From b64c247210c5a5067b5c76f6ab68c978606b0902 Mon Sep 17 00:00:00 2001 From: Andres Freund Date: Mon, 9 Dec 2024 14:14:13 -0500 Subject: [PATCH v2 04/20] aio: Core AIO implementation At this point nothing can use AIO - this commit does not include any implementation of aio subjects / callbacks. That will come in later commits. Todo: - lots of cleanup --- src/include/storage/aio.h | 296 ++++++ src/include/storage/aio_internal.h | 244 +++++ src/include/storage/aio_ref.h | 24 + src/include/utils/resowner.h | 5 + src/backend/access/transam/xact.c | 9 + src/backend/storage/aio/Makefile | 3 + src/backend/storage/aio/aio.c | 906 ++++++++++++++++++ src/backend/storage/aio/aio_init.c | 186 +++- src/backend/storage/aio/aio_io.c | 140 +++ src/backend/storage/aio/aio_subject.c | 231 +++++ src/backend/storage/aio/meson.build | 3 + src/backend/storage/aio/method_sync.c | 45 + .../utils/activity/wait_event_names.txt | 3 + src/backend/utils/resowner/resowner.c | 30 + src/tools/pgindent/typedefs.list | 18 + 15 files changed, 2139 insertions(+), 4 deletions(-) create mode 100644 src/include/storage/aio_internal.h create mode 100644 src/include/storage/aio_ref.h create mode 100644 src/backend/storage/aio/aio_io.c create mode 100644 src/backend/storage/aio/aio_subject.c create mode 100644 src/backend/storage/aio/method_sync.c diff --git a/src/include/storage/aio.h b/src/include/storage/aio.h index 0ee9d0043de..b386dabc921 100644 --- a/src/include/storage/aio.h +++ b/src/include/storage/aio.h @@ -15,9 +15,305 @@ #define AIO_H +#include "storage/aio_ref.h" +#include "storage/procnumber.h" #include "utils/guc_tables.h" +typedef struct PgAioHandle PgAioHandle; + +typedef enum PgAioOp +{ + /* intentionally the zero value, to help catch zeroed memory etc */ + PGAIO_OP_INVALID = 0, + + PGAIO_OP_READV, + PGAIO_OP_WRITEV, + + /** + * In the near term we'll need at least: + * - fsync / fdatasync + * - flush_range + * + * Eventually we'll additionally want at least: + * - send + * - recv + * - accept + **/ +} PgAioOp; + +#define PGAIO_OP_COUNT (PGAIO_OP_WRITEV + 1) + + +/* + * On what is IO being performed. + * + * PgAioSharedCallback specific behaviour should be implemented in + * aio_subject.c. + */ +typedef enum PgAioSubjectID +{ + /* intentionally the zero value, to help catch zeroed memory etc */ + ASI_INVALID = 0, +} PgAioSubjectID; + +#define ASI_COUNT (ASI_INVALID + 1) + +/* + * Flags for an IO that can be set with pgaio_io_set_flag(). + */ +typedef enum PgAioHandleFlags +{ + /* hint that IO will be executed synchronously */ + AHF_SYNCHRONOUS = 1 << 0, + + /* the IO references backend local memory */ + AHF_REFERENCES_LOCAL = 1 << 1, + + /* + * IO is using buffered IO, used to control heuristic in some IO + * methods. Advantageous to set, if applicable, but not required for + * correctness. + */ + AHF_BUFFERED = 1 << 2, +} PgAioHandleFlags; + + +/* + * IDs for callbacks that can be registered on an IO. + * + * Callbacks are identified by an ID rather than a function pointer. There are + * two main reasons: + + * 1) Memory within PgAioHandle is precious, due to the number of PgAioHandle + * structs in pre-allocated shared memory. + + * 2) Due to EXEC_BACKEND function pointers are not necessarily stable between + * different backends, therefore function pointers cannot directly be in + * shared memory. + * + * Without 2), we could fairly easily allow to add new callbacks, by filling a + * ID->pointer mapping table on demand. In the presence of 2 that's still + * doable, but harder, because every process has to re-register the pointers + * so that a local ID->"backend local pointer" mapping can be maintained. + */ +typedef enum PgAioHandleSharedCallbackID +{ + ASC_INVALID, +} PgAioHandleSharedCallbackID; + + +/* + * Data necessary for basic IO types (PgAioOp). + * + * NB: Note that the FDs in here may *not* be relied upon for re-issuing + * requests (e.g. for partial reads/writes) - the FD might be from another + * process, or closed since. That's not a problem for IOs waiting to be issued + * only because the queue is flushed when closing an FD. + */ +typedef union +{ + struct + { + int fd; + uint16 iov_length; + uint64 offset; + } read; + + struct + { + int fd; + uint16 iov_length; + uint64 offset; + } write; +} PgAioOpData; + + +/* XXX: Perhaps it's worth moving this to a dedicated file? */ +#include "storage/block.h" +#include "storage/relfilelocator.h" + +typedef union PgAioSubjectData +{ + /* just as an example placeholder for later */ + struct + { + uint32 queue_id; + } wal; +} PgAioSubjectData; + + +typedef enum PgAioResultStatus +{ + ARS_UNKNOWN, /* not yet completed / uninitialized */ + ARS_OK, + ARS_PARTIAL, /* did not fully succeed, but no error */ + ARS_ERROR, +} PgAioResultStatus; + +typedef struct PgAioResult +{ + /* + * This is of type PgAioHandleSharedCallbackID, but can't use a bitfield + * of an enum, because some compilers treat enums as signed. + */ + uint32 id:8; + + /* of type PgAioResultStatus, see above */ + uint32 status:2; + + /* meaning defined by callback->error */ + uint32 error_data:22; + + int32 result; +} PgAioResult; + +/* + * Result of IO operation, visible only to the initiator of IO. + */ +typedef struct PgAioReturn +{ + PgAioResult result; + PgAioSubjectData subject_data; +} PgAioReturn; + + +typedef struct PgAioSubjectInfo +{ + void (*reopen) (PgAioHandle *ioh); + +#ifdef NOT_YET + char *(*describe_identity) (PgAioHandle *ioh); +#endif + + const char *name; +} PgAioSubjectInfo; + + +typedef PgAioResult (*PgAioHandleSharedCallbackComplete) (PgAioHandle *ioh, PgAioResult prior_result); +typedef void (*PgAioHandleSharedCallbackPrepare) (PgAioHandle *ioh); +typedef void (*PgAioHandleSharedCallbackError) (PgAioResult result, const PgAioSubjectData *subject_data, int elevel); + +typedef struct PgAioHandleSharedCallbacks +{ + PgAioHandleSharedCallbackPrepare prepare; + PgAioHandleSharedCallbackComplete complete; + PgAioHandleSharedCallbackError error; +} PgAioHandleSharedCallbacks; + + + +/* + * How many callbacks can be registered for one IO handle. Currently we only + * need two, but it's not hard to imagine needing a few more. + */ +#define AIO_MAX_SHARED_CALLBACKS 4 + + + +/* AIO API */ + + +/* -------------------------------------------------------------------------------- + * IO Handles + * -------------------------------------------------------------------------------- + */ + +struct ResourceOwnerData; +extern PgAioHandle *pgaio_io_get(struct ResourceOwnerData *resowner, PgAioReturn *ret); +extern PgAioHandle *pgaio_io_get_nb(struct ResourceOwnerData *resowner, PgAioReturn *ret); + +extern void pgaio_io_release(PgAioHandle *ioh); +extern void pgaio_io_release_resowner(dlist_node *ioh_node, bool on_error); + +extern void pgaio_io_get_ref(PgAioHandle *ioh, PgAioHandleRef *ior); + +extern void pgaio_io_set_subject(PgAioHandle *ioh, PgAioSubjectID subjid); +extern void pgaio_io_set_flag(PgAioHandle *ioh, PgAioHandleFlags flag); + +extern void pgaio_io_add_shared_cb(PgAioHandle *ioh, PgAioHandleSharedCallbackID cbid); + +extern void pgaio_io_set_io_data_32(PgAioHandle *ioh, uint32 *data, uint8 len); +extern void pgaio_io_set_io_data_64(PgAioHandle *ioh, uint64 *data, uint8 len); +extern uint64 *pgaio_io_get_io_data(PgAioHandle *ioh, uint8 *len); + +extern void pgaio_io_prepare(PgAioHandle *ioh, PgAioOp op); + +extern int pgaio_io_get_id(PgAioHandle *ioh); +struct iovec; +extern int pgaio_io_get_iovec(PgAioHandle *ioh, struct iovec **iov); +extern bool pgaio_io_has_subject(PgAioHandle *ioh); + +extern PgAioSubjectData *pgaio_io_get_subject_data(PgAioHandle *ioh); +extern PgAioOpData *pgaio_io_get_op_data(PgAioHandle *ioh); +extern ProcNumber pgaio_io_get_owner(PgAioHandle *ioh); + + + +/* -------------------------------------------------------------------------------- + * IO