v37-0003-Adding-contrib-module-pg_amcheck.patch
application/octet-stream
Filename: v37-0003-Adding-contrib-module-pg_amcheck.patch
Type: application/octet-stream
Part: 2
Message:
Re: new heapcheck contrib module
Patch
Format: format-patch
Series: patch v37-0003
Subject: Adding contrib module pg_amcheck
| File | + | − |
|---|---|---|
| contrib/Makefile | 1 | 0 |
| contrib/pg_amcheck/.gitignore | 3 | 0 |
| contrib/pg_amcheck/Makefile | 29 | 0 |
| contrib/pg_amcheck/pg_amcheck.c | 1518 | 0 |
| contrib/pg_amcheck/pg_amcheck.h | 91 | 0 |
| contrib/pg_amcheck/t/001_basic.pl | 9 | 0 |
| contrib/pg_amcheck/t/002_nonesuch.pl | 78 | 0 |
| contrib/pg_amcheck/t/003_check.pl | 475 | 0 |
| contrib/pg_amcheck/t/004_verify_heapam.pl | 496 | 0 |
| contrib/pg_amcheck/t/005_opclass_damage.pl | 52 | 0 |
| doc/src/sgml/contrib.sgml | 1 | 0 |
| doc/src/sgml/filelist.sgml | 1 | 0 |
| doc/src/sgml/pgamcheck.sgml | 1004 | 0 |
| src/tools/msvc/Install.pm | 1 | 1 |
| src/tools/msvc/Mkvcbuild.pm | 3 | 3 |
| src/tools/pgindent/typedefs.list | 4 | 0 |
From d22394d457162a5591b2fe3659003737c1552229 Mon Sep 17 00:00:00 2001
From: Mark Dilger <mark.dilger@enterprisedb.com>
Date: Tue, 2 Feb 2021 12:36:59 -0800
Subject: [PATCH v37 3/4] Adding contrib module pg_amcheck
Adding new contrib module pg_amcheck, which is a command line
interface for running amcheck's verifications against tables and
indexes.
---
contrib/Makefile | 1 +
contrib/pg_amcheck/.gitignore | 3 +
contrib/pg_amcheck/Makefile | 29 +
contrib/pg_amcheck/pg_amcheck.c | 1518 ++++++++++++++++++++
contrib/pg_amcheck/pg_amcheck.h | 91 ++
contrib/pg_amcheck/t/001_basic.pl | 9 +
contrib/pg_amcheck/t/002_nonesuch.pl | 78 +
contrib/pg_amcheck/t/003_check.pl | 475 ++++++
contrib/pg_amcheck/t/004_verify_heapam.pl | 496 +++++++
contrib/pg_amcheck/t/005_opclass_damage.pl | 52 +
doc/src/sgml/contrib.sgml | 1 +
doc/src/sgml/filelist.sgml | 1 +
doc/src/sgml/pgamcheck.sgml | 1004 +++++++++++++
src/tools/msvc/Install.pm | 2 +-
src/tools/msvc/Mkvcbuild.pm | 6 +-
src/tools/pgindent/typedefs.list | 4 +
16 files changed, 3766 insertions(+), 4 deletions(-)
create mode 100644 contrib/pg_amcheck/.gitignore
create mode 100644 contrib/pg_amcheck/Makefile
create mode 100644 contrib/pg_amcheck/pg_amcheck.c
create mode 100644 contrib/pg_amcheck/pg_amcheck.h
create mode 100644 contrib/pg_amcheck/t/001_basic.pl
create mode 100644 contrib/pg_amcheck/t/002_nonesuch.pl
create mode 100644 contrib/pg_amcheck/t/003_check.pl
create mode 100644 contrib/pg_amcheck/t/004_verify_heapam.pl
create mode 100644 contrib/pg_amcheck/t/005_opclass_damage.pl
create mode 100644 doc/src/sgml/pgamcheck.sgml
diff --git a/contrib/Makefile b/contrib/Makefile
index f27e458482..a72dcf7304 100644
--- a/contrib/Makefile
+++ b/contrib/Makefile
@@ -30,6 +30,7 @@ SUBDIRS = \
old_snapshot \
pageinspect \
passwordcheck \
+ pg_amcheck \
pg_buffercache \
pg_freespacemap \
pg_prewarm \
diff --git a/contrib/pg_amcheck/.gitignore b/contrib/pg_amcheck/.gitignore
new file mode 100644
index 0000000000..c21a14de31
--- /dev/null
+++ b/contrib/pg_amcheck/.gitignore
@@ -0,0 +1,3 @@
+pg_amcheck
+
+/tmp_check/
diff --git a/contrib/pg_amcheck/Makefile b/contrib/pg_amcheck/Makefile
new file mode 100644
index 0000000000..bc61ee7970
--- /dev/null
+++ b/contrib/pg_amcheck/Makefile
@@ -0,0 +1,29 @@
+# contrib/pg_amcheck/Makefile
+
+PGFILEDESC = "pg_amcheck - detects corruption within database relations"
+PGAPPICON = win32
+
+PROGRAM = pg_amcheck
+OBJS = \
+ $(WIN32RES) \
+ pg_amcheck.o
+
+REGRESS_OPTS += --load-extension=amcheck --load-extension=pageinspect
+EXTRA_INSTALL += contrib/amcheck contrib/pageinspect
+
+TAP_TESTS = 1
+
+PG_CPPFLAGS = -I$(libpq_srcdir)
+PG_LIBS_INTERNAL = -L$(top_builddir)/src/fe_utils -lpgfeutils $(libpq_pgport)
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+SHLIB_PREREQS = submake-libpq
+subdir = contrib/pg_amcheck
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_amcheck/pg_amcheck.c b/contrib/pg_amcheck/pg_amcheck.c
new file mode 100644
index 0000000000..dc4da95ad3
--- /dev/null
+++ b/contrib/pg_amcheck/pg_amcheck.c
@@ -0,0 +1,1518 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_amcheck.c
+ * Detects corruption within database relations.
+ *
+ * Copyright (c) 2017-2020, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * contrib/pg_amcheck/pg_amcheck.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres_fe.h"
+
+#include "catalog/pg_class.h"
+#include "common/connect.h"
+#include "common/logging.h"
+#include "common/username.h"
+#include "fe_utils/cancel.h"
+#include "fe_utils/connect_utils.h"
+#include "fe_utils/option_utils.h"
+#include "fe_utils/parallel_slot.h"
+#include "fe_utils/query_utils.h"
+#include "fe_utils/simple_list.h"
+#include "fe_utils/string_utils.h"
+#include "getopt_long.h" /* pgrminclude ignore */
+#include "libpq-fe.h"
+#include "pg_amcheck.h"
+#include "pqexpbuffer.h" /* pgrminclude ignore */
+#include "storage/block.h"
+
+/* Keep this in order by CheckType */
+static const CheckTypeFilter ctfilter[] = {
+ {
+ .relam = HEAP_TABLE_AM_OID,
+ .relkinds = CppAsString2(RELKIND_RELATION) ","
+ CppAsString2(RELKIND_MATVIEW) ","
+ CppAsString2(RELKIND_TOASTVALUE),
+ .typname = "heap"
+ },
+ {
+ .relam = BTREE_AM_OID,
+ .relkinds = CppAsString2(RELKIND_INDEX),
+ .typname = "btree index"
+ }
+};
+
+/*
+ * Query for determining if contrib's amcheck is installed. If so, selects the
+ * namespace name where amcheck's functions can be found.
+ */
+static const char *amcheck_sql =
+"SELECT n.nspname, x.extversion"
+"\nFROM pg_catalog.pg_extension x"
+"\nJOIN pg_catalog.pg_namespace n"
+"\nON x.extnamespace OPERATOR(pg_catalog.=) n.oid"
+"\nWHERE x.extname OPERATOR(pg_catalog.=) 'amcheck'";
+
+static void check_each_database(ConnParams *cparams,
+ const amcheckObjects *objects,
+ const amcheckOptions *checkopts,
+ const char *progname);
+
+static void check_one_database(const ConnParams *cparams,
+ const amcheckObjects *objects,
+ const amcheckOptions *checkopts,
+ const char *progname);
+static void prepare_table_command(PQExpBuffer sql,
+ const amcheckOptions *checkopts, Oid reloid,
+ const char *nspname);
+
+static void prepare_btree_command(PQExpBuffer sql,
+ const amcheckOptions *checkopts, Oid reloid,
+ const char *nspname);
+
+static void run_command(PGconn *conn, const char *sql,
+ const amcheckOptions *checkopts, Oid reloid,
+ const char *typ);
+
+static PGresult *VerifyHeapamSlotHandler(PGresult *res, PGconn *conn,
+ void *context);
+
+static PGresult *VerifyBtreeSlotHandler(PGresult *res, PGconn *conn,
+ void *context);
+
+static void help(const char *progname);
+
+
+static void get_db_regexps_from_fqrps(SimpleStringList *regexps,
+ const SimpleStringList *patterns);
+
+static void get_db_regexps_from_patterns(SimpleStringList *regexps,
+ const SimpleStringList *patterns);
+
+static void appendDatabaseSelect(PGconn *conn, PQExpBuffer sql,
+ const SimpleStringList *regexps, bool alldb);
+
+static void appendTargetSelect(PGconn *conn, PQExpBuffer sql,
+ const amcheckObjects *objects,
+ const amcheckOptions *options, const char *progname,
+ bool inclusive);
+
+int
+main(int argc, char *argv[])
+{
+ static struct option long_options[] = {
+ /* Connection options */
+ {"host", required_argument, NULL, 'h'},
+ {"port", required_argument, NULL, 'p'},
+ {"username", required_argument, NULL, 'U'},
+ {"no-password", no_argument, NULL, 'w'},
+ {"password", no_argument, NULL, 'W'},
+ {"maintenance-db", required_argument, NULL, 1},
+
+ /* check options */
+ {"all", no_argument, NULL, 'a'},
+ {"dbname", required_argument, NULL, 'd'},
+ {"exclude-dbname", required_argument, NULL, 'D'},
+ {"echo", no_argument, NULL, 'e'},
+ {"heapallindexed", no_argument, NULL, 'H'},
+ {"index", required_argument, NULL, 'i'},
+ {"exclude-index", required_argument, NULL, 'I'},
+ {"jobs", required_argument, NULL, 'j'},
+ {"parent-check", no_argument, NULL, 'P'},
+ {"quiet", no_argument, NULL, 'q'},
+ {"relation", required_argument, NULL, 'r'},
+ {"exclude-relation", required_argument, NULL, 'R'},
+ {"schema", required_argument, NULL, 's'},
+ {"exclude-schema", required_argument, NULL, 'S'},
+ {"table", required_argument, NULL, 't'},
+ {"exclude-table", required_argument, NULL, 'T'},
+ {"verbose", no_argument, NULL, 'v'},
+ {"exclude-indexes", no_argument, NULL, 2},
+ {"exclude-toast", no_argument, NULL, 3},
+ {"exclude-toast-pointers", no_argument, NULL, 4},
+ {"on-error-stop", no_argument, NULL, 5},
+ {"skip", required_argument, NULL, 6},
+ {"startblock", required_argument, NULL, 7},
+ {"endblock", required_argument, NULL, 8},
+ {"rootdescend", no_argument, NULL, 9},
+ {"no-dependents", no_argument, NULL, 10},
+
+ {NULL, 0, NULL, 0}
+ };
+
+ const char *progname;
+ int optindex;
+ int c;
+
+ const char *maintenance_db = NULL;
+ const char *connect_db = NULL;
+ const char *host = NULL;
+ const char *port = NULL;
+ const char *username = NULL;
+ enum trivalue prompt_password = TRI_DEFAULT;
+ ConnParams cparams;
+
+ amcheckOptions checkopts = {
+ .alldb = false,
+ .echo = false,
+ .quiet = false,
+ .verbose = false,
+ .dependents = true,
+ .no_indexes = false,
+ .on_error_stop = false,
+ .parent_check = false,
+ .rootdescend = false,
+ .heapallindexed = false,
+ .exclude_toast = false,
+ .reconcile_toast = true,
+ .skip = "none",
+ .jobs = -1,
+ .startblock = -1,
+ .endblock = -1
+ };
+
+ amcheckObjects objects = {
+ .databases = {NULL, NULL},
+ .schemas = {NULL, NULL},
+ .tables = {NULL, NULL},
+ .indexes = {NULL, NULL},
+ .exclude_databases = {NULL, NULL},
+ .exclude_schemas = {NULL, NULL},
+ .exclude_tables = {NULL, NULL},
+ .exclude_indexes = {NULL, NULL}
+ };
+
+ pg_logging_init(argv[0]);
+ progname = get_progname(argv[0]);
+ set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("contrib"));
+
+ handle_help_version_opts(argc, argv, progname, help);
+
+ /* process command-line options */
+ while ((c = getopt_long(argc, argv, "ad:D:eh:Hi:I:j:p:Pqr:R:s:S:t:T:U:wWv",
+ long_options, &optindex)) != -1)
+ {
+ char *endptr;
+
+ switch (c)
+ {
+ case 'a':
+ checkopts.alldb = true;
+ break;
+ case 'd':
+ simple_string_list_append(&objects.databases, optarg);
+ break;
+ case 'D':
+ simple_string_list_append(&objects.exclude_databases, optarg);
+ break;
+ case 'e':
+ checkopts.echo = true;
+ break;
+ case 'h':
+ host = pg_strdup(optarg);
+ break;
+ case 'H':
+ checkopts.heapallindexed = true;
+ break;
+ case 'i':
+ simple_string_list_append(&objects.indexes, optarg);
+ break;
+ case 'I':
+ simple_string_list_append(&objects.exclude_indexes, optarg);
+ break;
+ case 'j':
+ checkopts.jobs = atoi(optarg);
+ if (checkopts.jobs <= 0)
+ {
+ pg_log_error("number of parallel jobs must be at least 1");
+ exit(1);
+ }
+ break;
+ case 'p':
+ port = pg_strdup(optarg);
+ break;
+ case 'P':
+ checkopts.parent_check = true;
+ break;
+ case 'q':
+ checkopts.quiet = true;
+ break;
+ case 'r':
+ simple_string_list_append(&objects.indexes, optarg);
+ simple_string_list_append(&objects.tables, optarg);
+ break;
+ case 'R':
+ simple_string_list_append(&objects.exclude_tables, optarg);
+ simple_string_list_append(&objects.exclude_indexes, optarg);
+ break;
+ case 's':
+ simple_string_list_append(&objects.schemas, optarg);
+ break;
+ case 'S':
+ simple_string_list_append(&objects.exclude_schemas, optarg);
+ break;
+ case 't':
+ simple_string_list_append(&objects.tables, optarg);
+ break;
+ case 'T':
+ simple_string_list_append(&objects.exclude_tables, optarg);
+ break;
+ case 'U':
+ username = pg_strdup(optarg);
+ break;
+ case 'w':
+ prompt_password = TRI_NO;
+ break;
+ case 'W':
+ prompt_password = TRI_YES;
+ break;
+ case 'v':
+ checkopts.verbose = true;
+ pg_logging_increase_verbosity();
+ break;
+ case 1:
+ maintenance_db = pg_strdup(optarg);
+ break;
+ case 2:
+ checkopts.no_indexes = true;
+ break;
+ case 3:
+ checkopts.exclude_toast = true;
+ break;
+ case 4:
+ checkopts.reconcile_toast = false;
+ break;
+ case 5:
+ checkopts.on_error_stop = true;
+ break;
+ case 6:
+ if (pg_strcasecmp(optarg, "all-visible") == 0)
+ checkopts.skip = "all visible";
+ else if (pg_strcasecmp(optarg, "all-frozen") == 0)
+ checkopts.skip = "all frozen";
+ else
+ {
+ fprintf(stderr, _("invalid skip options"));
+ exit(1);
+ }
+ break;
+ case 7:
+ checkopts.startblock = strtol(optarg, &endptr, 10);
+ if (*endptr != '\0')
+ {
+ fprintf(stderr,
+ _("relation starting block argument contains garbage characters"));
+ exit(1);
+ }
+ if (checkopts.startblock > (long) MaxBlockNumber)
+ {
+ fprintf(stderr,
+ _("relation starting block argument out of bounds"));
+ exit(1);
+ }
+ break;
+ case 8:
+ checkopts.endblock = strtol(optarg, &endptr, 10);
+ if (*endptr != '\0')
+ {
+ fprintf(stderr,
+ _("relation ending block argument contains garbage characters"));
+ exit(1);
+ }
+ if (checkopts.startblock > (long) MaxBlockNumber)
+ {
+ fprintf(stderr,
+ _("relation ending block argument out of bounds"));
+ exit(1);
+ }
+ break;
+ case 9:
+ checkopts.rootdescend = true;
+ checkopts.parent_check = true;
+ break;
+ case 10:
+ checkopts.dependents = false;
+ break;
+ default:
+ fprintf(stderr,
+ _("Try \"%s --help\" for more information.\n"),
+ progname);
+ exit(1);
+ }
+ }
+
+ if (checkopts.endblock >= 0 && checkopts.endblock < checkopts.startblock)
+ {
+ pg_log_error("relation ending block argument precedes starting block argument");
+ exit(1);
+ }
+
+ /* non-option arguments specify database names */
+ while (optind < argc)
+ {
+ if (connect_db == NULL)
+ connect_db = argv[optind];
+ simple_string_list_append(&objects.databases, argv[optind]);
+ optind++;
+ }
+
+ /* fill cparams except for dbname, which is set below */
+ cparams.pghost = host;
+ cparams.pgport = port;
+ cparams.pguser = username;
+ cparams.prompt_password = prompt_password;
+ cparams.override_dbname = NULL;
+
+ setup_cancel_handler(NULL);
+
+ /* choose the database for our initial connection */
+ if (maintenance_db)
+ cparams.dbname = maintenance_db;
+ else if (connect_db != NULL)
+ cparams.dbname = connect_db;
+ else if (objects.databases.head != NULL)
+ cparams.dbname = objects.databases.head->val;
+ else
+ {
+ const char *default_db;
+
+ if (getenv("PGDATABASE"))
+ default_db = getenv("PGDATABASE");
+ else if (getenv("PGUSER"))
+ default_db = getenv("PGUSER");
+ else
+ default_db = get_user_name_or_exit(progname);
+
+ if (objects.databases.head == NULL)
+ simple_string_list_append(&objects.databases, default_db);
+
+ cparams.dbname = default_db;
+ }
+
+ check_each_database(&cparams, &objects, &checkopts, progname);
+
+ exit(0);
+}
+
+/*
+ * check_each_database
+ *
+ * Connects to the initial database and resolves a list of all databases that
+ * should be checked per the user supplied options. Sequentially checks each
+ * database in the list.
