openldap/servers/slapd/back-sql/init.c

311 lines
7.6 KiB
C
Raw Normal View History

2000-03-17 03:08:22 +08:00
/*
* Copyright 1999, Dmitry Kovalev <mit@openldap.org>, All rights reserved.
2000-03-17 03:08:22 +08:00
*
* Redistribution and use in source and binary forms are permitted only
* as authorized by the OpenLDAP Public License. A copy of this
* license is available at http://www.OpenLDAP.org/license.html or
* in file LICENSE in the top-level directory of the distribution.
*/
#include "portable.h"
#ifdef SLAPD_SQL
2000-03-17 03:08:22 +08:00
#include <stdio.h>
#include <sys/types.h>
#include "slap.h"
#include "ldap_pvt.h"
2000-03-17 03:08:22 +08:00
#include "back-sql.h"
#include "sql-wrap.h"
#include "schema-map.h"
#include "util.h"
#ifdef SLAPD_SQL_DYNAMIC
int
backsql_LTX_init_module(
int argc,
char *argv[] )
{
BackendInfo bi;
2000-03-17 03:08:22 +08:00
memset( &bi, '\0', sizeof( bi ) );
bi.bi_type = "sql";
bi.bi_init = backbacksql_initialize;
2000-03-17 03:08:22 +08:00
backend_add( &bi );
return 0;
2000-03-17 03:08:22 +08:00
}
#endif /* SLAPD_SHELL_DYNAMIC */
int
sql_back_initialize(
BackendInfo *bi )
2000-03-17 03:08:22 +08:00
{
Debug( LDAP_DEBUG_TRACE,"==>backsql_initialize()\n", 0, 0, 0 );
2000-03-17 03:08:22 +08:00
bi->bi_open = 0;
bi->bi_config = 0;
bi->bi_close = 0;
bi->bi_destroy = 0;
bi->bi_db_init = backsql_db_init;
bi->bi_db_config = backsql_db_config;
bi->bi_db_open = backsql_db_open;
bi->bi_db_close = backsql_db_close;
bi->bi_db_destroy = backsql_db_destroy;
#ifdef BACKSQL_ALL_DONE
bi->bi_op_abandon = backsql_abandon;
bi->bi_op_compare = backsql_compare;
#else
bi->bi_op_abandon = 0;
bi->bi_op_compare = 0;
#endif
bi->bi_op_bind = backsql_bind;
bi->bi_op_unbind = backsql_unbind;
bi->bi_op_search = backsql_search;
bi->bi_op_modify = backsql_modify;
bi->bi_op_modrdn = backsql_modrdn;
bi->bi_op_add = backsql_add;
bi->bi_op_delete = backsql_delete;
bi->bi_acl_group = 0;
2000-06-22 01:41:49 +08:00
bi->bi_acl_attribute = 0;
bi->bi_chk_referrals = 0;
2000-03-17 03:08:22 +08:00
bi->bi_connection_init = 0;
bi->bi_connection_destroy = backsql_connection_destroy;
2000-03-17 03:08:22 +08:00
Debug( LDAP_DEBUG_TRACE,"<==backsql_initialize()\n", 0, 0, 0 );
2000-03-17 03:08:22 +08:00
return 0;
}
int
backsql_destroy(
BackendInfo *bi )
2000-03-17 03:08:22 +08:00
{
Debug( LDAP_DEBUG_TRACE, "==>backsql_destroy()\n", 0, 0, 0 );
Debug( LDAP_DEBUG_TRACE, "<==backsql_destroy()\n", 0, 0, 0 );
return 0;
2000-03-17 03:08:22 +08:00
}
int
backsql_db_init(
BackendDB *bd )
2000-03-17 03:08:22 +08:00
{
backsql_info *si;
2000-03-17 03:08:22 +08:00
Debug( LDAP_DEBUG_TRACE, "==>backsql_db_init()\n", 0, 0, 0 );
si = (backsql_info *)ch_calloc( 1, sizeof( backsql_info ) );
ldap_pvt_thread_mutex_init( &si->dbconn_mutex );
ldap_pvt_thread_mutex_init( &si->schema_mutex );
backsql_init_db_env( si );
si->has_ldapinfo_dn_ru = -1;
bd->be_private = si;
Debug( LDAP_DEBUG_TRACE, "<==backsql_db_init()\n", 0, 0, 0 );
return 0;
2000-03-17 03:08:22 +08:00
}
int
backsql_db_destroy(
BackendDB *bd )
2000-03-17 03:08:22 +08:00
{
backsql_info *si = (backsql_info*)bd->be_private;
2000-03-17 03:08:22 +08:00
Debug( LDAP_DEBUG_TRACE, "==>backsql_db_destroy()\n", 0, 0, 0 );
ldap_pvt_thread_mutex_lock( &si->dbconn_mutex );
backsql_free_db_env( si );
ldap_pvt_thread_mutex_unlock( &si->dbconn_mutex );
ldap_pvt_thread_mutex_lock( &si->schema_mutex );
backsql_destroy_schema_map( si );
ldap_pvt_thread_mutex_unlock( &si->schema_mutex );
ldap_pvt_thread_mutex_destroy( &si->schema_mutex );
ldap_pvt_thread_mutex_destroy( &si->dbconn_mutex );
free( si->dbname );
free( si->dbuser );
if ( si->dbpasswd ) {
free( si->dbpasswd );
}
if ( si->dbhost ) {
free( si->dbhost );
}
if ( si->upper_func ) {
free( si->upper_func );
}
free( si->subtree_cond );
free( si->oc_query );
free( si->at_query );
free( si->insentry_query );
free( si->delentry_query );
free( si );
Debug( LDAP_DEBUG_TRACE, "<==backsql_db_destroy()\n", 0, 0, 0 );