References + * -------------------------------------------------------------------------------- + */ + +extern void pgaio_io_ref_clear(PgAioHandleRef *ior); +extern bool pgaio_io_ref_valid(PgAioHandleRef *ior); +extern int pgaio_io_ref_get_id(PgAioHandleRef *ior); + + +extern void pgaio_io_ref_wait(PgAioHandleRef *ior); +extern bool pgaio_io_ref_check_done(PgAioHandleRef *ior); + + + +/* -------------------------------------------------------------------------------- + * IO Result + * -------------------------------------------------------------------------------- + */ + +extern void pgaio_result_log(PgAioResult result, const PgAioSubjectData *subject_data, + int elevel); + + + +/* -------------------------------------------------------------------------------- + * Actions on multiple IOs. + * -------------------------------------------------------------------------------- + */ + +extern void pgaio_submit_staged(void); +extern bool pgaio_have_staged(void); + + + +/* -------------------------------------------------------------------------------- + * Low level IO preparation routines + * + * These will often be called by code lowest level of initiating an + * IO. E.g. bufmgr.c may initiate IO for a buffer, but pgaio_io_prep_readv() + * will be called from within fd.c. + * + * Implemented in aio_io.c + * -------------------------------------------------------------------------------- + */ + +extern void pgaio_io_prep_readv(PgAioHandle *ioh, + int fd, int iovcnt, uint64 offset); + +extern void pgaio_io_prep_writev(PgAioHandle *ioh, + int fd, int iovcnt, uint64 offset); + + + +/* -------------------------------------------------------------------------------- + * Other + * -------------------------------------------------------------------------------- + */ + +extern void pgaio_closing_fd(int fd); +extern void pgaio_at_xact_end(bool is_subxact, bool is_commit); +extern void pgaio_at_error(void); + + /* GUC related */ extern void assign_io_method(int newval, void *extra); diff --git a/src/include/storage/aio_internal.h b/src/include/storage/aio_internal.h new file mode 100644 index 00000000000..d600d45b4fd --- /dev/null +++ b/src/include/storage/aio_internal.h @@ -0,0 +1,244 @@ +/*------------------------------------------------------------------------- + * + * aio_internal.h + * aio_internal + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/aio_internal.h + * + *------------------------------------------------------------------------- + */ +#ifndef AIO_INTERNAL_H +#define AIO_INTERNAL_H + + +#include "lib/ilist.h" +#include "port/pg_iovec.h" +#include "storage/aio.h" +#include "storage/condition_variable.h" + + +#define PGAIO_VERBOSE + + +/* AFIXME */ +#define PGAIO_SUBMIT_BATCH_SIZE 32 + + + +typedef enum PgAioHandleState +{ + /* not in use */ + AHS_IDLE = 0, + + /* returned by pgaio_io_get() */ + AHS_HANDED_OUT, + + /* pgaio_io_start_*() has been called, but IO hasn't been submitted yet */ + AHS_DEFINED, + + /* subjects prepare() callback has been called */ + AHS_PREPARED, + + /* IO is being executed */ + AHS_IN_FLIGHT, + + /* IO finished, but result has not yet been processed */ + AHS_REAPED, + + /* IO completed, shared completion has been called */ + AHS_COMPLETED_SHARED, + + /* IO completed, local completion has been called */ + AHS_COMPLETED_LOCAL, +} PgAioHandleState; + + +struct ResourceOwnerData; + +/* typedef is in public header */ +struct PgAioHandle +{ + /* all state updates should go through pgaio_io_update_state() */ + PgAioHandleState state:8; + + /* what are we operating on */ + PgAioSubjectID subject:8; + + /* which operation */ + PgAioOp op:8; + + /* bitfield of PgAioHandleFlags */ + uint8 flags; + + uint8 num_shared_callbacks; + + /* using the proper type here would use more space */ + uint8 shared_callbacks[AIO_MAX_SHARED_CALLBACKS]; + + uint8 iovec_data_len; + + /* XXX: could be optimized out with some pointer math */ + int32 owner_procno; + + /* FIXME: remove in favor of distilled_result */ + /* raw result of the IO operation */ + int32 result; + + /* index into PgAioCtl->iovecs */ + uint32 iovec_off; + + /** + * In which list the handle is registered, depends on the state: + * - IDLE, in per-backend list + * - HANDED_OUT - not in a list + * - DEFINED - in per-backend staged list + * - PREPARED - in per-backend staged list + * - IN_FLIGHT - in issuer's in_flight list + * - REAPED - in issuer's in_flight list + * - COMPLETED_SHARED - in issuer's in_flight list + * - COMPLETED_LOCAL - in issuer's in_flight list + * + * XXX: It probably make sense to optimize this out to save on per-io + * memory at the cost of per-backend memory. + **/ + dlist_node node; + + struct ResourceOwnerData *resowner; + dlist_node resowner_node; + + /* incremented every time the IO handle is reused */ + uint64 generation; + + ConditionVariable cv; + + /* result of shared callback, passed to issuer callback */ + PgAioResult distilled_result; + + PgAioReturn *report_return; + + PgAioOpData op_data; + + /* + * Data necessary for shared completions. Needs to be sufficient to allow + * another backend to retry an IO. + */ + PgAioSubjectData scb_data; +}; + + +typedef struct PgAioPerBackend +{ + /* index into PgAioCtl->io_handles */ + uint32 io_handle_off; + + /* IO Handles that currently are not used */ + dclist_head idle_ios; + + /* + * Only one IO may be returned by pgaio_io_get()/pgaio_io_get() without + * having been either defined (by actually associating it with IO) or by + * released (with pgaio_io_release()). This restriction is necessary to + * guarantee that we always can acquire an IO. ->handed_out_io is used to + * enforce that rule. + */ + PgAioHandle *handed_out_io; + + /* + * IOs that are defined, but not yet submitted. + */ + uint16 num_staged_ios; + PgAioHandle *staged_ios[PGAIO_SUBMIT_BATCH_SIZE]; + + /* + * List of in-flight IOs. Also contains IOs that aren't strict speaking + * in-flight anymore, but have been waited-for and completed by another + * backend. Once this backend sees such an IO it'll be reclaimed. + * + * The list is ordered by submission time, with more recently submitted + * IOs being appended at the end. + */ + dclist_head in_flight_ios; +} PgAioPerBackend; + + +typedef struct PgAioCtl +{ + int backend_state_count; + PgAioPerBackend *backend_state; + + /* + * Array of iovec structs. Each iovec is owned by a specific backend. The + * allocation is in PgAioCtl to allow the maximum number of iovecs for + * individual IOs to be configurable with PGC_POSTMASTER GUC. + */ + uint64 iovec_count; + struct iovec *iovecs; + + /* + * For, e.g., an IO covering multiple buffers in shared / temp buffers, we + * need to get Buffer IDs during completion to be able to change the + * BufferDesc state accordingly. This space can be used to store e.g. + * Buffer IDs. Note that the actual iovec might be shorter than this, + * because we combine neighboring pages into one larger iovec entry. + */ + uint64 *iovecs_data; + + uint64 io_handle_count; + PgAioHandle *io_handles; +} PgAioCtl; + + + +/* + * The set of callbacks that each IO method must implement. + */ +typedef struct IoMethodOps +{ + /* global initialization */ + size_t (*shmem_size) (void); + void (*shmem_init) (bool first_time); + + /* per-backend initialization */ + void (*init_backend) (void); + + /* handling of IOs */ + bool (*needs_synchronous_execution) (PgAioHandle *ioh); + int (*submit) (uint16 num_staged_ios, PgAioHandle **staged_ios); + + void (*wait_one) (PgAioHandle *ioh, + uint64 ref_generation); +} IoMethodOps; + + +extern bool pgaio_io_was_recycled(PgAioHandle *ioh, uint64 ref_generation, PgAioHandleState *state); + +extern void pgaio_io_prepare_subject(PgAioHandle *ioh); +extern void pgaio_io_process_completion_subject(PgAioHandle *ioh); +extern void pgaio_io_process_completion(PgAioHandle *ioh, int result); +extern void pgaio_io_prepare_submit(PgAioHandle *ioh); + +extern bool pgaio_io_needs_synchronous_execution(PgAioHandle *ioh); +extern void pgaio_io_perform_synchronously(PgAioHandle *ioh); + +extern bool pgaio_io_can_reopen(PgAioHandle *ioh); +extern void pgaio_io_reopen(PgAioHandle *ioh); + +extern const char *pgaio_io_get_subject_name(PgAioHandle *ioh); +extern const char *pgaio_io_get_op_name(PgAioHandle *ioh); +extern const char *pgaio_io_get_state_name(PgAioHandle *ioh); + + +/* Declarations for the tables of function pointers exposed by each IO method. */ +extern const IoMethodOps pgaio_sync_ops; + +extern const IoMethodOps *pgaio_impl; +extern PgAioCtl *aio_ctl; +extern PgAioPerBackend *my_aio; + + + +#endif /* AIO_INTERNAL_H */ diff --git a/src/include/storage/aio_ref.h b/src/include/storage/aio_ref.h new file mode 100644 index 00000000000..ad7e9ad34f3 --- /dev/null +++ b/src/include/storage/aio_ref.h @@ -0,0 +1,24 @@ +/*------------------------------------------------------------------------- + * + * aio_ref.h Definition of PgAioHandleRef, which sometimes needs to be used in + * headers. + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/aio_ref.h + * + *------------------------------------------------------------------------- + */ +#ifndef AIO_REF_H +#define AIO_REF_H + +typedef struct PgAioHandleRef +{ + uint32 aio_index; + uint32 generation_upper; + uint32 generation_lower; +} PgAioHandleRef; + +#endif /* AIO_REF_H */ diff --git a/src/include/utils/resowner.h b/src/include/utils/resowner.h index 4e534bc3e70..2d55720a54c 100644 --- a/src/include/utils/resowner.h +++ b/src/include/utils/resowner.h @@ -164,4 +164,9 @@ struct LOCALLOCK; extern void ResourceOwnerRememberLock(ResourceOwner owner, struct LOCALLOCK *locallock); extern void ResourceOwnerForgetLock(ResourceOwner owner, struct LOCALLOCK *locallock); +/* special support for AIO */ +struct dlist_node; +extern void ResourceOwnerRememberAioHandle(ResourceOwner owner, struct dlist_node *ioh_node); +extern void ResourceOwnerForgetAioHandle(ResourceOwner owner, struct dlist_node *ioh_node); + #endif /* RESOWNER_H */ diff --git a/src/backend/access/transam/xact.c b/src/backend/access/transam/xact.c index 3ebd7c40418..0356552c499 100644 --- a/src/backend/access/transam/xact.c +++ b/src/backend/access/transam/xact.c @@ -51,6 +51,7 @@ #include "replication/origin.h" #include "replication/snapbuild.h" #include "replication/syncrep.h" +#include "storage/aio.h" #include "storage/condition_variable.h" #include "storage/fd.h" #include "storage/lmgr.h" @@ -2475,6 +2476,8 @@ CommitTransaction(void) AtEOXact_LogicalRepWorkers(true); pgstat_report_xact_timestamp(0); + pgaio_at_xact_end( /* is_subxact = */ false, /* is_commit = */ true); + ResourceOwnerDelete(TopTransactionResourceOwner); s->curTransactionOwner = NULL; CurTransactionResourceOwner = NULL; @@ -2988,6 +2991,8 @@ AbortTransaction(void) pgstat_report_xact_timestamp(0); } + pgaio_at_xact_end( /* is_subxact = */ false, /* is_commit = */ false); + /* * State remains TRANS_ABORT until CleanupTransaction(). */ @@ -5185,6 +5190,8 @@ CommitSubTransaction(void) AtEOSubXact_PgStat(true, s->nestingLevel); AtSubCommit_Snapshot(s->nestingLevel); + pgaio_at_xact_end( /* is_subxact = */ true, /* is_commit = */ true); + /* * We need to restore the upper transaction's read-only state, in case the * upper is read-write while the child is read-only; GUC will incorrectly @@ -5351,6 +5358,8 @@ AbortSubTransaction(void) AtSubAbort_Snapshot(s->nestingLevel); } + pgaio_at_xact_end( /* is_subxact = */ true, /* is_commit = */ false); + /* * Restore the upper transaction's read-only state, too. This should be * redundant with GUC's cleanup but we may as well do it for consistency diff --git a/src/backend/storage/aio/Makefile b/src/backend/storage/aio/Makefile index eaeaeeee8e3..b253278f3c1 100644 --- a/src/backend/storage/aio/Makefile +++ b/src/backend/storage/aio/Makefile @@ -11,6 +11,9 @@ include $(top_builddir)/src/Makefile.global OBJS = \ aio.o \ aio_init.o \ + aio_io.o \ + aio_subject.o \ + method_sync.o \ read_stream.o include $(top_srcdir)/src/backend/common.mk diff --git a/src/backend/storage/aio/aio.c b/src/backend/storage/aio/aio.c index 72110c0df3e..3e2ff9718ca 100644 --- a/src/backend/storage/aio/aio.c +++ b/src/backend/storage/aio/aio.c @@ -3,6 +3,28 @@ * aio.c * AIO - Core Logic * + * For documentation about how AIO works on a higher level, including a + * schematic example, see README.md. + * + * + * AIO is a complicated subsystem. To keep things navigable it is split across + * a number of files: + * + * - aio.c - core AIO state handling + * + * - aio_init.c - initialization + * + * - aio_io.c - dealing with actual IO, including executing IOs synchronously + * + * - aio_subject.c - functionality related to executing IO for different + * subjects + * + * - method_*.c - different ways of executing AIO + * + * - read_stream.c - helper for accessing buffered relation data with + * look-ahead + * + * * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * @@ -14,7 +36,22 @@ #include "postgres.h" +#include "miscadmin.h" +#include "port/atomics.h" #include "storage/aio.h" +#include "storage/aio_internal.h" +#include "storage/bufmgr.h" +#include "utils/resowner.h" +#include "utils/wait_event_types.h" + + + +static inline void pgaio_io_update_state(PgAioHandle *ioh, PgAioHandleState new_state); +static void pgaio_io_reclaim(PgAioHandle *ioh); +static void pgaio_io_resowner_register(PgAioHandle *ioh); +static void pgaio_io_wait_for_free(void); +static PgAioHandle *pgaio_io_from_ref(PgAioHandleRef *ior, uint64 *ref_generation); + /* Options for io_method. */ @@ -27,7 +64,876 @@ int io_method = DEFAULT_IO_METHOD; int io_max_concurrency = -1; +/* global control for AIO */ +PgAioCtl *aio_ctl; + +/* current backend's per-backend state */ +PgAioPerBackend *my_aio; + + +static const IoMethodOps *pgaio_ops_table[] = { + [IOMETHOD_SYNC] = &pgaio_sync_ops, +}; + + +const IoMethodOps *pgaio_impl; + + + +/* -------------------------------------------------------------------------------- + * "Core" IO Api + * -------------------------------------------------------------------------------- + */ + +/* + * Acquire an AioHandle, waiting for IO completion if necessary. + * + * Each backend can only have one AIO handle that that has been "handed out" + * to code, but not yet submitted or released. This restriction is necessary + * to ensure that it is possible for code to wait for an unused handle by + * waiting for in-flight IO to complete. There is a limited number of handles + * in each backend, if multiple handles could be handed out without being + * submitted, waiting for all in-flight IO to complete would not guarantee + * that handles free up. + * + * It is cheap to acquire an IO handle, unless all handles are in use. In that + * case this function waits for the oldest IO to complete. In case that is not + * desirable, see pgaio_io_get_nb(). + * + * If a handle was acquired but then does not turn out to be needed, + * e.g. because pgaio_io_get() is called before starting an IO in a critical + * section, the handle needs to be be released with pgaio_io_release(). + * + * + * To react to the completion of the IO as soon as it is know to have + * completed, callbacks can be registered with pgaio_io_add_shared_cb(). + * + * To actually execute IO using the returned handle, the pgaio_io_prep_*() + * family of functions is used. In many cases the pgaio_io_prep_*() call will + * not be done directly by code that acquired the handle, but by lower level + * code that gets passed the handle. E.g. if code in bufmgr.c wants to perform + * AIO, it typically will pass the handle to smgr., which