+ *
+ * The user supplied options may include zero databases, or only one database,
+ * in which case we could skip the step of resolving a list of databases, but
+ * it seems not worth optimizing, especially considering that there are
+ * multiple ways in which no databases or just one database might be specified,
+ * including a pattern that happens to match no entries or to match only one
+ * entry in pg_database.
+ *
+ * cparams: parameters for the initial database connection
+ * objects: lists of include and exclude patterns for filtering objects
+ * checkopts: user supplied program options
+ * progname: name of this program, such as "pg_amcheck"
+ */
+static void
+check_each_database(ConnParams *cparams, const amcheckObjects *objects,
+ const amcheckOptions *checkopts, const char *progname)
+{
+ PGconn *conn;
+ PGresult *databases;
+ PQExpBufferData sql;
+ int ntups;
+ int i;
+ SimpleStringList dbregex = {NULL, NULL};
+ SimpleStringList exclude = {NULL, NULL};
+
+ /*
+ * Get a list of all database SQL regexps to use for selecting database
+ * names. We assemble these regexps from fully-qualified relation
+ * patterns and database patterns. This process may result in the same
+ * database regex in the list multiple times, but the query against
+ * pg_database will deduplice, so we don't care.
+ */
+ get_db_regexps_from_fqrps(&dbregex, &objects->tables);
+ get_db_regexps_from_fqrps(&dbregex, &objects->indexes);
+ get_db_regexps_from_patterns(&dbregex, &objects->databases);
+
+ /*
+ * Assemble SQL regexps for databases to be excluded. Note that excluded
+ * relations are not considered here, as excluding relation x.y.z does not
+ * imply excluding database x. Excluding x.*.* would imply excluding
+ * database x, but we do not check for that here.
+ */
+ get_db_regexps_from_patterns(&exclude, &objects->exclude_databases);
+
+ conn = connectMaintenanceDatabase(cparams, progname, checkopts->echo);
+
+ initPQExpBuffer(&sql);
+ appendDatabaseSelect(conn, &sql, &dbregex, checkopts->alldb);
+ appendPQExpBufferStr(&sql, "\nEXCEPT");
+ appendDatabaseSelect(conn, &sql, &exclude, false);
+ executeCommand(conn, "RESET search_path;", checkopts->echo);
+ databases = executeQuery(conn, sql.data, checkopts->echo);
+ if (PQresultStatus(databases) != PGRES_TUPLES_OK)
+ {
+ pg_log_error("query failed: %s", PQerrorMessage(conn));
+ pg_log_error("query was: %s", sql.data);
+ PQfinish(conn);
+ exit(1);
+ }
+
+ termPQExpBuffer(&sql);
+ PQclear(executeQuery(conn, ALWAYS_SECURE_SEARCH_PATH_SQL, checkopts->echo));
+ PQfinish(conn);
+
+ ntups = PQntuples(databases);
+ if (ntups == 0 && !checkopts->quiet)
+ printf(_("%s: no databases to check\n"), progname);
+
+ for (i = 0; i < ntups; i++)
+ {
+ cparams->override_dbname = PQgetvalue(databases, i, 0);
+ check_one_database(cparams, objects, checkopts, progname);
+ }
+
+ PQclear(databases);
+}
+
+/*
+ * string_in_list
+ *
+ * Returns whether a given string is in the list of strings.
+ */
+static bool
+string_in_list(const SimpleStringList *list, const char *str)
+{
+ const SimpleStringListCell *cell;
+
+ for (cell = list->head; cell; cell = cell->next)
+ if (strcmp(cell->val, str) == 0)
+ return true;
+ return false;
+}
+
+/*
+ * check_one_database
+ *
+ * Connects to this next database and checks all relations that match the
+ * supplied objects list. Patterns in the object lists are matched to the
+ * relations that exit in this next database.
+ *
+ * cparams: parameters for this next database connection
+ * objects: lists of include and exclude patterns for filtering objects
+ * checkopts: user supplied program options
+ * progname: name of this program, such as "pg_amcheck"
+ */
+static void
+check_one_database(const ConnParams *cparams, const amcheckObjects *objects,
+ const amcheckOptions *checkopts, const char *progname)
+{
+ PQExpBufferData sql;
+ PGconn *conn;
+ PGresult *result;
+ ParallelSlot *slots;
+ int ntups;
+ int i;
+ int parallel_workers;
+ bool inclusive;
+ bool failed = false;
+ char *amcheck_schema = NULL;
+
+ conn = connectDatabase(cparams, progname, checkopts->echo, false, true);
+
+ if (!checkopts->quiet)
+ {
+ printf(_("%s: checking database \"%s\"\n"),
+ progname, PQdb(conn));
+ fflush(stdout);
+ }
+
+ /*
+ * Verify that amcheck is installed for this next database. User error
+ * could result in a database not having amcheck that should have it, but
+ * we also could be iterating over multiple databases where not all of
+ * them have amcheck installed (for example, 'template1').
+ */
+ result = executeQuery(conn, amcheck_sql, checkopts->echo);
+ if (PQresultStatus(result) != PGRES_TUPLES_OK)
+ {
+ /* Querying the catalog failed. */
+ pg_log_error(_("%s: database \"%s\": %s\n"),
+ progname, PQdb(conn), PQerrorMessage(conn));
+ pg_log_error(_("%s: query was: %s"), progname, amcheck_sql);
+ PQclear(result);
+ PQfinish(conn);
+ return;
+ }
+ ntups = PQntuples(result);
+ if (ntups == 0)
+ {
+ /* Querying the catalog succeeded, but amcheck is missing. */
+ if (!checkopts->quiet &&
+ (checkopts->verbose ||
+ string_in_list(&objects->databases, PQdb(conn))))
+ {
+ printf(_("%s: skipping database \"%s\": amcheck is not installed"),
+ progname, PQdb(conn));
+ }
+ PQfinish(conn);
+ return;
+ }
+ amcheck_schema = PQgetvalue(result, 0, 0);
+ if (checkopts->verbose)
+ printf(_("%s: in database \"%s\": using amcheck version \"%s\" in schema \"%s\""),
+ progname, PQdb(conn), PQgetvalue(result, 0, 1), amcheck_schema);
+ amcheck_schema = PQescapeIdentifier(conn, amcheck_schema, strlen(amcheck_schema));
+ PQclear(result);
+
+ /*
+ * If we were given no tables nor indexes to check, then we select all
+ * targets not excluded. Otherwise, we select only the targets that we
+ * were given.
+ */
+ inclusive = objects->tables.head == NULL &&
+ objects->indexes.head == NULL;
+
+ initPQExpBuffer(&sql);
+ appendTargetSelect(conn, &sql, objects, checkopts, progname, inclusive);
+ executeCommand(conn, "RESET search_path;", checkopts->echo);
+ result = executeQuery(conn, sql.data, checkopts->echo);
+ if (PQresultStatus(result) != PGRES_TUPLES_OK)
+ {
+ pg_log_error("query failed: %s", PQerrorMessage(conn));
+ pg_log_error("query was: %s", sql.data);
+ PQfinish(conn);
+ exit(1);
+ }
+ termPQExpBuffer(&sql);
+ PQclear(executeQuery(conn, ALWAYS_SECURE_SEARCH_PATH_SQL, checkopts->echo));
+
+ /*
+ * If no rows are returned, there are no matching relations, so we are
+ * done.
+ */
+ ntups = PQntuples(result);
+ if (ntups == 0)
+ {
+ PQclear(result);
+ PQfinish(conn);
+ PQfreemem(amcheck_schema);
+ return;
+ }
+
+ /*
+ * Ensure parallel_workers is sane. If there are more connections than
+ * relations to be checked, we don't need to use them all.
+ */
+ parallel_workers = checkopts->jobs;
+ if (parallel_workers > ntups)
+ parallel_workers = ntups;
+ if (parallel_workers <= 0)
+ parallel_workers = 1;
+
+ /*
+ * Setup the database connections. We reuse the connection we already
+ * have for the first slot. If not in parallel mode, the first slot in
+ * the array contains the connection.
+ */
+ slots = ParallelSlotsSetup(cparams, progname, checkopts->echo, conn,
+ parallel_workers);
+
+ initPQExpBuffer(&sql);
+
+ /*
+ * Loop over all objects to be checked, and execute amcheck checking
+ * commands for each. We do not wait for the checks to complete, nor do
+ * we handle the results of those checks in the loop. We register
+ * handlers for doing all that.
+ */
+ for (i = 0; i < ntups; i++)
+ {
+ ParallelSlot *free_slot;
+
+ CheckType checktype = atoi(PQgetvalue(result, i, 0));
+ Oid reloid = atooid(PQgetvalue(result, i, 1));
+
+ if (CancelRequested)
+ {
+ failed = true;
+ goto finish;
+ }
+
+ /*
+ * Get a parallel slot for the next amcheck command, blocking if
+ * necessary until one is available, or until a previously issued slot
+ * command fails, indicating that we should abort checking the
+ * remaining objects.
+ */
+ free_slot = ParallelSlotsGetIdle(slots, parallel_workers);
+ if (!free_slot)
+ {
+ /*
+ * Something failed. We don't need to know what it was, because
+ * the handler should already have emitted the necessary error
+ * messages.
+ */
+ failed = true;
+ goto finish;
+ }
+
+ /* Execute the amcheck command for the given relation type. */
+ switch (checktype)
+ {
+ /* heapam types */
+ case CT_TABLE:
+ prepare_table_command(&sql, checkopts, reloid, amcheck_schema);
+ ParallelSlotSetHandler(free_slot, VerifyHeapamSlotHandler, sql.data);
+ run_command(free_slot->connection, sql.data, checkopts, reloid,
+ ctfilter[checktype].typname);
+ break;
+
+ /* btreeam types */
+ case CT_BTREE:
+ prepare_btree_command(&sql, checkopts, reloid, amcheck_schema);
+ ParallelSlotSetHandler(free_slot, VerifyBtreeSlotHandler, NULL);
+ run_command(free_slot->connection, sql.data, checkopts, reloid,
+ ctfilter[checktype].typname);
+ break;
+
+ /* intentionally no default here */
+ }
+ }
+
+ /*
+ * Wait for all slots to complete, or for one to indicate that an error
+ * occurred. Like above, we rely on the handler emitting the necessary
+ * error messages.
+ */
+ if (!ParallelSlotsWaitCompletion(slots, parallel_workers))
+ failed = true;
+
+finish:
+ ParallelSlotsTerminate(slots, parallel_workers);
+ pg_free(slots);
+
+ termPQExpBuffer(&sql);
+
+ if (amcheck_schema != NULL)
+ PQfreemem(amcheck_schema);
+
+ if (failed)
+ exit(1);
+}
+
+/*
+ * prepare_table_command
+ *
+ * Creates a SQL command for running amcheck checking on the given heap
+ * relation. The command is phrased as a SQL query, with column order and
+ * names matching the expectations of VerifyHeapamSlotHandler, which will
+ * receive and handle each row returned from the verify_heapam() function.
+ *
+ * sql: buffer into which the table checking command will be written
+ * checkopts: user supplied program options
+ * reloid: relation of the table to be checked
+ * amcheck_schema: schema in which amcheck contrib module is installed
+ */
+static void
+prepare_table_command(PQExpBuffer sql, const amcheckOptions *checkopts,
+ Oid reloid, const char *amcheck_schema)
+{
+ resetPQExpBuffer(sql);
+ appendPQExpBuffer(sql,
+ "SELECT n.nspname, c.relname, v.blkno, v.offnum, v.attnum, v.msg"
+ "\nFROM %s.verify_heapam("
+ "\nrelation := %u,"
+ "\non_error_stop := %s,"
+ "\ncheck_toast := %s,"
+ "\nskip := '%s'",
+ amcheck_schema,
+ reloid,
+ checkopts->on_error_stop ? "true" : "false",
+ checkopts->reconcile_toast ? "true" : "false",
+ checkopts->skip);
+ if (checkopts->startblock >= 0)
+ appendPQExpBuffer(sql, ",\nstartblock := %ld", checkopts->startblock);
+ if (checkopts->endblock >= 0)
+ appendPQExpBuffer(sql, ",\nendblock := %ld", checkopts->endblock);
+ appendPQExpBuffer(sql, "\n) v,"
+ "\npg_catalog.pg_class c"
+ "\nJOIN pg_catalog.pg_namespace n"
+ "\nON c.relnamespace OPERATOR(pg_catalog.=) n.oid"
+ "\nWHERE c.oid OPERATOR(pg_catalog.=) %u",
+ reloid);
+}
+
+/*
+ * prepare_btree_command
+ *
+ * Creates a SQL command for running amcheck checking on the given btree index
+ * relation. The command does not select any columns, as btree checking
+ * functions do not return any, but rather return corruption information by
+ * raising errors, which VerifyBtreeSlotHandler expects.
+ *
+ * sql: buffer into which the table checking command will be written
+ * checkopts: user supplied program options
+ * reloid: relation of the table to be checked
+ * amcheck_schema: schema in which amcheck contrib module is installed
+ */
+static void
+prepare_btree_command(PQExpBuffer sql, const amcheckOptions *checkopts,
+ Oid reloid, const char *amcheck_schema)
+{
+ resetPQExpBuffer(sql);
+ if (checkopts->parent_check)
+ appendPQExpBuffer(sql,
+ "SELECT %s.bt_index_parent_check("
+ "\nindex := '%u'::regclass,"
+ "\nheapallindexed := %s,"
+ "\nrootdescend := %s)",
+ amcheck_schema,
+ reloid,
+ (checkopts->heapallindexed ? "true" : "false"),
+ (checkopts->rootdescend ? "true" : "false"));
+ else
+ appendPQExpBuffer(sql,
+ "SELECT %s.bt_index_check("
+ "\nindex := '%u'::regclass,"
+ "\nheapallindexed := %s)",
+ amcheck_schema,
+ reloid,
+ (checkopts->heapallindexed ? "true" : "false"));
+}
+
+/*
+ * run_command
+ *
+ * Sends a command to the server without waiting for the command to complete.
+ * Logs an error if the command cannot be sent, but otherwise any errors are
+ * expected to be handled by a ParallelSlotHandler.
+ *
+ * conn: connection to the server associated with the slot to use
+ * sql: query to send
+ * checkopts: user supplied program options
+ * reloid: oid of the object being checked, for error reporting
+ * typ: type of object being checked, for error reporting
+ */
+static void
+run_command(PGconn *conn, const char *sql, const amcheckOptions *checkopts,
+ Oid reloid, const char *typ)
+{
+ bool status;
+
+ if (checkopts->echo)
+ printf("%s\n", sql);
+
+ status = PQsendQuery(conn, sql) == 1;
+
+ if (!status)
+ {
+ pg_log_error("check of %s with id %u in database \"%s\" failed: %s",
+ typ, reloid, PQdb(conn), PQerrorMessage(conn));
+ pg_log_error("command was: %s", sql);
+ }
+}
+
+/*
+ * VerifyHeapamSlotHandler
+ *
+ * ParallelSlotHandler that receives results from a table checking command
+ * created by prepare_table_command and outputs the results for the user.
