PostgreSQL pg_ctl start超时分析

一、问题
pg_ctl start启动时报错退出：pg_ctl：server did not start in time。超时时间是多少？从什么时候到哪个阶段算超时？

二、分析：该信息打印位置，从后面代码段do_start函数中可以看出
1、pg_ctl start调用start_postmaster启动PG的主进程后，每隔0.1ms检查一次postmaster.pid文件，是否已写入ready/standby
2、总共会检查600次，即从启动主进程后，最多等待60s，如果没有写入ready/standby则打印上述日志并退出
3、默认等待时间是60s，如果pg_ctl start -t指定等待时间，则等待时间为该指定时间

三、什么时候postmaster.pid文件写入ready/standby
1、如果是主机不管有没有设置hot standby
1）当startup进程恢复完成退出时，调用proc_exit函数向主进程发送SIGCHLD信号并退出
2）主进程接收到信号后，signal处理函数reaper调用AddToDataDirLockFile向postmaster.pid文件写入ready
2、如果是备机即data目录下有recovery.cnf文件，且设置了hot standby，在实际恢复前没有到达一致性位置
1）startup进程向主进程发送PMSIGNAL_RECOVERY_STARTED信号，主进程调用信号处理函数sigusr1_handler，将pmState=PM_RECOVERY
2）每次读取下一个xlog前都会调用CheckRecoveryConsistency函数进行一致性检查：
2.1 进入一致性状态，starup进程向主进程发送PMSIGNAL_BEGIN_HOT_STANDBY信号，主进程接收到信号后调用sigusr1_handler->AddToDataDirLockFile向postmaster.pid文件写入ready
3、如果是备机即data目录下有recovery.cnf文件，且设置了hot standby，在实际恢复前没有到达一致性位置
1）startup进程向主进程发送PMSIGNAL_RECOVERY_STARTED信号，主进程调用信号处理函数sigusr1_handler，将pmState=PM_RECOVERY
2）每次读取下一个xlog前都会调用CheckRecoveryConsistency函数进行一致性检查。如果没有进入一致性状态
3）本地日志恢复完成，切换日志源时同样调用CheckRecoveryConsistency函数进行一致性检查
3.1 进入一致性状态，starup进程向主进程发送PMSIGNAL_BEGIN_HOT_STANDBY信号，主进程接收到信号后调用sigusr1_handler->AddToDataDirLockFile向postmaster.pid文件写入ready
4、如果是备机即data目录下有recovery.cnf文件，且设置了hot standby，在实际恢复前到达一致性位置
1）startup进程向主进程发送PMSIGNAL_RECOVERY_STARTED信号，主进程调用信号处理函数sigusr1_handler，将pmState=PM_RECOVERY
2）CheckRecoveryConsistency函数进行一致性检查，向主进程发送PMSIGNAL_BEGIN_HOT_STANDBY信号，主进程接收到信号后调用sigusr1_handler->AddToDataDirLockFile向postmaster.pid文件写入ready
5、如果是备机即data目录下有recovery.cnf文件，没有设置hot standby
1）startup进程向主进程发送PMSIGNAL_RECOVERY_STARTED信号
2）主进程接收到信号后，向postmaster.将pmState=PM_RECOVERY

四、代码分析
1、pg_ctl start流程

do_start->    pm_pid = start_postmaster();    if (do_wait){        print_msg(_("waiting for server to start..."));        switch (wait_for_postmaster(pm_pid, false)){            case POSTMASTER_READY:                print_msg(_(" done\n"));                print_msg(_("server started\n"));                break;            case POSTMASTER_STILL_STARTING:                print_msg(_(" stopped waiting\n"));                write_stderr(_("%s: server did not start in time\n"), progname);                exit(1);                break;            case POSTMASTER_FAILED:                print_msg(_(" stopped waiting\n"));                write_stderr(_("%s: could not start server\n" "Examine the log output.\n"), progname);                exit(1);                break;        }    }else        print_msg(_("server starting\n"));

wait_for_postmaster->    for (i = 0; i < wait_seconds * WAITS_PER_SEC; i++){        if ((optlines = readfile(pid_file, &numlines)) != NULL && numlines >= LOCK_FILE_LINE_PM_STATUS){            pmpid = atol(optlines[LOCK_FILE_LINE_PID - 1]);            pmstart = atol(optlines[LOCK_FILE_LINE_START_TIME - 1]);            if (pmstart >= start_time - 2 && pmpid == pm_pid){                char       *pmstatus = optlines[LOCK_FILE_LINE_PM_STATUS - 1];                if (strcmp(pmstatus, PM_STATUS_READY) == 0 || strcmp(pmstatus, PM_STATUS_STANDBY) == 0){                    /* postmaster is done starting up */                    free_readfile(optlines);                    return POSTMASTER_READY;                }            }        }        free_readfile(optlines);        if (waitpid((pid_t) pm_pid, &exitstatus, WNOHANG) == (pid_t) pm_pid)            return POSTMASTER_FAILED;        pg_usleep(USEC_PER_SEC / WAITS_PER_SEC);    }    /* out of patience; report that postmaster is still starting up */    return POSTMASTER_STILL_STARTING;

2、server主进程及信号处理函数

PostmasterMain->    pqsignal_no_restart(SIGUSR1, sigusr1_handler);  /* message from child process */    pqsignal_no_restart(SIGCHLD, reaper);   /* handle child termination */    ...    StartupXLOG();    ...    proc_exit(0);//exit函数向主进程发送SIGCHLD信号

reaper->//进程终止或者停止的信号    AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_READY);

postmaster进程接收信号：sigusr1_handler->    if (CheckPostmasterSignal(PMSIGNAL_RECOVERY_STARTED) &&        pmState == PM_STARTUP && Shutdown == NoShutdown){        CheckpointerPID = StartCheckpointer();        BgWriterPID = StartBackgroundWriter();        if (XLogArchivingAlways())            PgArchPID = pgarch_start();        //hot_standby在postgresql.conf文件中配置TRUE        //表示在恢复的时候允许连接        if (!EnableHotStandby){            //将standby写入postmaster.pid文件，表示up但不允许连接            AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_STANDBY);        }        pmState = PM_RECOVERY;    }    if (CheckPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY) &&        pmState == PM_RECOVERY && Shutdown == NoShutdown){        PgStatPID = pgstat_start();        //将ready写入postmaster.pid文件，允许连接        AddToDataDirLockFile(LOCK_FILE_LINE_PM_STATUS, PM_STATUS_READY);        pmState = PM_HOT_STANDBY;    }    ...

3、Startup进程

StartupXLOG->    ReadCheckpointRecord    if (ArchiveRecoveryRequested && IsUnderPostmaster){//有recovery.conf文件则ArchiveRecoveryRequested为TRUE        //有recovery.conf文件则ArchiveRecoveryRequested为TRUE        PublishStartupProcessInformation();        SetForwardFsyncRequests();        //向master进程发送PMSIGNAL_RECOVERY_STARTED信号        SendPostmasterSignal(PMSIGNAL_RECOVERY_STARTED);        bgwriterLaunched = true;    }    CheckRecoveryConsistency();-->...    |-- if (standbyState == STANDBY_SNAPSHOT_READY && !LocalHotStandbyActive &&    |       reachedConsistency && IsUnderPostmaster){    |       SpinLockAcquire(&XLogCtl->info_lck);    |       XLogCtl->SharedHotStandbyActive = true;    |       SpinLockRelease(&XLogCtl->info_lck);    |       LocalHotStandbyActive = true;    |       SendPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY);    |-- }    ...    回放一个record后，每次读取下一个record前都会调用CheckRecoveryConsistency