From faeedbcefd40bfdf314e048c425b6d9208896d90 Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Sat, 8 Apr 2023 10:38:09 +1200 Subject: Introduce PG_IO_ALIGN_SIZE and align all I/O buffers. In order to have the option to use O_DIRECT/FILE_FLAG_NO_BUFFERING in a later commit, we need the addresses of user space buffers to be well aligned. The exact requirements vary by OS and file system (typically sectors and/or memory pages). The address alignment size is set to 4096, which is enough for currently known systems: it matches modern sectors and common memory page size. There is no standard governing O_DIRECT's requirements so we might eventually have to reconsider this with more information from the field or future systems. Aligning I/O buffers on memory pages is also known to improve regular buffered I/O performance. Three classes of I/O buffers for regular data pages are adjusted: (1) Heap buffers are now allocated with the new palloc_aligned() or MemoryContextAllocAligned() functions introduced by commit 439f6175. (2) Stack buffers now use a new struct PGIOAlignedBlock to respect PG_IO_ALIGN_SIZE, if possible with this compiler. (3) The buffer pool is also aligned in shared memory. WAL buffers were already aligned on XLOG_BLCKSZ. It's possible for XLOG_BLCKSZ to be configured smaller than PG_IO_ALIGNED_SIZE and thus for O_DIRECT WAL writes to fail to be well aligned, but that's a pre-existing condition and will be addressed by a later commit. BufFiles are not yet addressed (there's no current plan to use O_DIRECT for those, but they could potentially get some incidental speedup even in plain buffered I/O operations through better alignment). If we can't align stack objects suitably using the compiler extensions we know about, we disable the use of O_DIRECT by setting PG_O_DIRECT to 0. This avoids the need to consider systems that have O_DIRECT but can't align stack objects the way we want; such systems could in theory be supported with more work but we don't currently know of any such machines, so it's easier to pretend there is no O_DIRECT support instead. That's an existing and tested class of system. Add assertions that all buffers passed into smgrread(), smgrwrite() and smgrextend() are correctly aligned, unless PG_O_DIRECT is 0 (= stack alignment tricks may be unavailable) or the block size has been set too small to allow arrays of buffers to be all aligned. Author: Thomas Munro Author: Andres Freund Reviewed-by: Justin Pryzby Discussion: https://postgr.es/m/CA+hUKGK1X532hYqJ_MzFWt0n1zt8trz980D79WbjwnT-yYLZpg@mail.gmail.com --- src/backend/access/gist/gistbuild.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'src/backend/access/gist/gistbuild.c') diff --git a/src/backend/access/gist/gistbuild.c b/src/backend/access/gist/gistbuild.c index d2f8da5b026..5e0c1447f92 100644 --- a/src/backend/access/gist/gistbuild.c +++ b/src/backend/access/gist/gistbuild.c @@ -415,7 +415,7 @@ gist_indexsortbuild(GISTBuildState *state) * Write an empty page as a placeholder for the root page. It will be * replaced with the real root page at the end. */ - page = palloc0(BLCKSZ); + page = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO); smgrextend(RelationGetSmgr(state->indexrel), MAIN_FORKNUM, GIST_ROOT_BLKNO, page, true); state->pages_allocated++; @@ -509,7 +509,8 @@ gist_indexsortbuild_levelstate_add(GISTBuildState *state, levelstate->current_page++; if (levelstate->pages[levelstate->current_page] == NULL) - levelstate->pages[levelstate->current_page] = palloc(BLCKSZ); + levelstate->pages[levelstate->current_page] = + palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0); newPage = levelstate->pages[levelstate->current_page]; gistinitpage(newPage, old_page_flags); @@ -579,7 +580,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state, /* Create page and copy data */ data = (char *) (dist->list); - target = palloc0(BLCKSZ); + target = palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, MCXT_ALLOC_ZERO); gistinitpage(target, isleaf ? F_LEAF : 0); for (int i = 0; i < dist->block.num; i++) { @@ -630,7 +631,7 @@ gist_indexsortbuild_levelstate_flush(GISTBuildState *state, if (parent == NULL) { parent = palloc0(sizeof(GistSortedBuildLevelState)); - parent->pages[0] = (Page) palloc(BLCKSZ); + parent->pages[0] = (Page) palloc_aligned(BLCKSZ, PG_IO_ALIGN_SIZE, 0); parent->parent = NULL; gistinitpage(parent->pages[0], 0); -- cgit v1.2.3