+ *
+ * res: result from an executed sql query
+ * conn: connection on which the sql query was executed
+ * context: the sql query being handled, as a cstring
+ */
+static PGresult *
+VerifyHeapamSlotHandler(PGresult *res, PGconn *conn, void *context)
+{
+ int ntups = PQntuples(res);
+
+ if (PQresultStatus(res) == PGRES_TUPLES_OK)
+ {
+ int i;
+
+ for (i = 0; i < ntups; i++)
+ {
+ if (!PQgetisnull(res, i, 4))
+ printf("relation %s.%s.%s, block %s, offset %s, attribute %s\n %s\n",
+ PQdb(conn),
+ PQgetvalue(res, i, 0), /* schema */
+ PQgetvalue(res, i, 1), /* relname */
+ PQgetvalue(res, i, 2), /* blkno */
+ PQgetvalue(res, i, 3), /* offnum */
+ PQgetvalue(res, i, 4), /* attnum */
+ PQgetvalue(res, i, 5)); /* msg */
+
+ else if (!PQgetisnull(res, i, 3))
+ printf("relation %s.%s.%s, block %s, offset %s\n %s\n",
+ PQdb(conn),
+ PQgetvalue(res, i, 0), /* schema */
+ PQgetvalue(res, i, 1), /* relname */
+ PQgetvalue(res, i, 2), /* blkno */
+ PQgetvalue(res, i, 3), /* offnum */
+ /* attnum is null: 4 */
+ PQgetvalue(res, i, 5)); /* msg */
+
+ else if (!PQgetisnull(res, i, 2))
+ printf("relation %s.%s.%s, block %s\n %s\n",
+ PQdb(conn),
+ PQgetvalue(res, i, 0), /* schema */
+ PQgetvalue(res, i, 1), /* relname */
+ PQgetvalue(res, i, 2), /* blkno */
+ /* offnum is null: 3 */
+ /* attnum is null: 4 */
+ PQgetvalue(res, i, 5)); /* msg */
+
+ else if (!PQgetisnull(res, i, 1))
+ printf("relation %s.%s.%s\n %s\n",
+ PQdb(conn),
+ PQgetvalue(res, i, 0), /* schema */
+ PQgetvalue(res, i, 1), /* relname */
+ /* blkno is null: 2 */
+ /* offnum is null: 3 */
+ /* attnum is null: 4 */
+ PQgetvalue(res, i, 5)); /* msg */
+
+ else
+ printf("%s.%s\n",
+ PQdb(conn),
+ PQgetvalue(res, i, 5)); /* msg */
+ }
+ }
+ else if (PQresultStatus(res) != PGRES_TUPLES_OK)
+ {
+ printf("%s: %s\n", PQdb(conn), PQerrorMessage(conn));
+ printf(_("query was: %s\n"), (const char *) context);
+ }
+
+ return res;
+}
+
+/*
+ * VerifyBtreeSlotHandler
+ *
+ * ParallelSlotHandler that receives results from a btree checking command
+ * created by prepare_btree_command and outputs them for the user. The results
+ * from the btree checking command is assumed to be empty, but when the results
+ * are an error code, the useful information about the corruption is expected
+ * in the connection's error message.
+ *
+ * res: result from an executed sql query
+ * conn: connection on which the sql query was executed
+ * context: unused
+ */
+static PGresult *
+VerifyBtreeSlotHandler(PGresult *res, PGconn *conn, void *context)
+{
+ if (PQresultStatus(res) != PGRES_TUPLES_OK)
+ printf("%s: %s\n", PQdb(conn), PQerrorMessage(conn));
+ return res;
+}
+
+/*
+ * help
+ *
+ * Prints help page for the program
+ *
+ * progname: the name of the executed program, such as "pg_amcheck"
+ */
+static void
+help(const char *progname)
+{
+ printf(_("%s checks objects in a PostgreSQL database for corruption.\n\n"), progname);
+ printf(_("Usage:\n"));
+ printf(_(" %s [OPTION]... [DBNAME]\n"), progname);
+ printf(_("\nTarget Options:\n"));
+ printf(_(" -a, --all check all databases\n"));
+ printf(_(" -d, --dbname=DBNAME check specific database(s)\n"));
+ printf(_(" -D, --exclude-dbname=DBNAME do NOT check specific database(s)\n"));
+ printf(_(" -i, --index=INDEX check specific index(es)\n"));
+ printf(_(" -I, --exclude-index=INDEX do NOT check specific index(es)\n"));
+ printf(_(" -r, --relation=RELNAME check specific relation(s)\n"));
+ printf(_(" -R, --exclude-relation=RELNAME do NOT check specific relation(s)\n"));
+ printf(_(" -s, --schema=SCHEMA check specific schema(s)\n"));
+ printf(_(" -S, --exclude-schema=SCHEMA do NOT check specific schema(s)\n"));
+ printf(_(" -t, --table=TABLE check specific table(s)\n"));
+ printf(_(" -T, --exclude-table=TABLE do NOT check specific table(s)\n"));
+ printf(_(" --exclude-indexes do NOT perform any index checking\n"));
+ printf(_(" --exclude-toast do NOT check any toast tables or indexes\n"));
+ printf(_(" --no-dependents do NOT automatically check dependent objects\n"));
+ printf(_("\nIndex Checking Options:\n"));
+ printf(_(" -H, --heapallindexed check all heap tuples are found within indexes\n"));
+ printf(_(" -P, --parent-check check parent/child relationships during index checking\n"));
+ printf(_(" --rootdescend search from root page to refind tuples at the leaf level\n"));
+ printf(_("\nTable Checking Options:\n"));
+ printf(_(" --exclude-toast-pointers do NOT check relation toast pointers against toast\n"));
+ printf(_(" --on-error-stop stop checking a relation at end of first corrupt page\n"));
+ printf(_(" --skip=OPTION do NOT check \"all-frozen\" or \"all-visible\" blocks\n"));
+ printf(_(" --startblock begin checking table(s) at the given starting block number\n"));
+ printf(_(" --endblock check table(s) only up to the given ending block number\n"));
+ printf(_("\nConnection options:\n"));
+ printf(_(" -h, --host=HOSTNAME database server host or socket directory\n"));
+ printf(_(" -p, --port=PORT database server port\n"));
+ printf(_(" -U, --username=USERNAME user name to connect as\n"));
+ printf(_(" -w, --no-password never prompt for password\n"));
+ printf(_(" -W, --password force password prompt\n"));
+ printf(_(" --maintenance-db=DBNAME alternate maintenance database\n"));
+ printf(_("\nOther Options:\n"));
+ printf(_(" -e, --echo show the commands being sent to the server\n"));
+ printf(_(" -j, --jobs=NUM use this many concurrent connections to the server\n"));
+ printf(_(" -q, --quiet don't write any messages\n"));
+ printf(_(" -v, --verbose write a lot of output\n"));
+ printf(_(" -V, --version output version information, then exit\n"));
+ printf(_(" -?, --help show this help, then exit\n"));
+
+ printf(_("\nRead the description of the amcheck contrib module for details.\n"));
+ printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
+ printf(_("%s home page: <%s>\n"), PACKAGE_NAME, PACKAGE_URL);
+}
+
+/*
+ * get_db_regexps_from_fqrps
+ *
+ * For each pattern in the patterns list, if it is in fully-qualified
+ * database.schema.name format (fully-qualifed relation pattern (fqrp)), parse
+ * the database portion of the pattern, convert it to SQL regex format, and
+ * append it to the databases list. Patterns that are not fully-qualified are
+ * skipped over. No deduplication of regexps is performed.
+ *
+ * regexps: list to which parsed and converted database regexps are appended
+ * patterns: list of all patterns to parse
+ */
+static void
+get_db_regexps_from_fqrps(SimpleStringList *regexps,
+ const SimpleStringList *patterns)
+{
+ const SimpleStringListCell *cell;
+ PQExpBufferData dbnamebuf;
+ PQExpBufferData schemabuf;
+ PQExpBufferData namebuf;
+ int encoding = pg_get_encoding_from_locale(NULL, false);
+
+ initPQExpBuffer(&dbnamebuf);
+ initPQExpBuffer(&schemabuf);
+ initPQExpBuffer(&namebuf);
+ for (cell = patterns->head; cell; cell = cell->next)
+ {
+ /* parse the pattern as dbname.schema.relname, if possible */
+ patternToSQLRegex(encoding, &dbnamebuf, &schemabuf, &namebuf,
+ cell->val, false);
+
+ /* add the database name (or pattern), if any, to the list */
+ if (dbnamebuf.data[0])
+ simple_string_list_append(regexps, dbnamebuf.data);
+
+ /* we do not use the schema or relname portions */
+
+ /* we may have dirtied the buffers */
+ resetPQExpBuffer(&dbnamebuf);
+ resetPQExpBuffer(&schemabuf);
+ resetPQExpBuffer(&namebuf);
+ }
+ termPQExpBuffer(&dbnamebuf);
+ termPQExpBuffer(&schemabuf);
+ termPQExpBuffer(&namebuf);
+}
+
+/*
+ * get_db_regexps_from_patterns
+ *
+ * Convert each unqualified pattern in the list to SQL regex format and append
+ * it to the regexps list. No deduplication of regexps is performed.
+ *
+ * regexps: list to which converted regexps are appended
+ * patterns: list of patterns to be converted
+ */
+static void
+get_db_regexps_from_patterns(SimpleStringList *regexps,
+ const SimpleStringList *patterns)
+{
+ const SimpleStringListCell *cell;
+ PQExpBufferData buf;
+ int encoding = pg_get_encoding_from_locale(NULL, false);
+
+ initPQExpBuffer(&buf);
+ for (cell = patterns->head; cell; cell = cell->next)
+ {
+ patternToSQLRegex(encoding, NULL, NULL, &buf, cell->val, false);
+ if (buf.data[0])
+ simple_string_list_append(regexps, buf.data);
+ resetPQExpBuffer(&buf);
+ }
+ termPQExpBuffer(&buf);
+}
+
+/*
+ * appendDatabaseSelect
+ *
+ * Appends a statement which selects the names of all databases matching the
+ * given SQL regular expressions.
+ *
+ * conn: connection to the initial database
+ * sql: buffer into which the constructed sql statement is appended
+ * regexps: list of database name regular expressions to match
+ * alldb: when true, select all databases which allow connections
+ */
+static void
+appendDatabaseSelect(PGconn *conn, PQExpBuffer sql, const SimpleStringList *regexps,
+ bool alldb)
+{
+ SimpleStringListCell *cell;
+ const char *comma;
+
+ if (alldb)
+ {
+ appendPQExpBufferStr(sql,
+ "\nSELECT datname::TEXT AS datname"
+ "\nFROM pg_catalog.pg_database"
+ "\nWHERE datallowconn");
+ return;
+ }
+ else if (regexps->head == NULL)
+ {
+ appendPQExpBufferStr(sql,
+ "\nSELECT ''::TEXT AS datname"
+ "\nWHERE false");
+ return;
+ }
+
+ appendPQExpBufferStr(sql,
+ "\nSELECT datname::TEXT AS datname"
+ "\nFROM pg_catalog.pg_database"
+ "\nWHERE datallowconn"
+ "\nAND datname::TEXT OPERATOR(pg_catalog.~) ANY(ARRAY[\n");
+ for (cell = regexps->head, comma = ""; cell; cell = cell->next, comma = ",\n")
+ {
+ appendPQExpBufferStr(sql, comma);
+ appendStringLiteralConn(sql, cell->val, conn);
+ appendPQExpBufferStr(sql, "::TEXT COLLATE pg_catalog.default");
+ }
+ appendPQExpBufferStr(sql, "\n]::TEXT[])");
+}
+
+/*
+ * appendSchemaSelect
+ *
+ * Appends a statement which selects all schemas matching the given patterns
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql statement is appended
+ * patterns: list of schema name patterns to match
+ * inclusive: when patterns is an empty list, whether the select statement
+ * should match all non-system schemas
+ */
+static void
+appendSchemaSelect(PGconn *conn, PQExpBuffer sql,
+ const SimpleStringList *patterns, bool inclusive)
+{
+ SimpleStringListCell *cell;
+ const char *comma;
+ int encoding = PQclientEncoding(conn);
+
+ if (patterns->head == NULL)
+ {
+ if (!inclusive)
+ appendPQExpBufferStr(sql,
+ "\nSELECT 0::pg_catalog.oid AS nspoid WHERE false");
+ else
+ appendPQExpBufferStr(sql,
+ "\nSELECT oid AS nspoid"
+ "\nFROM pg_catalog.pg_namespace"
+ "\nWHERE oid OPERATOR(pg_catalog.!=) pg_catalog.regnamespace('pg_catalog')"
+ "\nAND oid OPERATOR(pg_catalog.!=) pg_catalog.regnamespace('pg_toast')");
+ return;
+ }
+
+ appendPQExpBufferStr(sql,
+ "\nSELECT oid AS nspoid"
+ "\nFROM pg_catalog.pg_namespace"
+ "\nWHERE nspname OPERATOR(pg_catalog.~) ANY(ARRAY[\n");
+ for (cell = patterns->head, comma = ""; cell; cell = cell->next, comma = ",\n")
+ {
+ PQExpBufferData regexbuf;
+
+ initPQExpBuffer(®exbuf);
+ patternToSQLRegex(encoding, NULL, NULL, ®exbuf, cell->val, false);
+ appendPQExpBufferStr(sql, comma);
+ appendStringLiteralConn(sql, regexbuf.data, conn);
+ appendPQExpBufferStr(sql, "::TEXT COLLATE pg_catalog.default");
+ termPQExpBuffer(®exbuf);
+ }
+ appendPQExpBufferStr(sql, "\n]::TEXT[])");
+}
+
+/*
+ * appendSchemaCTE
+ *
+ * Appends a Common Table Expression (CTE) which selects all schemas to be
+ * checked, with the CTE and oid field named as requested. The CTE will select
+ * all schemas matching the include list except any schemas matching the
+ * exclude list.
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql statement is appended
+ * ctename: name of the schema CTE to be created
+ * include: list of schema name patterns for inclusion
+ * exclude: list of schema name patterns for exclusion
+ * inclusive: when 'include' is an empty list, whether to use all schemas in
+ * the database in lieu of the include list.
+ */
+static void
+appendSchemaCTE(PGconn *conn, PQExpBuffer sql, const char *ctename, const
+ SimpleStringList *include, const SimpleStringList *exclude,
+ bool inclusive)
+{
+ appendPQExpBuffer(sql, "\n%s (nspoid) AS (", ctename);
+ appendSchemaSelect(conn, sql, include, inclusive);
+ appendPQExpBufferStr(sql, "\nEXCEPT");
+ appendSchemaSelect(conn, sql, exclude, false);
+ appendPQExpBufferStr(sql, "\n)");
+}
+
+/*
+ * appendCTFilterQuals
+ *
+ * Appends quals to a buffer that restrict the rows selected from pg_class to
+ * only those which match the given checktype. No initial "WHERE" or "AND" is
+ * appended, nor do we surround our appended clauses in parens. The caller is
+ * assumed to take care of such matters.
+ *
+ * sql: buffer into which the constructed sql quals are appended
+ * relname: name (or alias) of pg_class in the surrounding query
+ * checktype: struct containing filter info
+ */
+static void
+appendCTFilterQuals(PQExpBuffer sql, const char *relname, CheckType checktype)
+{
+ appendPQExpBuffer(sql,
+ "%s.relam OPERATOR(pg_catalog.=) %u"
+ "\nAND %s.relkind OPERATOR(pg_catalog.=) ANY(ARRAY[%s])",
+ relname, ctfilter[checktype].relam,
+ relname, ctfilter[checktype].relkinds);
+}
+
+/*
+ * appendRelationSelect
+ *
+ * Appends a statement which selects the oid of all relations matching the
+ * given parameters. Expects a mixture of qualified and unqualified relation
+ * name patterns.
+ *
+ * For unqualified relation patterns, selects relations that match the relation
+ * name portion of the pattern which are in namespaces that are in the given
+ * namespace CTE.
+ *
+ * For qualified relation patterns, ignores the given namespace CTE and selects
+ * relations that match the relation name portion of the pattern which are in
+ * namespaces that match the schema portion of the pattern.
+ *
+ * For fully qualified relation patterns (database.schema.name), the pattern
+ * will be ignored unless the database portion of the pattern matches the name
+ * of the current database, as retrieved from conn.
+ *
+ * Only relations of the specified checktype will be selected.
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql statement is appended
+ * schemacte: name of the CTE which selects all schemas to be checked
+ * patterns: list of (possibly qualified) relation name patterns to match
+ * checktype: the type of relation to select
+ * inclusive: when patterns is an empty list, whether the select statement
+ * should match all relations of the given type
+ */
+static void
+appendRelationSelect(PGconn *conn, PQExpBuffer sql, const char *schemacte,
+ const SimpleStringList *patterns, CheckType checktype,
+ bool inclusive)
+{
+ SimpleStringListCell *cell;
+ const char *comma = "";
+ const char *qor = "";
+ PQExpBufferData qualified;
+ PQExpBufferData unqualified;
+ PQExpBufferData dbnamebuf;
+ PQExpBufferData schemabuf;
+ PQExpBufferData namebuf;
+ int encoding = PQclientEncoding(conn);
+
+ if (patterns->head == NULL)
+ {
+ if (!inclusive)
+ appendPQExpBufferStr(sql,
+ "\nSELECT 0::pg_catalog.oid WHERE false");
+ else
+ {
+ appendPQExpBuffer(sql,
+ "\nSELECT oid"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN %s n"
+ "\nON n.nspoid OPERATOR(pg_catalog.=) c.relnamespace"
+ "\nWHERE ",
+ schemacte);
+ appendCTFilterQuals(sql, "c", checktype);
+ }
+ return;
+ }
+
+ /*
+ * We have to distinguish between schema-qualified and unqualified
+ * relation patterns. The unqualified patterns need to be restricted by
+ * the list of schemas returned by the schema CTE, but not so for the
+ * qualified patterns.
+ *
+ * We treat fully-qualified relation patterns (database.schema.relation)
+ * like schema-qualified patterns except that we also require the database
+ * portion to match the current database name.
+ */
+ initPQExpBuffer(&qualified);
+ initPQExpBuffer(&unqualified);
+ initPQExpBuffer(&dbnamebuf);
+ initPQExpBuffer(&schemabuf);
+ initPQExpBuffer(&namebuf);
+
+ for (cell = patterns->head; cell; cell = cell->next)
+ {
+ patternToSQLRegex(encoding, &dbnamebuf, &schemabuf, &namebuf,
+ cell->val, false);
+
+ if (schemabuf.data[0])
+ {
+ /* Qualified relation pattern */
+ appendPQExpBuffer(&qualified, "%s\n(", qor);
+
+ if (dbnamebuf.data[0])
+ {
+ /*
+ * Fully-qualified relation pattern. Require the database
+ * name of our connection to match the database portion of the
+ * relation pattern.