will pass it on to + * md.c, on to fd.c, which then finally calls pgaio_io_prep_*(). This + * forwarding allows the various layers to react to the IO's completion by + * registering callbacks. These callbacks in turn can translate a lower + * layer's result into a result understandable by a higher layer. + * + * Once pgaio_io_prep_*() is called, the IO may be in the process of being + * executed and might even complete before the functions return. That is, + * however, not guaranteed, to allow IO submission to be batched. To guarantee + * IO submission pgaio_submit_staged() needs to be called. + * + * After pgaio_io_prep_*() the AioHandle is "consumed" and may not be + * referenced by the IO issuing code. To e.g. wait for IO, references to the + * IO can be established with pgaio_io_get_ref() *before* pgaio_io_prep_*() is + * called. pgaio_io_ref_wait() can be used to wait for the IO to complete. + * + * + * To know if the IO [partially] succeeded or failed, a PgAioReturn * can be + * passed to pgaio_io_get(). Once the issuing backend has called + * pgaio_io_ref_wait(), the PgAioReturn contains information about whether the + * operation succeeded and details about the first failure, if any. The error + * can be raised / logged with pgaio_result_log(). + * + * The lifetime of the memory pointed to be *ret needs to be at least as long + * as the passed in resowner. If the resowner releases resources before the IO + * completes, the reference to *ret will be cleared. + */ +PgAioHandle * +pgaio_io_get(struct ResourceOwnerData *resowner, PgAioReturn *ret) +{ + PgAioHandle *h; + + while (true) + { + h = pgaio_io_get_nb(resowner, ret); + + if (h != NULL) + return h; + + /* + * Evidently all handles by this backend are in use. Just wait for + * some to complete. + */ + pgaio_io_wait_for_free(); + } +} + +/* + * Acquire an AioHandle, returning NULL if no handles are free. + * + * See pgaio_io_get(). The only difference is that this function will return + * NULL if there are no idle handles, instead of blocking. + */ +PgAioHandle * +pgaio_io_get_nb(struct ResourceOwnerData *resowner, PgAioReturn *ret) +{ + if (my_aio->num_staged_ios >= PGAIO_SUBMIT_BATCH_SIZE) + { + Assert(my_aio->num_staged_ios == PGAIO_SUBMIT_BATCH_SIZE); + pgaio_submit_staged(); + } + + if (my_aio->handed_out_io) + { + ereport(ERROR, + errmsg("API violation: Only one IO can be handed out")); + } + + if (!dclist_is_empty(&my_aio->idle_ios)) + { + dlist_node *ion = dclist_pop_head_node(&my_aio->idle_ios); + PgAioHandle *ioh = dclist_container(PgAioHandle, node, ion); + + Assert(ioh->state == AHS_IDLE); + Assert(ioh->owner_procno == MyProcNumber); + + pgaio_io_update_state(ioh, AHS_HANDED_OUT); + my_aio->handed_out_io = ioh; + + if (resowner) + pgaio_io_resowner_register(ioh); + + if (ret) + { + ioh->report_return = ret; + ret->result.status = ARS_UNKNOWN; + } + + return ioh; + } + + return NULL; +} + +/* + * Release IO handle that turned out to not be required. + * + * See pgaio_io_get() for more details. + */ +void +pgaio_io_release(PgAioHandle *ioh) +{ + if (ioh == my_aio->handed_out_io) + { + Assert(ioh->state == AHS_HANDED_OUT); + Assert(ioh->resowner); + + my_aio->handed_out_io = NULL; + pgaio_io_reclaim(ioh); + } + else + { + elog(ERROR, "release in unexpected state"); + } +} + +/* + * Release IO handle during resource owner cleanup. + */ +void +pgaio_io_release_resowner(dlist_node *ioh_node, bool on_error) +{ + PgAioHandle *ioh = dlist_container(PgAioHandle, resowner_node, ioh_node); + + Assert(ioh->resowner); + + ResourceOwnerForgetAioHandle(ioh->resowner, &ioh->resowner_node); + ioh->resowner = NULL; + + switch (ioh->state) + { + case AHS_IDLE: + elog(ERROR, "unexpected"); + break; + case AHS_HANDED_OUT: + Assert(ioh == my_aio->handed_out_io || my_aio->handed_out_io == NULL); + + if (ioh == my_aio->handed_out_io) + { + my_aio->handed_out_io = NULL; + if (!on_error) + elog(WARNING, "leaked AIO handle"); + } + + pgaio_io_reclaim(ioh); + break; + case AHS_DEFINED: + case AHS_PREPARED: + /* XXX: Should we warn about this when is_commit? */ + pgaio_submit_staged(); + break; + case AHS_IN_FLIGHT: + case AHS_REAPED: + case AHS_COMPLETED_SHARED: + /* this is expected to happen */ + break; + case AHS_COMPLETED_LOCAL: + /* XXX: unclear if this ought to be possible? */ + pgaio_io_reclaim(ioh); + break; + } + + /* + * Need to unregister the reporting of the IO's result, the memory it's + * referencing likely has gone away. + */ + if (ioh->report_return) + ioh->report_return = NULL; +} + +int +pgaio_io_get_iovec(PgAioHandle *ioh, struct iovec **iov) +{ + Assert(ioh->state == AHS_HANDED_OUT); + + *iov = &aio_ctl->iovecs[ioh->iovec_off]; + + /* AFIXME: Needs to be the value at startup time */ + return io_combine_limit; +} + +PgAioSubjectData * +pgaio_io_get_subject_data(PgAioHandle *ioh) +{ + return &ioh->scb_data; +} + +PgAioOpData * +pgaio_io_get_op_data(PgAioHandle *ioh) +{ + return &ioh->op_data; +} + +ProcNumber +pgaio_io_get_owner(PgAioHandle *ioh) +{ + return ioh->owner_procno; +} + +bool +pgaio_io_has_subject(PgAioHandle *ioh) +{ + return ioh->subject != ASI_INVALID; +} + +void +pgaio_io_set_flag(PgAioHandle *ioh, PgAioHandleFlags flag) +{ + Assert(ioh->state == AHS_HANDED_OUT); + + ioh->flags |= flag; +} + +void +pgaio_io_set_io_data_32(PgAioHandle *ioh, uint32 *data, uint8 len) +{ + Assert(ioh->state == AHS_HANDED_OUT); + + for (int i = 0; i < len; i++) + aio_ctl->iovecs_data[ioh->iovec_off + i] = data[i]; + ioh->iovec_data_len = len; +} + +uint64 * +pgaio_io_get_io_data(PgAioHandle *ioh, uint8 *len) +{ + Assert(ioh->iovec_data_len > 0); + + *len = ioh->iovec_data_len; + + return &aio_ctl->iovecs_data[ioh->iovec_off]; +} + +void +pgaio_io_set_subject(PgAioHandle *ioh, PgAioSubjectID subjid) +{ + Assert(ioh->state == AHS_HANDED_OUT); + + ioh->subject = subjid; + + elog(DEBUG3, "io:%d, op %s, subject %s, set subject", + pgaio_io_get_id(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh)); +} + +void +pgaio_io_get_ref(PgAioHandle *ioh, PgAioHandleRef *ior) +{ + Assert(ioh->state == AHS_HANDED_OUT || + ioh->state == AHS_DEFINED || + ioh->state == AHS_PREPARED); + Assert(ioh->generation != 0); + + ior->aio_index = ioh - aio_ctl->io_handles; + ior->generation_upper = (uint32) (ioh->generation >> 32); + ior->generation_lower = (uint32) ioh->generation; +} + +void +pgaio_io_ref_clear(PgAioHandleRef *ior) +{ + ior->aio_index = PG_UINT32_MAX; +} + +bool +pgaio_io_ref_valid(PgAioHandleRef *ior) +{ + return ior->aio_index != PG_UINT32_MAX; +} + +int +pgaio_io_ref_get_id(PgAioHandleRef *ior) +{ + Assert(pgaio_io_ref_valid(ior)); + return ior->aio_index; +} + +bool +pgaio_io_was_recycled(PgAioHandle *ioh, uint64 ref_generation, PgAioHandleState *state) +{ + *state = ioh->state; + pg_read_barrier(); + + return ioh->generation != ref_generation; +} + +void +pgaio_io_ref_wait(PgAioHandleRef *ior) +{ + uint64 ref_generation; + PgAioHandleState state; + bool am_owner; + PgAioHandle *ioh; + + ioh = pgaio_io_from_ref(ior, &ref_generation); + + am_owner = ioh->owner_procno == MyProcNumber; + + if (pgaio_io_was_recycled(ioh, ref_generation, &state)) + return; + + if (am_owner) + { + if (state == AHS_DEFINED || state == AHS_PREPARED) + { + /* XXX: Arguably this should be prevented by callers? */ + pgaio_submit_staged(); + } + else if (state != AHS_IN_FLIGHT + && state != AHS_REAPED + && state != AHS_COMPLETED_SHARED + && state != AHS_COMPLETED_LOCAL) + { + elog(PANIC, "waiting for own IO in wrong state: %d", + state); + } + + /* + * Somebody else completed the IO, need to execute issuer callback, so + * reclaim eagerly. + */ + if (state == AHS_COMPLETED_LOCAL) + { + pgaio_io_reclaim(ioh); + + return; + } + } + + while (true) + { + if (pgaio_io_was_recycled(ioh, ref_generation, &state)) + return; + + switch (state) + { + case AHS_IDLE: + case AHS_HANDED_OUT: + elog(ERROR, "IO in wrong state: %d", state); + break; + + case AHS_IN_FLIGHT: + /* + * If we need to wait via the IO method, do so now. Don't + * check via the IO method if the issuing backend is executing + * the IO synchronously. + */ + if (pgaio_impl->wait_one && !