From c69cd70431c5a349c762da2d5fcabee93419f8e8 Mon Sep 17 00:00:00 2001 From: Hayato Kuroda Date: Tue, 4 Apr 2023 05:49:34 +0000 Subject: [PATCH v35 2/2] pg_upgrade: Allow to replicate logical replication slots to new node This commit allows nodes with logical replication slots to be upgraded. While reading information from the old cluster, a list of logical replication slots is fetched. At the later part of upgrading, pg_upgrade revisits the list and restores slots by executing pg_create_logical_replication_slots() on the new cluster. Migration of logical replication slots is only supported when the old cluster is version 17.0 or later. If the old node has slots with the status 'lost' or with unconsumed WAL records, the pg_upgrade fails. These checks are needed to prevent data loss. Note that the pg_resetwal command would remove WAL files, which are required as restart_lsn. If WALs required by logical replication slots are removed, they are unusable. Therefore, during the upgrade, slot restoration is done after the final pg_resetwal command. The workflow ensures that required WALs are remained. The significant advantage of this commit is that it makes it easy to continue logical replication even after upgrading the publisher node. Previously, pg_upgrade allowed copying publications to a new node. With this new commit, adjusting the connection string to the new publisher will cause the apply worker on the subscriber to connect to the new publisher automatically. This enables seamless continuation of logical replication, even after an upgrade. Author: Hayato Kuroda Co-authored-by: Hou Zhijie Reviewed-by: Peter Smith, Julien Rouhaud, Vignesh C, Wang Wei, Masahiko Sawada, Dilip Kumar --- doc/src/sgml/ref/pgupgrade.sgml | 78 ++++++- src/backend/replication/slot.c | 7 + src/bin/pg_upgrade/Makefile | 3 + src/bin/pg_upgrade/check.c | 204 +++++++++++++++-- src/bin/pg_upgrade/controldata.c | 39 ++++ src/bin/pg_upgrade/function.c | 29 ++- src/bin/pg_upgrade/info.c | 148 +++++++++++- src/bin/pg_upgrade/meson.build | 1 + src/bin/pg_upgrade/pg_upgrade.c | 107 ++++++++- src/bin/pg_upgrade/pg_upgrade.h | 26 ++- src/bin/pg_upgrade/server.c | 7 +- .../t/003_logical_replication_slots.pl | 214 ++++++++++++++++++ src/tools/pgindent/typedefs.list | 3 + 13 files changed, 827 insertions(+), 39 deletions(-) create mode 100644 src/bin/pg_upgrade/t/003_logical_replication_slots.pl diff --git a/doc/src/sgml/ref/pgupgrade.sgml b/doc/src/sgml/ref/pgupgrade.sgml index bea0d1b93f..0752efcd75 100644 --- a/doc/src/sgml/ref/pgupgrade.sgml +++ b/doc/src/sgml/ref/pgupgrade.sgml @@ -383,6 +383,79 @@ make prefix=/usr/local/pgsql.new install + + Prepare for publisher upgrades + + + pg_upgrade attempts to migrate logical + replication slots. This helps avoid the need for manually defining the + same replication slots on the new publisher. Migration of logical + replication slots is only supported when the old cluster is version 17.0 + or later. + + + + Before you start upgrading the publisher cluster, ensure that the + subscription is temporarily disabled, by executing + ALTER SUBSCRIPTION ... DISABLE. + Re-enable the subscription after the upgrade. + + + + There are some prerequisites for pg_upgrade to + be able to upgrade the replication slots. If these are not met an error + will be reported. + + + + + + All slots on the old cluster must be usable, i.e., there are no slots + whose + pg_replication_slots.conflicting + is true. + + + + + pg_replication_slots.confirmed_flush_lsn + of all slots on the old cluster must be the same as the latest + checkpoint location. This ensures that all the data has been replicated + before the upgrade. + + + + + The output plugins referenced by the slots on the old cluster must be + installed in the new PostgreSQL executable directory. + + + + + The new cluster must not have permanent logical replication slots, i.e., + there are no slots whose + pg_replication_slots.temporary + is false. + + + + The new cluster must have + wal_level as + logical. + + + + + The new cluster must have + max_replication_slots + configured to a value greater than or equal to the number of slots + present in the old cluster. + + + + + + Stop both servers @@ -652,8 +725,9 @@ rsync --archive --delete --hard-links --size-only --no-inc-recursive /vol1/pg_tb Configure the servers for log shipping. (You do not need to run pg_backup_start() and pg_backup_stop() or take a file system backup as the standbys are still synchronized - with the primary.) Replication slots are not copied and must - be recreated. + with the primary.) Only logical slots on the primary are migrated to the + new standby, and other slots on the old standby must be