+ */
+ appendPQExpBufferStr(&qualified, "\n");
+ appendStringLiteralConn(&qualified, PQdb(conn), conn);
+ appendPQExpBufferStr(&qualified,
+ "::TEXT OPERATOR(pg_catalog.~) ");
+ appendStringLiteralConn(&qualified, dbnamebuf.data, conn);
+ appendPQExpBufferStr(&qualified,
+ "::TEXT COLLATE pg_catalog.default AND");
+ }
+
+ /*
+ * Require the namespace name to match the schema portion of the
+ * relation pattern and the relation name to match the relname
+ * portion of the relation pattern.
+ */
+ appendPQExpBufferStr(&qualified,
+ "\nn.nspname OPERATOR(pg_catalog.~) ");
+ appendStringLiteralConn(&qualified, schemabuf.data, conn);
+ appendPQExpBufferStr(&qualified,
+ "::TEXT COLLATE pg_catalog.default AND"
+ "\nc.relname OPERATOR(pg_catalog.~) ");
+ appendStringLiteralConn(&qualified, namebuf.data, conn);
+ appendPQExpBufferStr(&qualified,
+ "::TEXT COLLATE pg_catalog.default)");
+ qor = "\nOR";
+ }
+ else
+ {
+ /* Unqualified relation pattern */
+ appendPQExpBufferStr(&unqualified, comma);
+ appendStringLiteralConn(&unqualified, namebuf.data, conn);
+ appendPQExpBufferStr(&unqualified,
+ "::TEXT COLLATE pg_catalog.default");
+ comma = "\n, ";
+ }
+
+ resetPQExpBuffer(&dbnamebuf);
+ resetPQExpBuffer(&schemabuf);
+ resetPQExpBuffer(&namebuf);
+ }
+
+ if (qualified.data[0])
+ {
+ appendPQExpBufferStr(sql,
+ "\nSELECT c.oid"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN pg_catalog.pg_namespace n"
+ "\nON c.relnamespace OPERATOR(pg_catalog.=) n.oid"
+ "\nWHERE (");
+ appendPQExpBufferStr(sql, qualified.data);
+ appendPQExpBufferStr(sql, ")\nAND ");
+ appendCTFilterQuals(sql, "c", checktype);
+ if (unqualified.data[0])
+ appendPQExpBufferStr(sql, "\nUNION ALL");
+ }
+ if (unqualified.data[0])
+ {
+ appendPQExpBuffer(sql,
+ "\nSELECT c.oid"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN %s ls"
+ "\nON c.relnamespace OPERATOR(pg_catalog.=) ls.nspoid"
+ "\nWHERE c.relname OPERATOR(pg_catalog.~) ANY(ARRAY[",
+ schemacte);
+ appendPQExpBufferStr(sql, unqualified.data);
+ appendPQExpBufferStr(sql, "\n]::TEXT[])\nAND ");
+ appendCTFilterQuals(sql, "c", checktype);
+ }
+}
+
+/*
+ * appendTableCTE
+ *
+ * Appends to the buffer 'sql' a Common Table Expression (CTE) which selects
+ * all table relations matching the given filters.
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql statement is appended
+ * schemacte: name of the CTE which selects all schemas to be checked
+ * ctename: name of the table CTE to be created
+ * include: list of table name patterns for inclusion
+ * exclude: list of table name patterns for exclusion
+ * inclusive: when 'include' is an empty list, whether the select statement
+ * should match all relations
+ * toast: whether to also select the associated toast tables
+ */
+static void
+appendTableCTE(PGconn *conn, PQExpBuffer sql, const char *schemacte,
+ const char *ctename, const SimpleStringList *include,
+ const SimpleStringList *exclude, bool inclusive, bool toast)
+{
+ appendPQExpBuffer(sql, "\n%s (oid) AS (", ctename);
+
+ if (toast)
+ {
+ /*
+ * Compute the primary tables, then union on all associated toast
+ * tables. We depend on left to right evaluation of the UNION before
+ * the EXCEPT which gets added below. UNION and EXCEPT have equal
+ * precedence, so be careful if you rearrange this query.
+ */
+ appendPQExpBuffer(sql, "\nWITH primary_table AS (");
+ appendRelationSelect(conn, sql, schemacte, include, CT_TABLE, inclusive);
+ appendPQExpBufferStr(sql,
+ "\n)"
+ "\nSELECT oid"
+ "\nFROM primary_table"
+ "\nUNION"
+ "\nSELECT c.reltoastrelid AS oid"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN primary_table pt"
+ "\nON pt.oid OPERATOR(pg_catalog.=) c.oid"
+ "\nWHERE c.reltoastrelid OPERATOR(pg_catalog.!=) 0");
+ }
+ else
+ appendRelationSelect(conn, sql, schemacte, include, CT_TABLE, inclusive);
+
+ appendPQExpBufferStr(sql, "\nEXCEPT");
+ appendRelationSelect(conn, sql, schemacte, exclude, CT_TABLE, false);
+ appendPQExpBufferStr(sql, "\n)");
+}
+
+/*
+ * appendIndexCTE
+ *
+ * Appends a Common Table Expression (CTE) which selects all indexes to be
+ * checked
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql CTE is appended
+ * tablescte: optional; if automatically including indexes for checked tables,
+ * the name of the CTE which contains all tables to be checked
+ * patterns: list of index name patterns to match
+ * inclusive: when 'include' is an empty list, whether the select statement
+ * should match all relations
+ */
+static void
+appendIndexCTE(PGconn *conn, PQExpBuffer sql, const char *tablescte,
+ const SimpleStringList *patterns, bool inclusive)
+{
+ appendPQExpBufferStr(sql, "\nindexes (oid) AS (");
+ appendPQExpBufferStr(sql, "\nSELECT oid FROM (");
+ appendRelationSelect(conn, sql, "namespaces", patterns, CT_BTREE, inclusive);
+ if (tablescte)
+ {
+ appendPQExpBuffer(sql,
+ "\nUNION"
+ "\nSELECT i.indexrelid AS oid"
+ "\nFROM pg_catalog.pg_index i"
+ "\nJOIN %s t ON t.oid OPERATOR(pg_catalog.=) i.indrelid",
+ tablescte);
+ }
+ appendPQExpBufferStr(sql,
+ "\n) AS included_indexes"
+ "\nEXCEPT"
+ "\nSELECT oid FROM excluded_indexes");
+ appendPQExpBufferStr(sql, "\n)");
+}
+
+/*
+ * appendTargetSelect
+ *
+ * Construct a query that will return a list of all tables and indexes in
+ * the database matching the user specified options, sorted by size. We
+ * want the largest tables and indexes first, so that the parallel
+ * processing of the larger database objects gets started sooner.
+ *
+ * conn: connection to the current database
+ * sql: buffer into which the constructed sql select statement is appended
+ * objects: lists of include and exclude patterns for filtering objects
+ * checkopts: user supplied program options
+ * progname: name of this program, such as "pg_amcheck"
+ * inclusive: when list of objects to include is empty, whether the select
+ * statement should match all objects not otherwise excluded
+ */
+static void
+appendTargetSelect(PGconn *conn, PQExpBuffer sql,
+ const amcheckObjects *objects,
+ const amcheckOptions *checkopts, const char *progname,
+ bool inclusive)
+{
+ appendPQExpBufferStr(sql, "WITH");
+ appendSchemaCTE(conn, sql, "namespaces", &objects->schemas,
+ &objects->exclude_schemas, inclusive);
+ appendPQExpBufferStr(sql, ",");
+ appendTableCTE(conn, sql, "namespaces", "tables", &objects->tables,
+ &objects->exclude_tables, inclusive,
+ !checkopts->exclude_toast);
+ if (!checkopts->no_indexes)
+ {
+ appendPQExpBufferStr(sql, ",\nexcluded_indexes (oid) AS (");
+ appendRelationSelect(conn, sql, "namespaces",
+ &objects->exclude_indexes, CT_BTREE, false);
+ appendPQExpBufferStr(sql, "\n),");
+ if (checkopts->dependents)
+ appendIndexCTE(conn, sql, "tables", &objects->indexes, inclusive);
+ else
+ appendIndexCTE(conn, sql, NULL, &objects->indexes, inclusive);
+ }
+ appendPQExpBuffer(sql,
+ "\nSELECT checktype, oid FROM ("
+ "\nSELECT %u AS checktype, tables.oid, c.relpages"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN tables"
+ "\nON tables.oid OPERATOR(pg_catalog.=) c.oid"
+ "\nWHERE ",
+ CT_TABLE);
+ appendCTFilterQuals(sql, "c", CT_TABLE);
+ if (!checkopts->no_indexes)
+ {
+ appendPQExpBuffer(sql,
+ "\nUNION ALL"
+ "\nSELECT %u AS checktype, indexes.oid, c.relpages"
+ "\nFROM pg_catalog.pg_class c"
+ "\nJOIN indexes"
+ "\nON indexes.oid OPERATOR(pg_catalog.=) c.oid"
+ "\nWHERE ",
+ CT_BTREE);
+ appendCTFilterQuals(sql, "c", CT_BTREE);
+ }
+ appendPQExpBufferStr(sql,
+ "\n) AS ss"
+ "\nORDER BY relpages DESC, checktype, oid");
+}
diff --git a/contrib/pg_amcheck/pg_amcheck.h b/contrib/pg_amcheck/pg_amcheck.h
new file mode 100644
index 0000000000..7e9595a3a3
--- /dev/null
+++ b/contrib/pg_amcheck/pg_amcheck.h
@@ -0,0 +1,91 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_amcheck.h
+ * Detects corruption within database relations.
+ *
+ * Copyright (c) 2020-2021, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ * contrib/pg_amcheck/pg_amcheck.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef PG_AMCHECK_H
+#define PG_AMCHECK_H
+
+#include "fe_utils/simple_list.h"
+#include "fe_utils/string_utils.h"
+#include "libpq-fe.h"
+#include "pqexpbuffer.h" /* pgrminclude ignore */
+
+/* amcheck options controlled by user flags */
+typedef struct amcheckOptions
+{
+ bool alldb;
+ bool echo;
+ bool quiet;
+ bool verbose;
+ bool dependents;
+ bool no_indexes;
+ bool exclude_toast;
+ bool reconcile_toast;
+ bool on_error_stop;
+ bool parent_check;
+ bool rootdescend;
+ bool heapallindexed;
+ const char *skip;
+ int jobs; /* >= 0 indicates user specified the parallel
+ * degree, otherwise -1 */
+ long startblock;
+ long endblock;
+} amcheckOptions;
+
+/* names of database objects to include or exclude controlled by user flags */
+typedef struct amcheckObjects
+{
+ SimpleStringList databases;
+ SimpleStringList schemas;
+ SimpleStringList tables;
+ SimpleStringList indexes;
+ SimpleStringList exclude_databases;
+ SimpleStringList exclude_schemas;
+ SimpleStringList exclude_tables;
+ SimpleStringList exclude_indexes;
+} amcheckObjects;
+
+/*
+ * We cannot launch the same amcheck function for all checked objects. For
+ * btree indexes, we must use either bt_index_check() or
+ * bt_index_parent_check(). For heap relations, we must use verify_heapam().
+ * We silently ignore all other object types.
+ *
+ * The following CheckType enum and corresponding ctfilter array track which
+ * which kinds of relations get which treatment.
+ */
+typedef enum
+{
+ CT_TABLE = 0,
+ CT_BTREE
+} CheckType;
+
+/*
+ * This struct is used for filtering relations in pg_catalog.pg_class to just
+ * those of a given CheckType. The relam field should equal pg_class.relam,
+ * and the pg_class.relkind should be contained in the relkinds comma separated
+ * list.
+ *
+ * The 'typname' field is not strictly for filtering, but for printing messages
+ * about relations that matched the filter.
+ */
+typedef struct
+{
+ Oid relam;
+ const char *relkinds;
+ const char *typname;
+} CheckTypeFilter;
+
+/* Constants taken from pg_catalog/pg_am.dat */
+#define HEAP_TABLE_AM_OID 2
+#define BTREE_AM_OID 403
+
+#endif /* PG_AMCHECK_H */
diff --git a/contrib/pg_amcheck/t/001_basic.pl b/contrib/pg_amcheck/t/001_basic.pl
new file mode 100644
index 0000000000..dfa0ae9e06
--- /dev/null
+++ b/contrib/pg_amcheck/t/001_basic.pl
@@ -0,0 +1,9 @@
+use strict;
+use warnings;
+
+use TestLib;
+use Test::More tests => 8;
+
+program_help_ok('pg_amcheck');
+program_version_ok('pg_amcheck');
+program_options_handling_ok('pg_amcheck');
diff --git a/contrib/pg_amcheck/t/002_nonesuch.pl b/contrib/pg_amcheck/t/002_nonesuch.pl
new file mode 100644
index 0000000000..b52039c79b
--- /dev/null
+++ b/contrib/pg_amcheck/t/002_nonesuch.pl
@@ -0,0 +1,78 @@
+use strict;
+use warnings;
+
+use PostgresNode;
+use TestLib;
+use Test::More tests => 16;
+
+# Test set-up
+my ($node, $port);
+$node = get_new_node('test');
+$node->init;
+$node->start;
+$port = $node->port;
+
+# Load the amcheck extension, upon which pg_amcheck depends
+$node->safe_psql('postgres', q(CREATE EXTENSION amcheck));
+
+#########################################
+# Test connecting to a non-existent database
+
+command_fails_like(
+ [ 'pg_amcheck', '-p', $port, 'qqq' ],
+ qr/database "qqq" does not exist/,
+ 'checking a non-existent database');
+
+#########################################
+# Test connecting with a non-existent user
+
+command_fails_like(
+ [ 'pg_amcheck', '-p', $port, '-U=no_such_user', 'postgres' ],
+ qr/role "=no_such_user" does not exist/,
+ 'checking with a non-existent user');
+
+#########################################
+# Test checking a database without amcheck installed, by name. We should see a
+# message about missing amcheck
+
+$node->command_like(
+ [ 'pg_amcheck', '-p', $port, 'template1' ],
+ qr/pg_amcheck: skipping database "template1": amcheck is not installed/,
+ 'checking a database by name without amcheck installed');
+
+#########################################
+# Test checking a database without amcheck installed, by only indirectly using
+# a dbname pattern. In verbose mode, we should see a message about missing
+# amcheck
+
+$node->command_like(
+ [ 'pg_amcheck', '-p', $port, '-v', '-d', '*', 'postgres' ],
+ qr/pg_amcheck: skipping database "template1": amcheck is not installed/,
+ 'checking a database by dbname implication without amcheck installed');
+
+#########################################
+# Test checking non-existent schemas, tables, and indexes
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-s', 'no_such_schema' ],
+ 'checking a non-existent schema');
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-t', 'no_such_table' ],
+ 'checking a non-existent table');
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-i', 'no_such_index' ],
+ 'checking a non-existent schema');
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-s', 'no*such*schema*' ],
+ 'no matching schemas');
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-t', 'no*such*table*' ],
+ 'no matching tables');
+
+$node->command_ok(
+ [ 'pg_amcheck', '-p', $port, '-i', 'no*such*index' ],
+ 'no matching indexes');
diff --git a/contrib/pg_amcheck/t/003_check.pl b/contrib/pg_amcheck/t/003_check.pl
new file mode 100644
index 0000000000..957094fcdd
--- /dev/null
+++ b/contrib/pg_amcheck/t/003_check.pl
@@ -0,0 +1,475 @@
+use strict;
+use warnings;
+
+use PostgresNode;
+use TestLib;
+use Test::More tests => 70;
+
+my ($node, $port);
+
+# Returns the filesystem path for the named relation.
+#
+# Assumes the test node is running
+sub relation_filepath($$)
+{
+ my ($dbname, $relname) = @_;
+
+ my $pgdata = $node->data_dir;
+ my $rel = $node->safe_psql($dbname,
+ qq(SELECT pg_relation_filepath('$relname')));
+ die "path not found for relation $relname" unless defined $rel;
+ return "$pgdata/$rel";
+}
+
+# Returns the name of the toast relation associated with the named relation.
+#
+# Assumes the test node is running
+sub relation_toast($$)
+{
+ my ($dbname, $relname) = @_;
+
+ my $rel = $node->safe_psql($dbname, qq(
+ SELECT ct.relname
+ FROM pg_catalog.pg_class cr, pg_catalog.pg_class ct
+ WHERE cr.oid = '$relname'::regclass
+ AND cr.reltoastrelid = ct.oid
+ ));
+ return undef unless defined $rel;
+ return "pg_toast.$rel";
+}
+
+# Stops the test node, corrupts the first page of the named relation, and
+# restarts the node.
+#
+# Assumes the test node is running.
+sub corrupt_first_page($$)
+{
+ my ($dbname, $relname) = @_;
+ my $relpath = relation_filepath($dbname, $relname);
+
+ $node->stop;
+ my $fh;
+ open($fh, '+<', $relpath);
+ binmode $fh;
+ seek($fh, 32, 0);
+ syswrite($fh, '\x77\x77\x77\x77', 500);
+ close($fh);
+ $node->start;
+}
+
+# Stops the test node, unlinks the file from the filesystem that backs the
+# relation, and restarts the node.
