367 lines
9.7 KiB
Go
Raw Normal View History

2020-10-05 19:09:26 +02:00
package sql
import (
2020-10-21 19:00:41 +02:00
"context"
2020-10-05 19:09:26 +02:00
"database/sql"
2020-11-23 19:31:12 +01:00
"encoding/json"
2020-10-05 19:09:26 +02:00
"errors"
"fmt"
"strconv"
2020-10-05 19:09:26 +02:00
"strings"
"github.com/zitadel/logging"
"github.com/zitadel/zitadel/internal/api/call"
"github.com/zitadel/zitadel/internal/database"
"github.com/zitadel/zitadel/internal/database/dialect"
"github.com/zitadel/zitadel/internal/eventstore"
"github.com/zitadel/zitadel/internal/eventstore/repository"
"github.com/zitadel/zitadel/internal/zerrors"
2020-10-05 19:09:26 +02:00
)
2020-10-06 21:28:09 +02:00
type querier interface {
columnName(field repository.Field, useV1 bool) string
2020-10-05 19:09:26 +02:00
operation(repository.Operation) string
conditionFormat(repository.Operation) string
placeholder(query string) string
eventQuery(useV1 bool) string
maxSequenceQuery(useV1 bool) string
instanceIDsQuery(useV1 bool) string
Client() *database.DB
orderByEventSequence(desc, shouldOrderBySequence, useV1 bool) string
dialect.Database
2020-10-05 19:09:26 +02:00
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
type scan func(dest ...interface{}) error
2020-10-05 19:09:26 +02:00
type tx struct {
*sql.Tx
}
func (t *tx) QueryContext(ctx context.Context, scan func(rows *sql.Rows) error, query string, args ...any) error {
rows, err := t.Tx.QueryContext(ctx, query, args...)
if err != nil {
return err
}
defer func() {
closeErr := rows.Close()
logging.OnError(closeErr).Info("rows.Close failed")
}()
if err = scan(rows); err != nil {
return err
}
return rows.Err()
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func query(ctx context.Context, criteria querier, searchQuery *eventstore.SearchQueryBuilder, dest interface{}, useV1 bool) error {
q, err := repository.QueryFromBuilder(searchQuery)
if err != nil {
return err
}
query, rowScanner := prepareColumns(criteria, q.Columns, useV1)
where, values := prepareConditions(criteria, q, useV1)
2020-10-05 19:09:26 +02:00
if where == "" || query == "" {
return zerrors.ThrowInvalidArgument(nil, "SQL-rWeBw", "invalid query factory")
2020-10-05 19:09:26 +02:00
}
if q.Tx == nil {
if travel := prepareTimeTravel(ctx, criteria, q.AllowTimeTravel); travel != "" {
query += travel
}
}
2020-10-05 19:09:26 +02:00
query += where
// instead of using the max function of the database (which doesn't work for postgres)
// we select the most recent row
if q.Columns == eventstore.ColumnsMaxSequence {
q.Limit = 1
q.Desc = true
}
// if there is only one subquery we can optimize the query ordering by ordering by sequence
var shouldOrderBySequence bool
if len(q.SubQueries) == 1 {
for _, filter := range q.SubQueries[0] {
if filter.Field == repository.FieldAggregateID {
shouldOrderBySequence = filter.Operation == repository.OperationEquals
}
}
}
switch q.Columns {
case eventstore.ColumnsEvent,
eventstore.ColumnsMaxSequence:
query += criteria.orderByEventSequence(q.Desc, shouldOrderBySequence, useV1)
2020-10-05 19:09:26 +02:00
}
if q.Limit > 0 {
values = append(values, q.Limit)
2020-10-05 19:09:26 +02:00
query += " LIMIT ?"
}
if q.Offset > 0 {
values = append(values, q.Offset)
query += " OFFSET ?"
}
if q.LockRows {
query += " FOR UPDATE"
switch q.LockOption {
case eventstore.LockOptionWait: // default behavior
case eventstore.LockOptionNoWait:
query += " NOWAIT"
case eventstore.LockOptionSkipLocked:
query += " SKIP LOCKED"
}
}
2020-10-05 19:09:26 +02:00
query = criteria.placeholder(query)
var contextQuerier interface {
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
QueryContext(context.Context, func(rows *sql.Rows) error, string, ...interface{}) error
}
contextQuerier = criteria.Client()
if q.Tx != nil {
contextQuerier = &tx{Tx: q.Tx}
}
err = contextQuerier.QueryContext(ctx,
func(rows *sql.Rows) error {
for rows.Next() {
err := rowScanner(rows.Scan, dest)
if err != nil {
return err
}
}
return nil
}, query, values...)
