postgresql/src/bin/scripts/reindexdb.c

780 lines
20 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* reindexdb
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
*
2010-09-20 22:08:53 +02:00
* src/bin/scripts/reindexdb.c
*
*-------------------------------------------------------------------------
*/
#include "postgres_fe.h"
#include "catalog/pg_class_d.h"
#include "common.h"
#include "common/logging.h"
#include "fe_utils/cancel.h"
#include "fe_utils/connect.h"
#include "fe_utils/simple_list.h"
#include "fe_utils/string_utils.h"
#include "scripts_parallel.h"
typedef enum ReindexType
{
REINDEX_DATABASE,
REINDEX_INDEX,
REINDEX_SCHEMA,
REINDEX_SYSTEM,
REINDEX_TABLE
} ReindexType;
static SimpleStringList *get_parallel_object_list(PGconn *conn,
ReindexType type,
SimpleStringList *user_list,
bool echo);
static void reindex_one_database(const char *dbname, ReindexType type,
SimpleStringList *user_list, const char *host,
const char *port, const char *username,
enum trivalue prompt_password, const char *progname,
bool echo, bool verbose, bool concurrently,
int concurrentCons);
static void reindex_all_databases(const char *maintenance_db,
const char *host, const char *port,
const char *username, enum trivalue prompt_password,
const char *progname, bool echo,
bool quiet, bool verbose, bool concurrently,
int concurrentCons);
static void run_reindex_command(PGconn *conn, ReindexType type,
const char *name, bool echo, bool verbose,
bool concurrently, bool async);
static void help(const char *progname);
int
main(int argc, char *argv[])
{
static struct option long_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'},
{"echo", no_argument, NULL, 'e'},
{"quiet", no_argument, NULL, 'q'},
{"schema", required_argument, NULL, 'S'},
{"dbname", required_argument, NULL, 'd'},
{"all", no_argument, NULL, 'a'},
{"system", no_argument, NULL, 's'},
{"table", required_argument, NULL, 't'},
{"index", required_argument, NULL, 'i'},
{"jobs", required_argument, NULL, 'j'},
{"verbose", no_argument, NULL, 'v'},
{"concurrently", no_argument, NULL, 1},
{"maintenance-db", required_argument, NULL, 2},
{NULL, 0, NULL, 0}
};
2005-10-15 04:49:52 +02:00
const char *progname;
int optindex;
int c;
2005-10-15 04:49:52 +02:00
const char *dbname = NULL;
const char *maintenance_db = NULL;
2005-10-15 04:49:52 +02:00
const char *host = NULL;
const char *port = NULL;
const char *username = NULL;
enum trivalue prompt_password = TRI_DEFAULT;
bool syscatalog = false;
bool alldb = false;
bool echo = false;
bool quiet = false;
bool verbose = false;
bool concurrently = false;
SimpleStringList indexes = {NULL, NULL};
SimpleStringList tables = {NULL, NULL};
SimpleStringList schemas = {NULL, NULL};
int concurrentCons = 1;
2005-10-15 04:49:52 +02:00
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_logging_init(argv[0]);
progname = get_progname(argv[0]);
set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pgscripts"));
handle_help_version_opts(argc, argv, "reindexdb", help);
/* process command-line options */
while ((c = getopt_long(argc, argv, "h:p:U:wWeqS:d:ast:i:j:v", long_options, &optindex)) != -1)
{
switch (c)
{
case 'h':
host = pg_strdup(optarg);
break;
case 'p':
port = pg_strdup(optarg);
break;
case 'U':
username = pg_strdup(optarg);
break;
case 'w':
prompt_password = TRI_NO;
break;
case 'W':
prompt_password = TRI_YES;
break;
case 'e':
echo = true;
break;
case 'q':
quiet = true;
break;
case 'S':
simple_string_list_append(&schemas, optarg);
break;
case 'd':
dbname = pg_strdup(optarg);
break;
case 'a':
alldb = true;
break;
case 's':
syscatalog = true;
break;
case 't':
simple_string_list_append(&tables, optarg);
break;
case 'i':
simple_string_list_append(&indexes, optarg);
break;
case 'j':
concurrentCons = atoi(optarg);
if (concurrentCons <= 0)
{
pg_log_error("number of parallel jobs must be at least 1");
exit(1);
}
break;
case 'v':
verbose = true;
break;
case 1:
concurrently = true;
break;
case 2:
maintenance_db = pg_strdup(optarg);
break;
default:
fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
exit(1);
}
}
/*
* Non-option argument specifies database name as long as it wasn't
* already specified with -d / --dbname
*/
if (optind < argc && dbname == NULL)
{
dbname = argv[optind];
optind++;
}