+#
+# Assumes the test node is running
+sub remove_relation_file($$)
+{
+ my ($dbname, $relname) = @_;
+ my $relpath = relation_filepath($dbname, $relname);
+
+ $node->stop();
+ unlink($relpath);
+ $node->start;
+}
+
+# Stops the test node, unlinks the file from the filesystem that backs the
+# toast table (if any) corresponding to the given main table relation, and
+# restarts the node.
+#
+# Assumes the test node is running
+sub remove_toast_file($$)
+{
+ my ($dbname, $relname) = @_;
+ my $toastname = relation_toast($dbname, $relname);
+ remove_relation_file($dbname, $toastname) if ($toastname);
+}
+
+# Test set-up
+$node = get_new_node('test');
+$node->init;
+$node->start;
+$port = $node->port;
+
+for my $dbname (qw(db1 db2 db3))
+{
+ # Create the database
+ $node->safe_psql('postgres', qq(CREATE DATABASE $dbname));
+
+ # Load the amcheck extension, upon which pg_amcheck depends. Put the
+ # extension in an unexpected location to test that pg_amcheck finds it
+ # correctly. Create tables with names that look like pg_catalog names to
+ # check that pg_amcheck does not get confused by them. Create functions in
+ # schema public that look like amcheck functions to check that pg_amcheck
+ # does not use them.
+ $node->safe_psql($dbname, q(
+ CREATE SCHEMA amcheck_schema;
+ CREATE EXTENSION amcheck WITH SCHEMA amcheck_schema;
+ CREATE TABLE amcheck_schema.pg_database (junk text);
+ CREATE TABLE amcheck_schema.pg_namespace (junk text);
+ CREATE TABLE amcheck_schema.pg_class (junk text);
+ CREATE TABLE amcheck_schema.pg_operator (junk text);
+ CREATE TABLE amcheck_schema.pg_proc (junk text);
+ CREATE TABLE amcheck_schema.pg_tablespace (junk text);
+
+ CREATE FUNCTION public.bt_index_check(index regclass,
+ heapallindexed boolean default false)
+ RETURNS VOID AS $$
+ BEGIN
+ RAISE EXCEPTION 'Invoked wrong bt_index_check!';
+ END;
+ $$ LANGUAGE plpgsql;
+
+ CREATE FUNCTION public.bt_index_parent_check(index regclass,
+ heapallindexed boolean default false,
+ rootdescend boolean default false)
+ RETURNS VOID AS $$
+ BEGIN
+ RAISE EXCEPTION 'Invoked wrong bt_index_parent_check!';
+ END;
+ $$ LANGUAGE plpgsql;
+
+ CREATE FUNCTION public.verify_heapam(relation regclass,
+ on_error_stop boolean default false,
+ check_toast boolean default false,
+ skip text default 'none',
+ startblock bigint default null,
+ endblock bigint default null,
+ blkno OUT bigint,
+ offnum OUT integer,
+ attnum OUT integer,
+ msg OUT text)
+ RETURNS SETOF record AS $$
+ BEGIN
+ RAISE EXCEPTION 'Invoked wrong verify_heapam!';
+ END;
+ $$ LANGUAGE plpgsql;
+ ));
+
+ # Create schemas, tables and indexes in five separate
+ # schemas. The schemas are all identical to start, but
+ # we will corrupt them differently later.
+ #
+ for my $schema (qw(s1 s2 s3 s4 s5))
+ {
+ $node->safe_psql($dbname, qq(
+ CREATE SCHEMA $schema;
+ CREATE SEQUENCE $schema.seq1;
+ CREATE SEQUENCE $schema.seq2;
+ CREATE TABLE $schema.t1 (
+ i INTEGER,
+ b BOX,
+ ia int4[],
+ ir int4range,
+ t TEXT
+ );
+ CREATE TABLE $schema.t2 (
+ i INTEGER,
+ b BOX,
+ ia int4[],
+ ir int4range,
+ t TEXT
+ );
+ CREATE VIEW $schema.t2_view AS (
+ SELECT i*2, t FROM $schema.t2
+ );
+ ALTER TABLE $schema.t2
+ ALTER COLUMN t
+ SET STORAGE EXTERNAL;
+
+ INSERT INTO $schema.t1 (i, b, ia, ir, t)
+ (SELECT gs::INTEGER AS i,
+ box(point(gs,gs+5),point(gs*2,gs*3)) AS b,
+ array[gs, gs + 1]::int4[] AS ia,
+ int4range(gs, gs+100) AS ir,
+ repeat('foo', gs) AS t
+ FROM generate_series(1,10000,3000) AS gs);
+
+ INSERT INTO $schema.t2 (i, b, ia, ir, t)
+ (SELECT gs::INTEGER AS i,
+ box(point(gs,gs+5),point(gs*2,gs*3)) AS b,
+ array[gs, gs + 1]::int4[] AS ia,
+ int4range(gs, gs+100) AS ir,
+ repeat('foo', gs) AS t
+ FROM generate_series(1,10000,3000) AS gs);
+
+ CREATE MATERIALIZED VIEW $schema.t1_mv AS SELECT * FROM $schema.t1;
+ CREATE MATERIALIZED VIEW $schema.t2_mv AS SELECT * FROM $schema.t2;
+
+ create table $schema.p1 (a int, b int) PARTITION BY list (a);
+ create table $schema.p2 (a int, b int) PARTITION BY list (a);
+
+ create table $schema.p1_1 partition of $schema.p1 for values in (1, 2, 3);
+ create table $schema.p1_2 partition of $schema.p1 for values in (4, 5, 6);
+ create table $schema.p2_1 partition of $schema.p2 for values in (1, 2, 3);
+ create table $schema.p2_2 partition of $schema.p2 for values in (4, 5, 6);
+
+ CREATE INDEX t1_btree ON $schema.t1 USING BTREE (i);
+ CREATE INDEX t2_btree ON $schema.t2 USING BTREE (i);
+
+ CREATE INDEX t1_hash ON $schema.t1 USING HASH (i);
+ CREATE INDEX t2_hash ON $schema.t2 USING HASH (i);
+
+ CREATE INDEX t1_brin ON $schema.t1 USING BRIN (i);
+ CREATE INDEX t2_brin ON $schema.t2 USING BRIN (i);
+
+ CREATE INDEX t1_gist ON $schema.t1 USING GIST (b);
+ CREATE INDEX t2_gist ON $schema.t2 USING GIST (b);
+
+ CREATE INDEX t1_gin ON $schema.t1 USING GIN (ia);
+ CREATE INDEX t2_gin ON $schema.t2 USING GIN (ia);
+
+ CREATE INDEX t1_spgist ON $schema.t1 USING SPGIST (ir);
+ CREATE INDEX t2_spgist ON $schema.t2 USING SPGIST (ir);
+ ));
+ }
+}
+
+# Database 'db1' corruptions
+#
+
+# Corrupt indexes in schema "s1"
+remove_relation_file('db1', 's1.t1_btree');
+corrupt_first_page('db1', 's1.t2_btree');
+
+# Corrupt tables in schema "s2"
+remove_relation_file('db1', 's2.t1');
+corrupt_first_page('db1', 's2.t2');
+
+# Corrupt tables, partitions, matviews, and btrees in schema "s3"
+remove_relation_file('db1', 's3.t1');
+corrupt_first_page('db1', 's3.t2');
+
+remove_relation_file('db1', 's3.t1_mv');
+remove_relation_file('db1', 's3.p1_1');
+
+corrupt_first_page('db1', 's3.t2_mv');
+corrupt_first_page('db1', 's3.p2_1');
+
+remove_relation_file('db1', 's3.t1_btree');
+corrupt_first_page('db1', 's3.t2_btree');
+
+# Corrupt toast table, partitions, and materialized views in schema "s4"
+remove_toast_file('db1', 's4.t2');
+
+# Corrupt all other object types in schema "s5". We don't have amcheck support
+# for these types, but we check that their corruption does not trigger any
+# errors in pg_amcheck
+remove_relation_file('db1', 's5.seq1');
+remove_relation_file('db1', 's5.t1_hash');
+remove_relation_file('db1', 's5.t1_gist');
+remove_relation_file('db1', 's5.t1_gin');
+remove_relation_file('db1', 's5.t1_brin');
+remove_relation_file('db1', 's5.t1_spgist');
+
+corrupt_first_page('db1', 's5.seq2');
+corrupt_first_page('db1', 's5.t2_hash');
+corrupt_first_page('db1', 's5.t2_gist');
+corrupt_first_page('db1', 's5.t2_gin');
+corrupt_first_page('db1', 's5.t2_brin');
+corrupt_first_page('db1', 's5.t2_spgist');
+
+
+# Database 'db2' corruptions
+#
+remove_relation_file('db2', 's1.t1');
+remove_relation_file('db2', 's1.t1_btree');
+
+
+# Leave 'db3' uncorrupted
+#
+
+
+# Standard first arguments to TestLib functions
+my @cmd = ('pg_amcheck', '--quiet', '-p', $port);
+
+# The pg_amcheck command itself should return a success exit status, even
+# though tables and indexes are corrupt. An error code returned would mean the
+# pg_amcheck command itself failed, for example because a connection to the
+# database could not be established.
+#
+# For these checks, we're ignoring any corruption reported and focusing
+# exclusively on the exit code from pg_amcheck.
+#
+$node->command_ok(
+ [ @cmd,, 'db1' ],
+ 'pg_amcheck all schemas, tables and indexes in database db1');
+
+$node->command_ok(
+ [ @cmd,, 'db1', 'db2', 'db3' ],
+ 'pg_amcheck all schemas, tables and indexes in databases db1, db2 and db3');
+
+$node->command_ok(
+ [ @cmd, '--all' ],
+ 'pg_amcheck all schemas, tables and indexes in all databases');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-s', 's1' ],
+ 'pg_amcheck all objects in schema s1');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-r', 's*.t1' ],
+ 'pg_amcheck all tables named t1 and their indexes');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-i', 'i*.idx', '-i', 'idx.i*' ],
+ 'pg_amcheck all indexes with qualified names matching /i*.idx/ or /idx.i*/');
+
+$node->command_ok(
+ [ @cmd, '--no-dependents', 'db1', '-r', 's*.t1' ],
+ 'pg_amcheck all tables with qualified names matching /s*.t1/');
+
+$node->command_ok(
+ [ @cmd, '--no-dependents', 'db1', '-t', 's*.t1', '-t', 'foo*.bar*' ],
+ 'pg_amcheck all tables with qualified names matching /s*.t1/ or /foo*.bar*/');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-T', 't1' ],
+ 'pg_amcheck everything except tables named t1');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-S', 's1', '-R', 't1' ],
+ 'pg_amcheck everything not named t1 nor in schema s1');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-t', '*.*.*' ],
+ 'pg_amcheck all tables across all databases and schemas');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-t', '*.*.t1' ],
+ 'pg_amcheck all tables named t1 across all databases and schemas');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-t', '*.s1.*' ],
+ 'pg_amcheck all tables across all databases in schemas named s1');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-t', 'db2.*.*' ],
+ 'pg_amcheck all tables across all schemas in database db2');
+
+$node->command_ok(
+ [ @cmd, 'db1', '-t', 'db2.*.*', '-t', 'db3.*.*' ],
+ 'pg_amcheck all tables across all schemas in databases db2 and db3');
+
+# Scans of indexes in s1 should detect the specific corruption that we created
+# above. For missing relation forks, we know what the error message looks
+# like. For corrupted index pages, the error might vary depending on how the
+# page was formatted on disk, including variations due to alignment differences
+# between platforms, so we accept any non-empty error message.
+#
+$node->command_like(
+ [ @cmd, '--all', '-s', 's1', '-i', 't1_btree' ],
+ qr/index "t1_btree" lacks a main relation fork/,
+ 'pg_amcheck index s1.t1_btree reports missing main relation fork');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '-i', 't2_btree' ],
+ qr/.+/, # Any non-empty error message is acceptable
+ 'pg_amcheck index s1.s2 reports index corruption');
+
+# Checking db1.s1 should show no corruptions if indexes are excluded
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '--exclude-indexes' ],
+ qr/^$/,
+ 'pg_amcheck of db1.s1 excluding indexes');
+
+# But checking across all databases in schema s1 should show corruptions
+# messages for tables in db2
+$node->command_like(
+ [ @cmd, '--all', '-s', 's1', '--exclude-indexes' ],
+ qr/could not open file/,
+ 'pg_amcheck of schema s1 across all databases but excluding indexes');
+
+# Checking across a list of databases should also work
+$node->command_like(
+ [ @cmd, '-d', 'db2', '-d', 'db1', '-s', 's1', '--exclude-indexes' ],
+ qr/could not open file/,
+ 'pg_amcheck of schema s1 across db1 and db2 but excluding indexes');
+
+# In schema s3, the tables and indexes are both corrupt. We should see
+# corruption messages on stdout, nothing on stderr, and an exit
+# status of zero.
+#
+$node->command_checks_all(
+ [ @cmd, 'db1', '-s', 's3' ],
+ 0,
+ [ qr/index "t1_btree" lacks a main relation fork/,
+ qr/could not open file/ ],
+ [ qr/^$/ ],
+ 'pg_amcheck schema s3 reports table and index errors');
+
+# In schema s2, only tables are corrupt. Check that table corruption is
+# reported as expected.
+#
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's2', '-t', 't1' ],
+ qr/could not open file/,
+ 'pg_amcheck in schema s2 reports table corruption');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's2', '-t', 't2' ],
+ qr/.+/, # Any non-empty error message is acceptable
+ 'pg_amcheck in schema s2 reports table corruption');
+
+# In schema s4, only toast tables are corrupt. Check that under default
+# options the toast corruption is reported, but when excluding toast we get no
+# error reports.
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's4' ],
+ qr/could not open file/,
+ 'pg_amcheck in schema s4 reports toast corruption');
+
+$node->command_like(
+ [ @cmd, '--exclude-toast', '--exclude-toast-pointers', 'db1', '-s', 's4' ],
+ qr/^$/, # Empty
+ 'pg_amcheck in schema s4 excluding toast reports no corruption');
+
+# Check that no corruption is reported in schema s5
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's5' ],
+ qr/^$/, # Empty
+ 'pg_amcheck over schema s5 reports no corruption');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '-I', 't1_btree', '-I', 't2_btree' ],
+ qr/^$/, # Empty
+ 'pg_amcheck over schema s1 with corrupt indexes excluded reports no corruption');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '--exclude-indexes' ],
+ qr/^$/, # Empty
+ 'pg_amcheck over schema s1 with all indexes excluded reports no corruption');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's2', '-T', 't1', '-T', 't2' ],
+ qr/^$/, # Empty
+ 'pg_amcheck over schema s2 with corrupt tables excluded reports no corruption');
+
+# Check errors about bad block range command line arguments. We use schema s5
+# to avoid getting messages about corrupt tables or indexes.
+command_fails_like(
+ [ @cmd, 'db1', '-s', 's5', '--startblock', 'junk' ],
+ qr/relation starting block argument contains garbage characters/,
+ 'pg_amcheck rejects garbage startblock');
+
+command_fails_like(
+ [ @cmd, 'db1', '-s', 's5', '--endblock', '1234junk' ],
+ qr/relation ending block argument contains garbage characters/,
+ 'pg_amcheck rejects garbage endblock');
+
+command_fails_like(
+ [ @cmd, 'db1', '-s', 's5', '--startblock', '5', '--endblock', '4' ],
+ qr/relation ending block argument precedes starting block argument/,
+ 'pg_amcheck rejects invalid block range');
+
+# Check bt_index_parent_check alternates. We don't create any index corruption
+# that would behave differently under these modes, so just smoke test that the
+# arguments are handled sensibly.
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '-i', 't1_btree', '--parent-check' ],
+ qr/index "t1_btree" lacks a main relation fork/,
+ 'pg_amcheck smoke test --parent-check');
+
+$node->command_like(
+ [ @cmd, 'db1', '-s', 's1', '-i', 't1_btree', '--heapallindexed', '--rootdescend' ],
+ qr/index "t1_btree" lacks a main relation fork/,
+ 'pg_amcheck smoke test --heapallindexed --rootdescend');
diff --git a/contrib/pg_amcheck/t/004_verify_heapam.pl b/contrib/pg_amcheck/t/004_verify_heapam.pl
new file mode 100644
index 0000000000..7e71d612fc
--- /dev/null
+++ b/contrib/pg_amcheck/t/004_verify_heapam.pl
@@ -0,0 +1,496 @@
+use strict;
+use warnings;
+
+use PostgresNode;
+use TestLib;
+
+use Test::More tests => 22;
+
+# This regression test demonstrates that the pg_amcheck binary supplied with
+# the pg_amcheck contrib module correctly identifies specific kinds of
+# corruption within pages. To test this, we need a mechanism to create corrupt
+# pages with predictable, repeatable corruption. The postgres backend cannot
+# be expected to help us with this, as its design is not consistent with the
+# goal of intentionally corrupting pages.
+#
+# Instead, we create a table to corrupt, and with careful consideration of how
+# postgresql lays out heap pages, we seek to offsets within the page and
+# overwrite deliberately chosen bytes with specific values calculated to
+# corrupt the page in expected ways. We then verify that pg_amcheck reports
+# the corruption, and that it runs without crashing. Note that the backend
+# cannot simply be started to run queries against the corrupt table, as the
+# backend will crash, at least for some of the corruption types we generate.
