: Sebastien Dugue Signed-off-by: Roland Dreier --- src/buf.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/src/buf.c b/src/buf.c index 0e5f9b6..bbaff12 100644 --- a/src/buf.c +++ b/src/buf.c @@ -61,16 +61,15 @@ int mlx4_alloc_buf(struct mlx4_buf *buf, size_t size, int page_size) { int ret; - ret = posix_memalign(&buf->buf, page_size, align(size, page_size)); - if (ret) - return ret; + buf->length = align(size, page_size); + buf->buf = mmap(NULL, buf->length, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buf->buf == MAP_FAILED) + return errno; ret = ibv_dontfork_range(buf->buf, size); if (ret) - free(buf->buf); - - if (!ret) - buf->length = size; + munmap(buf->buf, buf->length); return ret; } @@ -78,5 +77,5 @@ int mlx4_alloc_buf(struct mlx4_buf *buf, size_t size, int page_size) void mlx4_free_buf(struct mlx4_buf *buf) { ibv_dofork_range(buf->buf, buf->length); - free(buf->buf); + munmap(buf->buf, buf->length); } -- 2.46.0