return 0;
2000-03-17 03:08:22 +08:00
}
int
backsql_db_open(
BackendDB *bd )
2000-03-17 03:08:22 +08:00
{
backsql_info *si = (backsql_info*)bd->be_private;
Connection tmp;
SQLHDBC dbh;
int idq_len;
struct berval bv;
Debug( LDAP_DEBUG_TRACE, "==>backsql_db_open(): "
"testing RDBMS connection\n", 0, 0, 0 );
if ( si->dbname == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"datasource name not specified "
"(use dbname directive in slapd.conf)\n", 0, 0, 0 );
return 1;
}
if ( si->dbuser == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"user name not specified "
"(use dbuser directive in slapd.conf)\n", 0, 0, 0 );
return 1;
}
if ( si->subtree_cond == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"subtree search SQL condition not specified "
"(use subtree_cond directive in slapd.conf)\n",
0, 0, 0);
if ( si->upper_func ) {
struct berval bv = { 0, NULL };
int len = 0;
backsql_strcat( &bv, &len, si->upper_func,
backsql_def_upper_subtree_cond, NULL );
si->subtree_cond = bv.bv_val;
} else {
si->subtree_cond = ch_strdup( backsql_def_subtree_cond );
}
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"setting '%s' as default\n",
si->subtree_cond, 0, 0 );
A big bunch of improvements, contributed by Sam Drake and Raj Damani. Summary of changes is cited below. The patch still needs some cosmetic changes to be made, but is ready for testing. -----Original Message----- From: Sam Drake [mailto:drake@timesten.com] Sent: Saturday, April 07, 2001 10:40 PM To: 'mitya@seismic.ru' Cc: openldap-devel@OpenLDAP.org Subject: RE: Slapd frontend performance issues FYI, here is a short description of the changes I made. I'll package up the changes asap, but it may take a couple of days. The performance numbers quoted in this report were seen at my location with a 100,000 object database ... the slower numbers I mentioned earlier were reported by a customer with a 1,000,000 object database. I also can't explain the very poor performance I saw with OpenLDAP and LDBM with a 100,000 object database. ...Sam Drake / TimesTen Performance Software ---------- Work Performed OpenLDAP 2.0.9, including back-sql, was built successfully on Solaris 8 using gcc. The LDAP server itself, slapd, passed all tests bundled with OpenLDAP. OpenLDAP was built using Sleepycat LDBM release 3.1.17 as the "native" storage manager. The experimental back-sql facility in slapd was also built successfully. It was built using Oracle release 8.1.7 and the Oracle ODBC driver and ODBC Driver Manager from Merant. Rudimentary testing was performed with the data and examples provided with back-sql, and back-sql was found to be functional. Slapd and back-sql were then tested with TimesTen, using TimesTen 4.1.1. Back-sql was not immediately functional with TimesTen due to a number of SQL limitations in the TimesTen product. Functional issues encountered were: 1. Back-sql issued SELECT statements including the construct, "UPPER(?)". While TimesTen supports UPPER, it does not support the use of parameters as input to builtin functions. Back-sql was modified to convert the parameter to upper case prior to giving it to the underlying database ... a change that is appropriate for all databases. 2. Back-sql issued SELECT statements using the SQL CONCAT function. TimesTen does not support this function. Back-sql was modified to concatentate the necessary strings itself (in "C" code) prior to passing the parameters to SQL. This change is also appropriate for all databases, not just TimesTen. Once these two issues were resolved, back-sql could successfully process LDAP searches using the sample data and examples provided with back-sql. While performance was not measured at this point, numerous serious performance problems were observed with the back-sql code and the generated SQL. In particular: 1. In the process of implementing an LDAP search, back-sql will generate and