尝试停库时遇到的两个现象：
- 当archiver process仍有.ready文件待处理时，执行fast模式执行stop时，必须等其处理完
- 当walsender进程仍有wal日志未发送至从库时，必须等其发送完
本来打算自己研究一下，发现阿里云早就有文章研究过了，学习记录一下。
原文链接：数据库内核月报
如果数据库开启了归档，smart, fast 停库时会怎么处理pgarch进程
发起最后一次archive周期，将所有.ready的wal进行归档，除非中间archive_command遇到错误，否则要等所有的.ready文件都触发并执行完成archive_command。
如果有walsender进程在，smart, fast 停库时会怎么处理walsender进程
如果有walsender进程存在（例如有standby，有pg_basebackup，有pg_receivewal等利用流复制协议的客户端就有walsender进程），那么要等这个walsender将所有未发送完的wal日志都发送给下游。
src/backend/postmaster/postmaster.c
/*
* Reaper -- signal handler to cleanup after a child process dies.
*/
static void
reaper(SIGNAL_ARGS)
{
.....................
while ((pid = waitpid(-1, &exitstatus, WNOHANG)) > 0)
{
.......................
/*
* Was it the checkpointer?
*/
if (pid == CheckpointerPID)
{
CheckpointerPID = 0;
if (EXIT_STATUS_0(exitstatus) && pmState == PM_SHUTDOWN)
{
/*
* OK, we saw normal exit of the checkpointer after it's been
* told to shut down. We expect that it wrote a shutdown
* checkpoint. (If for some reason it didn't, recovery will
* occur on next postmaster start.)
*
* At this point we should have no normal backend children
* left (else we'd not be in PM_SHUTDOWN state) but we might
* have dead_end children to wait for.
*
* If we have an archiver subprocess, tell it to do a last
* archive cycle and quit. Likewise, if we have walsender
* processes, tell them to send any remaining WAL and quit.
*/
Assert(Shutdown > NoShutdown);
/* 唤醒归档进程 进行一轮归档 */
/* Waken archiver for the last time */
if (PgArchPID != 0)
signal_child(PgArchPID, SIGUSR2);
/* wal sender，发送完所有未发送的redo */
/*
* Waken walsenders for the last time. No regular backends
* should be around anymore.
*/
SignalChildren(SIGUSR2);
pmState = PM_SHUTDOWN_2;
/*
* We can also shut down the stats collector now; there's
* nothing left for it to do.
*/
if (PgStatPID != 0)
signal_child(PgStatPID, SIGQUIT);
} 唤醒归档
src/backend/postmaster/pgarch.c
/* SIGUSR2 signal handler for archiver process */
static void
pgarch_waken_stop(SIGNAL_ARGS)
{
int save_errno = errno;
/* set flag to do a final cycle and shut down afterwards */
/* 停库，触发最后一轮归档周期 */
ready_to_stop = true;
SetLatch(MyLatch);
errno = save_errno;
} /*
* pgarch_MainLoop
*
* Main loop for archiver
*/
static void
pgarch_MainLoop(void)
{
pg_time_t last_copy_time = 0;
bool time_to_stop;
/*
* We run the copy loop immediately upon entry, in case there are
* unarchived files left over from a previous database run (or maybe the
* archiver died unexpectedly). After that we wait for a signal or
* timeout before doing more.
*/
wakened = true;
/*
* There shouldn't be anything for the archiver to do except to wait for a
* signal ... however, the archiver exists to protect our data, so she
* wakes up occasionally to allow herself to be proactive.
*/
do
{
ResetLatch(MyLatch);
/* When we get SIGUSR2, we do one more archive cycle, then exit */
/* 停库，触发最后一轮归档周期 */
time_to_stop = ready_to_stop;
/* Check for config update */
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
}
/*
* If we've gotten SIGTERM, we normally just sit and do nothing until
* SIGUSR2 arrives. However, that means a random SIGTERM would
* disable archiving indefinitely, which doesn't seem like a good
* idea. If more than 60 seconds pass since SIGTERM, exit anyway, so
* that the postmaster can start a new archiver if needed.
*/
if (got_SIGTERM)
{
time_t curtime = time(NULL);
if (last_sigterm_time == 0)
last_sigterm_time = curtime;
else if ((unsigned int) (curtime - last_sigterm_time) >=
(unsigned int) 60)
break;
}
/* Do what we're here for */
if (wakened || time_to_stop)
{
wakened = false;
pgarch_ArchiverCopyLoop(); // 最后一次循环
last_copy_time = time(NULL);
}
/*
* Sleep until a signal is received, or until a poll is forced by
* PGARCH_AUTOWAKE_INTERVAL having passed since last_copy_time, or
* until postmaster dies.
