Postgresql中xlog生成和清理邏輯操作

# 在自動(dòng)的WAL檢查點(diǎn)之間的日志文件段的最大數(shù)量
checkpoint_segments = 
# 在自動(dòng)WAL檢查點(diǎn)之間的最長(zhǎng)時(shí)間
checkpoint_timeout = 
# 緩解io壓力
checkpoint_completion_target = 
# 日志文件段的保存最小數(shù)量，為了備庫(kù)保留更多段
wal_keep_segments = 
# 已完成的WAL段通過(guò)archive_command發(fā)送到歸檔存儲(chǔ)
archive_mode = 
# 強(qiáng)制timeout切換到新的wal段文件
archive_timeout = 
max_wal_size = 
min_wal_size =

(2 + checkpoint_completion_target) * checkpoint_segments + 1

RemoveOldXlogFiles
> CreateCheckPoint
> CreateRestartPoint

static void
KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo)
{
 XLogSegNo segno;
 XLogRecPtr keep;
 XLByteToSeg(recptr, segno);
 keep = XLogGetReplicationSlotMinimumLSN();
 /* compute limit for wal_keep_segments first */
 if (wal_keep_segments > 0)
 {
 /* avoid underflow, don't go below 1 */
 if (segno = wal_keep_segments)
  segno = 1;
 else
  segno = segno - wal_keep_segments;
 }
 /* then check whether slots limit removal further */
 if (max_replication_slots > 0  keep != InvalidXLogRecPtr)
 {
 XLogSegNo slotSegNo;
 XLByteToSeg(keep, slotSegNo);
 if (slotSegNo = 0)
  segno = 1;
 else if (slotSegNo  segno)
  segno = slotSegNo;
 }
 /* don't delete WAL segments newer than the calculated segment */
 if (segno  *logSegNo)
 *logSegNo = segno;
}

static void
RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr endptr)
{
  ...
  ...
 while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
 {
 /* Ignore files that are not XLOG segments */
 if (strlen(xlde->d_name) != 24 ||
  strspn(xlde->d_name, "0123456789ABCDEF") != 24)
  continue;
 /*
  * We ignore the timeline part of the XLOG segment identifiers in
  * deciding whether a segment is still needed. This ensures that we
  * won't prematurely remove a segment from a parent timeline. We could
  * probably be a little more proactive about removing segments of
  * non-parent timelines, but that would be a whole lot more
  * complicated.
  *
  * We use the alphanumeric sorting property of the filenames to decide
  * which ones are earlier than the lastoff segment.
  */
 if (strcmp(xlde->d_name + 8, lastoff + 8) = 0)
 {
  if (XLogArchiveCheckDone(xlde->d_name))
        # 歸檔關(guān)閉返回真
        # 存在done文件返回真
        # 存在.ready返回假
        # recheck存在done文件返回真
        # 重建.ready文件返回假
  {
  /* Update the last removed location in shared memory first */
  UpdateLastRemovedPtr(xlde->d_name);
        
        # 回收 或者 直接刪除，清理.done和.ready文件
  RemoveXlogFile(xlde->d_name, endptr);
  }
 }
 }
  ...
  ...
}

static void
pgarch_ArchiverCopyLoop(void)
{
 char xlog[MAX_XFN_CHARS + 1];
  
  # 拿到最老那個(gè)沒(méi)有被歸檔的xlog文件名
 while (pgarch_readyXlog(xlog))
 {
 int  failures = 0;
 for (;;)
 {
  /*
  * 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);
  }
  # archive_command沒(méi)設(shè)的話不再執(zhí)行
      # 我們的command沒(méi)有設(shè)置，走的是這個(gè)分支
  if (!XLogArchiveCommandSet())
  {
  /*
   * Change WARNING to DEBUG1, since we will left archive_command empty to 
   * let external tools to manage archive
   */
  ereport(DEBUG1,
   (errmsg("archive_mode enabled, yet archive_command is not set")));
  return;
  }
      # 執(zhí)行歸檔命令！
  if (pgarch_archiveXlog(xlog))
  {
  # 成功了，把.ready改名為.done
  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 transaction 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 */
  }
 }
 }
}

static void
XLogWrite(XLogwrtRqst WriteRqst, bool flexible)
{
...
      if (finishing_seg)
  {
  issue_xlog_fsync(openLogFile, openLogSegNo);
  /* signal that we need to wakeup walsenders later */
  WalSndWakeupRequest();
  LogwrtResult.Flush = LogwrtResult.Write; /* end of page */
        # 歸檔打開(kāi)  wal_level >= archive
  if (XLogArchivingActive())
          # 生成ready文件
   XLogArchiveNotifySeg(openLogSegNo);
  XLogCtl->lastSegSwitchTime = (pg_time_t) time(NULL);
...

-- 流復(fù)制插槽
-- 如果restart_lsn和當(dāng)前XLOG相差非常大的字節(jié)數(shù), 需要排查slot的訂閱者是否能正常接收XLOG, 
-- 或者訂閱者是否正常. 長(zhǎng)時(shí)間不將slot的數(shù)據(jù)取走, pg_xlog目錄可能會(huì)撐爆
select pg_xlog_location_diff(pg_current_xlog_location(),restart_lsn), * 
from pg_replication_slots;

select pg_drop_replication_slot('xxx');

（archive_mode=on archive_command=''）