(ioh->flags & AHF_SYNCHRONOUS)) + { + pgaio_impl->wait_one(ioh, ref_generation); + continue; + } + /* fallthrough */ + + /* waiting for owner to submit */ + case AHS_PREPARED: + case AHS_DEFINED: + /* waiting for reaper to complete */ + /* fallthrough */ + case AHS_REAPED: + /* shouldn't be able to hit this otherwise */ + Assert(IsUnderPostmaster); + /* ensure we're going to get woken up */ + ConditionVariablePrepareToSleep(&ioh->cv); + + while (!pgaio_io_was_recycled(ioh, ref_generation, &state)) + { + if (state != AHS_REAPED && state != AHS_DEFINED && + state != AHS_IN_FLIGHT) + break; + ConditionVariableSleep(&ioh->cv, WAIT_EVENT_AIO_COMPLETION); + } + + ConditionVariableCancelSleep(); + break; + + case AHS_COMPLETED_SHARED: + /* see above */ + if (am_owner) + pgaio_io_reclaim(ioh); + return; + case AHS_COMPLETED_LOCAL: + return; + } + } +} + +/* + * Check if the the referenced IO completed, without blocking. + */ +bool +pgaio_io_ref_check_done(PgAioHandleRef *ior) +{ + uint64 ref_generation; + PgAioHandleState state; + bool am_owner; + PgAioHandle *ioh; + + ioh = pgaio_io_from_ref(ior, &ref_generation); + + if (pgaio_io_was_recycled(ioh, ref_generation, &state)) + return true; + + + if (state == AHS_IDLE) + return true; + + am_owner = ioh->owner_procno == MyProcNumber; + + if (state == AHS_COMPLETED_SHARED || state == AHS_COMPLETED_LOCAL) + { + if (am_owner) + pgaio_io_reclaim(ioh); + return true; + } + + return false; +} + +int +pgaio_io_get_id(PgAioHandle *ioh) +{ + Assert(ioh >= aio_ctl->io_handles && + ioh <= (aio_ctl->io_handles + aio_ctl->io_handle_count)); + return ioh - aio_ctl->io_handles; +} + +const char * +pgaio_io_get_state_name(PgAioHandle *ioh) +{ + switch (ioh->state) + { + case AHS_IDLE: + return "idle"; + case AHS_HANDED_OUT: + return "handed_out"; + case AHS_DEFINED: + return "DEFINED"; + case AHS_PREPARED: + return "PREPARED"; + case AHS_IN_FLIGHT: + return "IN_FLIGHT"; + case AHS_REAPED: + return "REAPED"; + case AHS_COMPLETED_SHARED: + return "COMPLETED_SHARED"; + case AHS_COMPLETED_LOCAL: + return "COMPLETED_LOCAL"; + } + pg_unreachable(); +} + +/* + * Internal, should only be called from pgaio_io_prep_*(). + */ +void +pgaio_io_prepare(PgAioHandle *ioh, PgAioOp op) +{ + bool needs_synchronous; + + Assert(ioh->state == AHS_HANDED_OUT); + Assert(pgaio_io_has_subject(ioh)); + + ioh->op = op; + ioh->result = 0; + + pgaio_io_update_state(ioh, AHS_DEFINED); + + /* allow a new IO to be staged */ + my_aio->handed_out_io = NULL; + + pgaio_io_prepare_subject(ioh); + + pgaio_io_update_state(ioh, AHS_PREPARED); + + needs_synchronous = pgaio_io_needs_synchronous_execution(ioh); + + elog(DEBUG3, "io:%d: prepared %s, executed synchronously: %d", + pgaio_io_get_id(ioh), pgaio_io_get_op_name(ioh), + needs_synchronous); + + if (!needs_synchronous) + { + my_aio->staged_ios[my_aio->num_staged_ios++] = ioh; + Assert(my_aio->num_staged_ios <= PGAIO_SUBMIT_BATCH_SIZE); + } + else + { + pgaio_io_prepare_submit(ioh); + pgaio_io_perform_synchronously(ioh); + } +} + +/* + * Handle IO getting completed by a method. + */ +void +pgaio_io_process_completion(PgAioHandle *ioh, int result) +{ + Assert(ioh->state == AHS_IN_FLIGHT); + + ioh->result = result; + + pgaio_io_update_state(ioh, AHS_REAPED); + + pgaio_io_process_completion_subject(ioh); + + pgaio_io_update_state(ioh, AHS_COMPLETED_SHARED); + + /* condition variable broadcast ensures state is visible before wakeup */ + ConditionVariableBroadcast(&ioh->cv); + + if (ioh->owner_procno == MyProcNumber) + pgaio_io_reclaim(ioh); +} + +bool +pgaio_io_needs_synchronous_execution(PgAioHandle *ioh) +{ + if (ioh->flags & AHF_SYNCHRONOUS) + { + /* XXX: should we also check if there are other IOs staged? */ + return true; + } + + if (pgaio_impl->needs_synchronous_execution) + return pgaio_impl->needs_synchronous_execution(ioh); + return false; +} + +/* + * Handle IO being processed by IO method. + */ +void +pgaio_io_prepare_submit(PgAioHandle *ioh) +{ + pgaio_io_update_state(ioh, AHS_IN_FLIGHT); + + dclist_push_tail(&my_aio->in_flight_ios, &ioh->node); +} + +static inline void +pgaio_io_update_state(PgAioHandle *ioh, PgAioHandleState new_state) +{ + /* + * Ensure the changes signified by the new state are visible before the + * new state becomes visible. + */ + pg_write_barrier(); + + ioh->state = new_state; +} + +static PgAioHandle * +pgaio_io_from_ref(PgAioHandleRef *ior, uint64 *ref_generation) +{ + PgAioHandle *ioh; + + Assert(ior->aio_index < aio_ctl->io_handle_count); + + ioh = &aio_ctl->io_handles[ior->aio_index]; + + *ref_generation = ((uint64) ior->generation_upper) << 32 | + ior->generation_lower; + + Assert(*ref_generation != 0); + + return ioh; +} + +static void +pgaio_io_resowner_register(PgAioHandle *ioh) +{ + Assert(!ioh->resowner); + Assert(CurrentResourceOwner); + + ResourceOwnerRememberAioHandle(CurrentResourceOwner, &ioh->resowner_node); + ioh->resowner = CurrentResourceOwner; +} + +static void +pgaio_io_reclaim(PgAioHandle *ioh) +{ + /* This is only ok if it's our IO */ + Assert(ioh->owner_procno == MyProcNumber); + + ereport(DEBUG3, + errmsg("reclaiming io:%d, state: %s, op %s, subject %s, result: %d, distilled_result: AFIXME, report to: %p", + pgaio_io_get_id(ioh), + pgaio_io_get_state_name(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh), + ioh->result, + ioh->report_return + ), + errhidestmt(true), errhidecontext(true)); + + /* if the IO has been defined, we might need to do more work */ + if (ioh->state != AHS_HANDED_OUT) + { + dclist_delete_from(&my_aio->in_flight_ios, &ioh->node); + + if (ioh->report_return) + { + ioh->report_return->result = ioh->distilled_result; + ioh->report_return->subject_data = ioh->scb_data; + } + } + + if (ioh->resowner) + { + ResourceOwnerForgetAioHandle(ioh->resowner, &ioh->resowner_node); + ioh->resowner = NULL; + } + + Assert(!ioh->resowner); + + ioh->num_shared_callbacks = 0; + ioh->iovec_data_len = 0; + ioh->report_return = NULL; + ioh->flags = 0; + + /* XXX: the barrier is probably superfluous */ + pg_write_barrier(); + ioh->generation++; + + pgaio_io_update_state(ioh, AHS_IDLE); + + /* + * We push the IO to the head of the idle IO list, that seems more cache + * efficient in cases where only a few IOs are used. + */ + dclist_push_head(&my_aio->idle_ios, &ioh->node); +} + +static void +pgaio_io_wait_for_free(void) +{ + int reclaimed = 0; + + elog(DEBUG2, + "waiting for self: %d pending", + my_aio->num_staged_ios); + + /* + * First check if any of our IOs actually have completed - when using + * worker, that'll often be the case. We could do so as part of the loop + * below, but that'd potentially lead us to wait for some IO submitted + * before. + */ + for (int i = 0; i < io_max_concurrency; i++) + { + PgAioHandle *ioh = &aio_ctl->io_handles[my_aio->io_handle_off + i]; + + if (ioh->state == AHS_COMPLETED_SHARED) + { + pgaio_io_reclaim(ioh); + reclaimed++; + } + } + + if (reclaimed > 0) + return; + + /* + * If we have any unsubmitted IOs, submit them now. We'll start waiting in + * a second, so it's better they're in flight. This also addresses the + * edge-case that all IOs are unsubmitted. + */ + if (my_aio->num_staged_ios > 0) + { + elog(DEBUG2, "submitting while acquiring free io"); + pgaio_submit_staged(); + } + + /* + * It's possible that we recognized there were free IOs while submitting. + */ + if (dclist_count(&my_aio->in_flight_ios) == 0) + { + elog(ERROR, "no free IOs despite no in-flight IOs"); + } + + /* + * Wait