if (optind < argc)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("too many command-line arguments (first is \"%s\")",
argv[optind]);
fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
exit(1);
}
setup_cancel_handler(NULL);
if (alldb)
{
if (dbname)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex all databases and a specific one at the same time");
exit(1);
}
if (syscatalog)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex all databases and system catalogs at the same time");
exit(1);
}
if (schemas.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific schema(s) in all databases");
exit(1);
}
if (tables.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific table(s) in all databases");
exit(1);
}
if (indexes.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific index(es) in all databases");
exit(1);
}
reindex_all_databases(maintenance_db, host, port, username,
prompt_password, progname, echo, quiet, verbose,
concurrently, concurrentCons);
}
else if (syscatalog)
{
if (schemas.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific schema(s) and system catalogs at the same time");
exit(1);
}
if (tables.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific table(s) and system catalogs at the same time");
exit(1);
}
if (indexes.head != NULL)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot reindex specific index(es) and system catalogs at the same time");
exit(1);
}
if (concurrentCons > 1)
{
pg_log_error("cannot use multiple jobs to reindex system catalogs");
exit(1);
}
if (dbname == NULL)
{
if (getenv("PGDATABASE"))
dbname = getenv("PGDATABASE");
else if (getenv("PGUSER"))
dbname = getenv("PGUSER");
else
dbname = get_user_name_or_exit(progname);
}
reindex_one_database(dbname, REINDEX_SYSTEM, NULL, host,
port, username, prompt_password, progname,
echo, verbose, concurrently, 1);
}
else
{
/*
* Index-level REINDEX is not supported with multiple jobs as we
* cannot control the concurrent processing of multiple indexes
* depending on the same relation.
*/
if (concurrentCons > 1 && indexes.head != NULL)
{
pg_log_error("cannot use multiple jobs to reindex indexes");
exit(1);
}
if (dbname == NULL)
{
if (getenv("PGDATABASE"))
dbname = getenv("PGDATABASE");
else if (getenv("PGUSER"))
dbname = getenv("PGUSER");
else
dbname = get_user_name_or_exit(progname);
}
if (schemas.head != NULL)
reindex_one_database(dbname, REINDEX_SCHEMA, &schemas, host,
port, username, prompt_password, progname,
echo, verbose, concurrently, concurrentCons);
if (indexes.head != NULL)
reindex_one_database(dbname, REINDEX_INDEX, &indexes, host,
port, username, prompt_password, progname,
echo, verbose, concurrently, 1);
if (tables.head != NULL)
reindex_one_database(dbname, REINDEX_TABLE, &tables, host,
port, username, prompt_password, progname,
echo, verbose, concurrently,
concurrentCons);
2015-05-24 03:35:49 +02:00
/*
* reindex database only if neither index nor table nor schema is
* specified
*/
if (indexes.head == NULL && tables.head == NULL && schemas.head == NULL)
reindex_one_database(dbname, REINDEX_DATABASE, NULL, host,
port, username, prompt_password, progname,
echo, verbose, concurrently, concurrentCons);
}
exit(0);
}
static void
reindex_one_database(const char *dbname, ReindexType type,
SimpleStringList *user_list, const char *host,
const char *port, const char *username,
enum trivalue prompt_password, const char *progname, bool echo,
bool verbose, bool concurrently, int concurrentCons)
{
2005-10-15 04:49:52 +02:00
PGconn *conn;
SimpleStringListCell *cell;
bool parallel = concurrentCons > 1;
SimpleStringList *process_list = user_list;
ReindexType process_type = type;
ParallelSlot *slots;
bool failed = false;
int items_count = 0;
conn = connectDatabase(dbname, host, port, username, prompt_password,
progname, echo, false, false);
if (concurrently && PQserverVersion(conn) < 120000)
{
PQfinish(conn);
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("cannot use the \"%s\" option on server versions older than PostgreSQL %s",
"concurrently", "12");
exit(1);
}
if (!parallel)
{
switch (process_type)
{
case REINDEX_DATABASE:
case REINDEX_SYSTEM:
/*
* Database and system reindexes only need to work on the
* database itself, so build a list with a single entry.
