pg_upgrade: detect stale postmaster.pid lock files

If the postmaster.pid lock file exists, try starting/stopping the
cluster to check if the lock file is valid.

Per request from Tom.

diff --git a/contrib/pg_upgrade/check.c b/contrib/pg_upgrade/check.c
index 1780788e003cf20c207623835667e59325c674e7..818864346ea416a648e5f0a330320b7357d87d50 100644 (file)
--- a/contrib/pg_upgrade/check.c
+++ b/contrib/pg_upgrade/check.c
@@ -56,11 +56,10 @@ fix_path_separator(char *path)
 }
 
 void
-output_check_banner(bool *live_check)
+output_check_banner(bool live_check)
 {
-   if (user_opts.check && is_server_running(old_cluster.pgdata))
+   if (user_opts.check && live_check)
    {
-       *live_check = true;
        pg_log(PG_REPORT, "Performing Consistency Checks on Old Live Server\n");
        pg_log(PG_REPORT, "------------------------------------------------\n");
    }
@@ -78,7 +77,7 @@ check_and_dump_old_cluster(bool live_check, char **sequence_script_file_name)
    /* -- OLD -- */
 
    if (!live_check)
-       start_postmaster(&old_cluster);
+       start_postmaster(&old_cluster, true);
 
    set_locale_and_encoding(&old_cluster);
 
@@ -201,7 +200,7 @@ issue_warnings(char *sequence_script_file_name)
    /* old = PG 8.3 warnings? */
    if (GET_MAJOR_VERSION(old_cluster.major_version) <= 803)
    {
-       start_postmaster(&new_cluster);
+       start_postmaster(&new_cluster, true);
 
        /* restore proper sequence values using file created from old server */
        if (sequence_script_file_name)
@@ -224,7 +223,7 @@ issue_warnings(char *sequence_script_file_name)
    /* Create dummy large object permissions for old < PG 9.0? */
    if (GET_MAJOR_VERSION(old_cluster.major_version) <= 804)
    {
-       start_postmaster(&new_cluster);
+       start_postmaster(&new_cluster, true);
        new_9_0_populate_pg_largeobject_metadata(&new_cluster, false);
        stop_postmaster(false);
    }

diff --git a/contrib/pg_upgrade/exec.c b/contrib/pg_upgrade/exec.c
index e326a10c6130afedc39031be13a060ce210076a0..44dafc36a9159933a9fc034d755c3f81d42fd87c 100644 (file)
--- a/contrib/pg_upgrade/exec.c
+++ b/contrib/pg_upgrade/exec.c
@@ -140,13 +140,12 @@ exec_prog(const char *log_file, const char *opt_log_file,
 
 
 /*
- * is_server_running()
+ * pid_lock_file_exists()
  *
- * checks whether postmaster on the given data directory is running or not.
- * The check is performed by looking for the existence of postmaster.pid file.
+ * Checks whether the postmaster.pid file exists.
  */
 bool
-is_server_running(const char *datadir)
+pid_lock_file_exists(const char *datadir)
 {
    char        path[MAXPGPATH];
    int         fd;
@@ -180,8 +179,6 @@ void
 verify_directories(void)
 {
 
-   prep_status("Checking current, bin, and data directories");
-
 #ifndef WIN32
    if (access(".", R_OK | W_OK | X_OK) != 0)
 #else
@@ -194,7 +191,6 @@ verify_directories(void)
    check_data_dir(old_cluster.pgdata);
    check_bin_dir(&new_cluster);
    check_data_dir(new_cluster.pgdata);
-   check_ok();
 }
 
 

diff --git a/contrib/pg_upgrade/pg_upgrade.c b/contrib/pg_upgrade/pg_upgrade.c
index a752fe8eda1a260c8332f6765706ad416e920a70..55155d22e287ed2c79b544feaae6b3993e8b71d8 100644 (file)
--- a/contrib/pg_upgrade/pg_upgrade.c
+++ b/contrib/pg_upgrade/pg_upgrade.c
@@ -48,7 +48,7 @@ static void prepare_new_databases(void);
 static void create_new_objects(void);
 static void copy_clog_xlog_xid(void);
 static void set_frozenxids(void);
-static void setup(char *argv0, bool live_check);
+static void setup(char *argv0, bool *live_check);
 static void cleanup(void);
 
 ClusterInfo old_cluster,
@@ -80,9 +80,9 @@ main(int argc, char **argv)
    adjust_data_dir(&old_cluster);
    adjust_data_dir(&new_cluster);
 
-   output_check_banner(&live_check);
+   setup(argv[0], &live_check);
 
-   setup(argv[0], live_check);
+   output_check_banner(live_check);
 
    check_cluster_versions();
 
@@ -95,7 +95,7 @@ main(int argc, char **argv)
 
 
    /* -- NEW -- */
-   start_postmaster(&new_cluster);
+   start_postmaster(&new_cluster, true);
 
    check_new_cluster();
    report_clusters_compatible();
@@ -116,7 +116,7 @@ main(int argc, char **argv)
    /* New now using xids of the old system */
 