for the oldest in-flight IO to complete. + * + * XXX: Reusing the general IO wait is suboptimal, we don't need to wait + * for that specific IO to complete, we just need *any* IO to complete. + */ + { + PgAioHandle *ioh = dclist_head_element(PgAioHandle, node, &my_aio->in_flight_ios); + + switch (ioh->state) + { + /* should not be in in-flight list */ + case AHS_IDLE: + case AHS_DEFINED: + case AHS_HANDED_OUT: + case AHS_PREPARED: + case AHS_COMPLETED_LOCAL: + elog(ERROR, "shouldn't get here with io:%d in state %d", + pgaio_io_get_id(ioh), ioh->state); + break; + + case AHS_REAPED: + case AHS_IN_FLIGHT: + { + PgAioHandleRef ior; + + ior.aio_index = ioh - aio_ctl->io_handles; + ior.generation_upper = (uint32) (ioh->generation >> 32); + ior.generation_lower = (uint32) ioh->generation; + + pgaio_io_ref_wait(&ior); + elog(DEBUG2, "waited for io:%d", + pgaio_io_get_id(ioh)); + } + break; + case AHS_COMPLETED_SHARED: + /* it's possible that another backend just finished this IO */ + pgaio_io_reclaim(ioh); + break; + } + + if (dclist_count(&my_aio->idle_ios) == 0) + elog(PANIC, "no idle IOs after waiting"); + return; + } +} + + + +/* -------------------------------------------------------------------------------- + * Actions on multiple IOs. + * -------------------------------------------------------------------------------- + */ + +void +pgaio_submit_staged(void) +{ + int total_submitted = 0; + int did_submit; + + if (my_aio->num_staged_ios == 0) + return; + + + START_CRIT_SECTION(); + + did_submit = pgaio_impl->submit(my_aio->num_staged_ios, my_aio->staged_ios); + + END_CRIT_SECTION(); + + total_submitted += did_submit; + + Assert(total_submitted == did_submit); + + my_aio->num_staged_ios = 0; + +#ifdef PGAIO_VERBOSE + ereport(DEBUG2, + errmsg("submitted %d", + total_submitted), + errhidestmt(true), + errhidecontext(true)); +#endif +} + +bool +pgaio_have_staged(void) +{ + return my_aio->num_staged_ios > 0; +} + + + +/* -------------------------------------------------------------------------------- + * Other + * -------------------------------------------------------------------------------- + */ + +/* + * Need to submit staged but not yet submitted IOs using the fd, otherwise + * the IO would end up targeting something bogus. + */ +void +pgaio_closing_fd(int fd) +{ + /* + * Might be called before AIO is initialized or in a subprocess that + * doesn't use AIO. + */ + if (!my_aio) + return; + + /* + * For now just submit all staged IOs - we could be more selective, but + * it's probably not worth it. + */ + pgaio_submit_staged(); +} + +void +pgaio_at_xact_end(bool is_subxact, bool is_commit) +{ + Assert(!my_aio->handed_out_io); +} + +/* + * Similar to pgaio_at_xact_end(..., is_commit = false), but for cases where + * errors happen outside of transactions. + */ +void +pgaio_at_error(void) +{ + Assert(!my_aio->handed_out_io); +} + + void assign_io_method(int newval, void *extra) { + pgaio_impl = pgaio_ops_table[newval]; } diff --git a/src/backend/storage/aio/aio_init.c b/src/backend/storage/aio/aio_init.c index 84e0e37baae..b9bdf51680a 100644 --- a/src/backend/storage/aio/aio_init.c +++ b/src/backend/storage/aio/aio_init.c @@ -14,28 +14,206 @@ #include "postgres.h" +#include "miscadmin.h" +#include "storage/aio.h" #include "storage/aio_init.h" +#include "storage/aio_internal.h" +#include "storage/bufmgr.h" +#include "storage/proc.h" +#include "storage/shmem.h" +static Size +AioCtlShmemSize(void) +{ + Size sz; + + /* aio_ctl itself */ + sz = offsetof(PgAioCtl, io_handles); + + return sz; +} + +static uint32 +AioProcs(void) +{ + return MaxBackends + NUM_AUXILIARY_PROCS; +} + +static Size +AioBackendShmemSize(void) +{ + return mul_size(AioProcs(), sizeof(PgAioPerBackend)); +} + +static Size +AioHandleShmemSize(void) +{ + Size sz; + + /* ios */ + sz = mul_size(AioProcs(), + mul_size(io_max_concurrency, sizeof(PgAioHandle))); + + return sz; +} + +static Size +AioIOVShmemSize(void) +{ + /* FIXME: io_combine_limit is USERSET */ + return mul_size(sizeof(struct iovec), + mul_size(mul_size(io_combine_limit, AioProcs()), + io_max_concurrency)); +} + +static Size +AioIOVDataShmemSize(void) +{ + /* FIXME: io_combine_limit is USERSET */ + return mul_size(sizeof(uint64), + mul_size(mul_size(io_combine_limit, AioProcs()), + io_max_concurrency)); +} + +/* + * Choose a suitable value for io_max_concurrency. + * + * It's unlikely that we could have more IOs in flight than buffers that we + * would be allowed to pin. + * + * On the upper end, apply a cap too - just because shared_buffers is large, + * it doesn't make sense have millions of buffers undergo IO concurrently. + */ +static int +AioChooseMaxConccurrency(void) +{ + uint32 max_backends; + int max_proportional_pins; + + /* Similar logic to LimitAdditionalPins() */ + max_backends = MaxBackends + NUM_AUXILIARY_PROCS; + max_proportional_pins = NBuffers / max_backends; + + max_proportional_pins = Max(max_proportional_pins, 1); + + /* apply upper limit */ + return Min(max_proportional_pins, 64); +} + Size AioShmemSize(void) { Size sz = 0; + /* + * We prefer to report this value's source as PGC_S_DYNAMIC_DEFAULT. + * However, if the DBA explicitly set wal_buffers = -1 in the config file, + * then PGC_S_DYNAMIC_DEFAULT will fail to override that and we must force + * + */ + if (io_max_concurrency == -1) + { + char buf[32]; + + snprintf(buf, sizeof(buf), "%d", AioChooseMaxConccurrency()); + SetConfigOption("io_max_concurrency", buf, PGC_POSTMASTER, + PGC_S_DYNAMIC_DEFAULT); + if (io_max_concurrency == -1) /* failed to apply it? */ + SetConfigOption("io_max_concurrency", buf, PGC_POSTMASTER, + PGC_S_OVERRIDE); + } + + sz = add_size(sz, AioCtlShmemSize()); + sz = add_size(sz, AioBackendShmemSize()); + sz = add_size(sz, AioHandleShmemSize()); + sz = add_size(sz, AioIOVShmemSize()); + sz = add_size(sz, AioIOVDataShmemSize()); + + if (pgaio_impl->shmem_size) + sz = add_size(sz, pgaio_impl->shmem_size()); + return sz; } void AioShmemInit(void) { + bool found; + uint32 io_handle_off = 0; + uint32 iovec_off = 0; + uint32 per_backend_iovecs = io_max_concurrency * io_combine_limit; + + aio_ctl = (PgAioCtl *) + ShmemInitStruct("AioCtl", AioCtlShmemSize(), &found); + + if (found) + goto out; + + memset(aio_ctl, 0, AioCtlShmemSize()); + + aio_ctl->io_handle_count = AioProcs() * io_max_concurrency; + aio_ctl->iovec_count = AioProcs() * per_backend_iovecs; + + aio_ctl->backend_state = (PgAioPerBackend *) + ShmemInitStruct("AioBackend", AioBackendShmemSize(), &found); + + aio_ctl->io_handles = (PgAioHandle *) + ShmemInitStruct("AioHandle", AioHandleShmemSize(), &found); + + aio_ctl->iovecs = ShmemInitStruct("AioIOV", AioIOVShmemSize(), &found); + aio_ctl->iovecs_data = ShmemInitStruct("AioIOVData", AioIOVDataShmemSize(), &found); + + for (int procno = 0; procno < AioProcs(); procno++) + { + PgAioPerBackend *bs = &aio_ctl->backend_state[procno]; + + bs->io_handle_off = io_handle_off; + io_handle_off += io_max_concurrency; + + dclist_init(&bs->idle_ios); + memset(bs->staged_ios, 0, sizeof(PgAioHandle *) * PGAIO_SUBMIT_BATCH_SIZE); + dclist_init(&bs->in_flight_ios); + + /* initialize per-backend IOs */ + for (int i = 0; i < io_max_concurrency; i++) + { + PgAioHandle *ioh = &aio_ctl->io_handles[bs->io_handle_off + i]; + + ioh->generation = 1; + ioh->owner_procno = procno; + ioh->iovec_off = iovec_off; + ioh->iovec_data_len = 0; + ioh->report_return = NULL; + ioh->resowner = NULL; + ioh->num_shared_callbacks = 0; + ioh->distilled_result.status = ARS_UNKNOWN; + ioh->flags = 0; + + ConditionVariableInit(&ioh->cv); + + dclist_push_tail(&bs->idle_ios, &ioh->node); + iovec_off += io_combine_limit; + } + } + +out: + /* Initialize IO method specific resources. */ + if (pgaio_impl->shmem_init) + pgaio_impl->shmem_init(!found); } void pgaio_init_backend(void) { -} + /* shouldn't be initialized twice */ + Assert(!my_aio); + + if (MyProc == NULL || MyProcNumber >= AioProcs()) + elog(ERROR, "aio requires a normal PGPROC"); + + my_aio = &aio_ctl->backend_state[MyProcNumber]; -void -pgaio_postmaster_child_init_local(void) -{ + if (pgaio_impl->init_backend) + pgaio_impl->init_backend(); } diff --git a/src/backend/storage/aio/aio_io.c b/src/backend/storage/aio/aio_io.c new file mode 100644 index 00000000000..3c255775833 --- /dev/null +++ b/src/backend/storage/aio/aio_io.c @@ -0,0 +1,140 @@ +/*------------------------------------------------------------------------- + * + * aio_io.c + * AIO - Low Level IO Handling + * + * Functions related to associating IO operations to IO Handles and IO-method + * independent support functions for actually performing IO. + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/aio/aio_io.