execute a SQL query for all object classes stored in back-sql. During the source of generating each SQL query, it is common for back-sql to determine that a particular object class can not possibly have any members satisfying the search. For example, this can occur if the query searches an attribute of the LDAP object that does not exist in the SQL schema. In this case, back-sql would generate and issue the SQL query anyway, including a clause such as "WHERE 1=0" in the generated SELECT. The overhead of parsing, optimizing and executing the query is non-trivial, and the answer (the empty set) is known in advance. Solution: Back-sql was modified to stop executing a SQL query when it can be predetermined that the query will return no rows. 2. Searches in LDAP are fundamentally case-insensitive ("abc" is equal to "aBc"). However, in SQL this is not normally the case. Back-sql thus generated SQL SELECT statements including clauses of the form, "WHERE UPPER(attribute) = 'JOE'". Even if an index is defined on the attribute in the relational database, the index can not be used to satisfy the query, as the index is case sensitive. The relational database then is forced to scan all rows in the table in order to satisfy the query ... an expensive and non-scalable proposition. Solution: Back-sql was modified to allow the schema designer to add additional "upper cased" columns to the SQL schema. These columns, if present, contain an upper cased version of the "standard" field, and will be used preferentially for searching. Such columns can be provided for all searchable columns, some columns, or no columns. An application using database "triggers" or similar mechanisms can automatically maintain these upper cased columns when the standard column is changed. 3. In order to implement the hierarchical nature of LDAP object hierarchies, OpenLDAP uses suffix searches in SQL. For example, to find all objects in the subtree "o=TimesTen,c=us", a SQL SELECT statement of the form, "WHERE UPPER(dn) LIKE '%O=TIMESTEN,C=US'" would be employed. Aside from the UPPER issue discussed above, a second performance problem in this query is the use of suffix search. In TimesTen (and most relational databases), indexes can be used to optimize exact-match searches and prefix searches. However, suffix searches must be performed by scanning every row in the table ... an expensive and non-scalable proposition. Solution: Back-sql was modified to optionally add a new "dn_ru" column to the ldap_entries table. This additional column, if present, contains a byte-reversed and upper cased version of the DN. This allows back-sql to generate indexable prefix searches. This column is also easily maintained automatically through the use of triggers. Results A simple database schema was generated holding the LDAP objects and attributes specified by our customer. An application was written to generate test databases. Both TimesTen and Oracle 8.1.7 were populated with 100,000 entry databases. Load Times Using "slapadd" followed by "slapindex", loading and indexing 100,000 entries in an LDBM database ran for 19 minutes 10 seconds. Using a C++ application that used ODBC, loading 100,000 entries into a disk based RDBMS took 17 minutes 53 seconds. Using a C++ application that used ODBC, loading 100,000 entries into TimesTen took 1 minute 40 seconds. Search Times The command, "timex timesearch.sh '(cn=fname210100*)'" was used to test search times. This command issues the same LDAP search 4000 times over a single LDAP connection. Both the client and server (slapd) were run on the same machine. With TimesTen as the database, 4000 queries took 14.93 seconds, for a rate of 267.9 per second. With a disk based RDBMS as the database, 4000 queries took 77.79 seconds, for a rate of 51.42 per second. With LDBM as the database, 1 query takes 76 seconds, or 0.076 per second. Something is clearly broken.