+#
+# Autovacuum potentially touching the table in the background makes the exact
+# behavior of this test harder to reason about. We turn it off to keep things
+# simpler. We use a "belt and suspenders" approach, turning it off for the
+# system generally in postgresql.conf, and turning it off specifically for the
+# test table.
+#
+# This test depends on the table being written to the heap file exactly as we
+# expect it to be, so we take care to arrange the columns of the table, and
+# insert rows of the table, that give predictable sizes and locations within
+# the table page.
+#
+# The HeapTupleHeaderData has 23 bytes of fixed size fields before the variable
+# length t_bits[] array. We have exactly 3 columns in the table, so natts = 3,
+# t_bits is 1 byte long, and t_hoff = MAXALIGN(23 + 1) = 24.
+#
+# We're not too fussy about which datatypes we use for the test, but we do care
+# about some specific properties. We'd like to test both fixed size and
+# varlena types. We'd like some varlena data inline and some toasted. And
+# we'd like the layout of the table such that the datums land at predictable
+# offsets within the tuple. We choose a structure without padding on all
+# supported architectures:
+#
+# a BIGINT
+# b TEXT
+# c TEXT
+#
+# We always insert a 7-ascii character string into field 'b', which with a
+# 1-byte varlena header gives an 8 byte inline value. We always insert a long
+# text string in field 'c', long enough to force toast storage.
+#
+# We choose to read and write binary copies of our table's tuples, using perl's
+# pack() and unpack() functions. Perl uses a packing code system in which:
+#
+# L = "Unsigned 32-bit Long",
+# S = "Unsigned 16-bit Short",
+# C = "Unsigned 8-bit Octet",
+# c = "signed 8-bit octet",
+# q = "signed 64-bit quadword"
+#
+# Each tuple in our table has a layout as follows:
+#
+# xx xx xx xx t_xmin: xxxx offset = 0 L
+# xx xx xx xx t_xmax: xxxx offset = 4 L
+# xx xx xx xx t_field3: xxxx offset = 8 L
+# xx xx bi_hi: xx offset = 12 S
+# xx xx bi_lo: xx offset = 14 S
+# xx xx ip_posid: xx offset = 16 S
+# xx xx t_infomask2: xx offset = 18 S
+# xx xx t_infomask: xx offset = 20 S
+# xx t_hoff: x offset = 22 C
+# xx t_bits: x offset = 23 C
+# xx xx xx xx xx xx xx xx 'a': xxxxxxxx offset = 24 q
+# xx xx xx xx xx xx xx xx 'b': xxxxxxxx offset = 32 Cccccccc
+# xx xx xx xx xx xx xx xx 'c': xxxxxxxx offset = 40 SSSS
+# xx xx xx xx xx xx xx xx : xxxxxxxx ...continued SSSS
+# xx xx : xx ...continued S
+#
+# We could choose to read and write columns 'b' and 'c' in other ways, but
+# it is convenient enough to do it this way. We define packing code
+# constants here, where they can be compared easily against the layout.
+
+use constant HEAPTUPLE_PACK_CODE => 'LLLSSSSSCCqCcccccccSSSSSSSSS';
+use constant HEAPTUPLE_PACK_LENGTH => 58; # Total size
+
+# Read a tuple of our table from a heap page.
+#
+# Takes an open filehandle to the heap file, and the offset of the tuple.
+#
+# Rather than returning the binary data from the file, unpacks the data into a
+# perl hash with named fields. These fields exactly match the ones understood
+# by write_tuple(), below. Returns a reference to this hash.
+#
+sub read_tuple ($$)
+{
+ my ($fh, $offset) = @_;
+ my ($buffer, %tup);
+ seek($fh, $offset, 0);
+ sysread($fh, $buffer, HEAPTUPLE_PACK_LENGTH);
+
+ @_ = unpack(HEAPTUPLE_PACK_CODE, $buffer);
+ %tup = (t_xmin => shift,
+ t_xmax => shift,
+ t_field3 => shift,
+ bi_hi => shift,
+ bi_lo => shift,
+ ip_posid => shift,
+ t_infomask2 => shift,
+ t_infomask => shift,
+ t_hoff => shift,
+ t_bits => shift,
+ a => shift,
+ b_header => shift,
+ b_body1 => shift,
+ b_body2 => shift,
+ b_body3 => shift,
+ b_body4 => shift,
+ b_body5 => shift,
+ b_body6 => shift,
+ b_body7 => shift,
+ c1 => shift,
+ c2 => shift,
+ c3 => shift,
+ c4 => shift,
+ c5 => shift,
+ c6 => shift,
+ c7 => shift,
+ c8 => shift,
+ c9 => shift);
+ # Stitch together the text for column 'b'
+ $tup{b} = join('', map { chr($tup{"b_body$_"}) } (1..7));
+ return \%tup;
+}
+
+# Write a tuple of our table to a heap page.
+#
+# Takes an open filehandle to the heap file, the offset of the tuple, and a
+# reference to a hash with the tuple values, as returned by read_tuple().
+# Writes the tuple fields from the hash into the heap file.
+#
+# The purpose of this function is to write a tuple back to disk with some
+# subset of fields modified. The function does no error checking. Use
+# cautiously.
+#
+sub write_tuple($$$)
+{
+ my ($fh, $offset, $tup) = @_;
+ my $buffer = pack(HEAPTUPLE_PACK_CODE,
+ $tup->{t_xmin},
+ $tup->{t_xmax},
+ $tup->{t_field3},
+ $tup->{bi_hi},
+ $tup->{bi_lo},
+ $tup->{ip_posid},
+ $tup->{t_infomask2},
+ $tup->{t_infomask},
+ $tup->{t_hoff},
+ $tup->{t_bits},
+ $tup->{a},
+ $tup->{b_header},
+ $tup->{b_body1},
+ $tup->{b_body2},
+ $tup->{b_body3},
+ $tup->{b_body4},
+ $tup->{b_body5},
+ $tup->{b_body6},
+ $tup->{b_body7},
+ $tup->{c1},
+ $tup->{c2},
+ $tup->{c3},
+ $tup->{c4},
+ $tup->{c5},
+ $tup->{c6},
+ $tup->{c7},
+ $tup->{c8},
+ $tup->{c9});
+ seek($fh, $offset, 0);
+ syswrite($fh, $buffer, HEAPTUPLE_PACK_LENGTH);
+ return;
+}
+
+# Set umask so test directories and files are created with default permissions
+umask(0077);
+
+# Set up the node. Once we create and corrupt the table,
+# autovacuum workers visiting the table could crash the backend.
+# Disable autovacuum so that won't happen.
+my $node = get_new_node('test');
+$node->init;
+$node->append_conf('postgresql.conf', 'autovacuum=off');
+
+# Start the node and load the extensions. We depend on both
+# amcheck and pageinspect for this test.
+$node->start;
+my $port = $node->port;
+my $pgdata = $node->data_dir;
+$node->safe_psql('postgres', "CREATE EXTENSION amcheck");
+$node->safe_psql('postgres', "CREATE EXTENSION pageinspect");
+
+# Get a non-zero datfrozenxid
+$node->safe_psql('postgres', qq(VACUUM FREEZE));
+
+# Create the test table with precisely the schema that our corruption function
+# expects.
+$node->safe_psql(
+ 'postgres', qq(
+ CREATE TABLE public.test (a BIGINT, b TEXT, c TEXT);
+ ALTER TABLE public.test SET (autovacuum_enabled=false);
+ ALTER TABLE public.test ALTER COLUMN c SET STORAGE EXTERNAL;
+ CREATE INDEX test_idx ON public.test(a, b);
+ ));
+
+# We want (0 < datfrozenxid < test.relfrozenxid). To achieve this, we freeze
+# an otherwise unused table, public.junk, prior to inserting data and freezing
+# public.test
+$node->safe_psql(
+ 'postgres', qq(
+ CREATE TABLE public.junk AS SELECT 'junk'::TEXT AS junk_column;
+ ALTER TABLE public.junk SET (autovacuum_enabled=false);
+ VACUUM FREEZE public.junk
+ ));
+
+my $rel = $node->safe_psql('postgres', qq(SELECT pg_relation_filepath('public.test')));
+my $relpath = "$pgdata/$rel";
+
+# Insert data and freeze public.test
+use constant ROWCOUNT => 16;
+$node->safe_psql('postgres', qq(
+ INSERT INTO public.test (a, b, c)
+ VALUES (
+ 12345678,
+ 'abcdefg',
+ repeat('w', 10000)
+ );
+ VACUUM FREEZE public.test
+ )) for (1..ROWCOUNT);
+
+my $relfrozenxid = $node->safe_psql('postgres',
+ q(select relfrozenxid from pg_class where relname = 'test'));
+my $datfrozenxid = $node->safe_psql('postgres',
+ q(select datfrozenxid from pg_database where datname = 'postgres'));
+
+# Find where each of the tuples is located on the page.
+my @lp_off;
+for my $tup (0..ROWCOUNT-1)
+{
+ push (@lp_off, $node->safe_psql('postgres', qq(
+select lp_off from heap_page_items(get_raw_page('test', 'main', 0))
+ offset $tup limit 1)));
+}
+
+# Check that pg_amcheck runs against the uncorrupted table without error.
+$node->command_ok(['pg_amcheck', '-p', $port, 'postgres'],
+ 'pg_amcheck test table, prior to corruption');
+
+# Check that pg_amcheck runs against the uncorrupted table and index without error.
+$node->command_ok(['pg_amcheck', '-p', $port, 'postgres'],
+ 'pg_amcheck test table and index, prior to corruption');
+
+$node->stop;
+
+# Sanity check that our 'test' table has a relfrozenxid newer than the
+# datfrozenxid for the database, and that the datfrozenxid is greater than the
+# first normal xid. We rely on these invariants in some of our tests.
+if ($datfrozenxid <= 3 || $datfrozenxid >= $relfrozenxid)
+{
+ fail('Xid thresholds not as expected');
+ $node->clean_node;
+ exit;
+}
+
+# Some #define constants from access/htup_details.h for use while corrupting.
+use constant HEAP_HASNULL => 0x0001;
+use constant HEAP_XMAX_LOCK_ONLY => 0x0080;
+use constant HEAP_XMIN_COMMITTED => 0x0100;
+use constant HEAP_XMIN_INVALID => 0x0200;
+use constant HEAP_XMAX_COMMITTED => 0x0400;
+use constant HEAP_XMAX_INVALID => 0x0800;
+use constant HEAP_NATTS_MASK => 0x07FF;
+use constant HEAP_XMAX_IS_MULTI => 0x1000;
+use constant HEAP_KEYS_UPDATED => 0x2000;
+
+# Helper function to generate a regular expression matching the header we
+# expect verify_heapam() to return given which fields we expect to be non-null.
+sub header
+{
+ my ($blkno, $offnum, $attnum) = @_;
+ return qr/relation postgres\.public\.test, block $blkno, offset $offnum, attribute $attnum\s+/ms
+ if (defined $attnum);
+ return qr/relation postgres\.public\.test, block $blkno, offset $offnum\s+/ms
+ if (defined $offnum);
+ return qr/relation postgres\.public\.test\s+/ms
+ if (defined $blkno);
+ return qr/relation postgres\.public\.test\s+/ms;
+}
+
+# Corrupt the tuples, one type of corruption per tuple. Some types of
+# corruption cause verify_heapam to skip to the next tuple without
+# performing any remaining checks, so we can't exercise the system properly if
+# we focus all our corruption on a single tuple.
+#
+my @expected;
+my $file;
+open($file, '+<', $relpath);
+binmode $file;
+
+for (my $tupidx = 0; $tupidx < ROWCOUNT; $tupidx++)
+{
+ my $offnum = $tupidx + 1; # offnum is 1-based, not zero-based
+ my $offset = $lp_off[$tupidx];
+ my $tup = read_tuple($file, $offset);
+
+ # Sanity-check that the data appears on the page where we expect.
+ if ($tup->{a} ne '12345678' || $tup->{b} ne 'abcdefg')
+ {
+ fail('Page layout differs from our expectations');
+ $node->clean_node;
+ exit;
+ }
+
+ my $header = header(0, $offnum, undef);
+ if ($offnum == 1)
+ {
+ # Corruptly set xmin < relfrozenxid
+ my $xmin = $relfrozenxid - 1;
+ $tup->{t_xmin} = $xmin;
+ $tup->{t_infomask} &= ~HEAP_XMIN_COMMITTED;
+ $tup->{t_infomask} &= ~HEAP_XMIN_INVALID;
+
+ # Expected corruption report
+ push @expected,
+ qr/${header}xmin $xmin precedes relation freeze threshold 0:\d+/;
+ }
+ if ($offnum == 2)
+ {
+ # Corruptly set xmin < datfrozenxid
+ my $xmin = 3;
+ $tup->{t_xmin} = $xmin;
+ $tup->{t_infomask} &= ~HEAP_XMIN_COMMITTED;
+ $tup->{t_infomask} &= ~HEAP_XMIN_INVALID;
+
+ push @expected,
+ qr/${$header}xmin $xmin precedes oldest valid transaction ID 0:\d+/;
+ }
+ elsif ($offnum == 3)
+ {
+ # Corruptly set xmin < datfrozenxid, further back, noting circularity
+ # of xid comparison. For a new cluster with epoch = 0, the corrupt
+ # xmin will be interpreted as in the future
+ $tup->{t_xmin} = 4026531839;
+ $tup->{t_infomask} &= ~HEAP_XMIN_COMMITTED;
+ $tup->{t_infomask} &= ~HEAP_XMIN_INVALID;
+
+ push @expected,
+ qr/${$header}xmin 4026531839 equals or exceeds next valid transaction ID 0:\d+/;
+ }
+ elsif ($offnum == 4)
+ {
+ # Corruptly set xmax < relminmxid;
+ $tup->{t_xmax} = 4026531839;
+ $tup->{t_infomask} &= ~HEAP_XMAX_INVALID;
+
+ push @expected,
+ qr/${$header}xmax 4026531839 equals or exceeds next valid transaction ID 0:\d+/;
+ }
+ elsif ($offnum == 5)
+ {
+ # Corrupt the tuple t_hoff, but keep it aligned properly
+ $tup->{t_hoff} += 128;
+
+ push @expected,
+ qr/${$header}data begins at offset 152 beyond the tuple length 58/,
+ qr/${$header}tuple data should begin at byte 24, but actually begins at byte 152 \(3 attributes, no nulls\)/;
+ }
+ elsif ($offnum == 6)
+ {
+ # Corrupt the tuple t_hoff, wrong alignment
+ $tup->{t_hoff} += 3;
+
+ push @expected,
+ qr/${$header}tuple data should begin at byte 24, but actually begins at byte 27 \(3 attributes, no nulls\)/;
+ }
+ elsif ($offnum == 7)
+ {
+ # Corrupt the tuple t_hoff, underflow but correct alignment
+ $tup->{t_hoff} -= 8;
+
+ push @expected,
+ qr/${$header}tuple data should begin at byte 24, but actually begins at byte 16 \(3 attributes, no nulls\)/;
+ }
+ elsif ($offnum == 8)
+ {
+ # Corrupt the tuple t_hoff, underflow and wrong alignment
+ $tup->{t_hoff} -= 3;
+
+ push @expected,
+ qr/${$header}tuple data should begin at byte 24, but actually begins at byte 21 \(3 attributes, no nulls\)/;
+ }
+ elsif ($offnum == 9)
+ {
+ # Corrupt the tuple to look like it has lots of attributes, not just 3
+ $tup->{t_infomask2} |= HEAP_NATTS_MASK;
+
+ push @expected,
+ qr/${$header}number of attributes 2047 exceeds maximum expected for table 3/;
+ }
+ elsif ($offnum == 10)
+ {
+ # Corrupt the tuple to look like it has lots of attributes, some of
+ # them null. This falsely creates the impression that the t_bits
+ # array is longer than just one byte, but t_hoff still says otherwise.