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "storage/aio.h" +#include "storage/aio_internal.h" +#include "storage/fd.h" +#include "utils/wait_event.h" + + +static void pgaio_io_before_prep(PgAioHandle *ioh); + + + +/* -------------------------------------------------------------------------------- + * "Preparation" routines for individual IO types + * + * These are called by place the place actually initiating an IO, to associate + * the IO specific data with an AIO handle. + * + * Each of the preparation routines first needs to call + * pgaio_io_before_prep(), then fill IO specific fields in the handle and then + * finally call pgaio_io_prepare(). + * -------------------------------------------------------------------------------- + */ + +void +pgaio_io_prep_readv(PgAioHandle *ioh, + int fd, int iovcnt, uint64 offset) +{ + pgaio_io_before_prep(ioh); + + ioh->op_data.read.fd = fd; + ioh->op_data.read.offset = offset; + ioh->op_data.read.iov_length = iovcnt; + + pgaio_io_prepare(ioh, PGAIO_OP_READV); +} + +void +pgaio_io_prep_writev(PgAioHandle *ioh, + int fd, int iovcnt, uint64 offset) +{ + pgaio_io_before_prep(ioh); + + ioh->op_data.write.fd = fd; + ioh->op_data.write.offset = offset; + ioh->op_data.write.iov_length = iovcnt; + + pgaio_io_prepare(ioh, PGAIO_OP_WRITEV); +} + + + +/* -------------------------------------------------------------------------------- + * Functions implementing IO handle operations that are directly related to IO + * operations. + * -------------------------------------------------------------------------------- + */ + +/* + * Execute IO operation synchronously. This is implemented here, not in + * method_sync.c, because other IO methods lso might use it / fall back to it. + */ +void +pgaio_io_perform_synchronously(PgAioHandle *ioh) +{ + ssize_t result = 0; + struct iovec *iov = &aio_ctl->iovecs[ioh->iovec_off]; + + /* Perform IO. */ + switch (ioh->op) + { + case PGAIO_OP_READV: + pgstat_report_wait_start(WAIT_EVENT_DATA_FILE_READ); + result = pg_preadv(ioh->op_data.read.fd, iov, + ioh->op_data.read.iov_length, + ioh->op_data.read.offset); + pgstat_report_wait_end(); + break; + case PGAIO_OP_WRITEV: + pgstat_report_wait_start(WAIT_EVENT_DATA_FILE_WRITE); + result = pg_pwritev(ioh->op_data.write.fd, iov, + ioh->op_data.write.iov_length, + ioh->op_data.write.offset); + pgstat_report_wait_end(); + break; + case PGAIO_OP_INVALID: + elog(ERROR, "trying to execute invalid IO operation"); + } + + ioh->result = result < 0 ? -errno : result; + + pgaio_io_process_completion(ioh, ioh->result); +} + +const char * +pgaio_io_get_op_name(PgAioHandle *ioh) +{ + Assert(ioh->op >= 0 && ioh->op < PGAIO_OP_COUNT); + + switch (ioh->op) + { + case PGAIO_OP_INVALID: + return "invalid"; + case PGAIO_OP_READV: + return "read"; + case PGAIO_OP_WRITEV: + return "write"; + } + + pg_unreachable(); +} + +/* + * Helper function to be called by IO operation preparation functions, before + * any data in the handle is set. Mostly to centralize assertions. + */ +static void +pgaio_io_before_prep(PgAioHandle *ioh) +{ + Assert(ioh->state == AHS_HANDED_OUT); + Assert(pgaio_io_has_subject(ioh)); +} diff --git a/src/backend/storage/aio/aio_subject.c b/src/backend/storage/aio/aio_subject.c new file mode 100644 index 00000000000..8694cfafcd1 --- /dev/null +++ b/src/backend/storage/aio/aio_subject.c @@ -0,0 +1,231 @@ +/*------------------------------------------------------------------------- + * + * aio_subject.c + * AIO - Functionality related to executing IO for different subjects + * + * XXX Write me + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/aio/aio_subject.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "storage/aio.h" +#include "storage/aio_internal.h" +#include "storage/buf_internals.h" +#include "storage/bufmgr.h" +#include "storage/smgr.h" +#include "utils/memutils.h" + + +/* + * Registry for entities that can be the target of AIO. + * + * To support executing using worker processes, the file descriptor for an IO + * may need to be be reopened in a different process. This is done via the + * PgAioSubjectInfo.reopen callback. + */ +static const PgAioSubjectInfo *aio_subject_info[] = { + [ASI_INVALID] = &(PgAioSubjectInfo) { + .name = "invalid", + }, +}; + + +typedef struct PgAioHandleSharedCallbacksEntry +{ + const PgAioHandleSharedCallbacks *const cb; + const char *const name; +} PgAioHandleSharedCallbacksEntry; + +static const PgAioHandleSharedCallbacksEntry aio_shared_cbs[] = { +#define CALLBACK_ENTRY(id, callback) [id] = {.cb = &callback, .name = #callback} +#undef CALLBACK_ENTRY +}; + + +/* + * Register callback for the IO handle. + * + * Only a limited number (AIO_MAX_SHARED_CALLBACKS) of callbacks can be + * registered for each IO. + * + * Callbacks need to be registered before [indirectly] calling + * pgaio_io_prep_*(), as the IO may be executed immediately. + * + * + * Note that callbacks are executed in critical sections. This is necessary + * to be able to execute IO in critical sections (consider e.g. WAL + * logging). To perform AIO we first need to acquire a handle, which, if there + * are no free handles, requires waiting for IOs to complete and to execute + * their completion callbacks. + * + * Callbacks may be executed in the issuing backend but also in another + * backend (because that backend is waiting for the IO) or in IO workers (if + * io_method=worker is used). + * + * + * See PgAioHandleSharedCallbackID's definition for an explanation for why + * callbacks are not identified by a pointer. + */ +void +pgaio_io_add_shared_cb(PgAioHandle *ioh, PgAioHandleSharedCallbackID cbid) +{ + const PgAioHandleSharedCallbacksEntry *ce = &aio_shared_cbs[cbid]; + + if (cbid >= lengthof(aio_shared_cbs)) + elog(ERROR, "callback %d is out of range", cbid); + if (aio_shared_cbs[cbid].cb->complete == NULL) + elog(ERROR, "callback %d is undefined", cbid); + if (ioh->num_shared_callbacks >= AIO_MAX_SHARED_CALLBACKS) + elog(PANIC, "too many callbacks, the max is %d", AIO_MAX_SHARED_CALLBACKS); + ioh->shared_callbacks[ioh->num_shared_callbacks] = cbid; + + elog(DEBUG3, "io:%d, op %s, subject %s, adding cb #%d, id %d/%s", + pgaio_io_get_id(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh), + ioh->num_shared_callbacks + 1, + cbid, ce->name); + + ioh->num_shared_callbacks++; +} + +/* + * Return the name for the subject associated with the IO. Mostly useful for + * debugging/logging. + */ +const char * +pgaio_io_get_subject_name(PgAioHandle *ioh) +{ + Assert(ioh->subject >= 0 && ioh->subject < ASI_COUNT); + + return aio_subject_info[ioh->subject]->name; +} + +/* + * Internal function which invokes ->prepare for all the registered callbacks. + */ +void +pgaio_io_prepare_subject(PgAioHandle *ioh) +{ + Assert(ioh->subject > ASI_INVALID && ioh->subject < ASI_COUNT); + Assert(ioh->op >= 0 && ioh->op < PGAIO_OP_COUNT); + + for (int i = ioh->num_shared_callbacks; i > 0; i--) + { + PgAioHandleSharedCallbackID cbid = ioh->shared_callbacks[i - 1]; + const PgAioHandleSharedCallbacksEntry *ce = &aio_shared_cbs[cbid]; + + if (!ce->cb->prepare) + continue; + + elog(DEBUG3, "io:%d, op %s, subject %s, calling cb #%d %d/%s->prepare", + pgaio_io_get_id(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh), + i, + cbid, ce->name); + ce->cb->prepare(ioh); + } +} + +/* + * Internal function which invokes ->complete for all the registered + * callbacks. + */ +void +pgaio_io_process_completion_subject(PgAioHandle *ioh) +{ + PgAioResult result; + + Assert(ioh->subject >= 0 && ioh->subject < ASI_COUNT); + Assert(ioh->op >= 0 && ioh->op < PGAIO_OP_COUNT); + + result.status = ARS_OK; /* low level IO is always considered OK */ + result.result = ioh->result; + result.id = ASC_INVALID; + result.error_data = 0; + + for (int i = ioh->num_shared_callbacks; i > 0; i--) + { + PgAioHandleSharedCallbackID cbid = ioh->shared_callbacks[i - 1]; + const PgAioHandleSharedCallbacksEntry *ce = &aio_shared_cbs[cbid]; + + elog(DEBUG3, "io:%d, op %s, subject %s, calling cb #%d, id %d/%s->complete with distilled result status %d, id %u, error_data: %d, result: %d", + pgaio_io_get_id(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh), + i, + cbid, ce->name, + result.status, + result.id, + result.error_data, + result.result); + result = ce->cb->complete(ioh, result); + } + + ioh->distilled_result = result; + + elog(DEBUG3, "io:%d, op %s, subject %s, distilled result status %d, id %u, error_data: %d, result: %d, raw_result %d", + pgaio_io_get_id(ioh), + pgaio_io_get_op_name(ioh), + pgaio_io_get_subject_name(ioh), + result.status, + result.id, + result.error_data, + result.result, + ioh->result); +} + +/* + * Check if pgaio_io_reopen() is available for the IO. + */ +bool +pgaio_io_can_reopen(PgAioHandle *ioh) +{ + return aio_subject_info[ioh->subject]->reopen != NULL; +} + +/* + * Before executing an IO outside of the context of the process the IO has + * been prepared in, the file descriptor has to be reopened - any FD + * referenced in the IO itself, won't be valid in the separate process. + */ +void +pgaio_io_reopen(PgAioHandle *ioh) +{ + Assert(ioh->subject >= 0 && ioh->subject < ASI_COUNT); + Assert(ioh->op >= 0 && ioh->op < PGAIO_OP_COUNT); + + aio_subject_info[ioh->subject]->reopen(ioh); +} + + + +/* -------------------------------------------------------------------------------- + * IO Result + * -------------------------------------------------------------------------------- + */ + +void +pgaio_result_log(PgAioResult result, const PgAioSubjectData *subject_data, int elevel) +{ + PgAioHandleSharedCallbackID cbid = result.id; + const PgAioHandleSharedCallbacksEntry *ce = &aio_shared_cbs[cbid]; + + Assert(result.status != ARS_UNKNOWN); + Assert(result.status != ARS_OK); + + if (ce->cb->error == NULL) + elog(ERROR, "scb id %d/%s does not have an error callback", + result.id, ce->name); + + ce->cb->error(result, subject_data, elevel); +} diff --git a/src/backend/storage/aio/meson.build b/src/backend/storage/aio/meson.build index 8d20759ebf8..8339d473aae 100644 --- a/src/backend/storage/aio/meson.build +++ b/src/backend/storage/aio/meson.build @@ -3,5 +3,8 @@ backend_sources += files( 'aio.c', 'aio_init.c', + 'aio_io.c', + 'aio_subject.c', + 'method_sync.c', 'read_stream.c', ) diff --git a/src/backend/storage/aio/method_sync.c b/src/backend/storage/aio/method_sync.c new file mode 100644 index 00000000000..61fd06a277b --- /dev/null +++ b/src/backend/storage/aio/method_sync.c @@ -0,0 +1,45 @@ +/*------------------------------------------------------------------------- + * + * method_sync.c + * AIO - perform "AIO" by executing it synchronously + * + * This method is mainly to check if AIO use causes regressions. Other IO + * methods might also fall back to the synchronous method for functionality + * they cannot provide. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/aio/method_sync.c + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include "storage/aio.h" +#include "storage/aio_internal.h" + +static bool pgaio_sync_needs_synchronous_execution(PgAioHandle *ioh); +static int pgaio_sync_submit(uint16 num_staged_ios, PgAioHandle **staged_ios); + + +const IoMethodOps pgaio_sync_ops = { + .needs_synchronous_execution = pgaio_sync_needs_synchronous_execution, + .submit = pgaio_sync_submit, +}; + +static bool +pgaio_sync_needs_synchronous_execution(PgAioHandle *ioh) +{ + return true; +} + +static int +pgaio_sync_submit(uint16 num_staged_ios, PgAioHandle **staged_ios) +{ + elog(ERROR, "should be unreachable"); + + return 0; +} diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt index 16144c2b72d..7a2e2b4432e 100644 --- a/src/backend/utils/activity/wait_event_names.txt +++ b/src/backend/utils/activity/wait_event_names.txt @@ -190,6 +190,9 @@ ABI_compatibility: Section: ClassName - WaitEventIO +AIO_SUBMIT "Waiting for AIO submission." +AIO_DRAIN "Waiting for IOs to finish." +AIO_COMPLETION "Waiting for completion callback." BASEBACKUP_READ "Waiting for base backup to read from a file." BASEBACKUP_SYNC "Waiting for data written by a base backup to reach durable storage." BASEBACKUP_WRITE "Waiting for base backup to write to a file." diff --git a/src/backend/utils/resowner/resowner.c b/src/backend/utils/resowner/resowner.c index 505534ee8d3..5cf14472ebd 100644 --- a/src/backend/utils/resowner/resowner.c +++ b/src/backend/utils/resowner/resowner.c @@ -47,6 +47,8 @@ #include "common/hashfn.h" #include "common/int.h" +#include "lib/ilist.h" +#include "storage/aio.h" #include "storage/ipc.h" #include "storage/predicate.h" #include "storage/proc.h" @@ -155,6 +157,12 @@ struct ResourceOwnerData /* The local locks cache. */ LOCALLOCK *locks[MAX_RESOWNER_LOCKS]; /* list of owned locks */ + + /* + * AIO handles need be registered in critical sections and therefore + * cannot use the normal ResoureElem mechanism. + */ + dlist_head aio_handles; }; @@ -425,6 +433,8 @@ ResourceOwnerCreate(ResourceOwner parent, const char *name) parent->firstchild = owner; } + dlist_init(&owner->aio_handles); + return owner; } @@ -725,6 +735,14 @@ ResourceOwnerReleaseInternal(ResourceOwner owner, * so issue warnings. In the abort case, just clean up quietly. */ ResourceOwnerReleaseAll(owner, phase, isCommit); + + /* XXX: Could probably be a later phase? */ + while (!dlist_is_empty(&owner->aio_handles)) + { + dlist_node *node = dlist_head_node(&owner->aio_handles); + + pgaio_io_release_resowner(node, !isCommit); + } } else if (phase == RESOURCE_RELEASE_LOCKS) { @@ -1082,3 +1100,15 @@ ResourceOwnerForgetLock(ResourceOwner owner, LOCALLOCK *locallock) elog(ERROR, "lock reference %p is not owned by resource owner %s", locallock, owner->name); } + +void +ResourceOwnerRememberAioHandle(ResourceOwner owner, struct dlist_node *ioh_node) +{ + dlist_push_tail(&owner->aio_handles, ioh_node); +} + +void +ResourceOwnerForgetAioHandle(ResourceOwner owner, struct dlist_node *ioh_node) +{ + dlist_delete_from(&owner->aio_handles, ioh_node); +} diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 2586d1cf53f..bc1acbb98ee 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1263,6 +1263,7 @@ InvalMessageArray InvalidationInfo InvalidationMsgsGroup IoMethod +IoMethodOps IpcMemoryId IpcMemoryKey IpcMemoryState @@ -2100,6 +2101,23 @@ Permutation PermutationStep PermutationStepBlocker PermutationStepBlockerType +PgAioCtl +PgAioHandle +PgAioHandleFlags +PgAioHandleRef +PgAioHandleSharedCallbackID +PgAioHandleSharedCallbacks +PgAioHandleSharedCallbacksEntry +PgAioHandleState +PgAioOp +PgAioOpData +PgAioPerBackend +PgAioResultStatus +PgAioResult +PgAioReturn +PgAioSubjectData +PgAioSubjectID +PgAioSubjectInfo PgArchData PgBackendGSSStatus PgBackendSSLStatus -- 2.45.2.746.g06e570c0df.dirty