*/
Assert(user_list == NULL);
process_list = pg_malloc0(sizeof(SimpleStringList));
simple_string_list_append(process_list, PQdb(conn));
break;
case REINDEX_INDEX:
case REINDEX_SCHEMA:
case REINDEX_TABLE:
Assert(user_list != NULL);
break;
}
}
else
{
switch (process_type)
{
case REINDEX_DATABASE:
/*
* Database-wide parallel reindex requires special processing.
* If multiple jobs were asked, we have to reindex system
* catalogs first as they cannot be processed in parallel.
*/
if (concurrently)
pg_log_warning("cannot reindex system catalogs concurrently, skipping all");
else
run_reindex_command(conn, REINDEX_SYSTEM, PQdb(conn), echo,
verbose, concurrently, false);
/* Build a list of relations from the database */
process_list = get_parallel_object_list(conn, process_type,
user_list, echo);
process_type = REINDEX_TABLE;
/* Bail out if nothing to process */
if (process_list == NULL)
return;
break;
case REINDEX_SCHEMA:
Assert(user_list != NULL);
/* Build a list of relations from all the schemas */
process_list = get_parallel_object_list(conn, process_type,
user_list, echo);
process_type = REINDEX_TABLE;
/* Bail out if nothing to process */
if (process_list == NULL)
return;
break;
case REINDEX_SYSTEM:
case REINDEX_INDEX:
/* not supported */
Assert(false);
break;
case REINDEX_TABLE:
/*
* Fall through. The list of items for tables is already
* created.
*/
break;
}
}
/*
* Adjust the number of concurrent connections depending on the items in
* the list. We choose the minimum between the number of concurrent
* connections and the number of items in the list.
*/
for (cell = process_list->head; cell; cell = cell->next)
{
items_count++;
/* no need to continue if there are more elements than jobs */
if (items_count >= concurrentCons)
break;
}
concurrentCons = Min(concurrentCons, items_count);
Assert(concurrentCons > 0);
Assert(process_list != NULL);
slots = ParallelSlotsSetup(dbname, host, port, username, prompt_password,
progname, echo, conn, concurrentCons);
cell = process_list->head;
do
{
const char *objname = cell->val;
ParallelSlot *free_slot = NULL;
if (CancelRequested)
{
failed = true;
goto finish;
}
free_slot = ParallelSlotsGetIdle(slots, concurrentCons);
if (!free_slot)
{
failed = true;
goto finish;
}
run_reindex_command(free_slot->connection, process_type, objname,
echo, verbose, concurrently, true);
cell = cell->next;
} while (cell != NULL);
if (!ParallelSlotsWaitCompletion(slots, concurrentCons))
failed = true;
finish:
if (process_list != user_list)
{
simple_string_list_destroy(process_list);
pg_free(process_list);
}
ParallelSlotsTerminate(slots, concurrentCons);
pfree(slots);
if (failed)
exit(1);
}
static void
run_reindex_command(PGconn *conn, ReindexType type, const char *name,
bool echo, bool verbose, bool concurrently, bool async)
{
PQExpBufferData sql;
bool status;
Assert(name);
/* build the REINDEX query */
initPQExpBuffer(&sql);
appendPQExpBufferStr(&sql, "REINDEX ");
if (verbose)
appendPQExpBufferStr(&sql, "(VERBOSE) ");
