git.postgresql.org Git - postgresql.git/commitdiff

git projects / postgresql.git / commitdiff

Make smart shutdown work in combination with Hot Standby/Streaming Replication.

author Robert Haas <rhaas@postgresql.org>

Thu, 8 Apr 2010 01:39:37 +0000 (01:39 +0000)

committer Robert Haas <rhaas@postgresql.org>

Thu, 8 Apr 2010 01:39:37 +0000 (01:39 +0000)

At present, killing the startup process does not release any locks it holds,
so we must wait to stop the startup and walreceiver processes until all
read-only backends have exited. Without this patch, the startup and
walreceiver processes never exit, so the server gets permanently stuck in
a half-shutdown state.

Fujii Masao, with review, docs, and comment adjustments by me.

doc/src/sgml/ref/pg_ctl-ref.sgml patch | blob | blame | history

doc/src/sgml/runtime.sgml patch | blob | blame | history

src/backend/postmaster/postmaster.c patch | blob | blame | history

diff --git a/doc/src/sgml/ref/pg_ctl-ref.sgml b/doc/src/sgml/ref/pg_ctl-ref.sgml

index e11e59a3fa1ebec3110d923eef2d0999a082979f..99d9eb0ca723679a9de62e4cc67f6d2b7a72f3f0 100644 (file)

--- a/doc/src/sgml/ref/pg_ctl-ref.sgml

+++ b/doc/src/sgml/ref/pg_ctl-ref.sgml

@@ -1,5 +1,5 @@

<!--

-$PostgreSQL: pgsql/doc/src/sgml/ref/pg_ctl-ref.sgml,v 1.49 2010年04月03日 07:23:01 petere Exp $

+$PostgreSQL: pgsql/doc/src/sgml/ref/pg_ctl-ref.sgml,v 1.50 2010年04月08日 01:39:37 rhaas Exp $

PostgreSQL documentation

-->

@@ -152,6 +152,8 @@ PostgreSQL documentation

shutdown methods can be selected with the <option>-m</option>

option: <quote>Smart</quote> mode waits for online backup mode

to finish and all the clients to disconnect. This is the default.

+ If the server is in recovery, recovery and streaming replication

+ will be terminated once all clients have disconnected.

<quote>Fast</quote> mode does not wait for clients to disconnect and

will terminate an online backup in progress. All active transactions are

rolled back and clients are forcibly disconnected, then the

diff --git a/doc/src/sgml/runtime.sgml b/doc/src/sgml/runtime.sgml

index fd84d67f51e3e0d4105adeaadb7ea83a1292ac82..cb76b1d7b57daf74f69b903cb14fd5bf028a2dbb 100644 (file)

--- a/doc/src/sgml/runtime.sgml

+++ b/doc/src/sgml/runtime.sgml

@@ -1,4 +1,4 @@

-

+

<title>Server Setup and Operation</title>

@@ -1338,7 +1338,9 @@ echo -17 > /proc/self/oom_adj

until online backup mode is no longer active. While backup mode is

active, new connections will still be allowed, but only to superusers

(this exception allows a superuser to connect to terminate

- online backup mode).

+ online backup mode). If the server is in recovery when a smart

+ shutdown is requested, recovery and streaming replication will be

+ stopped only after all regular sessions have terminated.

</para>

</listitem>

</varlistentry>

diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c

index 43ecfac65b4ad6397b31a7d3e018967ead41f5dd..d77ffd07438d81397a4d546a6a1c5ea389555706 100644 (file)

--- a/src/backend/postmaster/postmaster.c

+++ b/src/backend/postmaster/postmaster.c

@@ -37,7 +37,7 @@

* IDENTIFICATION

- * $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.604 2010年03月25日 20:40:17 sriggs Exp $

+ * $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.605 2010年04月08日 01:39:37 rhaas Exp $

* NOTES

@@ -278,6 +278,7 @@ typedef enum

PM_RECOVERY_CONSISTENT, /* consistent recovery mode */

PM_RUN, /* normal "database is alive" state */

PM_WAIT_BACKUP, /* waiting for online backup mode to end */

+ PM_WAIT_READONLY, /* waiting for read only backends to exit */

PM_WAIT_BACKENDS, /* waiting for live backends to exit */

PM_SHUTDOWN, /* waiting for bgwriter to do shutdown ckpt */

PM_SHUTDOWN_2, /* waiting for archiver and walsenders to

@@ -2173,7 +2174,17 @@ pmdie(SIGNAL_ARGS)

/* and the walwriter too */

if (WalWriterPID != 0)

signal_child(WalWriterPID, SIGTERM);

- pmState = PM_WAIT_BACKUP;

+ /*

+ * If we're in recovery, we can't kill the startup process

+ * right away, because at present doing so does not release

+ * its locks. We might want to change this in a future

+ * release. For the time being, the PM_WAIT_READONLY state

+ * indicates that we're waiting for the regular (read only)

+ * backends to die off; once they do, we'll kill the startup

+ * and walreceiver processes.

+ */

+ pmState = (pmState == PM_RUN) ?

+ PM_WAIT_BACKUP : PM_WAIT_READONLY;

}

@@ -2209,6 +2220,7 @@ pmdie(SIGNAL_ARGS)

}

if (pmState == PM_RUN ||

pmState == PM_WAIT_BACKUP ||

+ pmState == PM_WAIT_READONLY ||

pmState == PM_WAIT_BACKENDS ||

pmState == PM_RECOVERY_CONSISTENT)

{

@@ -2771,6 +2783,7 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)

pmState == PM_RECOVERY_CONSISTENT ||

pmState == PM_RUN ||

pmState == PM_WAIT_BACKUP ||

+ pmState == PM_WAIT_READONLY ||

pmState == PM_SHUTDOWN)

pmState = PM_WAIT_BACKENDS;

}

@@ -2846,6 +2859,26 @@ PostmasterStateMachine(void)

pmState = PM_WAIT_BACKENDS;

}

+ if (pmState == PM_WAIT_READONLY)

+ {

+ /*

+ * PM_WAIT_READONLY state ends when we have no regular backends that

+ * have been started during recovery. We kill the startup and

+ * walreceiver processes and transition to PM_WAIT_BACKENDS. Ideally,

+ * we might like to kill these processes first and then wait for

+ * backends to die off, but that doesn't work at present because

+ * killing the startup process doesn't release its locks.

+ */

+ if (CountChildren(BACKEND_TYPE_NORMAL) == 0)

+ {

+ if (StartupPID != 0)

+ signal_child(StartupPID, SIGTERM);

+ if (WalReceiverPID != 0)

+ signal_child(WalReceiverPID, SIGTERM);

+ pmState = PM_WAIT_BACKENDS;

+ }

* If we are in a state-machine state that implies waiting for backends to

* exit, see if they're all gone, and change state if so.

This is the main PostgreSQL git repository.

RSS Atom