*/
if (!time_to_stop) /* Don't wait during last iteration */
{
pg_time_t curtime = (pg_time_t) time(NULL);
int timeout;
timeout = PGARCH_AUTOWAKE_INTERVAL - (curtime - last_copy_time);
if (timeout > 0)
{
int rc;
rc = WaitLatch(MyLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
timeout * 1000L,
WAIT_EVENT_ARCHIVER_MAIN);
if (rc & WL_TIMEOUT)
wakened = true;
if (rc & WL_POSTMASTER_DEATH)
time_to_stop = true;
}
else
wakened = true;
}
/*
* The archiver quits either when the postmaster dies (not expected)
* or after completing one more archiving cycle after receiving
* SIGUSR2.
*/
} while (!time_to_stop); /* 停库，触发最后一轮归档周期 */
} 归档所有未归档日志，直到全部的.ready对应调度wal都归档完成，或者报错
/*
* pgarch_ArchiverCopyLoop
*
* Archives all outstanding xlogs then returns
*/
static void
pgarch_ArchiverCopyLoop(void)
{
char xlog[MAX_XFN_CHARS + 1];
/*
* loop through all xlogs with archive_status of .ready and archive
* them...mostly we expect this to be a single file, though it is possible
* some backend will add files onto the list of those that need archiving
* while we are still copying earlier archives
*/
while (pgarch_readyXlog(xlog))
{
int failures = 0;
int failures_orphan = 0;
for (;;)
{
struct stat stat_buf;
char pathname[MAXPGPATH];
/*
* Do not initiate any more archive commands after receiving
* SIGTERM, nor after the postmaster has died unexpectedly. The
* first condition is to try to keep from having init SIGKILL the
* command, and the second is to avoid conflicts with another
* archiver spawned by a newer postmaster.
*/
if (got_SIGTERM || !PostmasterIsAlive())
return;
/*
* Check for config update. This is so that we'll adopt a new
* setting for archive_command as soon as possible, even if there
* is a backlog of files to be archived.
*/
if (got_SIGHUP)
{
got_SIGHUP = false;
ProcessConfigFile(PGC_SIGHUP);
}
/* can't do anything if no command ... */
if (!XLogArchiveCommandSet())
{
ereport(WARNING,
(errmsg("archive_mode enabled, yet archive_command is not set")));
return;
}
/*
* Since archive status files are not removed in a durable manner,
* a system crash could leave behind .ready files for WAL segments
* that have already been recycled or removed. In this case,
* simply remove the orphan status file and move on. unlink() is
* used here as even on subsequent crashes the same orphan files
* would get removed, so there is no need to worry about
* durability.
*/
snprintf(pathname, MAXPGPATH, XLOGDIR "/%s", xlog);
if (stat(pathname, &stat_buf) != 0 && errno == ENOENT)
{
char xlogready[MAXPGPATH];
StatusFilePath(xlogready, xlog, ".ready");
if (unlink(xlogready) == 0)
{
ereport(WARNING,
(errmsg("removed orphan archive status file \"%s\"",
xlogready)));
/* leave loop and move to the next status file */
break;
}
if (++failures_orphan >= NUM_ORPHAN_CLEANUP_RETRIES)
{
ereport(WARNING,
(errmsg("removal of orphan archive status file \"%s\" failed too many times, will try again later",
xlogready)));
/* give up cleanup of orphan status files */
return;
}
/* wait a bit before retrying */
pg_usleep(1000000L);
continue;
}
if (pgarch_archiveXlog(xlog))
{
/* successful */
pgarch_archiveDone(xlog);
/*
* Tell the collector about the WAL file that we successfully
* archived
*/
pgstat_send_archiver(xlog, false);
break; /* out of inner retry loop */
}
else
{
/*
* Tell the collector about the WAL file that we failed to
* archive
*/
pgstat_send_archiver(xlog, true);
if (++failures >= NUM_ARCHIVE_RETRIES)
{
ereport(WARNING,
(errmsg("archiving write-ahead log file \"%s\" failed too many times, will try again later",
xlog)));
return; /* give up archiving for now */
}
pg_usleep(1000000L); /* wait a bit before retrying */
}
}
}
} 那么fast,smart停库时，如果有walsender或归档时到底有什么问题？
- 如果walsender有很多很多的wal没有发送完，则停库可能要很久很久（因为要等walsender发完）
- 同样的道理，如果有很多很多文件没有归档，并且归档过程中没有报错，则一个归档周期会非常漫长，也会导致停库可能要很久很久。
- immediate模式停库没有影响，但是immediate停库不写检查点，启动数据库时需要进入recovery模式恢复数据库。
扫一扫
1140
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