2001-08-03 01:28:59 +08:00
}
if ( si->oc_query == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"objectclass mapping SQL statement not specified "
"(use oc_query directive in slapd.conf)\n", 0, 0, 0 );
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"setting '%s' by default\n",
backsql_def_oc_query, 0, 0 );
si->oc_query = ch_strdup( backsql_def_oc_query );
}
if ( si->at_query == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"attribute mapping SQL statement not specified "
"(use at_query directive in slapd.conf)\n",
0, 0, 0 );
Debug(LDAP_DEBUG_TRACE, "backsql_db_open(): "
"setting '%s' by default\n",
backsql_def_at_query, 0, 0 );
si->at_query = ch_strdup( backsql_def_at_query );
}
if ( si->insentry_query == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"entry insertion SQL statement not specified "
"(use insentry_query directive in slapd.conf)\n",
0, 0, 0 );
Debug(LDAP_DEBUG_TRACE, "backsql_db_open(): "
"setting '%s' by default\n",
backsql_def_insentry_query, 0, 0 );
si->insentry_query = ch_strdup( backsql_def_insentry_query );
}
if ( si->delentry_query == NULL ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"entry deletion SQL statement not specified "
"(use delentry_query directive in slapd.conf)\n",
0, 0, 0 );
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"setting '%s' by default\n",
backsql_def_delentry_query, 0, 0 );
si->delentry_query = ch_strdup( backsql_def_delentry_query );
}
tmp.c_connid =- 1;
if ( backsql_get_db_conn( bd, &tmp, &dbh ) != LDAP_SUCCESS ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"connection failed, exiting\n", 0, 0, 0 );
return 1;
}
si->id_query = NULL;
idq_len = 0;
bv.bv_val = NULL;
bv.bv_len = 0;
if ( si->upper_func == NULL ) {
backsql_strcat( &bv, &idq_len, backsql_id_query,
"dn=?", NULL );
} else {
if ( si->has_ldapinfo_dn_ru ) {
backsql_strcat( &bv, &idq_len, backsql_id_query,
"dn_ru=?", NULL );
} else {
if ( si->isTimesTen ) {
backsql_strcat( &bv, &idq_len,
backsql_id_query,
si->upper_func, "(dn)=?",
NULL );
} else {
backsql_strcat( &bv, &idq_len,
backsql_id_query,
si->upper_func, "(dn)=",
si->upper_func, "(?)", NULL );
}
}
}
si->id_query = bv.bv_val;
A big bunch of improvements, contributed by Sam Drake and Raj Damani. Summary of changes is cited below. The patch still needs some cosmetic changes to be made, but is ready for testing. -----Original Message----- From: Sam Drake [mailto:drake@timesten.com] Sent: Saturday, April 07, 2001 10:40 PM To: 'mitya@seismic.ru' Cc: openldap-devel@OpenLDAP.org Subject: RE: Slapd frontend performance issues FYI, here is a short description of the changes I made. I'll package up the changes asap, but it may take a couple of days. The performance numbers quoted in this report were seen at my location with a 100,000 object database ... the slower numbers I mentioned earlier were reported by a customer with a 1,000,000 object database. I also can't explain the very poor performance I saw with OpenLDAP and LDBM with a 100,000 object database. ...Sam Drake / TimesTen Performance Software ---------- Work Performed OpenLDAP 2.0.9, including back-sql, was built successfully on Solaris 8 using gcc. The LDAP server itself, slapd, passed all tests bundled with OpenLDAP. OpenLDAP was built using Sleepycat LDBM release 3.1.17 as the "native" storage manager. The experimental back-sql facility in slapd was also built successfully. It was built using Oracle release 8.1.7 and the Oracle ODBC driver and ODBC Driver Manager from Merant. Rudimentary testing was performed with the data and examples provided with back-sql, and back-sql was found to be functional. Slapd and back-sql were then tested with TimesTen, using TimesTen 4.1.1. Back-sql was not immediately functional with TimesTen due to a number of SQL limitations in the TimesTen product. Functional issues encountered were: 1. Back-sql issued SELECT statements including the construct, "UPPER(?)". While TimesTen supports UPPER, it does not support the use of parameters as input to builtin functions. Back-sql was modified to convert the parameter to upper case prior to giving it to the underlying database ... a change that is appropriate for all databases. 