MDEV-36536 Add option to not collect statistics for long char/varchars

This is needed to make it easy for users to automatically ignore long
char and varchars when using  ANALYZE TABLE PERSISTENT.
These fields can cause problems as they will consume
'CHARACTERS * MAX_CHARACTER_LENGTH * 2 * number_of_rows' space on disk
during analyze, which can easily be much bigger than the analyzed table.

This commit adds a new user variable, analyze_max_length, default value 4G.
Any field that is bigger than this in bytes, will be ignored by
ANALYZE TABLE PERSISTENT unless it is specified in FOR COLUMNS().

While doing this patch, I noticed that we do not skip GEOMETRY columns from
ANALYZE TABLE, like we do with BLOB. This should be fixed when merging
to the 'main' branch. At the same time we should add a resonable default
value for analyze_max_length, probably 1024, like we have for
max_sort_length.

mysql-test/main/analyze.result

@@ -453,5 +453,56 @@ SELECT * FROM t1 WHERE f LIKE '2023%';
 f
 DROP TABLE t1;
 #
+# MDEV-36536 Add option to not collect statistics for long char/varchars
+#
+select  @@session.analyze_max_length;
+@@session.analyze_max_length
+4294967295
+create table t1 (c0 char(2), c1 char(16), c2 char(64), v1 varchar(16), v2 varchar(1000), b1 blob, i1 int)
+character set utf8mb4 COLLATE utf8mb4_bin;
+insert into t1 values ("A", "A","A","A","A","A",1), ("B","B","B","B","B","B",1);
+ANALYZE TABLE t1 PERSISTENT FOR ALL;
+Table	Op	Msg_type	Msg_text
+test.t1	analyze	status	Engine-independent statistics collected
+test.t1	analyze	Warning	Engine-independent statistics are not collected for column 'b1'
+test.t1	analyze	status	OK
+select column_name from mysql.column_stats where table_name = 't1';
+column_name
+c0
+c1
+c2
+i1
+v1
+v2
+set @@session.analyze_max_length= 64;
+truncate table mysql.column_stats;
+ANALYZE TABLE t1 PERSISTENT FOR ALL;
+Table	Op	Msg_type	Msg_text
+test.t1	analyze	status	Engine-independent statistics collected
+test.t1	analyze	Warning	Engine-independent statistics are not collected for column 'c2'
+test.t1	analyze	Warning	Engine-independent statistics are not collected for column 'v2'
+test.t1	analyze	Warning	Engine-independent statistics are not collected for column 'b1'
+test.t1	analyze	status	Table is already up to date
+select column_name from mysql.column_stats where table_name = 't1';
+column_name
+c0
+c1
+i1
+v1
+truncate table mysql.column_stats;
+ANALYZE TABLE t1 PERSISTENT for COLUMNS (c0,c2,v1,v2,i1) INDEXES ALL;
+Table	Op	Msg_type	Msg_text
+test.t1	analyze	status	Engine-independent statistics collected
+test.t1	analyze	status	Table is already up to date
+select column_name from mysql.column_stats where table_name = 't1';
+column_name
+c0
+c2
+i1
+v1
+v2
+set @@session.analyze_max_length= default;
+drop table t1;
+#
 # End of 10.6 tests
 #

mysql-test/main/analyze.test

@@ -306,6 +306,26 @@ ANALYZE TABLE t1 PERSISTENT FOR ALL;
 SELECT * FROM t1 WHERE f LIKE '2023%';
 DROP TABLE t1;
 
+--echo #
+--echo # MDEV-36536 Add option to not collect statistics for long char/varchars
+--echo #
+
+select  @@session.analyze_max_length;
+create table t1 (c0 char(2), c1 char(16), c2 char(64), v1 varchar(16), v2 varchar(1000), b1 blob, i1 int)
+character set utf8mb4 COLLATE utf8mb4_bin;
+insert into t1 values ("A", "A","A","A","A","A",1), ("B","B","B","B","B","B",1);
+ANALYZE TABLE t1 PERSISTENT FOR ALL;
+select column_name from mysql.column_stats where table_name = 't1';
+set @@session.analyze_max_length= 64;
+truncate table mysql.column_stats;
+ANALYZE TABLE t1 PERSISTENT FOR ALL;
+select column_name from mysql.column_stats where table_name = 't1';
+truncate table mysql.column_stats;
+ANALYZE TABLE t1 PERSISTENT for COLUMNS (c0,c2,v1,v2,i1) INDEXES ALL;
+select column_name from mysql.column_stats where table_name = 't1';
+set @@session.analyze_max_length= default;
+drop table t1;
+
 --echo #
 --echo # End of 10.6 tests
 --echo #

mysql-test/main/mysqld--help.result

@@ -15,6 +15,10 @@ The following specify which files/extra groups are read (specified before remain
  --alter-algorithm[=name] 
  Specify the alter table algorithm. One of: DEFAULT, COPY,
  INPLACE, NOCOPY, INSTANT
+ --analyze-max-length=# 
+ Fields that require more storage than analyze_max_length
+ and are not listed in ANALYZE ... FOR COLUMNS () will
+ automatically be skipped by ANALYZE TABLE PERSISTENT
  --analyze-sample-percentage=# 
  Percentage of rows from the table ANALYZE TABLE will
  sample to collect table statistics. Set to 0 to let

mysql-test/main/mysqld--help.test

@@ -20,14 +20,14 @@ exec $MYSQLD_BOOTSTRAP_CMD --symbolic-links=0 --log-bin=foo --lower-case-table-n
 
 perl;
   # Variables which we don't want to display in the result file since
-  # their paths may vary:
+  # their paths may vary or they may use a default of 4294967295 :
   @skipvars=qw/basedir open-files-limit general-log-file log plugin-dir plugin-maturity
                log-slow-queries pid-file slow-query-log-file log-basename
                datadir slave-load-tmpdir tmpdir socket thread-pool-size
                large-files-support lower-case-file-system system-time-zone
                collation-server character-set-server log-tc-size table-cache
                table-open-cache table-open-cache-instances max-connections
-               server-uid tls-version version.*/;
+               server-uid tls-version version.* analyze-max-length/;
 