recreated as + they are not copied. diff --git a/src/backend/replication/slot.c b/src/backend/replication/slot.c index 63b80d321c..2bdaeb93b2 100644 --- a/src/backend/replication/slot.c +++ b/src/backend/replication/slot.c @@ -1423,6 +1423,13 @@ InvalidatePossiblyObsoleteSlot(ReplicationSlotInvalidationCause cause, SpinLockRelease(&s->mutex); + /* + * The logical replication slots shouldn't be invalidated as + * max_slot_wal_keep_size is set to -1 during the upgrade. + */ + if (*invalidated && SlotIsLogical(s) && IsBinaryUpgrade) + elog(ERROR, "Replication slots must not be invalidated during the upgrade."); + if (active_pid != 0) { /* diff --git a/src/bin/pg_upgrade/Makefile b/src/bin/pg_upgrade/Makefile index 5834513add..815d1a7ca1 100644 --- a/src/bin/pg_upgrade/Makefile +++ b/src/bin/pg_upgrade/Makefile @@ -3,6 +3,9 @@ PGFILEDESC = "pg_upgrade - an in-place binary upgrade utility" PGAPPICON = win32 +# required for 003_logical_replication_slots.pl +EXTRA_INSTALL=contrib/test_decoding + subdir = src/bin/pg_upgrade top_builddir = ../../.. include $(top_builddir)/src/Makefile.global diff --git a/src/bin/pg_upgrade/check.c b/src/bin/pg_upgrade/check.c index 56e313f562..698f9052bf 100644 --- a/src/bin/pg_upgrade/check.c +++ b/src/bin/pg_upgrade/check.c @@ -30,6 +30,8 @@ static void check_for_jsonb_9_4_usage(ClusterInfo *cluster); static void check_for_pg_role_prefix(ClusterInfo *cluster); static void check_for_new_tablespace_dir(void); static void check_for_user_defined_encoding_conversions(ClusterInfo *cluster); +static void check_new_cluster_logical_replication_slots(void); +static void check_old_cluster_for_valid_slots(bool live_check); /* @@ -86,8 +88,11 @@ check_and_dump_old_cluster(bool live_check) if (!live_check) start_postmaster(&old_cluster, true); - /* Extract a list of databases and tables from the old cluster */ - get_db_and_rel_infos(&old_cluster); + /* + * Extract a list of databases, tables, and logical replication slots from + * the old cluster. + */ + get_db_rel_and_slot_infos(&old_cluster); init_tablespaces(); @@ -104,6 +109,13 @@ check_and_dump_old_cluster(bool live_check) check_for_reg_data_type_usage(&old_cluster); check_for_isn_and_int8_passing_mismatch(&old_cluster); + /* + * Logical replication slots can be migrated since PG17. See comments atop + * get_old_cluster_logical_slot_infos(). + */ + if (GET_MAJOR_VERSION(old_cluster.major_version) >= 1700) + check_old_cluster_for_valid_slots(live_check); + /* * PG 16 increased the size of the 'aclitem' type, which breaks the * on-disk format for existing data. @@ -187,7 +199,7 @@ check_and_dump_old_cluster(bool live_check) void check_new_cluster(void) { - get_db_and_rel_infos(&new_cluster); + get_db_rel_and_slot_infos(&new_cluster); check_new_cluster_is_empty(); @@ -210,6 +222,8 @@ check_new_cluster(void) check_for_prepared_transactions(&new_cluster); check_for_new_tablespace_dir(); + + check_new_cluster_logical_replication_slots(); } @@ -232,27 +246,6 @@ report_clusters_compatible(void) } -void -issue_warnings_and_set_wal_level(void) -{ - /* - * We unconditionally start/stop the new server because pg_resetwal -o set - * wal_level to 'minimum'. If the user is upgrading standby servers using - * the rsync instructions, they will need pg_upgrade to write its final - * WAL record showing wal_level as 'replica'. - */ - start_postmaster(&new_cluster, true); - - /* Reindex hash indexes for old < 10.0 */ - if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906) - old_9_6_invalidate_hash_indexes(&new_cluster, false); - - report_extension_updates(&new_cluster); - - stop_postmaster(false); -} - - void output_completion_banner(char *deletion_script_file_name) { @@ -1402,3 +1395,166 @@ check_for_user_defined_encoding_conversions(ClusterInfo *cluster) else check_ok(); } + +/* + * check_new_cluster_logical_replication_slots() + * + * Make sure there are no logical replication slots on the new cluster and that + * the parameter settings necessary for creating slots are sufficient. + */ +static void +check_new_cluster_logical_replication_slots(void) +{ + PGresult *res; + PGconn *conn; + int nslots_on_old; + int nslots_on_new; + int max_replication_slots; + char *wal_level; + + /* Logical slots can be migrated since PG17. */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1600) + return; + + nslots_on_old = count_old_cluster_logical_slots(); + + /* Quick return if there are no logical slots to be migrated. */ + if (nslots_on_old == 0) + return; + + conn = connectToServer(&new_cluster, "template1"); + + prep_status("Checking for logical replication slots"); + + res = executeQueryOrDie(conn, "SELECT count(*) " + "FROM pg_catalog.pg_replication_slots " + "WHERE slot_type = 'logical' AND " + "temporary IS FALSE;"); + + if (PQntuples(res) != 1) + pg_fatal("could not count the number of logical replication slots"); + + nslots_on_new = atoi(PQgetvalue(res, 0, 0)); + + if (nslots_on_new) + pg_fatal(ngettext("New cluster must not have logical replication slots but found %d slot.", + "New cluster must not have logical replication slots but found %d slots.", + nslots_on_new), + nslots_on_new); + + PQclear(res); + + res = executeQueryOrDie(conn, "SHOW wal_level;"); + + if (PQntuples(res) != 1) + pg_fatal("could not determine wal_level"); + + wal_level = PQgetvalue(res, 0, 0); + + if (strcmp(wal_level, "logical") != 0) + pg_fatal("wal_level must be \"logical\", but is set to \"%s\"", + wal_level); + + PQclear(res); + + res = executeQueryOrDie(conn, "SHOW max_replication_slots;"); + + if (PQntuples(res) != 1) + pg_fatal("could not determine max_replication_slots"); + + max_replication_slots = atoi(PQgetvalue(res, 0, 0)); + + if (nslots_on_old > max_replication_slots) + pg_fatal("max_replication_slots (%d) must be greater than or equal to the number of " + "logical replication slots (%d) on the old cluster.", + max_replication_slots, nslots_on_old); + + PQclear(res); + PQfinish(conn); + + check_ok(); +} + +/* + * check_old_cluster_for_valid_slots() + * + * Make sure logical replication slots can be migrated to new cluster. + * Following points are checked: + * + * - All logical replication slots are usable. + * - All logical replication slots consumed all WALs, except a + * CHECKPOINT_SHUTDOWN record. + */ +static void +check_old_cluster_for_valid_slots(bool live_check) +{ + int dbnum; + char output_path[MAXPGPATH]; + FILE *script = NULL; + + prep_status("Checking for valid logical replication slots"); + + snprintf(output_path, sizeof(output_path), "%s/%s", + log_opts.basedir, + "invalid_logical_relication_slots.txt"); + + for (dbnum = 0; dbnum < old_cluster.dbarr.ndbs; dbnum++) + { + int slotnum; + LogicalSlotInfoArr *slot_arr = &old_cluster.dbarr.dbs[dbnum].slot_arr; + + for (slotnum = 0; slotnum < slot_arr->nslots; slotnum++) + { + LogicalSlotInfo *slot = &slot_arr->slots[slotnum]; + + /* Is the slot usable? */ + if (slot->invalid) + { + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s", + output_path, strerror(errno)); + + fprintf(script, "The slot \"%s\" is invalid\n", + slot->slotname); + + /* No need to check this slot, seek to new one */ + continue; + } + + /* + * Do additional checks to ensure that confirmed_flush LSN of all + * the slots is the same as the latest checkpoint location. + * + * Note: This can be satisfied only when the old cluster has been + * shut down, so we skip this for live checks. + */ + if (!live_check && !slot->caught_up) + { + if (script == NULL && + (script = fopen_priv(output_path, "w")) == NULL) + pg_fatal("could not open file \"%s\": %s", + output_path, strerror(errno)); + + fprintf(script, + "The slot \"%s\" has not consumed the WAL yet\n", + slot->slotname); + } + } + } + + if (script) + { + fclose(script); + + pg_log(PG_REPORT, "fatal"); + pg_fatal("Your installation contains invalid logical replication slots.\n" + "These slots can't be copied, so this cluster cannot be upgraded.\n" + "Consider removing such slots or consuming the pending WAL if any,\n" + "and then restart the upgrade.\n" + "A list of invalid logical replication slots is in the file:\n" + " %s", output_path); + } + + check_ok(); +} diff --git a/src/bin/pg_upgrade/controldata.c b/src/bin/pg_upgrade/controldata.c index 4beb65ab22..f8f823e2be 100644 --- a/src/bin/pg_upgrade/controldata.c +++ b/src/bin/pg_upgrade/controldata.c @@ -169,6 +169,45 @@ get_control_data(ClusterInfo *cluster, bool live_check) } got_cluster_state = true; } + + else if ((p = strstr(bufin, "Latest checkpoint location:")) != NULL) + { + /* + * Read the latest checkpoint location if the cluster is PG17 + * or later. This is used for upgrading logical replication + * slots. Currently, we need it only for the old cluster but + * for simplicity chose not to have additional checks. + */ + if (GET_MAJOR_VERSION(cluster->major_version) >= 1700) + { + char *slash = NULL; + uint32 upper_lsn, + lower_lsn; + + p = strchr(p, ':'); + + if (p == NULL || strlen(p) <= 1) + pg_fatal("%d: controldata retrieval problem", __LINE__); + + p++; /* remove ':' char */ + + p = strpbrk(p, "01234567890ABCDEF"); + + if (p == NULL || strlen(p) <= 1) + pg_fatal("%d: controldata retrieval problem", __LINE__); + + /* + * The upper and lower part of LSN must be read separately + * because it is stored as in %X/%X format. + */ + upper_lsn = strtoul(p, &slash, 16); + lower_lsn = strtoul(++slash, NULL, 