/* object type */
switch (type)
{
case REINDEX_DATABASE:
appendPQExpBufferStr(&sql, "DATABASE ");
break;
case REINDEX_INDEX:
appendPQExpBufferStr(&sql, "INDEX ");
break;
case REINDEX_SCHEMA:
appendPQExpBufferStr(&sql, "SCHEMA ");
break;
case REINDEX_SYSTEM:
appendPQExpBufferStr(&sql, "SYSTEM ");
break;
case REINDEX_TABLE:
appendPQExpBufferStr(&sql, "TABLE ");
break;
}
if (concurrently)
appendPQExpBufferStr(&sql, "CONCURRENTLY ");
/* object name */
switch (type)
{
case REINDEX_DATABASE:
case REINDEX_SYSTEM:
appendPQExpBufferStr(&sql, fmtId(name));
break;
case REINDEX_INDEX:
case REINDEX_TABLE:
appendQualifiedRelation(&sql, name, conn, echo);
break;
case REINDEX_SCHEMA:
appendPQExpBufferStr(&sql, name);
break;
}
/* finish the query */
appendPQExpBufferChar(&sql, ';');
if (async)
{
if (echo)
printf("%s\n", sql.data);
status = PQsendQuery(conn, sql.data) == 1;
}
else
status = executeMaintenanceCommand(conn, sql.data, echo);
if (!status)
{
switch (type)
{
case REINDEX_DATABASE:
pg_log_error("reindexing of database \"%s\" failed: %s",
PQdb(conn), PQerrorMessage(conn));
break;
case REINDEX_INDEX:
pg_log_error("reindexing of index \"%s\" in database \"%s\" failed: %s",
name, PQdb(conn), PQerrorMessage(conn));
break;
case REINDEX_SCHEMA:
pg_log_error("reindexing of schema \"%s\" in database \"%s\" failed: %s",
name, PQdb(conn), PQerrorMessage(conn));
break;
case REINDEX_SYSTEM:
pg_log_error("reindexing of system catalogs on database \"%s\" failed: %s",
PQdb(conn), PQerrorMessage(conn));
break;
case REINDEX_TABLE:
pg_log_error("reindexing of table \"%s\" in database \"%s\" failed: %s",
name, PQdb(conn), PQerrorMessage(conn));
break;
}
if (!async)
{
PQfinish(conn);
exit(1);
}
}
termPQExpBuffer(&sql);
}
/*
* Prepare the list of objects to process by querying the catalogs.
*
* This function will return a SimpleStringList object containing the entire
* list of tables in the given database that should be processed by a parallel
* database-wide reindex (excluding system tables), or NULL if there's no such
* table.
*/
static SimpleStringList *
get_parallel_object_list(PGconn *conn, ReindexType type,
SimpleStringList *user_list, bool echo)
{
PQExpBufferData catalog_query;
PQExpBufferData buf;
PGresult *res;
SimpleStringList *tables;
int ntups,
i;
initPQExpBuffer(&catalog_query);
/*
* The queries here are using a safe search_path, so there's no need to
* fully qualify everything.
*/
switch (type)
{
case REINDEX_DATABASE:
Assert(user_list == NULL);
appendPQExpBuffer(&catalog_query,
"SELECT c.relname, ns.nspname\n"
" FROM pg_catalog.pg_class c\n"
" JOIN pg_catalog.pg_namespace ns"
" ON c.relnamespace = ns.oid\n"
" WHERE ns.nspname != 'pg_catalog'\n"
" AND c.relkind IN ("
CppAsString2(RELKIND_RELATION) ", "
CppAsString2(RELKIND_MATVIEW) ")\n"
" ORDER BY c.relpages DESC;");
break;
case REINDEX_SCHEMA:
{
SimpleStringListCell *cell;
bool nsp_listed = false;
Assert(user_list != NULL);
/*
* All the tables from all the listed schemas are grabbed at
* once.