+ $tup->{t_infomask} |= HEAP_HASNULL;
+ $tup->{t_infomask2} |= HEAP_NATTS_MASK;
+ $tup->{t_bits} = 0xAA;
+
+ push @expected,
+ qr/${$header}tuple data should begin at byte 280, but actually begins at byte 24 \(2047 attributes, has nulls\)/;
+ }
+ elsif ($offnum == 11)
+ {
+ # Same as above, but this time t_hoff plays along
+ $tup->{t_infomask} |= HEAP_HASNULL;
+ $tup->{t_infomask2} |= (HEAP_NATTS_MASK & 0x40);
+ $tup->{t_bits} = 0xAA;
+ $tup->{t_hoff} = 32;
+
+ push @expected,
+ qr/${$header}number of attributes 67 exceeds maximum expected for table 3/;
+ }
+ elsif ($offnum == 12)
+ {
+ # Corrupt the bits in column 'b' 1-byte varlena header
+ $tup->{b_header} = 0x80;
+
+ $header = header(0, $offnum, 1);
+ push @expected,
+ qr/${header}attribute 1 with length 4294967295 ends at offset 416848000 beyond total tuple length 58/;
+ }
+ elsif ($offnum == 13)
+ {
+ # Corrupt the bits in column 'c' toast pointer
+ $tup->{c6} = 41;
+ $tup->{c7} = 41;
+
+ $header = header(0, $offnum, 2);
+ push @expected,
+ qr/${header}final toast chunk number 0 differs from expected value 6/,
+ qr/${header}toasted value for attribute 2 missing from toast table/;
+ }
+ elsif ($offnum == 14)
+ {
+ # Set both HEAP_XMAX_LOCK_ONLY and HEAP_KEYS_UPDATED
+ $tup->{t_infomask} |= HEAP_XMAX_LOCK_ONLY;
+ $tup->{t_infomask2} |= HEAP_KEYS_UPDATED;
+
+ push @expected,
+ qr/${header}tuple is marked as only locked, but also claims key columns were updated/;
+ }
+ elsif ($offnum == 15)
+ {
+ # Set both HEAP_XMAX_COMMITTED and HEAP_XMAX_IS_MULTI
+ $tup->{t_infomask} |= HEAP_XMAX_COMMITTED;
+ $tup->{t_infomask} |= HEAP_XMAX_IS_MULTI;
+ $tup->{t_xmax} = 4;
+
+ push @expected,
+ qr/${header}multitransaction ID 4 equals or exceeds next valid multitransaction ID 1/;
+ }
+ elsif ($offnum == 16) # Last offnum must equal ROWCOUNT
+ {
+ # Set both HEAP_XMAX_COMMITTED and HEAP_XMAX_IS_MULTI
+ $tup->{t_infomask} |= HEAP_XMAX_COMMITTED;
+ $tup->{t_infomask} |= HEAP_XMAX_IS_MULTI;
+ $tup->{t_xmax} = 4000000000;
+
+ push @expected,
+ qr/${header}multitransaction ID 4000000000 precedes relation minimum multitransaction ID threshold 1/;
+ }
+ write_tuple($file, $offset, $tup);
+}
+close($file);
+$node->start;
+
+# Run pg_amcheck against the corrupt table with epoch=0, comparing actual
+# corruption messages against the expected messages
+$node->command_checks_all(
+ ['pg_amcheck', '--exclude-indexes', '-p', $port, 'postgres'],
+ 0,
+ [ @expected ],
+ [ qr/^$/ ],
+ 'Expected corruption message output');
+
+$node->teardown_node;
+$node->clean_node;
diff --git a/contrib/pg_amcheck/t/005_opclass_damage.pl b/contrib/pg_amcheck/t/005_opclass_damage.pl
new file mode 100644
index 0000000000..379225cbf8
--- /dev/null
+++ b/contrib/pg_amcheck/t/005_opclass_damage.pl
@@ -0,0 +1,52 @@
+# This regression test checks the behavior of the btree validation in the
+# presence of breaking sort order changes.
+#
+use strict;
+use warnings;
+use PostgresNode;
+use TestLib;
+use Test::More tests => 6;
+
+my $node = get_new_node('test');
+$node->init;
+$node->start;
+
+# Create a custom operator class and an index which uses it.
+$node->safe_psql('postgres', q(
+ CREATE EXTENSION amcheck;
+
+ CREATE FUNCTION int4_asc_cmp (a int4, b int4) RETURNS int LANGUAGE sql AS $$
+ SELECT CASE WHEN $1 = $2 THEN 0 WHEN $1 > $2 THEN 1 ELSE -1 END; $$;
+
+ CREATE OPERATOR CLASS int4_fickle_ops FOR TYPE int4 USING btree AS
+ OPERATOR 1 < (int4, int4), OPERATOR 2 <= (int4, int4),
+ OPERATOR 3 = (int4, int4), OPERATOR 4 >= (int4, int4),
+ OPERATOR 5 > (int4, int4), FUNCTION 1 int4_asc_cmp(int4, int4);
+
+ CREATE TABLE int4tbl (i int4);
+ INSERT INTO int4tbl (SELECT * FROM generate_series(1,1000) gs);
+ CREATE INDEX fickleidx ON int4tbl USING btree (i int4_fickle_ops);
+));
+
+# We have not yet broken the index, so we should get no corruption
+$node->command_like(
+ [ 'pg_amcheck', '--quiet', '-p', $node->port, 'postgres' ],
+ qr/^$/,
+ 'pg_amcheck all schemas, tables and indexes reports no corruption');
+
+# Change the operator class to use a function which sorts in a different
+# order to corrupt the btree index
+$node->safe_psql('postgres', q(
+ CREATE FUNCTION int4_desc_cmp (int4, int4) RETURNS int LANGUAGE sql AS $$
+ SELECT CASE WHEN $1 = $2 THEN 0 WHEN $1 > $2 THEN -1 ELSE 1 END; $$;
+ UPDATE pg_catalog.pg_amproc
+ SET amproc = 'int4_desc_cmp'::regproc
+ WHERE amproc = 'int4_asc_cmp'::regproc
+));
+
+# Index corruption should now be reported
+$node->command_like(
+ [ 'pg_amcheck', '-p', $node->port, 'postgres' ],
+ qr/item order invariant violated for index "fickleidx"/,
+ 'pg_amcheck all schemas, tables and indexes reports fickleidx corruption'
+);
diff --git a/doc/src/sgml/contrib.sgml b/doc/src/sgml/contrib.sgml
index d3ca4b6932..7e101f7c11 100644
--- a/doc/src/sgml/contrib.sgml
+++ b/doc/src/sgml/contrib.sgml
@@ -185,6 +185,7 @@ pages.
</para>
&oid2name;
+ &pgamcheck;
&vacuumlo;
</sect1>
diff --git a/doc/src/sgml/filelist.sgml b/doc/src/sgml/filelist.sgml
index db1d369743..5115cb03d0 100644
--- a/doc/src/sgml/filelist.sgml
+++ b/doc/src/sgml/filelist.sgml
@@ -133,6 +133,7 @@
<!ENTITY oldsnapshot SYSTEM "oldsnapshot.sgml">
<!ENTITY pageinspect SYSTEM "pageinspect.sgml">
<!ENTITY passwordcheck SYSTEM "passwordcheck.sgml">
+<!ENTITY pgamcheck SYSTEM "pgamcheck.sgml">
<!ENTITY pgbuffercache SYSTEM "pgbuffercache.sgml">
<!ENTITY pgcrypto SYSTEM "pgcrypto.sgml">
<!ENTITY pgfreespacemap SYSTEM "pgfreespacemap.sgml">
diff --git a/doc/src/sgml/pgamcheck.sgml b/doc/src/sgml/pgamcheck.sgml
new file mode 100644
index 0000000000..2b2c73ca8b
--- /dev/null
+++ b/doc/src/sgml/pgamcheck.sgml
@@ -0,0 +1,1004 @@
+<!-- doc/src/sgml/pgamcheck.sgml -->
+
+<refentry id="pgamcheck">
+ <indexterm zone="pgamcheck">
+ <primary>pg_amcheck</primary>
+ </indexterm>
+
+ <refmeta>
+ <refentrytitle><application>pg_amcheck</application></refentrytitle>
+ <manvolnum>1</manvolnum>
+ <refmiscinfo>Application</refmiscinfo>
+ </refmeta>
+
+ <refnamediv>
+ <refname>pg_amcheck</refname>
+ <refpurpose>checks for corruption in one or more <productname>PostgreSQL</productname> databases</refpurpose>
+ </refnamediv>
+
+ <refsynopsisdiv>
+ <cmdsynopsis>
+ <command>pg_amcheck</command>
+ <arg rep="repeat"><replaceable>option</replaceable></arg>
+ <arg rep="repeat"><replaceable>dbname</replaceable></arg>
+ </cmdsynopsis>
+ </refsynopsisdiv>
+
+ <refsect1>
+ <title>Description</title>
+
+ <para>
+ <application>pg_amcheck</application> supports running
+ <xref linkend="amcheck"/>'s corruption checking functions against one or more
+ databases, with options to select which schemas, tables and indexes to check,
+ which kinds of checking to perform, and whether to perform the checks in
+ parallel, and if so, the number of parallel connections to establish and use.
+ </para>
+
+ <para>
+ Only table relations and btree indexes are currently supported. Other
+ relation types are silently skipped.
+ </para>
+
+ </refsect1>
+
+ <refsect1>
+ <title>Usage</title>
+
+ <refsect2>
+ <title>Parallelism Options</title>
+
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><literal>pg_amcheck --jobs=20 --all</literal></term>
+ <listitem>
+ <para>
+ Check all databases one after another, but for each database checked,
+ use up to 20 simultaneous connections to check relations in parallel.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --jobs=8 mydb yourdb</literal></term>
+ <listitem>
+ <para>
+ Check databases <literal>mydb</literal> and <literal>yourdb</literal>
+ one after another, using up to 8 simultaneous connections to check
+ relations in parallel.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect2>
+
+ <refsect2>
+ <title>Checking Option Specification</title>
+
+ <para>
+ If no checking options are specified, by default all table relation checks
+ and default level btree index checks are performed. A variety of options
+ exist to change the set of checks performed on whichever relations are
+ being checked. They are briefly mentioned here in the following examples,
+ but see their full descriptions below.
+ </para>
+
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><literal>pg_amcheck --parent-check --heapallindexed</literal></term>
+ <listitem>
+ <para>
+ For each btree index checked, performs more extensive checks.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --exclude-toast-pointers</literal></term>
+ <listitem>
+ <para>
+ For each table relation checked, do not check toast pointers against
+ the toast relation.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --on-error-stop</literal></term>
+ <listitem>
+ <para>
+ For each table relation checked, do not continue checking pages after
+ the first page where corruption is encountered.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --skip="all-frozen"</literal></term>
+ <listitem>
+ <para>
+ For each table relation checked, skips over blocks marked as all
+ frozen. Note that "all-visible" may also be specified.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --startblock=3000 --endblock=4000</literal></term>
+ <listitem>
+ <para>
+ For each table relation checked, check only blocks in the given block
+ range.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect2>
+
+ <refsect2>
+ <title>Relation Specification</title>
+
+ <para>
+ If no relations are explicitly listed, by default all relations will be
+ checked, but there are options to specify which relations to check.
+ </para>
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><literal>pg_amcheck -r mytable -r yourtable</literal></term>
+ <listitem>
+ <para>
+ If one or more relations are explicitly given, they are interpreted as
+ an exhaustive list of all relations to be checked, with one caveat:
+ for all such relations, associated toast relations and indexes are by
+ default included in the list of relations to check.
+ </para>
+ <para>
+ Assuming <literal>mytable</literal> is an ordinary table, and that it
+ is indexed by <literal>mytable_idx</literal> and has an associated
+ toast table <literal>pg_toast_12345</literal>, checking will be
+ performed on <literal>mytable</literal>,
+ <literal>mytable_idx</literal>, and <literal>pg_toast_12345</literal>.
+ </para>
+ <para>
+ Likewise for <literal>yourtable</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -r mytable --no-dependents</literal></term>
+ <listitem>
+ <para>
+ This restricts the list of relations checked to just
+ <literal>mytable</literal>, without pulling in the corresponding
+ indexes or toast, but see also
+ <option>--exclude-toast-pointers</option>.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -t mytable -i myindex</literal></term>
+ <listitem>
+ <para>
+ The <option>-r</option> (<option>--relation</option>) will match any
+ relation, but <option>-t</option> (<option>--table</option>) and
+ <option>-i</option> (<option>--index</option>) may be used to avoid
+ matching objects of the other type.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -r="my*" -R="mytemp*"</literal></term>
+ <listitem>
+ <para>
+ Relations may be included (<option>-r</option>) or excluded
+ (<option>-R</option>) using shell-style patterns.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -r="my*" -I="myanmar"</literal></term>
+ <listitem>
+ <para>
+ Table and index inclusion and exclusion patterns may be used
+ equivalently with <option>-t</option>, <option>-T</option>,
+ <option>-i</option> and <option>-I</option>. The above example checks
+ all tables and indexes starting with <literal>my</literal> except for
+ indexes starting with <literal>myanmar</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -R="india" -T="laos" -I="myanmar"</literal></term>
+ <listitem>
+ <para>
+ Unlike specifying one ore more <option>--relation</option> options, which
+ disables the default behavior of checking all relations, specifying one or
+ more of <option>-R</option>, <option>-T</option> or <option>-I</option> does not.
+ The above command will check all relations not named
+ <literal>india</literal>, not a table named
+ <literal>laos</literal>, nor an index named <literal>myanmar</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect2>
+
+ <refsect2>
+ <title>Schema Specification</title>
+
+ <para>
+ If no schemas are explicitly listed, by default all schemas except
+ <literal>pg_catalog</literal> and <literal>pg_toast</literal> will be
+ checked.
+ </para>
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><literal>pg_amcheck -s s1 -s s2 -r mytable</literal></term>
+ <listitem>
+ <para>
+ If one or more schemas are listed with <option>-s</option>, unqualified
+ relation names will be checked only in the given schemas. The above
+ command will check tables <literal>s1.mytable</literal> and
+ <literal>s2.mytable</literal> but not tables named
+ <literal>mytable</literal> in other schemas.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -S s1 -S s2 -r mytable</literal></term>
+ <listitem>
+ <para>
+ As with relations, schemas may be excluded. The above command will
+ check any table named <literal>mytable</literal> not in schemas
+ <literal>s1</literal> and <literal>s2</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -S s1 -S s2 -r mytable -t s1.stuff</literal></term>
+ <listitem>
+ <para>
+ Relations may be included or excluded with a schema-qualified name
+ without interference from the <option>-s</option> or
+ <option>-S</option> options. Even though schema <literal>s1</literal>
+ has been excluded, the table <literal>s1.stuff</literal> will be
+ checked.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect2>
+
+ <refsect2>
+ <title>Database Specification</title>
+
+ <para>
+ If no databases are explicitly listed, the database to check is obtained
+ from environment variables in the usual way. Otherwise, when one or more
+ databases are explicitly given, they are interpreted as an exhaustive list
+ of all databases to be checked. This list of databases to check may
+ contain patterns, but because any such patterns need to be reconciled
+ against a list of all databases to find the matching database names, at
+ least one database specified must be a literal database name and not merely
+ a pattern, and the one so specified must be in a location where
+ <application>pg_amcheck</application> expects to find it.
+ </para>
+ <para>
+ For example:
+ </para>
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><literal>pg_amcheck --all --maintenance-db=foo</literal></term>
+ <listitem>
+ <para>
+ If the <option>--maintenance-db</option> option is given, it will be
+ used to look up the matching databases, though it will not itself be
+ added to the list of databases for checking.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck foo bar baz</literal></term>
+ <listitem>
+ <para>
+ Otherwise, if one or more plain database name arguments not preceded by
+ <option>-d</option> or <option>--dbname</option> are given, the first
+ one will be used for this purpose, and it will also be included in the
+ list of databases to check.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck -d foo -d bar baz</literal></term>
+ <listitem>
+ <para>
+ If a mixture of plain database names and databases preceded with
+ <option>-d</option> or <option>--dbname</option> are given, the first
+ plain database name will be used for this purpose. In the above
+ example, <literal>baz</literal> will be used.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --dbname=foo --dbname="bar*"</literal></term>
+ <listitem>
+ <para>
+ Otherwise, if one or more databases are given with the
+ <option>-d</option> or <option>--dbname</option> option, the first one
+ will be used and must be a literal database name. In this example,
+ <literal>foo</literal> will be used.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><literal>pg_amcheck --relation="accounts_*.*.*"</literal></term>
+ <listitem>
+ <para>
+ Otherwise, the environment will be consulted for the database to be
+ used. In the example above, the default database will be queried to
+ find all databases with names that begin with
+ <literal>accounts_</literal>.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+
+ <para>
+ As discussed above for schema-qualified relations, a database-qualified
+ relation name or pattern may also be given.
+<programlisting>
+pg_amcheck mydb \
+ --schema="t*" \
+ --exclude-schema="tmp*" \
+ --relation=baz \
+ --relation=bar.baz \
+ --relation=foo.bar.baz \
+ --relation="f*".a.b \
+ --exclude-relation=foo.a.b
+</programlisting>
+ will check relations in database <literal>mydb</literal> using the schema
+ resolution rules discussed above, but additionally will check all relations
+ named <literal>a.b</literal> in all databases with names starting with
+ <literal>f</literal> except database <literal>foo</literal>.
+ </para>
+
+ </refsect2>
+ </refsect1>
+
+ <refsect1>
+ <title>Options</title>
+
+ <para>
+ <application>pg_amcheck</application> accepts the following command-line arguments:
+ </para>
+
+ <refsect2>
+ <title>Help and Version Information Options</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><option>-?</option></term>
+ <term><option>--help</option></term>
+ <listitem>
+ <para>
+ Show help about <application>pg_amcheck</application> command line
+ arguments, and exit.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-V</option></term>
+ <term><option>--version</option></term>
+ <listitem>
+ <para>
+ Print the <application>pg_amcheck</application> version and exit.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-e</option></term>
+ <term><option>--echo</option></term>
+ <listitem>
+ <para>
+ Print to stdout all commands and queries being executed against the
+ server.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-q</option></term>
+ <term><option>--quiet</option></term>
+ <listitem>
+ <para>
+ Do not write additional messages beyond those about corruption.
+ </para>
+ <para>
+ This option does not quiet any output specifically due to the use of
+ the <option>-e</option> <option>--echo</option> option.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-v</option></term>
+ <term><option>--verbose</option></term>
+ <listitem>
+ <para>
+ Increases the log level verbosity. This option may be given more than
+ once.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </refsect2>
+
+ <refsect2>
+ <title>Database Connection and Concurrent Connection Options</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><option>-h</option></term>
+ <term><option>--host=HOSTNAME</option></term>
+ <listitem>
+ <para>
+ Specifies the host name of the machine on which the server is running.