16); + + /* And combine them */ + cluster->controldata.chkpnt_latest = + ((uint64) upper_lsn << 32) | lower_lsn; + } + } } rc = pclose(output); diff --git a/src/bin/pg_upgrade/function.c b/src/bin/pg_upgrade/function.c index dc8800c7cd..6a7c0a2733 100644 --- a/src/bin/pg_upgrade/function.c +++ b/src/bin/pg_upgrade/function.c @@ -11,6 +11,7 @@ #include "access/transam.h" #include "catalog/pg_language_d.h" +#include "fe_utils/string_utils.h" #include "pg_upgrade.h" /* @@ -46,7 +47,9 @@ library_name_compare(const void *p1, const void *p2) /* * get_loadable_libraries() * - * Fetch the names of all old libraries containing C-language functions. + * Fetch the names of all old libraries containing either C-language functions + * or are corresponding to logical replication output plugins. + * * We will later check that they all exist in the new installation. */ void @@ -55,6 +58,7 @@ get_loadable_libraries(void) PGresult **ress; int totaltups; int dbnum; + int array_size; ress = (PGresult **) pg_malloc(old_cluster.dbarr.ndbs * sizeof(PGresult *)); totaltups = 0; @@ -81,7 +85,12 @@ get_loadable_libraries(void) PQfinish(conn); } - os_info.libraries = (LibraryInfo *) pg_malloc(totaltups * sizeof(LibraryInfo)); + /* + * Allocate memory for required libraries and logical replication output + * plugins. + */ + array_size = totaltups + count_old_cluster_logical_slots(); + os_info.libraries = (LibraryInfo *) pg_malloc(sizeof(LibraryInfo) * (array_size)); totaltups = 0; for (dbnum = 0; dbnum < old_cluster.dbarr.ndbs; dbnum++) @@ -89,6 +98,8 @@ get_loadable_libraries(void) PGresult *res = ress[dbnum]; int ntups; int rowno; + int slotno; + LogicalSlotInfoArr *slot_arr = &old_cluster.dbarr.dbs[dbnum].slot_arr; ntups = PQntuples(res); for (rowno = 0; rowno < ntups; rowno++) @@ -101,6 +112,20 @@ get_loadable_libraries(void) totaltups++; } PQclear(res); + + /* + * Store the names of output plugins as well. There is a possibility + * that duplicated plugins are set, but the consumer function + * check_loadable_libraries() will avoid checking the same library, so + * we do not have to consider their uniqueness here. + */ + for (slotno = 0; slotno < slot_arr->nslots; slotno++) + { + os_info.libraries[totaltups].name = pg_strdup(slot_arr->slots[slotno].plugin); + os_info.libraries[totaltups].dbnum = dbnum; + + totaltups++; + } } pg_free(ress); diff --git a/src/bin/pg_upgrade/info.c b/src/bin/pg_upgrade/info.c index aa5faca4d6..3829c3c355 100644 --- a/src/bin/pg_upgrade/info.c +++ b/src/bin/pg_upgrade/info.c @@ -26,6 +26,8 @@ static void get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo); static void free_rel_infos(RelInfoArr *rel_arr); static void print_db_infos(DbInfoArr *db_arr); static void print_rel_infos(RelInfoArr *rel_arr); +static void print_slot_infos(LogicalSlotInfoArr *slot_arr); +static void get_old_cluster_logical_slot_infos(DbInfo *dbinfo); /* @@ -266,13 +268,13 @@ report_unmatched_relation(const RelInfo *rel, const DbInfo *db, bool is_new_db) } /* - * get_db_and_rel_infos() + * get_db_rel_and_slot_infos() * * higher level routine to generate dbinfos for the database running * on the given "port". Assumes that server is already running. */ void -get_db_and_rel_infos(ClusterInfo *cluster) +get_db_rel_and_slot_infos(ClusterInfo *cluster) { int dbnum; @@ -283,7 +285,17 @@ get_db_and_rel_infos(ClusterInfo *cluster) get_db_infos(cluster); for (dbnum = 0; dbnum < cluster->dbarr.ndbs; dbnum++) - get_rel_infos(cluster, &cluster->dbarr.dbs[dbnum]); + { + DbInfo *pDbInfo = &cluster->dbarr.dbs[dbnum]; + + get_rel_infos(cluster, pDbInfo); + + /* + * Retrieve the logical replication slots infos for the old cluster. + */ + if (cluster == &old_cluster) + get_old_cluster_logical_slot_infos(pDbInfo); + } if (cluster == &old_cluster) pg_log(PG_VERBOSE, "\nsource databases:"); @@ -600,6 +612,107 @@ get_rel_infos(ClusterInfo *cluster, DbInfo *dbinfo) dbinfo->rel_arr.nrels = num_rels; } +/* + * get_old_cluster_logical_slot_infos() + * + * gets the LogicalSlotInfos for all the logical replication slots of the + * database referred to by "dbinfo". + * + * Note: This function will not do anything if the old cluster is pre-PG17. + * This is because before that the logical slots are not saved at shutdown, so + * there is no guarantee that the latest confirmed_flush_lsn is saved to disk + * which can lead to data loss. It is still not guaranteed for manually created + * slots in PG17, so subsequent checks done in + * check_old_cluster_for_valid_slots() would raise a FATAL error if such slots + * are included. + */ +static void +get_old_cluster_logical_slot_infos(DbInfo *dbinfo) +{ + PGconn *conn; + PGresult *res; + LogicalSlotInfo *slotinfos = NULL; + int num_slots; + + /* Logical slots can be migrated since PG17. */ + if (GET_MAJOR_VERSION(old_cluster.major_version) <= 1600) + return; + + conn = connectToServer(&old_cluster, dbinfo->db_name); + + /* + * The temporary slots are explicitly ignored while checking because such + * slots cannot exist after the upgrade. During the upgrade, clusters are + * started and stopped several times causing any temporary slots to be + * removed. + */ + res = executeQueryOrDie(conn, "SELECT slot_name, plugin, two_phase, " + "(confirmed_flush_lsn = '%X/%X') as caught_up, conflicting " + "FROM pg_catalog.pg_replication_slots " + "WHERE slot_type = 'logical' AND " + "database = current_database() AND " + "temporary IS FALSE;", + LSN_FORMAT_ARGS(old_cluster.controldata.chkpnt_latest)); + + num_slots = PQntuples(res); + + if (num_slots) + { + int slotnum; + int i_slotname; + int i_plugin; + int i_twophase; + int i_caught_up; + int i_invalid; + + slotinfos = (LogicalSlotInfo *) pg_malloc(sizeof(LogicalSlotInfo) * num_slots); + + i_slotname = PQfnumber(res, "slot_name"); + i_plugin = PQfnumber(res, "plugin"); + i_twophase = PQfnumber(res, "two_phase"); + i_caught_up = PQfnumber(res, "caught_up"); + i_invalid = PQfnumber(res, "conflicting"); + + for (slotnum = 0; slotnum < num_slots; slotnum++) + { + LogicalSlotInfo *curr = &slotinfos[slotnum]; + + curr->slotname = pg_strdup(PQgetvalue(res, slotnum, i_slotname)); + curr->plugin = pg_strdup(PQgetvalue(res, slotnum, i_plugin)); + curr->two_phase = (strcmp(PQgetvalue(res, slotnum, i_twophase), "t") == 0); + curr->caught_up = (strcmp(PQgetvalue(res, slotnum, i_caught_up), "t") == 0); + curr->invalid = (strcmp(PQgetvalue(res, slotnum, i_invalid), "t") == 0); + } + } + + PQclear(res); + PQfinish(conn); + + dbinfo->slot_arr.slots = slotinfos; + dbinfo->slot_arr.nslots = num_slots; +} + + +/* + * count_old_cluster_logical_slots() + * + * Returns the number of logical replication slots for all databases. + * + * Note: this function always returns 0 if the old_cluster is PG16 and prior + * because we gather slot information only for cluster versions greater than or + * equal to PG17. See get_old_cluster_logical_slot_infos(). + */ +int +count_old_cluster_logical_slots(void) +{ + int dbnum; + int slot_count = 0; + + for (dbnum = 0; dbnum < old_cluster.dbarr.ndbs; dbnum++) + slot_count += old_cluster.dbarr.dbs[dbnum].slot_arr.nslots; + + return slot_count; +} static void free_db_and_rel_infos(DbInfoArr *db_arr) @@ -642,8 +755,11 @@ print_db_infos(DbInfoArr *db_arr) for (dbnum = 0; dbnum < db_arr->ndbs; dbnum++) { - pg_log(PG_VERBOSE, "Database: \"%s\"", db_arr->dbs[dbnum].db_name); - print_rel_infos(&db_arr->dbs[dbnum].rel_arr); + DbInfo *pDbInfo = &db_arr->dbs[dbnum]; + + pg_log(PG_VERBOSE, "Database: \"%s\"", pDbInfo->db_name); + print_rel_infos(&pDbInfo->rel_arr); + print_slot_infos(&pDbInfo->slot_arr); } } @@ -660,3 +776,25 @@ print_rel_infos(RelInfoArr *rel_arr) rel_arr->rels[relnum].reloid, rel_arr->rels[relnum].tablespace); } + +static void +print_slot_infos(LogicalSlotInfoArr *slot_arr) +{ + int slotnum; + + /* Quick return if there are no logical slots. */ + if (slot_arr->nslots == 0) + return; + + pg_log(PG_VERBOSE, "Logical replication slots within the database:"); + + for (slotnum = 0; slotnum < slot_arr->nslots; slotnum++) + { + LogicalSlotInfo *slot_info = &slot_arr->slots[slotnum]; + + pg_log(PG_VERBOSE, "slotname: \"%s\", plugin: \"%s\", two_phase: %d", + slot_info->slotname, + slot_info->plugin, + slot_info->two_phase); + } +} diff --git a/src/bin/pg_upgrade/meson.build b/src/bin/pg_upgrade/meson.build index 12a97f84e2..228f29b688 100644 --- a/src/bin/pg_upgrade/meson.build +++ b/src/bin/pg_upgrade/meson.build @@ -42,6 +42,7 @@ tests += { 'tests': [ 't/001_basic.pl', 't/002_pg_upgrade.pl', + 't/003_logical_replication_slots.pl', ], 'test_kwargs': {'priority': 40}, # pg_upgrade tests are slow }, diff --git a/src/bin/pg_upgrade/pg_upgrade.c b/src/bin/pg_upgrade/pg_upgrade.c index 96bfb67167..6be236dc9a 100644 --- a/src/bin/pg_upgrade/pg_upgrade.c +++ b/src/bin/pg_upgrade/pg_upgrade.c @@ -59,6 +59,8 @@ static void copy_xact_xlog_xid(void); static void set_frozenxids(bool minmxid_only); static void make_outputdirs(char *pgdata); static void setup(char *argv0, bool *live_check); +static void create_logical_replication_slots(void); +static void setup_new_cluster(void); ClusterInfo old_cluster, new_cluster; @@ -188,6 +190,8 @@ main(int argc, char **argv) new_cluster.pgdata); check_ok(); + setup_new_cluster(); + if (user_opts.do_sync) { prep_status("Sync data directory to disk"); @@ -201,8 +205,6 @@ main(int argc, char **argv) create_script_for_old_cluster_deletion(&deletion_script_file_name); - issue_warnings_and_set_wal_level(); - pg_log(PG_REPORT, "\n" "Upgrade Complete\n" @@ -593,7 +595,7 @@ create_new_objects(void) set_frozenxids(true); /* update new_cluster info now that we have objects in the databases */ - get_db_and_rel_infos(&new_cluster); + get_db_rel_and_slot_infos(&new_cluster); } /* @@ -862,3 +864,102 @@ set_frozenxids(bool minmxid_only) check_ok(); } + +/* + * create_logical_replication_slots() + * + * Similar to create_new_objects() but only restores logical replication slots. + */ +static void +create_logical_replication_slots(void) +{ + int dbnum; + + prep_status_progress("Restoring logical replication slots in the new cluster"); + + for (dbnum = 0; dbnum < old_cluster.dbarr.ndbs; dbnum++) + { + DbInfo *old_db = &old_cluster.dbarr.dbs[dbnum]; + LogicalSlotInfoArr *slot_arr = &old_db->slot_arr; + PGconn *conn; + PQExpBuffer query; + int slotnum; + char log_file_name[MAXPGPATH]; + + /* Skip this database if there are no slots */ + if (slot_arr->nslots == 0) + continue; + + conn = connectToServer(&new_cluster, old_db->db_name); + query = createPQExpBuffer(); + + snprintf(log_file_name, sizeof(log_file_name), + DB_DUMP_LOG_FILE_MASK, old_db->db_oid); + + pg_log(PG_STATUS, "%s", old_db->db_name); + + for (slotnum = 0; slotnum < slot_arr->nslots; slotnum++) + { + LogicalSlotInfo *slot_info = &slot_arr->slots[slotnum]; + + /* Constructs a query for creating logical replication slots. */ + appendPQExpBuffer(query, "SELECT pg_catalog.pg_create_logical_replication_slot("); + appendStringLiteralConn(query, slot_info->slotname, conn); + appendPQExpBuffer(query, ", "); + appendStringLiteralConn(query, slot_info->plugin, conn); + appendPQExpBuffer(query, ", false, %s);", + slot_info->two_phase ? "true" : "false"); + + PQclear(executeQueryOrDie(conn, "%s", query->data)); + + resetPQExpBuffer(query); + } + + PQfinish(conn); + + destroyPQExpBuffer(query); + } + + end_progress_output(); + check_ok(); +} + +/* + * setup_new_cluster() + * + * Starts a new cluster for updating the wal_level in the control file, then + * does final setups. Logical slots are also created here. + */ +static void +setup_new_cluster(void) +{ + /* + * We unconditionally start/stop the new server because pg_resetwal -o set + * wal_level to 'minimum'. If the user is upgrading standby servers using + * the rsync instructions, they will need pg_upgrade to write its final + * WAL record showing wal_level as 'replica'. + */ + start_postmaster(&new_cluster, true); + + /* + * If the old cluster has logical slots, migrate them to a new cluster. + * + * Note: This must be done after executing pg_resetwal command in the + * caller because pg_resetwal would remove required WALs. + */ + if (count_old_cluster_logical_slots()) + create_logical_replication_slots(); + + /* + * Reindex hash indexes for old < 10.0. count_old_cluster_logical_slots() + * returns non-zero when the old_cluster is PG17 and later, so it's OK to + * use "else if" here. See comments atop count_old_cluster_logical_slots() + * and get_old_cluster_logical_slot_infos(). + */ + else if (GET_MAJOR_VERSION(old_cluster.major_version) <= 906) + old_9_6_invalidate_hash_indexes(&new_cluster, false); + + report_extension_updates(&new_cluster); + + stop_postmaster(false); +} diff --git a/src/bin/pg_upgrade/pg_upgrade.h b/src/bin/pg_upgrade/pg_upgrade.h index 842f3b6cd3..7ae37cc458 100644 --- a/src/bin/pg_upgrade/pg_upgrade.h +++ b/src/bin/pg_upgrade/pg_upgrade.h @@ -10,6 +10,7 @@ #include #include +#include "access/xlogdefs.h" #include "common/relpath.h" #include "libpq-fe.h" @@ -150,6 +151,25 @@ typedef struct int nrels; } RelInfoArr; +/* + * Structure to store logical replication slot information + */ +typedef struct +{ + char *slotname; /* slot name */ + char *plugin; /* plugin */ + bool two_phase; /* can the slot decode 2PC? */ + bool caught_up; /* Is confirmed_flush_lsn the same as latest + * checkpoint LSN? */ + bool invalid; /* Is the slot usable? */ +} LogicalSlotInfo; + +typedef struct +{ + int nslots; /* number of logical slot infos */ + LogicalSlotInfo *slots; /* array of logical slot infos */ +} LogicalSlotInfoArr; + /* * The following structure represents a relation mapping. */ @@ -176,6 +196,7 @@ typedef struct char db_tablespace[MAXPGPATH]; /* database default tablespace * path */ RelInfoArr rel_arr; /* array of all user relinfos */ + LogicalSlotInfoArr slot_arr; /* array of all LogicalSlotInfo */ } DbInfo; /* @@ -225,6 +246,7 @@ typedef struct bool date_is_int; bool float8_pass_by_value; uint32 data_checksum_version; + XLogRecPtr chkpnt_latest; } ControlData; /* @@ -345,7 +367,6 @@ void output_check_banner(bool live_check); void