2020-10-21 19:00:41 +02:00
if err != nil {
logging.New().WithError(err).Info("query failed")
return zerrors.ThrowInternal(err, "SQL-KyeAx", "unable to filter events")
2020-10-21 19:00:41 +02:00
}
return nil
2020-10-05 19:09:26 +02:00
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func prepareColumns(criteria querier, columns eventstore.Columns, useV1 bool) (string, func(s scan, dest interface{}) error) {
2020-10-05 19:09:26 +02:00
switch columns {
case eventstore.ColumnsMaxSequence:
return criteria.maxSequenceQuery(useV1), maxSequenceScanner
case eventstore.ColumnsInstanceIDs:
return criteria.instanceIDsQuery(useV1), instanceIDsScanner
case eventstore.ColumnsEvent:
return criteria.eventQuery(useV1), eventsScanner(useV1)
2020-10-05 19:09:26 +02:00
default:
return "", nil
}
}
func prepareTimeTravel(ctx context.Context, criteria querier, allow bool) string {
if !allow {
return ""
}
took := call.Took(ctx)
return criteria.Timetravel(took)
}
2020-10-05 19:09:26 +02:00
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func maxSequenceScanner(row scan, dest interface{}) (err error) {
position, ok := dest.(*sql.NullFloat64)
2020-10-05 19:09:26 +02:00
if !ok {
return zerrors.ThrowInvalidArgumentf(nil, "SQL-NBjA9", "type must be sql.NullInt64 got: %T", dest)
2020-10-05 19:09:26 +02:00
}
err = row(position)
2020-10-05 19:09:26 +02:00
if err == nil || errors.Is(err, sql.ErrNoRows) {
return nil
}
return zerrors.ThrowInternal(err, "SQL-bN5xg", "something went wrong")
2020-10-05 19:09:26 +02:00
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func instanceIDsScanner(scanner scan, dest interface{}) (err error) {
ids, ok := dest.(*[]string)
if !ok {
return zerrors.ThrowInvalidArgument(nil, "SQL-Begh2", "type must be an array of string")
}
var id string
err = scanner(&id)
if err != nil {
logging.WithError(err).Warn("unable to scan row")
return zerrors.ThrowInternal(err, "SQL-DEFGe", "unable to scan row")
}
*ids = append(*ids, id)
return nil
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func eventsScanner(useV1 bool) func(scanner scan, dest interface{}) (err error) {
return func(scanner scan, dest interface{}) (err error) {
reduce, ok := dest.(eventstore.Reducer)
if !ok {
return zerrors.ThrowInvalidArgumentf(nil, "SQL-4GP6F", "events scanner: invalid type %T", dest)
}
event := new(repository.Event)
position := new(sql.NullFloat64)
if useV1 {
err = scanner(
&event.CreationDate,
&event.Typ,
&event.Seq,
&event.Data,
&event.EditorUser,
&event.ResourceOwner,
&event.InstanceID,
&event.AggregateType,
&event.AggregateID,
&event.Version,
)
} else {
var revision uint8
err = scanner(
&event.CreationDate,
&event.Typ,
&event.Seq,
position,
&event.Data,
&event.EditorUser,
&event.ResourceOwner,
&event.InstanceID,
&event.AggregateType,
&event.AggregateID,
&revision,
)
event.Version = eventstore.Version("v" + strconv.Itoa(int(revision)))
}
2020-10-05 19:09:26 +02:00
if err != nil {
logging.New().WithError(err).Warn("unable to scan row")
return zerrors.ThrowInternal(err, "SQL-M0dsf", "unable to scan row")
}
event.Pos = position.Float64
return reduce(event)
}
2020-10-05 19:09:26 +02:00
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
func prepareConditions(criteria querier, query *repository.SearchQuery, useV1 bool) (_ string, args []any) {
clauses, args := prepareQuery(criteria, useV1, query.InstanceID, query.InstanceIDs, query.ExcludedInstances)
if clauses != "" && len(query.SubQueries) > 0 {
clauses += " AND "
}
subClauses := make([]string, len(query.SubQueries))
for i, filters := range query.SubQueries {
var subArgs []any
subClauses[i], subArgs = prepareQuery(criteria, useV1, filters...)
