{"Entry":{"collection":"guc","key":"io_max_concurrency","name":"io_max_concurrency","aliases":[],"metadata":{"baseline":false,"boot_human":"Not specified","boot_val":null,"category":"Resource Usage / I/O","category_zh":"","changed_in":["19"],"changes":[{"documentation_changed":false,"fields":{},"from":"17","status":"added","to":"18"},{"documentation_changed":false,"fields":{"extra_desc":{"from":null,"to":"-1 means use a value based on \"shared_buffers\" and the maximum number of processes."}},"from":"18","status":"changed","to":"19"}],"content_hash":"17dabd969d276bcff2636a10cbe60a7dde354fe3f88431a313008476d2729485","context":"","default_changed_in":[],"default_history":[{"from":"18","to":"19","value":"-1"}],"editorial":{"advice":{"olap":"Raise the per-process ceiling only when one scan or maintenance process cannot keep high-IOPS storage busy and the target-concurrency settings are already appropriate. Compare outstanding-operation counts, throughput, and latency; this parameter does not change request size.","oltp":"Leave -1 until measurements show the automatic per-process ceiling constrains eligible AIO. If setting it explicitly, multiply the value across concurrently active processes and test device queueing plus tail latency after the required restart.","small":"Prefer -1. An explicit high ceiling is multiplied by concurrent processes and can overwhelm a small device even though no single process exceeds its configured limit."},"mechanism":["io_max_concurrency is a PostgreSQL 18 server-start ceiling on the number of I/O operations that one process may execute simultaneously. It is per process, not a reservation and not a cluster-wide cap.","The default -1 asks PostgreSQL to derive a value from shared_buffers and configured process maxima, capped at 64. Because many backends and workers can each reach their own ceiling, possible cluster-wide outstanding I/O can be much larger.","effective_io_concurrency and maintenance_io_concurrency are workload targets below this ceiling; io_method chooses the execution mechanism, and combine limits control bytes per request. Changing io_max_concurrency requires a restart."],"pitfalls":["Treating the per-process ceiling as a cluster-wide I/O limit.","Reading -1 as unlimited rather than automatic sizing capped at 64.","Calling the ceiling reserved capacity; it permits concurrency but does not preallocate I/O slots.","Confusing operation count with io_combine_limit's bytes per request.","Changing the value without a restart or without multiplying exposure across processes."],"references":[{"title":"PostgreSQL 19 Beta 4: io_max_concurrency","url":"https://www.postgresql.org/docs/19/runtime-config-resource.html#GUC-IO-MAX-CONCURRENCY"},{"title":"PostgreSQL 19 release notes","url":"https://www.postgresql.org/docs/19/release-19.html"}],"related":["io_method","io_workers","effective_io_concurrency","maintenance_io_concurrency","io_combine_limit","max_connections"],"summary":"io_max_concurrency — Max number of IOs that one process can execute simultaneously. Observed in PG18–19 Beta 4; its last measured boot default is -1 in PG19 Beta 4, with postmaster context. This is a beta-snapshot fact and can change before PostgreSQL 19 GA."},"enumvals":[],"first_version":"18","group":"Resource Usage","group_slug":"resource","imported_at":"2026-09-27T17:57:31.405386+08:00","intro_commit":{"authored_at":"2025-03-17T18:51:33-04:00","discussion":["https://postgr.es/m/uvrtrknj4kdytuboidbhwclo4gxhswwcpgadptsjvjqcluzmah%40brqs62irg4dt"],"hash":"02844012b304ba80d1c48d51f6fe10bb622490cc","subject":"aio: Basic subsystem initialization","url":"https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=02844012b304ba80d1c48d51f6fe10bb622490cc"},"key":"io_max_concurrency","last_version":"20","max_val":"","min_val":"","name":"io_max_concurrency","position":183,"present_in":["18","19","20"],"short_desc":"Controls the