database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-11-07 19:06:32 +03:00
Code Activity

Add a new slot sync worker to synchronize logical slots.

Browse Source 
By enabling slot synchronization, all the failover logical replication
slots on the primary (assuming configurations are appropriate) are
automatically created on the physical standbys and are synced
periodically. The slot sync worker on the standby server pings the primary
server at regular intervals to get the necessary failover logical slots
information and create/update the slots locally. The slots that no longer
require synchronization are automatically dropped by the worker.

The nap time of the worker is tuned according to the activity on the
primary. The slot sync worker waits for some time before the next
synchronization, with the duration varying based on whether any slots were
updated during the last cycle.

A new parameter sync_replication_slots enables or disables this new
process.

On promotion, the slot sync worker is shut down by the startup process to
drop any temporary slots acquired by the slot sync worker and to prevent
the worker from trying to fetch the failover slots.

A functionality to allow logical walsenders to wait for the physical will
be done in a subsequent commit.

Author: Shveta Malik, Hou Zhijie based on design inputs by Masahiko Sawada and Amit Kapila
Reviewed-by: Masahiko Sawada, Bertrand Drouvot, Peter Smith, Dilip Kumar, Ajin Cherian, Nisha Moond, Kuroda Hayato, Amit Kapila
Discussion: https://postgr.es/m/514f6f2f-6833-4539-39f1-96cd1e011f23@enterprisedb.com
This commit is contained in:
Amit Kapila
2024-02-22 15:25:15 +05:30
parent 3d47b75546
commit 93db6cbda0
19 changed files with 989 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
src/backend/postmaster/postmaster.c
View File