// an error is thrown in [query]
if subClauses[i] == "" {
return "", nil
}
if len(query.SubQueries) > 1 && len(subArgs) > 1 {
subClauses[i] = "(" + subClauses[i] + ")"
}
args = append(args, subArgs...)
}
if len(subClauses) == 1 {
clauses += subClauses[0]
} else if len(subClauses) > 1 {
clauses += "(" + strings.Join(subClauses, " OR ") + ")"
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
additionalClauses, additionalArgs := prepareQuery(criteria, useV1,
query.Position,
query.Owner,
query.Sequence,
query.CreatedAfter,
query.CreatedBefore,
query.Creator,
)
if additionalClauses != "" {
if clauses != "" {
clauses += " AND "
}
clauses += additionalClauses
args = append(args, additionalArgs...)
}
2020-10-05 19:09:26 +02:00
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
excludeAggregateIDs := query.ExcludeAggregateIDs
if len(excludeAggregateIDs) > 0 {
excludeAggregateIDs = append(excludeAggregateIDs, query.InstanceID, query.InstanceIDs, query.Position, query.CreatedAfter, query.CreatedBefore)
}
excludeAggregateIDsClauses, excludeAggregateIDsArgs := prepareQuery(criteria, useV1, excludeAggregateIDs...)
if excludeAggregateIDsClauses != "" {
feat(eventstore): exclude aggregate IDs when event_type occurred (#8940) # Which Problems Are Solved For truly event-based notification handler, we need to be able to filter out events of aggregates which are already handled. For example when an event like `notify.success` or `notify.failed` was created on an aggregate, we no longer require events from that aggregate ID. # How the Problems Are Solved Extend the query builder to use a `NOT IN` clause which excludes aggregate IDs when they have certain events for a certain aggregate type. For optimization and proper index usages, certain filters are inherited from the parent query, such as: - Instance ID - Instance IDs - Position offset This is a prettified query as used by the unit tests: ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = $1 AND aggregate_type = $2 AND event_type = $3 AND "position" > $4 AND aggregate_id NOT IN ( SELECT aggregate_id FROM eventstore.events2 WHERE aggregate_type = $5 AND event_type = ANY($6) AND instance_id = $7 AND "position" > $8 ) ORDER BY "position" DESC, in_tx_order DESC LIMIT $9 ``` I used this query to run it against the `oidc_session` aggregate looking for added events, excluding aggregates where a token was revoked, against a recent position. It fully used index scans: <details> ```json [ { "Plan": { "Node Type": "Index Scan", "Parallel Aware": false, "Async Capable": false, "Scan Direction": "Forward", "Index Name": "es_projection", "Relation Name": "events2", "Alias": "events2", "Actual Rows": 2, "Actual Loops": 1, "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.added'::text) AND (\"position\" > 1731582100.784168))", "Rows Removed by Index Recheck": 0, "Filter": "(NOT (hashed SubPlan 1))", "Rows Removed by Filter": 1, "Plans": [ { "Node Type": "Index Scan", "Parent Relationship": "SubPlan", "Subplan Name": "SubPlan 1", "Parallel Aware": false, "Async Capable": false, "Scan Direction": "Forward", "Index Name": "es_projection", "Relation Name": "events2", "Alias": "events2_1", "Actual Rows": 1, "Actual Loops": 1, "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.access_token.revoked'::text) AND (\"position\" > 1731582100.784168))", "Rows Removed by Index Recheck": 0 } ] }, "Triggers": [ ] } ] ``` </details> # Additional Changes - None # Additional Context - Related to https://github.com/zitadel/zitadel/issues/8931 --------- Co-authored-by: adlerhurst <silvan.reusser@gmail.com>
2024-11-25 17:25:11 +02:00
if clauses != "" {
clauses += " AND "
}
fix(perf): simplify eventstore queries by removing or in projection handlers (#9530) # Which Problems Are Solved [A recent performance enhancement]((https://github.com/zitadel/zitadel/pull/9497)) aimed at optimizing event store queries, specifically those involving multiple aggregate type filters, has successfully improved index utilization. While the query planner now correctly selects relevant indexes, it employs [bitmap index scans](https://www.postgresql.org/docs/current/indexes-bitmap-scans.html) to retrieve data. This approach, while beneficial in many scenarios, introduces a potential I/O bottleneck. The bitmap index scan first identifies the required database blocks and