maximum number of I/O operations that one process can execute simultaneously.","short_desc_zh":"","source_rev":"english-manuals:1dcd04a4e96190a465f3a43a0b75603f5e871780a65ec58a075149572c0c42e3","unit":"","vartype":"integer"}},"Definition":{"Collection":"guc","Key":"io_max_concurrency","SourceDatabase":"center","Version":"18","SourceTable":"guc","SourceKey":"io_max_concurrency","SourceRevision":"english-manuals:1dcd04a4e96190a465f3a43a0b75603f5e871780a65ec58a075149572c0c42e3","Facts":{"boot_val":"-1","category":"Resource Usage / I/O","context":"postmaster","description":"Controls the maximum number of I/O operations that one process can execute simultaneously. The default setting of -1 selects a number based on shared_buffers and the maximum number of processes (max_connections, autovacuum_worker_slots, max_worker_processes and max_wal_senders), but not more than 64. This parameter can only be set at server start.","doc":{"anchor":"GUC-IO-MAX-CONCURRENCY","file":"runtime-config-resource.html","lang":"en","sha256":"2e207c599f0884dfbe594558c478a2c7c132578981071e980e2015f31dfce28c","slug":"18"},"documented":true,"enumvals":null,"extra_desc":null,"lang":"en","max_val":"1024","metadata_version":"18","min_val":"-1","name":"io_max_concurrency","short_desc":"Max number of IOs that one process can execute simultaneously.","source":"pg-settings-source-snapshot","unit":null,"vartype":"integer"},"ManualEvidence":{"doc":{"anchor":"GUC-IO-MAX-CONCURRENCY","file":"runtime-config-resource.html","lang":"en","sha256":"2e207c599f0884dfbe594558c478a2c7c132578981071e980e2015f31dfce28c","slug":"18"}},"MeasuredEvidence":{"metadata_version":"18"}},"Text":{"Collection":"guc","Key":"io_max_concurrency","SourceDatabase":"pgweb","Version":"18","Locale":"zh-Hans","Title":"io_max_concurrency","Summary":"","BodyHTML":"\u003cp\u003e控制一个进程可以同时执行的最大 I/O 操作数。\u003c/p\u003e\u003cp\u003e默认设置 \u003ccode\u003e-1\u003c/code\u003e 会根据\u003ca href=\"/docs/18/runtime-config-resource.html#GUC-SHARED-BUFFERS\" rel=\"nofollow\"\u003eshared_buffers\u003c/a\u003e以及最大进程数（\u003ca href=\"/docs/18/runtime-config-connection.html#GUC-MAX-CONNECTIONS\" rel=\"nofollow\"\u003emax_connections\u003c/a\u003e、\u003ca href=\"/docs/18/runtime-config-vacuum.html#GUC-AUTOVACUUM-WORKER-SLOTS\" rel=\"nofollow\"\u003eautovacuum_worker_slots\u003c/a\u003e、\u003ca href=\"/docs/18/runtime-config-resource.html#GUC-MAX-WORKER-PROCESSES\" rel=\"nofollow\"\u003emax_worker_processes\u003c/a\u003e和\u003ca href=\"/docs/18/runtime-config-replication.html#GUC-MAX-WAL-SENDERS\" rel=\"nofollow\"\u003emax_wal_senders\u003c/a\u003e）来选择一个值，但不会超过 \u003ccode\u003e64\u003c/code\u003e。\u003c/p\u003e\u003cp\u003e此参数只能在服务器启动时设置。\u003c/p\u003e","SourceRevision":"2026-09-11@29c86d9","ContentHash":"a9114b3ccbbe94c182beeb9dc264465d54884b1024b23b021094723b311679e8","Payload":{"carried_from":"","carry_reason":"","doc_html":"\u003cp\u003e控制一个进程可以同时执行的最大 I/O 操作数。\u003c/p\u003e\u003cp\u003e默认设置 \u003ccode class=\"literal\"\u003e-1\u003c/code\u003e 会根据\u003ca href=\"/docs/18/runtime-config-resource.html#GUC-SHARED-BUFFERS\"\u003eshared_buffers\u003c/a\u003e以及最大进程数（\u003ca href=\"/docs/18/runtime-config-connection.html#GUC-MAX-CONNECTIONS\"\u003emax_connections\u003c/a\u003e、\u003ca href=\"/docs/18/runtime-config-vacuum.html#GUC-AUTOVACUUM-WORKER-SLOTS\"\u003eautovacuum_worker_slots\u003c/a\u003e、\u003ca href=\"/docs/18/runtime-config-resource.html#GUC-MAX-WORKER-PROCESSES\"\u003emax_worker_processes\u003c/a\u003e和\u003ca href=\"/docs/18/runtime-config-replication.html#GUC-MAX-WAL-SENDERS\"\u003emax_wal_senders\u003c/a\u003e）来选择一个值，但不会超过 \u003ccode class=\"literal\"\u003e64\u003c/code\u003e。\u003c/p\u003e\u003cp\u003e此参数只能在服务器启动时设置。\u003c/p\u003e","doc_same_as":""}},"RequestedLocale":"zh-Hans","Fallback":false,"Versions":["18","19","20"],"Locales":["en","zh-Hans"],"Signatures":null,"Spellings":null,"SQLState":null,"Evidence":null}