@@ -115,6 +115,7 @@
#include "postmaster/syslogger.h"
#include "postmaster/walsummarizer.h"
#include "replication/logicallauncher.h"
#include "replication/slotsync.h"
#include "replication/walsender.h"
#include "storage/fd.h"
#include "storage/ipc.h"
@@ -167,11 +168,11 @@
* they will never become live backends. dead_end children are not assigned a
* PMChildSlot. dead_end children have bkend_type NORMAL.
*
* "Special" children such as the startup, bgwriter and autovacuum launcher
* tasks are not in this list. They are tracked via StartupPID and other
* pid_t variables below. (Thus, there can't be more than one of any given
* "special" child process type. We use BackendList entries for any child
* process there can be more than one of.)
* "Special" children such as the startup, bgwriter, autovacuum launcher, and
* slot sync worker tasks are not in this list. They are tracked via StartupPID
* and other pid_t variables below. (Thus, there can't be more than one of any
* given "special" child process type. We use BackendList entries for any
* child process there can be more than one of.)
*/
typedef struct bkend
{
@@ -254,7 +255,8 @@ static pid_t StartupPID = 0,
WalSummarizerPID = 0,
AutoVacPID = 0,
PgArchPID = 0,
SysLoggerPID = 0;
SysLoggerPID = 0,
SlotSyncWorkerPID = 0;
/* Startup process's status */
typedef enum
@@ -445,6 +447,7 @@ static void StartAutovacuumWorker(void);
static void MaybeStartWalReceiver(void);
static void MaybeStartWalSummarizer(void);
static void InitPostmasterDeathWatchHandle(void);
static void MaybeStartSlotSyncWorker(void);
/*
* Archiver is allowed to start up at the current postmaster state?
@@ -1822,6 +1825,9 @@ ServerLoop(void)
if (PgArchPID == 0 && PgArchStartupAllowed())
PgArchPID = StartChildProcess(ArchiverProcess);
/* If we need to start a slot sync worker, try to do that now */
MaybeStartSlotSyncWorker();
/* If we need to signal the autovacuum launcher, do so now */
if (avlauncher_needs_signal)
{
@@ -2661,6 +2667,8 @@ process_pm_reload_request(void)
signal_child(PgArchPID, SIGHUP);
if (SysLoggerPID != 0)
signal_child(SysLoggerPID, SIGHUP);
if (SlotSyncWorkerPID != 0)
signal_child(SlotSyncWorkerPID, SIGHUP);
/* Reload authentication config files too */
if (!load_hba())
@@ -3010,6 +3018,7 @@ process_pm_child_exit(void)
AutoVacPID = StartAutoVacLauncher();
if (PgArchStartupAllowed() && PgArchPID == 0)
PgArchPID = StartChildProcess(ArchiverProcess);
MaybeStartSlotSyncWorker();
/* workers may be scheduled to start now */
maybe_start_bgworkers();
@@ -3180,6 +3189,22 @@ process_pm_child_exit(void)
continue;
}
/*
* Was it the slot sync worker? Normal exit or FATAL exit can be
* ignored (FATAL can be caused by libpqwalreceiver on receiving
* shutdown request by the startup process during promotion); we'll
* start a new one at the next iteration of the postmaster's main
* loop, if necessary. Any other exit condition is treated as a crash.
*/
if (pid == SlotSyncWorkerPID)
{
SlotSyncWorkerPID = 0;
if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
HandleChildCrash(pid, exitstatus,
_("slot sync worker process"));
continue;
}
/* Was it one of our background workers? */
if (CleanupBackgroundWorker(pid, exitstatus))
{
@@ -3384,7 +3409,7 @@ CleanupBackend(int pid,
/*
* HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
* walwriter, autovacuum, archiver or background worker.
* walwriter, autovacuum, archiver, slot sync worker, or background worker.
*
* The objectives here are to clean up our local state about the child
* process, and to signal all other remaining children to quickdie.
@@ -3546,6 +3571,12 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
else if (PgArchPID != 0 && take_action)
sigquit_child(PgArchPID);
/* Take care of the slot sync worker too */
if (pid == SlotSyncWorkerPID)
SlotSyncWorkerPID = 0;
else if (SlotSyncWorkerPID != 0 && take_action)
sigquit_child(SlotSyncWorkerPID);
/* We do NOT restart the syslogger */
if (Shutdown != ImmediateShutdown)
@@ -3686,6 +3717,8 @@ PostmasterStateMachine(void)
signal_child(WalReceiverPID, SIGTERM);
if (WalSummarizerPID != 0)
signal_child(WalSummarizerPID, SIGTERM);
if (SlotSyncWorkerPID != 0)
signal_child(SlotSyncWorkerPID, SIGTERM);
/* checkpointer, archiver, stats, and syslogger may continue for now */
/* Now transition to PM_WAIT_BACKENDS state to wait for them to die */
@@ -3701,13 +3734,13 @@ PostmasterStateMachine(void)
/*
* PM_WAIT_BACKENDS state ends when we have no regular backends
* (including autovac workers), no bgworkers (including unconnected
* ones), and no walwriter, autovac launcher or bgwriter. If we are
* doing crash recovery or an immediate shutdown then we expect the
* checkpointer to exit as well, otherwise not. The stats and
* syslogger processes are disregarded since they are not connected to
* shared memory; we also disregard dead_end children here. Walsenders
* and archiver are also disregarded, they will be terminated later
* after writing the checkpoint record.
* ones), and no walwriter, autovac launcher, bgwriter or slot sync
* worker. If we are doing crash recovery or an immediate shutdown
* then we expect the checkpointer to exit as well, otherwise not. The
* stats and syslogger processes are disregarded since they are not
* connected to shared memory; we also disregard dead_end children
* here. Walsenders and archiver are also disregarded, they will be
* terminated later after writing the checkpoint record.
*/
if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
StartupPID == 0 &&
@@ -3717,7 +3750,8 @@ PostmasterStateMachine(void)
(CheckpointerPID == 0 ||
(!FatalError && Shutdown < ImmediateShutdown)) &&
WalWriterPID == 0 &&
AutoVacPID == 0)
AutoVacPID == 0 &&
SlotSyncWorkerPID == 0)
{
if (Shutdown >= ImmediateShutdown || FatalError)
{
@@ -3815,6 +3849,7 @@ PostmasterStateMachine(void)
Assert(CheckpointerPID == 0);
Assert(WalWriterPID == 0);
Assert(AutoVacPID == 0);
Assert(SlotSyncWorkerPID == 0);
/* syslogger is not considered here */
pmState = PM_NO_CHILDREN;
}
@@ -4038,6 +4073,8 @@ TerminateChildren(int signal)
signal_child(AutoVacPID, signal);
if (PgArchPID != 0)
signal_child(PgArchPID, signal);
if (SlotSyncWorkerPID != 0)
signal_child(SlotSyncWorkerPID, signal);
}
/*
@@ -4850,6 +4887,7 @@ SubPostmasterMain(int argc, char *argv[])
*/
if (strcmp(argv[1], "--forkbackend") == 0 ||
strcmp(argv[1], "--forkavlauncher") == 0 ||
strcmp(argv[1], "--forkssworker") == 0 ||
strcmp(argv[1], "--forkavworker") == 0 ||
strcmp(argv[1], "--forkaux") == 0 ||
strcmp(argv[1], "--forkbgworker") == 0)
@@ -4953,6 +4991,13 @@ SubPostmasterMain(int argc, char *argv[])
AutoVacWorkerMain(argc - 2, argv + 2); /* does not return */
}
if (strcmp(argv[1], "--forkssworker") == 0)
{
/* Restore basic shared memory pointers */
InitShmemAccess(UsedShmemSegAddr);
ReplSlotSyncWorkerMain(argc - 2, argv + 2); /* does not return */
}
if (strcmp(argv[1], "--forkbgworker") == 0)
{
/* do this as early as possible; in particular, before InitProcess() */
@@ -5498,6 +5543,24 @@ MaybeStartWalSummarizer(void)
}
/*
* MaybeStartSlotSyncWorker
* Start the slot sync worker, if not running and our state allows.
*
* We allow to start the slot sync worker when we are on a hot standby,
* fast or immediate shutdown is not in progress, slot sync parameters
* are configured correctly, and it is the first time of worker's launch,
* or enough time has passed since the worker was launched last.
*/
static void
MaybeStartSlotSyncWorker(void)
{
if (SlotSyncWorkerPID == 0 && pmState == PM_HOT_STANDBY &&
Shutdown <= SmartShutdown && sync_replication_slots &&
ValidateSlotSyncParams(LOG) && SlotSyncWorkerCanRestart())
SlotSyncWorkerPID = StartSlotSyncWorker();
}
/*
* Create the opts file
*/