then utilizes a bitmap to access the corresponding rows from the table's heap. This subsequent "bitmap heap scan" can result in significant I/O overhead, particularly when queries return a substantial number of rows across numerous data pages. ## Impact: Under heavy load or with queries filtering for a wide range of events across multiple aggregate types, this increased I/O activity may lead to: - Increased query latency. - Elevated disk utilization. - Potential performance degradation of the event store and dependent systems. # How the Problems Are Solved To address this I/O bottleneck and further optimize query performance, the projection handler has been modified. Instead of employing multiple OR clauses for each aggregate type, the aggregate and event type filters are now combined using IN ARRAY filters. Technical Details: This change allows the PostgreSQL query planner to leverage [index-only scans](https://www.postgresql.org/docs/current/indexes-index-only-scans.html). By utilizing IN ARRAY filters, the database can efficiently retrieve the necessary data directly from the index, eliminating the need to access the table's heap. This results in: * Reduced I/O: Index-only scans significantly minimize disk I/O operations, as the database avoids reading data pages from the main table. * Improved Query Performance: By reducing I/O, query execution times are substantially improved, leading to lower latency. # Additional Changes - rollback of https://github.com/zitadel/zitadel/pull/9497 # Additional Information ## Query Plan of previous query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND ( ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'project' AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ]) ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'org' AND event_type = 'org.removed' ) OR ( instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = 'instance' AND event_type = 'instance.removed' ) ) AND "position" > 1741600905.3495 AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=120.08..120.09 rows=7 width=361) (actual time=2.167..2.172 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.813..1.815 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.803..1.805 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.016..0.021 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.781..1.781 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 49 -> Sort (cost=117.31..117.33 rows=8 width=361) (actual time=2.167..2.168 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Bitmap Heap Scan on eventstore.events2 (cost=84.92..117.19 rows=8 width=361) (actual time=2.088..2.089 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Recheck Cond: (((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) OR ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1))) -> BitmapOr (cost=84.88..84.88 rows=8 width=0) (actual time=2.080..2.081 rows=0 loops=1) -> Bitmap Index Scan on es_projection (cost=0.00..75.44 rows=8 width=0) (actual time=2.016..2.017 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'project'::text) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.016..0.016 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'org'::text) AND (events2.event_type = 'org.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) -> Bitmap Index Scan on es_projection (cost=0.00..4.71 rows=1 width=0) (actual time=0.045..0.045 rows=0 loops=1) Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = 'instance'::text) AND (events2.event_type = 'instance.removed'::text) AND (events2."position" > <POSITION>) AND (events2."position" > 1741600905.3495) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: 3194938266011254479 Planning Time: 1.295 ms Execution Time: 2.832 ms ``` ## Query Plan of new query ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = '<INSTANCE_ID>' AND "position" > <POSITION> AND aggregate_type = ANY(ARRAY['project', 'instance', 'org']) AND event_type = ANY(ARRAY[ 'project.application.added' ,'project.application.changed' ,'project.application.deactivated' ,'project.application.reactivated' ,'project.application.removed' ,'project.removed' ,'project.application.config.api.added' ,'project.application.config.api.changed' ,'project.application.config.api.secret.changed' ,'project.application.config.api.secret.updated' ,'project.application.config.oidc.added' ,'project.application.config.oidc.changed' ,'project.application.config.oidc.secret.changed' ,'project.application.config.oidc.secret.updated' ,'project.application.config.saml.added' ,'project.application.config.saml.changed' ,'org.removed' ,'instance.removed' ]) AND "position" < ( SELECT COALESCE(EXTRACT(EPOCH FROM min(xact_start)), EXTRACT(EPOCH FROM now())) FROM pg_stat_activity WHERE datname = current_database() AND application_name = ANY(ARRAY['zitadel_es_pusher_', 'zitadel_es_pusher', 'zitadel_es_pusher_<INSTANCE_ID>']) AND state <> 'idle' ) ORDER BY "position", in_tx_order LIMIT 200 OFFSET 1; ``` ``` Limit (cost=293.34..293.36 rows=8 width=361) (actual time=4.686..4.689 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order InitPlan 1 -> Aggregate (cost=2.74..2.76 rows=1 width=32) (actual time=1.717..1.719 rows=1 loops=1) Output: COALESCE(EXTRACT(epoch FROM min(s.xact_start)), EXTRACT(epoch FROM now())) -> Nested Loop (cost=0.00..2.74 rows=1 width=8) (actual time=1.658..1.659 rows=0 loops=1) Output: s.xact_start Join Filter: (d.oid = s.datid) -> Seq Scan on pg_catalog.pg_database d (cost=0.00..1.07 rows=1 width=4) (actual time=0.026..0.028 rows=1 loops=1) Output: d.oid, d.datname, d.datdba, d.encoding, d.datlocprovider, d.datistemplate, d.datallowconn, d.dathasloginevt, d.datconnlimit, d.datfrozenxid, d.datminmxid, d.dattablespace, d.datcollate, d.datctype, d.datlocale, d.daticurules, d.datcollversion, d.datacl Filter: (d.datname = current_database()) Rows Removed by Filter: 4 -> Function Scan on pg_catalog.pg_stat_get_activity s (cost=0.00..1.63 rows=3 width=16) (actual time=1.628..1.628 rows=0 loops=1) Output: s.datid, s.pid, s.usesysid, s.application_name, s.state, s.query, s.wait_event_type, s.wait_event, s.xact_start, s.query_start, s.backend_start, s.state_change, s.client_addr, s.client_hostname, s.client_port, s.backend_xid, s.backend_xmin, s.backend_type, s.ssl, s.sslversion, s.sslcipher, s.sslbits, s.ssl_client_dn, s.ssl_client_serial, s.ssl_issuer_dn, s.gss_auth, s.gss_princ, s.gss_enc, s.gss_delegation, s.leader_pid, s.query_id Function Call: pg_stat_get_activity(NULL::integer) Filter: ((s.state <> 'idle'::text) AND (s.application_name = ANY ('{zitadel_es_pusher_,zitadel_es_pusher,zitadel_es_pusher_<INSTANCE_ID>}'::text[]))) Rows Removed by Filter: 42 -> Sort (cost=290.58..290.60 rows=9 width=361) (actual time=4.685..4.685 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Sort Key: events2."position", events2.in_tx_order Sort Method: quicksort Memory: 25kB -> Index Scan using es_projection on eventstore.events2 (cost=0.70..290.43 rows=9 width=361) (actual time=4.616..4.617 rows=0 loops=1) Output: events2.created_at, events2.event_type, events2.sequence, events2."position", events2.payload, events2.creator, events2.owner, events2.instance_id, events2.aggregate_type, events2.aggregate_id, events2.revision, events2.in_tx_order Index Cond: ((events2.instance_id = '<INSTANCE_ID>'::text) AND (events2.aggregate_type = ANY ('{project,instance,org}'::text[])) AND (events2.event_type = ANY ('{project.application.added,project.application.changed,project.application.deactivated,project.application.reactivated,project.application.removed,project.removed,project.application.config.api.added,project.application.config.api.changed,project.application.config.api.secret.changed,project.application.config.api.secret.updated,project.application.config.oidc.added,project.application.config.oidc.changed,project.application.config.oidc.secret.changed,project.application.config.oidc.secret.updated,project.application.config.saml.added,project.application.config.saml.changed,org.removed,instance.removed}'::text[])) AND (events2."position" > <POSITION>) AND (events2."position" < (InitPlan 1).col1)) Query Identifier: -8254550537132386499 Planning Time: 2.864 ms Execution Time: 5.414 ms ```
2025-03-13 16:50:23 +01:00
if useV1 {
clauses += "aggregate_id NOT IN (SELECT aggregate_id FROM eventstore.events WHERE " + excludeAggregateIDsClauses + ")"
} else {
clauses += "aggregate_id NOT IN (SELECT aggregate_id FROM eventstore.events2 WHERE " + excludeAggregateIDsClauses + ")"
}
