diff options
Diffstat (limited to 'src/backend/storage/aio')
| -rw-r--r-- | src/backend/storage/aio/aio.c | 27 | ||||
| -rw-r--r-- | src/backend/storage/aio/aio_callback.c | 7 | ||||
| -rw-r--r-- | src/backend/storage/aio/method_io_uring.c | 218 | ||||
| -rw-r--r-- | src/backend/storage/aio/method_worker.c | 7 |
4 files changed, 243 insertions, 16 deletions
diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c index c64d815ebd1..3643f27ad6e 100644 --- a/src/backend/storage/aio/aio.c +++ b/src/backend/storage/aio/aio.c @@ -556,6 +556,13 @@ bool pgaio_io_was_recycled(PgAioHandle *ioh, uint64 ref_generation, PgAioHandleState *state) { *state = ioh->state; + + /* + * Ensure that we don't see an earlier state of the handle than ioh->state + * due to compiler or CPU reordering. This protects both ->generation as + * directly used here, and other fields in the handle accessed in the + * caller if the handle was not reused. + */ pg_read_barrier(); return ioh->generation != ref_generation; @@ -752,7 +759,7 @@ pgaio_io_wait_for_free(void) { int reclaimed = 0; - pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %d in-flight, %d idle IOs", + pgaio_debug(DEBUG2, "waiting for free IO with %d pending, %u in-flight, %u idle IOs", pgaio_my_backend->num_staged_ios, dclist_count(&pgaio_my_backend->in_flight_ios), dclist_count(&pgaio_my_backend->idle_ios)); @@ -773,7 +780,12 @@ pgaio_io_wait_for_free(void) * Note that no interrupts are processed between the state check * and the call to reclaim - that's important as otherwise an * interrupt could have already reclaimed the handle. + * + * Need to ensure that there's no reordering, in the more common + * paths, where we wait for IO, that's done by + * pgaio_io_was_recycled(). */ + pg_read_barrier(); pgaio_io_reclaim(ioh); reclaimed++; } @@ -797,7 +809,7 @@ pgaio_io_wait_for_free(void) if (dclist_count(&pgaio_my_backend->in_flight_ios) == 0) ereport(ERROR, errmsg_internal("no free IOs despite no in-flight IOs"), - errdetail_internal("%d pending, %d in-flight, %d idle IOs", + errdetail_internal("%d pending, %u in-flight, %u idle IOs", pgaio_my_backend->num_staged_ios, dclist_count(&pgaio_my_backend->in_flight_ios), dclist_count(&pgaio_my_backend->idle_ios))); @@ -828,7 +840,7 @@ pgaio_io_wait_for_free(void) case PGAIO_HS_COMPLETED_IO: case PGAIO_HS_SUBMITTED: pgaio_debug_io(DEBUG2, ioh, - "waiting for free io with %d in flight", + "waiting for free io with %u in flight", dclist_count(&pgaio_my_backend->in_flight_ios)); /* @@ -852,7 +864,12 @@ pgaio_io_wait_for_free(void) * check and the call to reclaim - that's important as * otherwise an interrupt could have already reclaimed the * handle. + * + * Need to ensure that there's no reordering, in the more + * common paths, where we wait for IO, that's done by + * pgaio_io_was_recycled(). */ + pg_read_barrier(); pgaio_io_reclaim(ioh); break; } @@ -1252,7 +1269,7 @@ pgaio_closing_fd(int fd) break; pgaio_debug_io(DEBUG2, ioh, - "waiting for IO before FD %d gets closed, %d in-flight IOs", + "waiting for IO before FD %d gets closed, %u in-flight IOs", fd, dclist_count(&pgaio_my_backend->in_flight_ios)); /* see comment in pgaio_io_wait_for_free() about raciness */ @@ -1288,7 +1305,7 @@ pgaio_shutdown(int code, Datum arg) uint64 generation = ioh->generation; pgaio_debug_io(DEBUG2, ioh, - "waiting for IO to complete during shutdown, %d in-flight IOs", + "waiting for IO to complete during shutdown, %u in-flight IOs", dclist_count(&pgaio_my_backend->in_flight_ios)); /* see comment in pgaio_io_wait_for_free() about raciness */ diff --git a/src/backend/storage/aio/aio_callback.c b/src/backend/storage/aio/aio_callback.c index 0ad9795bb7e..03c9bba0802 100644 --- a/src/backend/storage/aio/aio_callback.c +++ b/src/backend/storage/aio/aio_callback.c @@ -256,6 +256,9 @@ pgaio_io_call_complete_shared(PgAioHandle *ioh) pgaio_result_status_string(result.status), result.id, result.error_data, result.result); result = ce->cb->complete_shared(ioh, result, cb_data); + + /* the callback should never transition to unknown */ + Assert(result.status != PGAIO_RS_UNKNOWN); } ioh->distilled_result = result; @@ -290,6 +293,7 @@ pgaio_io_call_complete_local(PgAioHandle *ioh) /* start with distilled result from shared callback */ result = ioh->distilled_result; + Assert(result.status != PGAIO_RS_UNKNOWN); for (int i = ioh->num_callbacks; i > 0; i--) { @@ -306,6 +310,9 @@ pgaio_io_call_complete_local(PgAioHandle *ioh) pgaio_result_status_string(result.status), result.id, result.error_data, result.result); result = ce->cb->complete_local(ioh, result, cb_data); + + /* the callback should never transition to unknown */ + Assert(result.status != PGAIO_RS_UNKNOWN); } /* diff --git a/src/backend/storage/aio/method_io_uring.c b/src/backend/storage/aio/method_io_uring.c index c719ba2727a..0a8c054162f 100644 --- a/src/backend/storage/aio/method_io_uring.c +++ b/src/backend/storage/aio/method_io_uring.c @@ -29,6 +29,9 @@ #ifdef IOMETHOD_IO_URING_ENABLED +#include <sys/mman.h> +#include <unistd.h> + #include <liburing.h> #include "miscadmin.h" @@ -94,12 +97,32 @@ PgAioUringContext struct io_uring io_uring_ring; } PgAioUringContext; +/* + * Information about the capabilities that io_uring has. + * + * Depending on liburing and kernel version different features are + * supported. At least for the kernel a kernel version check does not suffice + * as various vendors do backport features to older kernels :(. + */ +typedef struct PgAioUringCaps +{ + bool checked; + /* -1 if io_uring_queue_init_mem() is unsupported */ + int mem_init_size; +} PgAioUringCaps; + + /* PgAioUringContexts for all backends */ static PgAioUringContext *pgaio_uring_contexts; /* the current backend's context */ static PgAioUringContext *pgaio_my_uring_context; +static PgAioUringCaps pgaio_uring_caps = +{ + .checked = false, + .mem_init_size = -1, +}; static uint32 pgaio_uring_procs(void) @@ -111,30 +134,184 @@ pgaio_uring_procs(void) return MaxBackends + NUM_AUXILIARY_PROCS - MAX_IO_WORKERS; } -static Size +/* + * Initializes pgaio_uring_caps, unless that's already done. + */ +static void +pgaio_uring_check_capabilities(void) +{ + if (pgaio_uring_caps.checked) + return; + + /* + * By default io_uring creates a shared memory mapping for each io_uring + * instance, leading to a large number of memory mappings. Unfortunately a + * large number of memory mappings slows things down, backend exit is + * particularly affected. To address that, newer kernels (6.5) support + * using user-provided memory for the memory, by putting the relevant + * memory into shared memory we don't need any additional mappings. + * + * To know whether this is supported, we unfortunately need to probe the + * kernel by trying to create a ring with userspace-provided memory. This + * also has a secondary benefit: We can determine precisely how much + * memory we need for each io_uring instance. + */ +#if defined(HAVE_LIBURING_QUEUE_INIT_MEM) && defined(IORING_SETUP_NO_MMAP) + { + struct io_uring test_ring; + size_t ring_size; + void *ring_ptr; + struct io_uring_params p = {0}; + int ret; + + /* + * Liburing does not yet provide an API to query how much memory a + * ring will need. So we over-estimate it here. As the memory is freed + * just below that's small temporary waste of memory. + * + * 1MB is more than enough for rings within io_max_concurrency's + * range. + */ + ring_size = 1024 * 1024; + + /* + * Hard to believe a system exists where 1MB would not be a multiple + * of the page size. But it's cheap to ensure... + */ + ring_size -= ring_size % sysconf(_SC_PAGESIZE); + + ring_ptr = mmap(NULL, ring_size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (ring_ptr == MAP_FAILED) + elog(ERROR, + "mmap(%zu) to determine io_uring_queue_init_mem() support failed: %m", + ring_size); + + ret = io_uring_queue_init_mem(io_max_concurrency, &test_ring, &p, ring_ptr, ring_size); + if (ret > 0) + { + pgaio_uring_caps.mem_init_size = ret; + + elog(DEBUG1, + "can use combined memory mapping for io_uring, each ring needs %d bytes", + ret); + + /* clean up the created ring, it was just for a test */ + io_uring_queue_exit(&test_ring); + } + else + { + /* + * There are different reasons for ring creation to fail, but it's + * ok to treat that just as io_uring_queue_init_mem() not being + * supported. We'll report a more detailed error in + * pgaio_uring_shmem_init(). + */ + errno = -ret; + elog(DEBUG1, + "cannot use combined memory mapping for io_uring, ring creation failed: %m"); + + } + + if (munmap(ring_ptr, ring_size) != 0) + elog(ERROR, "munmap() failed: %m"); + } +#else + { + elog(DEBUG1, + "can't use combined memory mapping for io_uring, kernel or liburing too old"); + } +#endif + + pgaio_uring_caps.checked = true; +} + +/* + * Memory for all PgAioUringContext instances + */ +static size_t pgaio_uring_context_shmem_size(void) { return