2. Back-sql issued SELECT statements using the SQL CONCAT function. TimesTen does not support this function. Back-sql was modified to concatentate the necessary strings itself (in "C" code) prior to passing the parameters to SQL. This change is also appropriate for all databases, not just TimesTen. Once these two issues were resolved, back-sql could successfully process LDAP searches using the sample data and examples provided with back-sql. While performance was not measured at this point, numerous serious performance problems were observed with the back-sql code and the generated SQL. In particular: 1. In the process of implementing an LDAP search, back-sql will generate and execute a SQL query for all object classes stored in back-sql. During the source of generating each SQL query, it is common for back-sql to determine that a particular object class can not possibly have any members satisfying the search. For example, this can occur if the query searches an attribute of the LDAP object that does not exist in the SQL schema. In this case, back-sql would generate and issue the SQL query anyway, including a clause such as "WHERE 1=0" in the generated SELECT. The overhead of parsing, optimizing and executing the query is non-trivial, and the answer (the empty set) is known in advance. Solution: Back-sql was modified to stop executing a SQL query when it can be predetermined that the query will return no rows. 2. Searches in LDAP are fundamentally case-insensitive ("abc" is equal to "aBc"). However, in SQL this is not normally the case. Back-sql thus generated SQL SELECT statements including clauses of the form, "WHERE UPPER(attribute) = 'JOE'". Even if an index is defined on the attribute in the relational database, the index can not be used to satisfy the query, as the index is case sensitive. The relational database then is forced to scan all rows in the table in order to satisfy the query ... an expensive and non-scalable proposition. Solution: Back-sql was modified to allow the schema designer to add additional "upper cased" columns to the SQL schema. These columns, if present, contain an upper cased version of the "standard" field, and will be used preferentially for searching. Such columns can be provided for all searchable columns, some columns, or no columns. An application using database "triggers" or similar mechanisms can automatically maintain these upper cased columns when the standard column is changed. 3. In order to implement the hierarchical nature of LDAP object hierarchies, OpenLDAP uses suffix searches in SQL. For example, to find all objects in the subtree "o=TimesTen,c=us", a SQL SELECT statement of the form, "WHERE UPPER(dn) LIKE '%O=TIMESTEN,C=US'" would be employed. Aside from the UPPER issue discussed above, a second performance problem in this query is the use of suffix search. In TimesTen (and most relational databases), indexes can be used to optimize exact-match searches and prefix searches. However, suffix searches must be performed by scanning every row in the table ... an expensive and non-scalable proposition. Solution: Back-sql was modified to optionally add a new "dn_ru" column to the ldap_entries table. This additional column, if present, contains a byte-reversed and upper cased version of the DN. This allows back-sql to generate indexable prefix searches. This column is also easily maintained automatically through the use of triggers. Results A simple database schema was generated holding the LDAP objects and attributes specified by our customer. An application was written to generate test databases. Both TimesTen and Oracle 8.1.7 were populated with 100,000 entry databases. Load Times Using "slapadd" followed by "slapindex", loading and indexing 100,000 entries in an LDBM database ran for 19 minutes 10 seconds. Using a C++ application that used ODBC, loading 100,000 entries into a disk based RDBMS took 17 minutes 53 seconds. Using a C++ application that used ODBC, loading 100,000 entries into TimesTen took 1 minute 40 seconds. Search Times The command, "timex timesearch.sh '(cn=fname210100*)'" was used to test search times. This command issues the same LDAP search 4000 times over a single LDAP connection. Both the client and server (slapd) were run on the same machine. With TimesTen as the database, 4000 queries took 14.93 seconds, for a rate of 267.9 per second. With a disk based RDBMS as the database, 4000 queries took 77.79 seconds, for a rate of 51.42 per second. With LDBM as the database, 1 query takes 76 seconds, or 0.076 per second. Something is clearly broken.
2001-08-03 01:28:59 +08:00
backsql_free_db_conn( bd, &tmp );
if ( !si->schema_loaded ) {
Debug( LDAP_DEBUG_TRACE, "backsql_db_open(): "
"test failed, schema map not loaded - exiting\n",
0, 0, 0 );
return 1;
}
Debug( LDAP_DEBUG_TRACE, "<==backsql_db_open(): "
"test succeeded, schema map loaded\n", 0, 0, 0 );
return 0;
2000-03-17 03:08:22 +08:00
}
int
backsql_db_close(
BackendDB *bd )
2000-03-17 03:08:22 +08:00
{
Debug( LDAP_DEBUG_TRACE, "==>backsql_db_close()\n", 0, 0, 0 );
Debug( LDAP_DEBUG_TRACE, "<==backsql_db_close()\n", 0, 0, 0 );
return 0;
}
int
backsql_connection_destroy(
BackendDB *be,
Connection *conn )
{
Debug( LDAP_DEBUG_TRACE, "==>backsql_connection_destroy()\n", 0, 0, 0 );
backsql_free_db_conn( be, conn );
Debug( LDAP_DEBUG_TRACE, "<==backsql_connection_destroy()\n", 0, 0, 0 );
return 0;
}
#endif /* SLAPD_SQL */