On Thu, Feb 5, 2015 at 11:58 PM, Michael Paquier wrote:
> An updated patch is attached.
I just noticed that the patch I sent was incorrect:
- Parameter name was still wal_availability_check_interval and not
wal_retrieve_retry_interval
- Documentation was incorrect.
Please use the patch attached instead for further review.
--
Michael
From 06a4d3d1f5fe4362d7be1404cbf0b45b74fea69f Mon Sep 17 00:00:00 2001
From: Michael Paquier <[email protected]>
Date: Mon, 19 Jan 2015 16:08:48 +0900
Subject: [PATCH] Add wal_retrieve_retry_interval
This parameter aids to control at which timing WAL availability is checked
when a node is in recovery, particularly when successive failures happen when
fetching WAL archives, or when fetching WAL records from a streaming source.
Default value is 5s.
---
doc/src/sgml/recovery-config.sgml | 17 +++++++++
src/backend/access/transam/recovery.conf.sample | 9 +++++
src/backend/access/transam/xlog.c | 47 +++++++++++++++++--------
src/backend/utils/adt/timestamp.c | 38 ++++++++++++++++++++
src/include/utils/timestamp.h | 2 ++
5 files changed, 99 insertions(+), 14 deletions(-)
diff --git a/doc/src/sgml/recovery-config.sgml b/doc/src/sgml/recovery-config.sgml
index 0c64ff2..d4babbd 100644
--- a/doc/src/sgml/recovery-config.sgml
+++ b/doc/src/sgml/recovery-config.sgml
@@ -145,6 +145,23 @@ restore_command = 'copy "C:\\server\\archivedir\\%f" "%p"' # Windows
</listitem>
</varlistentry>
+ <varlistentry id="wal-retrieve-retry-interval" xreflabel="wal_retrieve_retry_interval">
+ <term><varname>wal_retrieve_retry_interval</varname> (<type>integer</type>)
+ <indexterm>
+ <primary><varname>wal_retrieve_retry_interval</> recovery parameter</primary>
+ </indexterm>
+ </term>
+ <listitem>
+ <para>
+ This parameter specifies the amount of time to wait when a failure
+ occurred when reading WAL from a source (be it via streaming
+ replication, local <filename>pg_xlog</> or WAL archive) for a node
+ in standby mode, or when WAL is expected from a source. Default
+ value is <literal>5s</>.
+ </para>
+ </listitem>
+ </varlistentry>
+
</variablelist>
</sect1>
diff --git a/src/backend/access/transam/recovery.conf.sample b/src/backend/access/transam/recovery.conf.sample
index b777400..458308c 100644
--- a/src/backend/access/transam/recovery.conf.sample
+++ b/src/backend/access/transam/recovery.conf.sample
@@ -58,6 +58,15 @@
#
#recovery_end_command = ''
#
+#
+# wal_retrieve_retry_interval
+#
+# specifies an optional internal to wait for WAL to become available when
+# a failure occurred when reading WAL from a source for a node in standby
+# mode, or when WAL is expected from a source.
+#
+#wal_retrieve_retry_interval = '5s'
+#
#---------------------------------------------------------------------------
# RECOVERY TARGET PARAMETERS
#---------------------------------------------------------------------------
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 629a457..111e53d 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -235,6 +235,7 @@ static TimestampTz recoveryTargetTime;
static char *recoveryTargetName;
static int recovery_min_apply_delay = 0;
static TimestampTz recoveryDelayUntilTime;
+static int wal_retrieve_retry_interval = 5000;
/* options taken from recovery.conf for XLOG streaming */
static bool StandbyModeRequested = false;
@@ -4881,6 +4882,26 @@ readRecoveryCommandFile(void)
(errmsg_internal("trigger_file = '%s'",
TriggerFile)));
}
+ else if (strcmp(item->name, "wal_retrieve_retry_interval") == 0)
+ {
+ const char *hintmsg;
+
+ if (!parse_int(item->value, &wal_retrieve_retry_interval, GUC_UNIT_MS,
+ &hintmsg))
+ ereport(ERROR,
+ (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("parameter \"%s\" requires a temporal value",
+ "wal_retrieve_retry_interval"),
+ hintmsg ? errhint("%s", _(hintmsg)) : 0));
+ ereport(DEBUG2,
+ (errmsg_internal("wal_retrieve_retry_interval = '%s'", item->value)));
+
+ if (wal_retrieve_retry_interval <= 0)
+ ereport(ERROR,
+ (errcode(ERRCODE_INVALID_PARAMETER_VALUE),
+ errmsg("\"%s\" must have a value strictly positive",
+ "wal_retrieve_retry_interval")));
+ }
else if (strcmp(item->name, "recovery_min_apply_delay") == 0)
{
const char *hintmsg;
@@ -10340,8 +10361,8 @@ static bool
WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
bool fetching_ckpt, XLogRecPtr tliRecPtr)
{
- static pg_time_t last_fail_time = 0;
- pg_time_t now;
+ TimestampTz now = GetCurrentTimestamp();
+ TimestampTz last_fail_time = now;
/*-------
* Standby mode is implemented by a state machine:
@@ -10490,15 +10511,13 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
* machine, so we've exhausted all the options for
* obtaining the requested WAL. We're going to loop back
* and retry from the archive, but if it hasn't been long
- * since last attempt, sleep 5 seconds to avoid
- * busy-waiting.