feat(eventstore): exclude aggregate IDs when event_type occurred (#8940) # Which Problems Are Solved For truly event-based notification handler, we need to be able to filter out events of aggregates which are already handled. For example when an event like `notify.success` or `notify.failed` was created on an aggregate, we no longer require events from that aggregate ID. # How the Problems Are Solved Extend the query builder to use a `NOT IN` clause which excludes aggregate IDs when they have certain events for a certain aggregate type. For optimization and proper index usages, certain filters are inherited from the parent query, such as: - Instance ID - Instance IDs - Position offset This is a prettified query as used by the unit tests: ```sql SELECT created_at, event_type, "sequence", "position", payload, creator, "owner", instance_id, aggregate_type, aggregate_id, revision FROM eventstore.events2 WHERE instance_id = $1 AND aggregate_type = $2 AND event_type = $3 AND "position" > $4 AND aggregate_id NOT IN ( SELECT aggregate_id FROM eventstore.events2 WHERE aggregate_type = $5 AND event_type = ANY($6) AND instance_id = $7 AND "position" > $8 ) ORDER BY "position" DESC, in_tx_order DESC LIMIT $9 ``` I used this query to run it against the `oidc_session` aggregate looking for added events, excluding aggregates where a token was revoked, against a recent position. It fully used index scans: <details> ```json [ { "Plan": { "Node Type": "Index Scan", "Parallel Aware": false, "Async Capable": false, "Scan Direction": "Forward", "Index Name": "es_projection", "Relation Name": "events2", "Alias": "events2", "Actual Rows": 2, "Actual Loops": 1, "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.added'::text) AND (\"position\" > 1731582100.784168))", "Rows Removed by Index Recheck": 0, "Filter": "(NOT (hashed SubPlan 1))", "Rows Removed by Filter": 1, "Plans": [ { "Node Type": "Index Scan", "Parent Relationship": "SubPlan", "Subplan Name": "SubPlan 1", "Parallel Aware": false, "Async Capable": false, "Scan Direction": "Forward", "Index Name": "es_projection", "Relation Name": "events2", "Alias": "events2_1", "Actual Rows": 1, "Actual Loops": 1, "Index Cond": "((instance_id = '286399006995644420'::text) AND (aggregate_type = 'oidc_session'::text) AND (event_type = 'oidc_session.access_token.revoked'::text) AND (\"position\" > 1731582100.784168))", "Rows Removed by Index Recheck": 0 } ] }, "Triggers": [ ] } ] ``` </details> # Additional Changes - None # Additional Context - Related to https://github.com/zitadel/zitadel/issues/8931 --------- Co-authored-by: adlerhurst <silvan.reusser@gmail.com>
2024-11-25 17:25:11 +02:00
args = append(args, excludeAggregateIDsArgs...)
}
if query.AwaitOpenTransactions {
instanceIDs := make(database.TextArray[string], 0, 3)
if query.InstanceID != nil {
instanceIDs = append(instanceIDs, query.InstanceID.Value.(string))
} else if query.InstanceIDs != nil {
instanceIDs = append(instanceIDs, query.InstanceIDs.Value.(database.TextArray[string])...)
}
for i := range instanceIDs {
instanceIDs[i] = "zitadel_es_pusher_" + instanceIDs[i]
}
clauses += awaitOpenTransactions(useV1)
args = append(args, instanceIDs)
2020-10-05 19:09:26 +02:00
}
if clauses == "" {
return "", nil
}
return " WHERE " + clauses, args
}
func prepareQuery(criteria querier, useV1 bool, filters ...*repository.Filter) (_ string, args []any) {
clauses := make([]string, 0, len(filters))
args = make([]any, 0, len(filters))
for _, filter := range filters {
if filter == nil {
continue
}
arg := filter.Value
// marshal if payload filter
if filter.Field == repository.FieldEventData {
var err error
arg, err = json.Marshal(arg)
if err != nil {
logging.WithError(err).Warn("unable to marshal search value")
continue
}
}
clauses = append(clauses, getCondition(criteria, filter, useV1))
// if mapping failed an error is thrown in [query]
if clauses[len(clauses)-1] == "" {
return "", nil
2020-10-05 19:09:26 +02:00
}
args = append(args, arg)
2020-10-05 19:09:26 +02:00
}
return strings.Join(clauses, " AND "), args
2020-10-05 19:09:26 +02:00
}
func getCondition(cond querier, filter *repository.Filter, useV1 bool) (condition string) {
field := cond.columnName(filter.Field, useV1)
2020-10-05 20:39:36 +02:00
operation := cond.operation(filter.Operation)
2020-10-05 19:09:26 +02:00
if field == "" || operation == "" {
return ""
}
2020-10-05 20:39:36 +02:00
format := cond.conditionFormat(filter.Operation)
2020-10-05 19:09:26 +02:00
return fmt.Sprintf(format, field, operation)
}