*/
appendPQExpBuffer(&catalog_query,
"SELECT c.relname, ns.nspname\n"
" FROM pg_catalog.pg_class c\n"
" JOIN pg_catalog.pg_namespace ns"
" ON c.relnamespace = ns.oid\n"
" WHERE c.relkind IN ("
CppAsString2(RELKIND_RELATION) ", "
CppAsString2(RELKIND_MATVIEW) ")\n"
" AND ns.nspname IN (");
for (cell = user_list->head; cell; cell = cell->next)
{
const char *nspname = cell->val;
if (nsp_listed)
appendPQExpBuffer(&catalog_query, ", ");
else
nsp_listed = true;
appendStringLiteralConn(&catalog_query, nspname, conn);
}
appendPQExpBuffer(&catalog_query, ")\n"
" ORDER BY c.relpages DESC;");
}
break;
case REINDEX_SYSTEM:
case REINDEX_INDEX:
case REINDEX_TABLE:
Assert(false);
break;
}
res = executeQuery(conn, catalog_query.data, echo);
termPQExpBuffer(&catalog_query);
/*
* If no rows are returned, there are no matching tables, so we are done.
*/
ntups = PQntuples(res);
if (ntups == 0)
{
PQclear(res);
PQfinish(conn);
return NULL;
}
tables = pg_malloc0(sizeof(SimpleStringList));
/* Build qualified identifiers for each table */
initPQExpBuffer(&buf);
for (i = 0; i < ntups; i++)
{
appendPQExpBufferStr(&buf,
fmtQualifiedId(PQgetvalue(res, i, 1),
PQgetvalue(res, i, 0)));
simple_string_list_append(tables, buf.data);
resetPQExpBuffer(&buf);
}
termPQExpBuffer(&buf);
PQclear(res);
return tables;
}
static void
reindex_all_databases(const char *maintenance_db,
const char *host, const char *port,
const char *username, enum trivalue prompt_password,
const char *progname, bool echo, bool quiet, bool verbose,
bool concurrently, int concurrentCons)
{
2005-10-15 04:49:52 +02:00
PGconn *conn;
PGresult *result;
PQExpBufferData connstr;
2005-10-15 04:49:52 +02:00
int i;
conn = connectMaintenanceDatabase(maintenance_db, host, port, username,
prompt_password, progname, echo);
result = executeQuery(conn, "SELECT datname FROM pg_database WHERE datallowconn ORDER BY 1;", echo);
PQfinish(conn);
initPQExpBuffer(&connstr);
for (i = 0; i < PQntuples(result); i++)
{
2005-10-15 04:49:52 +02:00
char *dbname = PQgetvalue(result, i, 0);
if (!quiet)
{
printf(_("%s: reindexing database \"%s\"\n"), progname, dbname);
fflush(stdout);
}
resetPQExpBuffer(&connstr);
appendPQExpBufferStr(&connstr, "dbname=");
appendConnStrVal(&connstr, dbname);
reindex_one_database(connstr.data, REINDEX_DATABASE, NULL, host,
port, username, prompt_password,
progname, echo, verbose, concurrently,
concurrentCons);
}
termPQExpBuffer(&connstr);
PQclear(result);
}
static void
help(const char *progname)
{
printf(_("%s reindexes a PostgreSQL database.\n\n"), progname);
printf(_("Usage:\n"));
printf(_(" %s [OPTION]... [DBNAME]\n"), progname);
printf(_("\nOptions:\n"));
2005-09-30 09:58:01 +02:00
printf(_(" -a, --all reindex all databases\n"));
printf(_(" --concurrently reindex concurrently\n"));
2005-09-30 09:58:01 +02:00
printf(_(" -d, --dbname=DBNAME database to reindex\n"));
printf(_(" -e, --echo show the commands being sent to the server\n"));
printf(_(" -i, --index=INDEX recreate specific index(es) only\n"));
printf(_(" -j, --jobs=NUM use this many concurrent connections to reindex\n"));
printf(_(" -q, --quiet don't write any messages\n"));
printf(_(" -s, --system reindex system catalogs\n"));
2015-09-27 17:22:16 +02:00
printf(_(" -S, --schema=SCHEMA reindex specific schema(s) only\n"));
printf(_(" -t, --table=TABLE reindex specific table(s) only\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(_("\nConnection options:\n"));
printf(_(" -h, --host=HOSTNAME database server host or socket directory\n"));
2005-09-30 09:58:01 +02:00
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(_("\nRead the description of the SQL command REINDEX for details.\n"));
printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
printf(_("%s home page: <%s>\n"), PACKAGE_NAME, PACKAGE_URL);
}