check_and_dump_old_cluster(bool live_check); void check_new_cluster(void); void report_clusters_compatible(void); -void issue_warnings_and_set_wal_level(void); void output_completion_banner(char *deletion_script_file_name); void check_cluster_versions(void); void check_cluster_compatibility(bool live_check); @@ -400,7 +421,8 @@ void check_loadable_libraries(void); FileNameMap *gen_db_file_maps(DbInfo *old_db, DbInfo *new_db, int *nmaps, const char *old_pgdata, const char *new_pgdata); -void get_db_and_rel_infos(ClusterInfo *cluster); +void get_db_rel_and_slot_infos(ClusterInfo *cluster); +int count_old_cluster_logical_slots(void); /* option.c */ diff --git a/src/bin/pg_upgrade/server.c b/src/bin/pg_upgrade/server.c index 0bc3d2806b..d083a001f1 100644 --- a/src/bin/pg_upgrade/server.c +++ b/src/bin/pg_upgrade/server.c @@ -234,6 +234,10 @@ start_postmaster(ClusterInfo *cluster, bool report_and_exit_on_error) * we only modify the new cluster, so only use it there. If there is a * crash, the new cluster has to be recreated anyway. fsync=off is a big * win on ext4. + * + * Use max_slot_wal_keep_size as -1 to prevent the WAL removal that is + * required by logical slots. This would avoid the invalidation of slots + * during the upgrade. */ snprintf(cmd, sizeof(cmd), "\"%s/pg_ctl\" -w -l \"%s/%s\" -D \"%s\" -o \"-p %d -b%s %s%s\" start", @@ -241,7 +245,8 @@ start_postmaster(ClusterInfo *cluster, bool report_and_exit_on_error) log_opts.logdir, SERVER_LOG_FILE, cluster->pgconfig, cluster->port, (cluster == &new_cluster) ? - " -c synchronous_commit=off -c fsync=off -c full_page_writes=off" : "", + " -c synchronous_commit=off -c fsync=off -c full_page_writes=off -c max_slot_wal_keep_size=-1 " : + " -c max_slot_wal_keep_size=-1", cluster->pgopts ? cluster->pgopts : "", socket_string); /* diff --git a/src/bin/pg_upgrade/t/003_logical_replication_slots.pl b/src/bin/pg_upgrade/t/003_logical_replication_slots.pl new file mode 100644 index 0000000000..640964c4e1 --- /dev/null +++ b/src/bin/pg_upgrade/t/003_logical_replication_slots.pl @@ -0,0 +1,214 @@ +# Copyright (c) 2023, PostgreSQL Global Development Group + +# Tests for upgrading replication slots + +use strict; +use warnings; + +use File::Path qw(rmtree); + +use PostgreSQL::Test::Cluster; +use PostgreSQL::Test::Utils; +use Test::More; + +# Can be changed to test the other modes +my $mode = $ENV{PG_TEST_PG_UPGRADE_MODE} || '--copy'; + +# Initialize old cluster +my $old_publisher = PostgreSQL::Test::Cluster->new('old_publisher'); +$old_publisher->init(allows_streaming => 'logical'); + +# Initialize new cluster +my $new_publisher = PostgreSQL::Test::Cluster->new('new_publisher'); +$new_publisher->init(allows_streaming => 'replica'); + +# Initialize subscriber cluster +my $subscriber = PostgreSQL::Test::Cluster->new('subscriber'); +$subscriber->init(allows_streaming => 'logical'); + +my $bindir = $new_publisher->config_data('--bindir'); + +# ------------------------------ +# TEST: Confirm pg_upgrade fails when new cluster wal_level is not 'logical' + +# Preparations for the subsequent test: +# 1. Create a slot on the old cluster +$old_publisher->start; +$old_publisher->safe_psql('postgres', + "SELECT pg_create_logical_replication_slot('test_slot1', 'test_decoding', false, true);" +); +$old_publisher->stop; + +# pg_upgrade will fail because the new cluster wal_level is 'replica' +command_fails( + [ + 'pg_upgrade', '--no-sync', + '-d', $old_publisher->data_dir, + '-D', $new_publisher->data_dir, + '-b', $bindir, + '-B', $bindir, + '-s', $new_publisher->host, + '-p', $old_publisher->port, + '-P', $new_publisher->port, + $mode, + ], + 'run of pg_upgrade where the new cluster has the wrong wal_level'); +ok( -d $new_publisher->data_dir . "/pg_upgrade_output.d", + "pg_upgrade_output.d/ not removed after pg_upgrade failure"); + +# Clean up +rmtree($new_publisher->data_dir . "/pg_upgrade_output.d"); + +# ------------------------------ +# TEST: Confirm pg_upgrade fails when max_replication_slots on a new cluster is +# too low + +# Preparations for the subsequent test: +# 1. Create a second slot on the old cluster +$old_publisher->start; +$old_publisher->safe_psql('postgres', + "SELECT pg_create_logical_replication_slot('test_slot2', 'test_decoding', false, true);" +); + +# 2. Consume WAL records to avoid another type of upgrade failure. It will be +# tested in subsequent cases. +$old_publisher->safe_psql('postgres', + "SELECT count(*) FROM pg_logical_slot_get_changes('test_slot1', NULL, NULL);" +); +$old_publisher->stop; + +# 3. max_replication_slots is set to smaller than the number of slots (2) +# present on the old cluster +$new_publisher->append_conf('postgresql.conf', "max_replication_slots = 1"); + +# 4. wal_level is set correctly on the new cluster +$new_publisher->append_conf('postgresql.conf', "wal_level = 'logical'"); + +# pg_upgrade will fail because the new cluster has insufficient max_replication_slots +command_fails( + [ + 'pg_upgrade', '--no-sync', + '-d', $old_publisher->data_dir, + '-D', $new_publisher->data_dir, + '-b', $bindir, + '-B', $bindir, + '-s', $new_publisher->host, + '-p', $old_publisher->port, + '-P', $new_publisher->port, + $mode, + ], + 'run of pg_upgrade where the new cluster has insufficient max_replication_slots'); +ok( -d $new_publisher->data_dir . "/pg_upgrade_output.d", + "pg_upgrade_output.d/ not removed after pg_upgrade failure"); + +# Clean up +rmtree($new_publisher->data_dir . "/pg_upgrade_output.d"); + +# ------------------------------ +# TEST: Confirm pg_upgrade fails when the slot still has unconsumed WAL records + +# Preparations for the subsequent test: +# 1. Remove the slot 'test_slot2', leaving only 1 slot remaining on the old +# cluster, so the new cluster config max_replication_slots=1 will now be +# enough. +$old_publisher->start; +$old_publisher->safe_psql('postgres', + "SELECT * FROM pg_drop_replication_slot('test_slot2');" +); + +# 2. Generate extra WAL records. Because these WAL records do not get consumed +# it will cause the upcoming pg_upgrade test to fail. +$old_publisher->safe_psql('postgres', + "CREATE TABLE tbl AS SELECT generate_series(1, 10) AS a;" +); +$old_publisher->stop; + +# pg_upgrade will fail because the slot still has unconsumed WAL records +command_fails( + [ + 'pg_upgrade', '--no-sync', + '-d', $old_publisher->data_dir, + '-D', $new_publisher->data_dir, + '-b', $bindir, + '-B', $bindir, + '-s', $new_publisher->host, + '-p', $old_publisher->port, + '-P', $new_publisher->port, + $mode, + ], + 'run of pg_upgrade of old cluster with idle replication slots'); +ok( -d $new_publisher->data_dir . "/pg_upgrade_output.d", + "pg_upgrade_output.d/ not removed after pg_upgrade failure"); + +# Clean up +rmtree($new_publisher->data_dir . "/pg_upgrade_output.d"); +# Remove the remained slot +$old_publisher->start; +$old_publisher->safe_psql('postgres', + "SELECT * FROM pg_drop_replication_slot('test_slot1');" +); + +# ------------------------------ +# TEST: Successful upgrade + +# Preparations for the subsequent test: +# 1. Setup logical replication +my $old_connstr = $old_publisher->connstr . ' dbname=postgres'; +$old_publisher->safe_psql('postgres', + "CREATE PUBLICATION pub FOR ALL TABLES;" +); +$subscriber->start; +$subscriber->safe_psql( + 'postgres', qq[ + CREATE TABLE tbl (a int); + CREATE SUBSCRIPTION sub CONNECTION '$old_connstr' PUBLICATION pub WITH (two_phase = 'true') +]); +$subscriber->wait_for_subscription_sync($old_publisher, 'sub'); + +# 2. Temporarily disable the subscription +$subscriber->safe_psql('postgres', "ALTER SUBSCRIPTION sub DISABLE"); +$old_publisher->stop; + +# Actual run, successful upgrade is expected +command_ok( + [ + 'pg_upgrade', '--no-sync', + '-d', $old_publisher->data_dir, + '-D', $new_publisher->data_dir, + '-b', $bindir, + '-B', $bindir, + '-s', $new_publisher->host, + '-p', $old_publisher->port, + '-P', $new_publisher->port, + $mode, + ], + 'run of pg_upgrade of old cluster'); +ok( !-d $new_publisher->data_dir . "/pg_upgrade_output.d", + "pg_upgrade_output.d/ removed after pg_upgrade success"); + +# Check that the slot 'sub' has migrated to the new cluster +$new_publisher->start; +my $result = $new_publisher->safe_psql('postgres', + "SELECT slot_name, two_phase FROM pg_replication_slots"); +is($result, qq(sub|t), 'check the slot exists on new cluster'); + +# Update the connection +my $new_connstr = $new_publisher->connstr . ' dbname=postgres'; +$subscriber->safe_psql( + 'postgres', qq[ + ALTER SUBSCRIPTION sub CONNECTION '$new_connstr'; + ALTER SUBSCRIPTION sub ENABLE; +]); + +# Check whether changes on the new publisher get replicated to the subscriber +$new_publisher->safe_psql('postgres', + "INSERT INTO tbl VALUES (generate_series(11, 20))"); +$new_publisher->wait_for_catchup('sub'); +$result = $subscriber->safe_psql('postgres', "SELECT count(*) FROM tbl"); +is($result, qq(20), 'check changes are replicated to the subscriber'); + +# Clean up +$subscriber->stop(); +$new_publisher->stop(); + +done_testing(); diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index f2af84d7ca..98c01fa05f 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1502,7 +1502,10 @@ LogicalRepTupleData LogicalRepTyp LogicalRepWorker LogicalRepWorkerType +LogicalReplicationSlotInfo LogicalRewriteMappingData +LogicalSlotInfo +LogicalSlotInfoArr LogicalTape LogicalTapeSet LsnReadQueue -- 2.27.0