mirror of
https://github.com/postgres/postgres.git
synced 2025-11-25 12:03:53 +03:00
216a784829
Currently, for large transactions, the publisher sends the data in multiple streams (changes divided into chunks depending upon logical_decoding_work_mem), and then on the subscriber-side, the apply worker writes the changes into temporary files and once it receives the commit, it reads from those files and applies the entire transaction. To improve the performance of such transactions, we can instead allow them to be applied via parallel workers. In this approach, we assign a new parallel apply worker (if available) as soon as the xact's first stream is received and the leader apply worker will send changes to this new worker via shared memory. The parallel apply worker will directly apply the change instead of writing it to temporary files. However, if the leader apply worker times out while attempting to send a message to the parallel apply worker, it will switch to "partial serialize" mode - in this mode, the leader serializes all remaining changes to a file and notifies the parallel apply workers to read and apply them at the end of the transaction. We use a non-blocking way to send the messages from the leader apply worker to the parallel apply to avoid deadlocks. We keep this parallel apply assigned till the transaction commit is received and also wait for the worker to finish at commit. This preserves commit ordering and avoid writing to and reading from files in most cases. We still need to spill if there is no worker available. This patch also extends the SUBSCRIPTION 'streaming' parameter so that the user can control whether to apply the streaming transaction in a parallel apply worker or spill the change to disk. The user can set the streaming parameter to 'on/off', or 'parallel'. The parameter value 'parallel' means the streaming will be applied via a parallel apply worker, if available. The parameter value 'on' means the streaming transaction will be spilled to disk. The default value is 'off' (same as current behaviour). In addition, the patch extends the logical replication STREAM_ABORT message so that abort_lsn and abort_time can also be sent which can be used to update the replication origin in parallel apply worker when the streaming transaction is aborted. Because this message extension is needed to support parallel streaming, parallel streaming is not supported for publications on servers < PG16. Author: Hou Zhijie, Wang wei, Amit Kapila with design inputs from Sawada Masahiko Reviewed-by: Sawada Masahiko, Peter Smith, Dilip Kumar, Shi yu, Kuroda Hayato, Shveta Mallik Discussion: https://postgr.es/m/CAA4eK1+wyN6zpaHUkCLorEWNx75MG0xhMwcFhvjqm2KURZEAGw@mail.gmail.com
73 lines
2.4 KiB
C
73 lines
2.4 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* procsignal.h
|
|
* Routines for interprocess signaling
|
|
*
|
|
*
|
|
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
|
|
* Portions Copyright (c) 1994, Regents of the University of California
|
|
*
|
|
* src/include/storage/procsignal.h
|
|
*
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#ifndef PROCSIGNAL_H
|
|
#define PROCSIGNAL_H
|
|
|
|
#include "storage/backendid.h"
|
|
|
|
|
|
/*
|
|
* Reasons for signaling a Postgres child process (a backend or an auxiliary
|
|
* process, like checkpointer). We can cope with concurrent signals for different
|
|
* reasons. However, if the same reason is signaled multiple times in quick
|
|
* succession, the process is likely to observe only one notification of it.
|
|
* This is okay for the present uses.
|
|
*
|
|
* Also, because of race conditions, it's important that all the signals be
|
|
* defined so that no harm is done if a process mistakenly receives one.
|
|
*/
|
|
typedef enum
|
|
{
|
|
PROCSIG_CATCHUP_INTERRUPT, /* sinval catchup interrupt */
|
|
PROCSIG_NOTIFY_INTERRUPT, /* listen/notify interrupt */
|
|
PROCSIG_PARALLEL_MESSAGE, /* message from cooperating parallel backend */
|
|
PROCSIG_WALSND_INIT_STOPPING, /* ask walsenders to prepare for shutdown */
|
|
PROCSIG_BARRIER, /* global barrier interrupt */
|
|
PROCSIG_LOG_MEMORY_CONTEXT, /* ask backend to log the memory contexts */
|
|
PROCSIG_PARALLEL_APPLY_MESSAGE, /* Message from parallel apply workers */
|
|
|
|
/* Recovery conflict reasons */
|
|
PROCSIG_RECOVERY_CONFLICT_DATABASE,
|
|
PROCSIG_RECOVERY_CONFLICT_TABLESPACE,
|
|
PROCSIG_RECOVERY_CONFLICT_LOCK,
|
|
PROCSIG_RECOVERY_CONFLICT_SNAPSHOT,
|
|
PROCSIG_RECOVERY_CONFLICT_BUFFERPIN,
|
|
PROCSIG_RECOVERY_CONFLICT_STARTUP_DEADLOCK,
|
|
|
|
NUM_PROCSIGNALS /* Must be last! */
|
|
} ProcSignalReason;
|
|
|
|
typedef enum
|
|
{
|
|
PROCSIGNAL_BARRIER_SMGRRELEASE /* ask smgr to close files */
|
|
} ProcSignalBarrierType;
|
|
|
|
/*
|
|
* prototypes for functions in procsignal.c
|
|
*/
|
|
extern Size ProcSignalShmemSize(void);
|
|
extern void ProcSignalShmemInit(void);
|
|
|
|
extern void ProcSignalInit(int pss_idx);
|
|
extern int SendProcSignal(pid_t pid, ProcSignalReason reason,
|
|
BackendId backendId);
|
|
|
|
extern uint64 EmitProcSignalBarrier(ProcSignalBarrierType type);
|
|
extern void WaitForProcSignalBarrier(uint64 generation);
|
|
extern void ProcessProcSignalBarrier(void);
|
|
|
|
extern void procsignal_sigusr1_handler(SIGNAL_ARGS);
|
|
|
|
#endif /* PROCSIGNAL_H */
|