   # Plugins which may or may not be there:
   @plugins=qw/innodb archive blackhole federated partition s3

mysql-test/suite/sys_vars/r/sysvars_server_embedded.result

@@ -22,6 +22,16 @@ NUMERIC_BLOCK_SIZE	NULL
 ENUM_VALUE_LIST	DEFAULT,COPY,INPLACE,NOCOPY,INSTANT
 READ_ONLY	NO
 COMMAND_LINE_ARGUMENT	OPTIONAL
+VARIABLE_NAME	ANALYZE_MAX_LENGTH
+VARIABLE_SCOPE	SESSION
+VARIABLE_TYPE	BIGINT UNSIGNED
+VARIABLE_COMMENT	Fields which length in bytes are more than analyze_max_length are skipped by ANALYZE TABLE PERSISTENT unless explicitly listed in the FOR COLUMNS () clause
+NUMERIC_MIN_VALUE	32
+NUMERIC_MAX_VALUE	4294967295
+NUMERIC_BLOCK_SIZE	1
+ENUM_VALUE_LIST	NULL
+READ_ONLY	NO
+COMMAND_LINE_ARGUMENT	REQUIRED
 VARIABLE_NAME	ANALYZE_SAMPLE_PERCENTAGE
 VARIABLE_SCOPE	SESSION
 VARIABLE_TYPE	DOUBLE

mysql-test/suite/sys_vars/r/sysvars_server_notembedded.result

@@ -22,6 +22,16 @@ NUMERIC_BLOCK_SIZE	NULL
 ENUM_VALUE_LIST	DEFAULT,COPY,INPLACE,NOCOPY,INSTANT
 READ_ONLY	NO
 COMMAND_LINE_ARGUMENT	OPTIONAL
+VARIABLE_NAME	ANALYZE_MAX_LENGTH
+VARIABLE_SCOPE	SESSION
+VARIABLE_TYPE	BIGINT UNSIGNED
+VARIABLE_COMMENT	Fields that require more storage than analyze_max_length and are not listed in ANALYZE ... FOR COLUMNS () will automatically be skipped by ANALYZE TABLE PERSISTENT
+NUMERIC_MIN_VALUE	32
+NUMERIC_MAX_VALUE	4294967295
+NUMERIC_BLOCK_SIZE	1
+ENUM_VALUE_LIST	NULL
+READ_ONLY	NO
+COMMAND_LINE_ARGUMENT	REQUIRED
 VARIABLE_NAME	ANALYZE_SAMPLE_PERCENTAGE
 VARIABLE_SCOPE	SESSION
 VARIABLE_TYPE	DOUBLE

sql/sql_admin.cc

@@ -988,8 +988,9 @@ static bool mysql_admin_table(THD* thd, TABLE_LIST* tables,
               types here.
             */
             enum enum_field_types type= field->type();
-            if (type < MYSQL_TYPE_TINY_BLOB ||
-                type > MYSQL_TYPE_BLOB)
+            if ((type < MYSQL_TYPE_TINY_BLOB ||
+                 type > MYSQL_TYPE_BLOB) &&
+                field->field_length <= thd->variables.analyze_max_length)
             {
               field->register_field_in_read_map();
               bitmap_set_bit(&tab->has_value_set, field->field_index);

sql/sql_class.h

@@ -731,6 +731,7 @@ typedef struct system_variables
   ha_rows select_limit;
   ha_rows max_join_size;
   ha_rows expensive_subquery_limit;
+  ulong analyze_max_length;
   ulong auto_increment_increment, auto_increment_offset;
 #ifdef WITH_WSREP
   /*

sql/sys_vars.cc

@@ -445,6 +445,20 @@ static Sys_var_double Sys_analyze_sample_percentage(
        CMD_LINE(REQUIRED_ARG), VALID_RANGE(0, 100),
        DEFAULT(100));
 
+/*
+  The max length have to be UINT_MAX32 to not remove GEOMETRY fields
+  from analyze.
+*/
+
+static Sys_var_ulong Sys_analyze_max_length(
+       "analyze_max_length",
+       "Fields that require more storage than analyze_max_length and are not "
+       "listed in ANALYZE ... FOR COLUMNS () will automatically be skipped by "
+       "ANALYZE TABLE PERSISTENT",
+       SESSION_VAR(analyze_max_length),
+       CMD_LINE(REQUIRED_ARG), VALID_RANGE(32, UINT_MAX32),
+       DEFAULT(UINT_MAX32), BLOCK_SIZE(1));
+
 static Sys_var_ulong Sys_auto_increment_increment(
        "auto_increment_increment",
        "Auto-increment columns are incremented by this",