mul_size(pgaio_uring_procs(), sizeof(PgAioUringContext)); } +/* + * Memory for the combined memory used by io_uring instances. Returns 0 if + * that is not supported by kernel/liburing. + */ +static size_t +pgaio_uring_ring_shmem_size(void) +{ + size_t sz = 0; + + if (pgaio_uring_caps.mem_init_size > 0) + { + /* + * Memory for rings needs to be allocated to the page boundary, + * reserve space. Luckily it does not need to be aligned to hugepage + * boundaries, even if huge pages are used. + */ + sz = add_size(sz, sysconf(_SC_PAGESIZE)); + sz = add_size(sz, mul_size(pgaio_uring_procs(), + pgaio_uring_caps.mem_init_size)); + } + + return sz; +} + static size_t pgaio_uring_shmem_size(void) { - return pgaio_uring_context_shmem_size(); + size_t sz; + + /* + * Kernel and liburing support for various features influences how much + * shmem we need, perform the necessary checks. + */ + pgaio_uring_check_capabilities(); + + sz = pgaio_uring_context_shmem_size(); + sz = add_size(sz, pgaio_uring_ring_shmem_size()); + + return sz; } static void pgaio_uring_shmem_init(bool first_time) { - int TotalProcs = MaxBackends + NUM_AUXILIARY_PROCS - MAX_IO_WORKERS; + int TotalProcs = pgaio_uring_procs(); bool found; + char *shmem; + size_t ring_mem_remain = 0; + char *ring_mem_next = 0; - pgaio_uring_contexts = (PgAioUringContext *) - ShmemInitStruct("AioUring", pgaio_uring_shmem_size(), &found); - + /* + * We allocate memory for all PgAioUringContext instances and, if + * supported, the memory required for each of the io_uring instances, in + * one ShmemInitStruct(). + */ + shmem = ShmemInitStruct("AioUringContext", pgaio_uring_shmem_size(), &found); if (found) return; + pgaio_uring_contexts = (PgAioUringContext *) shmem; + shmem += pgaio_uring_context_shmem_size(); + + /* if supported, handle memory alignment / sizing for io_uring memory */ + if (pgaio_uring_caps.mem_init_size > 0) + { + ring_mem_remain = pgaio_uring_ring_shmem_size(); + ring_mem_next = (char *) shmem; + + /* align to page boundary, see also pgaio_uring_ring_shmem_size() */ + ring_mem_next = (char *) TYPEALIGN(sysconf(_SC_PAGESIZE), ring_mem_next); + + /* account for alignment */ + ring_mem_remain -= ring_mem_next - shmem; + shmem += ring_mem_next - shmem; + + shmem += ring_mem_remain; + } + for (int contextno = 0; contextno < TotalProcs; contextno++) { PgAioUringContext *context = &pgaio_uring_contexts[contextno]; @@ -158,7 +335,28 @@ pgaio_uring_shmem_init(bool first_time) * be worth using that - also need to evaluate if that causes * noticeable additional contention? */ - ret = io_uring_queue_init(io_max_concurrency, &context->io_uring_ring, 0); + + /* + * If supported (c.f. pgaio_uring_check_capabilities()), create ring + * with its data in shared memory. Otherwise fall back io_uring + * creating a memory mapping for each ring. + */ +#if defined(HAVE_LIBURING_QUEUE_INIT_MEM) && defined(IORING_SETUP_NO_MMAP) + if (pgaio_uring_caps.mem_init_size > 0) + { + struct io_uring_params p = {0}; + + ret = io_uring_queue_init_mem(io_max_concurrency, &context->io_uring_ring, &p, ring_mem_next, ring_mem_remain); + + ring_mem_remain -= ret; + ring_mem_next += ret; + } + else +#endif + { + ret = io_uring_queue_init(io_max_concurrency, &context->io_uring_ring, 0); + } + if (ret < 0) { char *hint = NULL; @@ -400,9 +598,9 @@ pgaio_uring_wait_one(PgAioHandle *ioh, uint64 ref_generation) while (true) { pgaio_debug_io(DEBUG3, ioh, - "wait_one io_gen: %llu, ref_gen: %llu, cycle %d", - (long long unsigned) ioh->generation, - (long long unsigned) ref_generation, + "wait_one io_gen: %" PRIu64 ", ref_gen: %" PRIu64 ", cycle %d", + ioh->generation, + ref_generation, waited); if (pgaio_io_was_recycled(ioh, ref_generation, &state) || diff --git a/src/backend/storage/aio/method_worker.c b/src/backend/storage/aio/method_worker.c index 743cccc2acd..36be179678d 100644 --- a/src/backend/storage/aio/method_worker.c +++ b/src/backend/storage/aio/method_worker.c @@ -461,7 +461,12 @@ IoWorkerMain(const void *startup_data, size_t startup_data_len) int nwakeups = 0; int worker; - /* Try to get a job to do. */ + /* + * Try to get a job to do. + * + * The lwlock acquisition also provides the necessary memory barrier + * to ensure that we don't see an outdated data in the handle. + */ LWLockAcquire(AioWorkerSubmissionQueueLock, LW_EXCLUSIVE); if ((io_index = pgaio_worker_submission_queue_consume()) == UINT32_MAX) { |