+ * since last attempt, sleep the amount of time specified
+ * by wal_retrieve_retry_interval to avoid busy-waiting.
*/
- now = (pg_time_t) time(NULL);
- if ((now - last_fail_time) < 5)
- {
- pg_usleep(1000000L * (5 - (now - last_fail_time)));
- now = (pg_time_t) time(NULL);
- }
+ now = GetCurrentTimestamp();
+ if (TimestampSleepDifference(last_fail_time, now,
+ wal_retrieve_retry_interval))
+ now = GetCurrentTimestamp();
last_fail_time = now;
currentSource = XLOG_FROM_ARCHIVE;
break;
@@ -10653,13 +10672,13 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
}
/*
- * Wait for more WAL to arrive. Time out after 5 seconds,
- * like when polling the archive, to react to a trigger
- * file promptly.
+ * Wait for more WAL to arrive. Time out after the amount of
+ * time specified by wal_retrieve_retry_interval, like
+ * when polling the archive, to react to a trigger file promptly.
*/
WaitLatch(&XLogCtl->recoveryWakeupLatch,
WL_LATCH_SET | WL_TIMEOUT,
- 5000L);
+ wal_retrieve_retry_interval * 1000L);
ResetLatch(&XLogCtl->recoveryWakeupLatch);
break;
}
diff --git a/src/backend/utils/adt/timestamp.c b/src/backend/utils/adt/timestamp.c
index 67e0cf9..a4cf717 100644
--- a/src/backend/utils/adt/timestamp.c
+++ b/src/backend/utils/adt/timestamp.c
@@ -1674,6 +1674,44 @@ TimestampDifferenceExceeds(TimestampTz start_time,
}
/*
+ * TimestampSleepDifference -- sleep for the amout of interval time
+ * specified, reduced by the difference between two timestamps.
+ * Returns true if sleep is done, false otherwise.
+ *
+ * Both inputs must be ordinary finite timestamps (in current usage,
+ * they'll be results from GetCurrentTimestamp()). Sleep is done
+ * per steps of 1s to be able to handle process interruptions without
+ * having to wait for a too long time.
+ */
+bool
+TimestampSleepDifference(TimestampTz start_time,
+ TimestampTz stop_time,
+ int interval_msec)
+{
+ long secs, total_time;
+ int microsecs;
+
+ if (TimestampDifferenceExceeds(start_time, stop_time, interval_msec))
+ return false;
+
+ TimestampDifference(start_time, stop_time, &secs, µsecs);
+ total_time = interval_msec * 1000L - (1000000L * secs + 1L * microsecs);
+
+ while (total_time > 0)
+ {
+ long wait_time = 1000000L; /* 1s */
+
+ if (total_time < wait_time)
+ wait_time = total_time;
+
+ pg_usleep(wait_time);
+ HandleStartupProcInterrupts();
+ total_time -= wait_time;
+ }
+ return true;
+}
+
+/*
* Convert a time_t to TimestampTz.
*
* We do not use time_t internally in Postgres, but this is provided for use
diff --git a/src/include/utils/timestamp.h b/src/include/utils/timestamp.h
index 70118f5..e4a7673 100644
--- a/src/include/utils/timestamp.h
+++ b/src/include/utils/timestamp.h
@@ -217,6 +217,8 @@ extern void TimestampDifference(TimestampTz start_time, TimestampTz stop_time,
extern bool TimestampDifferenceExceeds(TimestampTz start_time,
TimestampTz stop_time,
int msec);
+extern bool TimestampSleepDifference(TimestampTz start_time,
+ TimestampTz stop_time, int interval_msec);
/*
* Prototypes for functions to deal with integer timestamps, when the native
--
2.2.2
--
Sent via pgsql-hackers mailing list ([email protected])
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