+ If the value begins with a slash, it is used as the directory for the
+ Unix domain socket.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-p</option></term>
+ <term><option>--port=PORT</option></term>
+ <listitem>
+ <para>
+ Specifies the TCP port or local Unix domain socket file extension on
+ which the server is listening for connections.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-U</option></term>
+ <term><option>--username=USERNAME</option></term>
+ <listitem>
+ <para>
+ User name to connect as.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-w</option></term>
+ <term><option>--no-password</option></term>
+ <listitem>
+ <para>
+ Never issue a password prompt. If the server requires password
+ authentication and a password is not available by other means such as
+ a <filename>.pgpass</filename> file, the connection attempt will fail.
+ This option can be useful in batch jobs and scripts where no user is
+ present to enter a password.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-W</option></term>
+ <term><option>--password</option></term>
+ <listitem>
+ <para>
+ Force <application>pg_amcheck</application> to prompt for a password
+ before connecting to a database.
+ </para>
+ <para>
+ This option is never essential, since
+ <application>pg_amcheck</application> will automatically prompt for a
+ password if the server demands password authentication. However,
+ <application>pg_amcheck</application> will waste a connection attempt
+ finding out that the server wants a password. In some cases it is
+ worth typing <option>-W</option> to avoid the extra connection attempt.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--maintenance-db=DBNAME</option></term>
+ <listitem>
+ <para>
+ Specifies the name of the database to connect to when querying the
+ list of all databases. If not specified, the
+ <literal>postgres</literal> database will be used; if that does not
+ exist <literal>template1</literal> will be used. This can be a
+ <link linkend="libpq-connstring">connection string</link>. If so,
+ connection string parameters will override any conflicting command
+ line options.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-j</option></term>
+ <term><option>--jobs=NUM</option></term>
+ <listitem>
+ <para>
+ Use the specified number of concurrent connections to the server, or
+ one per object to be checked, whichever number is smaller.
+ </para>
+ <para>
+ When used in conjunction with the <option>-a</option>
+ <option>--all</option> option, the total number of objects to check,
+ and correspondingly the number of concurrent connections to use, is
+ recalculated per database. If the number of objects to check differs
+ from one database to the next and is less than the concurrency level
+ specified, the number of concurrent connections open to the server
+ will fluctuate to meet the needs of each database processed.
+ </para>
+ <para>
+ The default is to use a single connection.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </refsect2>
+
+ <refsect2>
+ <title>Options Controlling Index Checking Functions</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><option>-P</option></term>
+ <term><option>--parent-check</option></term>
+ <listitem>
+ <para>
+ For each btree index checked, use <xref linkend="amcheck"/>'s
+ <function>bt_index_parent_check</function> function, which performs
+ additional checks of parent/child relationships during index checking.
+ </para>
+ <para>
+ The default is to use <application>amcheck</application>'s
+ <function>bt_index_check</function> function, but note that use of the
+ <option>--rootdescend</option> option implicitly
+ selects <function>bt_index_parent_check</function>.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>-H</option></term>
+ <term><option>--heapallindexed</option></term>
+ <listitem>
+ <para>
+ For each index checked, verify the presence of all heap tuples as index
+ tuples in the index using <application>amcheck</application>'s
+ <option>heapallindexed</option> option.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--rootdescend</option></term>
+ <listitem>
+ <para>
+ For each index checked, re-find tuples on the leaf level by performing
+ a new search from the root page for each tuple using
+ <xref linkend="amcheck"/>'s <option>rootdescend</option> option.
+ </para>
+ <para>
+ Use of this option implicitly also selects the <option>-P</option>
+ <option>--parent-check</option> option.
+ </para>
+ <para>
+ This form of verification was originally written to help in the
+ development of btree index features. It may be of limited use or even
+ of no use in helping detect the kinds of corruption that occur in
+ practice. It may also cause corruption checking to take considerably
+ longer and consume considerably more resources on the server.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </refsect2>
+
+ <refsect2>
+ <title>Options Controlling Table Checking Functions</title>
+
+ <variablelist>
+ <varlistentry>
+ <term><option>--exclude-toast-pointers</option></term>
+ <listitem>
+ <para>
+ When checking main relations, do not look up entries in toast tables
+ corresponding to toast pointers in the main releation.
+ </para>
+ <para>
+ The default behavior checks each toast pointer encountered in the main
+ table to verify, as much as possible, that the pointer points at
+ something in the toast table that is reasonable. Toast pointers which
+ point beyond the end of the toast table, or to the middle (rather than
+ the beginning) of a toast entry, are identified as corrupt.
+ </para>
+ <para>
+ The process by which <xref linkend="amcheck"/>'s
+ <function>verify_heapam</function> function checks each toast pointer
+ is slow and may be improved in a future release. Some users may wish
+ to disable this check to save time.
+ </para>
+ <para>
+ Note that, despite their similar names, this option is unrelated to the
+ <option>--exclude-toast</option> option.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--on-error-stop</option></term>
+ <listitem>
+ <para>
+ After reporting all corruptions on the first page of a table where
+ corruptions are found, stop processing that table relation and move on
+ to the next table or index.
+ </para>
+ <para>
+ Note that index checking always stops after the first corrupt page.
+ This option only has meaning relative to table relations.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--skip=OPTION</option></term>
+ <listitem>
+ <para>
+ If <literal>"all-frozen"</literal> is given, table corruption checks
+ will skip over pages in all tables that are marked as all frozen.
+ </para>
+ <para>
+ If <literal>"all-visible"</literal> is given, table corruption checks
+ will skip over pages in all tables that are marked as all visible.
+ </para>
+ <para>
+ By default, no pages are skipped.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--startblock=BLOCK</option></term>
+ <listitem>
+ <para>
+ Skip (do not check) pages prior to the given starting block.
+ </para>
+ <para>
+ By default, no pages are skipped. This option will be applied to all
+ table relations that are checked, including toast tables.
+ </para>
+ </listitem>
+ </varlistentry>
+ <varlistentry>
+ <term><option>--endblock=BLOCK</option></term>
+ <listitem>
+ <para>
+ Skip (do not check) all pages after the given ending block.
+ </para>
+ <para>
+ By default, no pages are skipped. This option will be applied to all
+ table relations that are checked, including toast tables.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </refsect2>
+
+ <refsect2>
+ <title>Corruption Checking Target Options</title>
+
+ <para>
+ Objects to be checked may span schemas in more than one database. Options
+ for restricting the list of databases, schemas, tables and indexes are
+ described below. In each place where a name may be specified, a
+ <link linkend="app-psql-patterns"><replaceable class="parameter">pattern</replaceable></link>
+ may also be used.
+ </para>
+
+ <para>
+ <variablelist>
+ <varlistentry>
+ <term><option>--all</option></term>
+ <listitem>
+ <para>
+ Perform checking in all databases.
+ </para>
+ <para>
+ In the absence of any other options, selects all objects across all
+ schemas and databases.
+ </para>
+ <para>
+ Option <option>-D</option> <option>--exclude-db</option> takes
+ precedence over <option>--all</option>.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-d</option></term>
+ <term><option>--dbname</option></term>
+ <listitem>
+ <para>
+ Perform checking in the specified database.
+ </para>
+ <para>
+ This option may be specified multiple times to list more than one
+ database (or database pattern) for checking. By default, all objects in
+ the matching database(s) will be checked.
+ </para>
+ <para>
+ If no <option>maintenance-db</option> argument is given nor is any
+ database name given as a command line argument, the first argument
+ specified with <option>-d</option> <option>--dbname</option> will be
+ used for the initial connection. If that argument is not a literal
+ database name, the attempt to connect will fail.
+ </para>
+ <para>
+ If <option>--all</option> is also specified, <option>-d</option>
+ <option>--dbname</option> does not affect which databases are checked,
+ but may be used to specify the database for the initial connection.
+ </para>
+ <para>
+ Option <option>-D</option> <option>--exclude-db</option> takes
+ precedence over <option>-d</option> <option>--dbname</option>.
+ </para>
+ <para>
+ Examples:
+ <simplelist>
+ <member><literal>--dbname=africa</literal></member>
+ <member><literal>--dbname="a*"</literal></member>
+ <member><literal>--dbname="africa|asia|europe"</literal></member>
+ </simplelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-D</option></term>
+ <term><option>--exclude-db</option></term>
+ <listitem>
+ <para>
+ Do not perform checking in the specified database.
+ </para>
+ <para>
+ This option may be specified multiple times to list more than one
+ database (or database pattern) for exclusion.
+ </para>
+ <para>
+ If a database which is included using <option>--all</option> or
+ <option>-d</option> <option>--dbname</option> is also excluded using
+ <option>-D</option> <option>--exclude-db</option>, the database will be
+ excluded.
+ </para>
+ <para>
+ Examples:
+ <simplelist>
+ <member><literal>--exclude-db=america</literal></member>
+ <member><literal>--exclude-db="*pacific*"</literal></member>
+ </simplelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-s</option></term>
+ <term><option>--schema</option></term>
+ <listitem>
+ <para>
+ Perform checking in the specified schema(s).
+ </para>
+ <para>
+ This option may be specified multiple times to list more than one
+ schema (or schema pattern) for checking. By default, all objects in
+ the matching schema(s) will be checked.
+ </para>
+ <para>
+ Option <option>-S</option> <option>--exclude-schema</option> takes
+ precedence over <option>-s</option> <option>--schema</option>.
+ </para>
+ <para>
+ Examples:
+ <simplelist>
+ <member><literal>--schema=corp</literal></member>
+ <member><literal>--schema="corp|llc|npo"</literal></member>
+ </simplelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-S</option></term>
+ <term><option>--exclude-schema</option></term>
+ <listitem>
+ <para>
+ Do not perform checking in the specified schema.
+ </para>
+ <para>
+ This option may be specified multiple times to list more than one
+ schema (or schema pattern) for exclusion.
+ </para>
+ <para>
+ If a schema which is included using
+ <option>-s</option> <option>--schema</option> is also excluded using
+ <option>-S</option> <option>--exclude-schema</option>, the schema will be
+ excluded.
+ </para>
+ <para>
+ Examples:
+ <simplelist>
+ <member><literal>-S corp -S llc</literal></member>
+ <member><literal>--exclude-schema="*c*"</literal></member>
+ </simplelist>
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-r</option></term>
+ <term><option>--relation</option></term>
+ <listitem>
+ <para>
+ Perform checking on the specified relation(s).
+ </para>
+ <para>
+ This option may be specified multiple times to list more than one
+ relation (or relation pattern) for checking.
+ </para>
+ <para>
+ Option <option>-R</option> <option>--exclude-relation</option> takes
+ precedence over <option>-r</option> <option>--relation</option>.
+ </para>
+ <para>
+ If the relation is not schema qualified, database and schema
+ inclusion/exclusion lists will determine in which databases or schemas
+ matching relations will be checked.
+ </para>
+ <para>
+ Examples:
+ <simplelist>
+ <member><literal>--relation=accounts_idx</literal></member>
+ <member><literal>--relation="llc.accounts_idx"</literal></member>
+ <member><literal>--relation="asia|africa.corp|llc.accounts_idx"</literal></member>
+ </simplelist>
+ </para>
+ <para>
+ The first example, <literal>--relation=accounts_idx</literal>, checks
+ relations named <literal>accounts_idx</literal> in all selected schemas
+ and databases.
+ </para>
+ <para>
+ The second example, <literal>--relation="llc.accounts_idx"</literal>,
+ checks relations named <literal>accounts_idx</literal> in schema
+ <literal>llc</literal> in all selected databases.
+ </para>
+ <para>
+ The third example,
+ <literal>--relation="asia|africa.corp|llc.accounts_idx"</literal>,
+ checks relations named <literal>accounts_idx</literal> in
+ schemas <literal>corp</literal> and <literal>llc</literal> in databases
+ <literal>asia</literal> and <literal>africa</literal>.
+ </para>
+ <para>
+ Note that if a database is implicated in a relation pattern, such as
+ <literal>asia</literal> and <literal>africa</literal> in the third
+ example above, the database need not be otherwise given in the command
+ arguments for the relation to be checked. As an extreme example of
+ this:
+ <simplelist>
+ <member><literal>pg_amcheck --relation="*.*.*" mydb</literal></member>
+ </simplelist>
+ will check all relations in all databases. The <literal>mydb</literal>
+ argument only serves to tell <application>pg_amcheck</application> the
+ name of the database to use for querying the list of all databases.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-R</option></term>
+ <term><option>--exclude-relation</option></term>
+ <listitem>
+ <para>
+ Exclude checks on the specified relation(s).
+ </para>
+ <para>
+ Option <option>-R</option> <option>--exclude-relation</option> takes
+ precedence over <option>-r</option> <option>--relation</option>,
+ <option>-t</option> <option>--table</option> and <option>-i</option>
+ <option>--index</option>.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-t</option></term>
+ <term><option>--table</option></term>
+ <listitem>
+ <para>
+ Perform checks on the specified tables(s). This is an alias for the
+ <option>-r</option> <option>--relation</option> option, except that it
+ applies only to tables, not indexes.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-T</option></term>
+ <term><option>--exclude-table</option></term>
+ <listitem>
+ <para>
+ Exclude checks on the specified tables(s). This is an alias for the
+ <option>-R</option> <option>--exclude-relation</option> option, except
+ that it applies only to tables, not indexes.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-i</option></term>
+ <term><option>--index</option></term>
+ <listitem>
+ <para>
+ Perform checks on the specified index(es). This is an alias for the
+ <option>-r</option> <option>--relation</option> option, except that it
+ applies only to indexes, not tables.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>-I</option></term>
+ <term><option>--exclude-index</option></term>
+ <listitem>
+ <para>
+ Exclude checks on the specified index(es). This is an alias for the
+ <option>-R</option> <option>--exclude-relation</option> option, except
+ that it applies only to indexes, not tables.
+ </para>
+ </listitem>
+ </varlistentry>
+
+ <varlistentry>
+ <term><option>--no-dependents</option></term>
+ <listitem>
+ <para>
+ When calculating the list of objects to be checked, do not automatically
+ expand the list to include associated indexes and toast tables of
+ elements otherwise in the list.
+ </para>
+ <para>
+ By default, for each main table relation checked, any associated toast
+ table and all associated indexes are also checked, unless explicitly
+ excluded.
+ </para>
+ </listitem>
+ </varlistentry>
+ </variablelist>
+ </para>
+ </refsect2>
+ </refsect1>
+
+ <refsect1>
+ <title>Notes</title>
+
+ <para>
+ <application>pg_amcheck</application> is designed to work with
+ <productname>PostgreSQL</productname> 14.0 and later.
+ </para>
+ </refsect1>
+
+ <refsect1>
+ <title>Author</title>
+
+ <para>
+ Mark Dilger <email>mark.dilger@enterprisedb.com</email>
+ </para>
+ </refsect1>
+
+ <refsect1>
+ <title>See Also</title>
+
+ <simplelist type="inline">
+ <member><xref linkend="amcheck"/></member>
+ </simplelist>
+ </refsect1>
+</refentry>
diff --git a/src/tools/msvc/Install.pm b/src/tools/msvc/Install.pm
index ea3af48777..49ad558b74 100644
--- a/src/tools/msvc/Install.pm
+++ b/src/tools/msvc/Install.pm
@@ -18,7 +18,7 @@ our (@ISA, @EXPORT_OK);
@EXPORT_OK = qw(Install);
my $insttype;
-my @client_contribs = ('oid2name', 'pgbench', 'vacuumlo');
+my @client_contribs = ('oid2name', 'pg_amcheck', 'pgbench', 'vacuumlo');
my @client_program_files = (
'clusterdb', 'createdb', 'createuser', 'dropdb',
'dropuser', 'ecpg', 'libecpg', 'libecpg_compat',
diff --git a/src/tools/msvc/Mkvcbuild.pm b/src/tools/msvc/Mkvcbuild.pm
index 7be6e6c9e5..53fbfa012e 100644
--- a/src/tools/msvc/Mkvcbuild.pm
+++ b/src/tools/msvc/Mkvcbuild.pm
@@ -33,9 +33,9 @@ my @unlink_on_exit;
# Set of variables for modules in contrib/ and src/test/modules/
my $contrib_defines = { 'refint' => 'REFINT_VERBOSE' };
-my @contrib_uselibpq = ('dblink', 'oid2name', 'postgres_fdw', 'vacuumlo');
-my @contrib_uselibpgport = ('oid2name', 'vacuumlo');
-my @contrib_uselibpgcommon = ('oid2name', 'vacuumlo');
+my @contrib_uselibpq = ('dblink', 'oid2name', 'pg_amcheck', 'postgres_fdw', 'vacuumlo');
+my @contrib_uselibpgport = ('oid2name', 'pg_amcheck', 'vacuumlo');
+my @contrib_uselibpgcommon = ('oid2name', 'pg_amcheck', 'vacuumlo');
my $contrib_extralibs = undef;
my $contrib_extraincludes = { 'dblink' => ['src/backend'] };
my $contrib_extrasource = {
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 4d0d09a5dd..26920cc512 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -336,6 +336,8 @@ CheckPointStmt
CheckpointStatsData
CheckpointerRequest
CheckpointerShmemStruct
+CheckType
+CheckTypeFilter
Chromosome
CkptSortItem
CkptTsStatus
@@ -2847,6 +2849,8 @@ ambuildempty_function
ambuildphasename_function
ambulkdelete_function
amcanreturn_function
+amcheckObjects
+amcheckOptions
amcostestimate_function
amendscan_function
amestimateparallelscan_function
--
2.21.1 (Apple Git-122.3)