    /* -- NEW -- */
-   start_postmaster(&new_cluster);
+   start_postmaster(&new_cluster, true);
 
    prepare_new_databases();
 
@@ -177,7 +177,7 @@ main(int argc, char **argv)
 
 
 static void
-setup(char *argv0, bool live_check)
+setup(char *argv0, bool *live_check)
 {
    char        exec_path[MAXPGPATH];   /* full path to my executable */
 
@@ -189,15 +189,39 @@ setup(char *argv0, bool live_check)
 
    verify_directories();
 
-   /* no postmasters should be running */
-   if (!live_check && is_server_running(old_cluster.pgdata))
-       pg_log(PG_FATAL, "There seems to be a postmaster servicing the old cluster.\n"
-              "Please shutdown that postmaster and try again.\n");
+   /* no postmasters should be running, except for a live check */
+   if (pid_lock_file_exists(old_cluster.pgdata))
+   {
+       /*
+        *  If we have a postmaster.pid file, try to start the server.  If
+        *  it starts, the pid file was stale, so stop the server.  If it
+        *  doesn't start, assume the server is running.  If the pid file
+        *  is left over from a server crash, this also allows any committed
+        *  transactions stored in the WAL to be replayed so they are not
+        *  lost, because WAL files are not transfered from old to new
+        *  servers.
+        */     
+       if (start_postmaster(&old_cluster, false))
+           stop_postmaster(false);
+       else
+       {
+           if (!user_opts.check)
+               pg_log(PG_FATAL, "There seems to be a postmaster servicing the old cluster.\n"
+                      "Please shutdown that postmaster and try again.\n");
+           else
+               *live_check = true;
+       }
+   }
 
    /* same goes for the new postmaster */
-   if (is_server_running(new_cluster.pgdata))
-       pg_log(PG_FATAL, "There seems to be a postmaster servicing the new cluster.\n"
+   if (pid_lock_file_exists(new_cluster.pgdata))
+   {
+       if (start_postmaster(&new_cluster, false))
+           stop_postmaster(false);
+       else
+           pg_log(PG_FATAL, "There seems to be a postmaster servicing the new cluster.\n"
               "Please shutdown that postmaster and try again.\n");
+   }
 
    /* get path to pg_upgrade executable */
    if (find_my_exec(argv0, exec_path) < 0)

diff --git a/contrib/pg_upgrade/pg_upgrade.h b/contrib/pg_upgrade/pg_upgrade.h
index 70b93816679800bdf3b1c22cae9d12281e0c6d66..69b9c6030b71fe1cb6810c6db84669bd4b69e6af 100644 (file)
--- a/contrib/pg_upgrade/pg_upgrade.h
+++ b/contrib/pg_upgrade/pg_upgrade.h
@@ -307,7 +307,7 @@ extern OSInfo os_info;
 
 /* check.c */
 
-void       output_check_banner(bool *live_check);
+void       output_check_banner(bool live_check);
 void       check_and_dump_old_cluster(bool live_check,
                  char **sequence_script_file_name);
 void       check_new_cluster(void);
@@ -341,7 +341,7 @@ exec_prog(const char *log_file, const char *opt_log_file,
          bool throw_error, const char *fmt,...)
 __attribute__((format(PG_PRINTF_ATTRIBUTE, 4, 5)));
 void       verify_directories(void);
-bool       is_server_running(const char *datadir);
+bool       pid_lock_file_exists(const char *datadir);
 
 
 /* file.c */
@@ -429,7 +429,7 @@ __attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3)));
 
 char      *cluster_conn_opts(ClusterInfo *cluster);
 
-void       start_postmaster(ClusterInfo *cluster);
+bool       start_postmaster(ClusterInfo *cluster, bool throw_error);
 void       stop_postmaster(bool fast);
 uint32     get_major_server_version(ClusterInfo *cluster);
 void       check_pghost_envvar(void);

diff --git a/contrib/pg_upgrade/server.c b/contrib/pg_upgrade/server.c
index 0b4825181bdff6452f34e526cd3488bff4d65c48..d1a3f76eff377a8ce51d3d05666bf3fd48420882 100644 (file)
--- a/contrib/pg_upgrade/server.c
+++ b/contrib/pg_upgrade/server.c
@@ -170,8 +170,8 @@ stop_postmaster_atexit(void)
 }
 
 
-void
-start_postmaster(ClusterInfo *cluster)
+bool
+start_postmaster(ClusterInfo *cluster, bool throw_error)
 {
    char        cmd[MAXPGPATH * 4 + 1000];
    PGconn     *conn;
@@ -236,6 +236,9 @@ start_postmaster(ClusterInfo *cluster)
                              false,
                              "%s", cmd);
 
+   if (!pg_ctl_return && !throw_error)
+       return false;
+                             
    /* Check to see if we can connect to the server; if not, report it. */
    if ((conn = get_db_conn(cluster, "template1")) == NULL ||
        PQstatus(conn) != CONNECTION_OK)
@@ -256,6 +259,8 @@ start_postmaster(ClusterInfo *cluster)
               CLUSTER_NAME(cluster));
 
    os_info.running_cluster = cluster;
+
+   return true;
 }