Skip to content

source-postgres: connect with adaptiveFetch=true #38289

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
May 20, 2024
Merged

source-postgres: connect with adaptiveFetch=true #38289

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7021b71
source-postgres: connect with adaptiveFetch=true
May 16, 2024
c09da61
bump patch version number and update changelog
May 16, 2024
6543803
fixes
May 16, 2024
f70aa12
Merge remote-tracking branch 'origin/master' into postamar/source-pos…
xiaohansong May 20, 2024
dc44f48
bump up version
xiaohansong May 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion airbyte-integrations/connectors/source-postgres/metadata.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ data:
connectorSubtype: database
connectorType: source
definitionId: decd338e-5647-4c0b-adf4-da0e75f5a750
dockerImageTag: 3.4.4
dockerImageTag: 3.4.5
dockerRepository: airbyte/source-postgres
documentationUrl: https://docs.airbyte.com/integrations/sources/postgres
githubIssueLabel: source-postgres
Expand Down
40 changes: 26 additions & 14 deletions ...source-postgres/src/main/java/io/airbyte/integrations/source/postgres/PostgresSource.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,11 @@
import static io.airbyte.integrations.source.postgres.xmin.XminCtidUtils.reclassifyCategorisedCtidStreams;
import static java.util.stream.Collectors.toList;
import static java.util.stream.Collectors.toSet;
import static org.postgresql.PGProperty.ADAPTIVE_FETCH;
import static org.postgresql.PGProperty.CURRENT_SCHEMA;
import static org.postgresql.PGProperty.DEFAULT_ROW_FETCH_SIZE;
import static org.postgresql.PGProperty.MAX_RESULT_BUFFER;
import static org.postgresql.PGProperty.PREPARE_THRESHOLD;

import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.node.ObjectNode;
Expand All @@ -52,7 +57,6 @@
import io.airbyte.cdk.db.jdbc.JdbcDatabase;
import io.airbyte.cdk.db.jdbc.JdbcUtils;
import io.airbyte.cdk.db.jdbc.StreamingJdbcDatabase;
import io.airbyte.cdk.db.jdbc.streaming.AdaptiveStreamingQueryConfig;
import io.airbyte.cdk.integrations.base.AirbyteTraceMessageUtility;
import io.airbyte.cdk.integrations.base.IntegrationRunner;
import io.airbyte.cdk.integrations.base.Source;
Expand Down Expand Up @@ -122,6 +126,7 @@
import java.util.stream.Stream;
import javax.sql.DataSource;
import org.apache.commons.lang3.StringUtils;
import org.postgresql.PGProperty;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

Expand All @@ -146,6 +151,14 @@ public class PostgresSource extends AbstractJdbcSource<PostgresType> implements
public static final String SSL_MODE_DISABLE = "disable";
public static final String SSL_MODE_REQUIRE = "require";

public static final Map<PGProperty, String> JDBC_CONNECTION_PARAMS = ImmutableMap.of(
// Initialize parameters with prepareThreshold=0 to mitigate pgbouncer errors
// https://github.com/airbytehq/airbyte/issues/24796
PREPARE_THRESHOLD, "0",
DEFAULT_ROW_FETCH_SIZE, "1",
ADAPTIVE_FETCH, "true",
MAX_RESULT_BUFFER, "10percent");

private List<String> schemas;

private Set<AirbyteStreamNameNamespacePair> publicizedTablesInCdc;
Expand All @@ -157,7 +170,7 @@ public static Source sshWrappedSource(PostgresSource source) {
}

PostgresSource() {
super(DRIVER_CLASS, AdaptiveStreamingQueryConfig::new, new PostgresSourceOperations());
super(DRIVER_CLASS, PostgresStreamingQueryConfig::new, new PostgresSourceOperations());
this.stateEmissionFrequency = INTERMEDIATE_STATE_EMISSION_FREQUENCY;
}

Expand All @@ -176,9 +189,9 @@ public ConnectorSpecification spec() throws Exception {
@Override
public JsonNode toDatabaseConfig(final JsonNode config) {
final List<String> additionalParameters = new ArrayList<>();
// Initialize parameters with prepareThreshold=0 to mitigate pgbouncer errors
// https://github.com/airbytehq/airbyte/issues/24796
additionalParameters.add("prepareThreshold=0");
for (var e : JDBC_CONNECTION_PARAMS.entrySet()) {
additionalParameters.add(e.getKey().getName() + EQUALS + e.getValue());
}

final String encodedDatabaseName = URLEncoder.encode(config.get(JdbcUtils.DATABASE_KEY).asText(), StandardCharsets.UTF_8);

Expand All @@ -188,7 +201,7 @@ public JsonNode toDatabaseConfig(final JsonNode config) {
encodedDatabaseName));

if (config.get(JdbcUtils.JDBC_URL_PARAMS_KEY) != null && !config.get(JdbcUtils.JDBC_URL_PARAMS_KEY).asText().isEmpty()) {
jdbcUrl.append(config.get(JdbcUtils.JDBC_URL_PARAMS_KEY).asText()).append(AMPERSAND);
additionalParameters.add(config.get(JdbcUtils.JDBC_URL_PARAMS_KEY).asText());
}

final Map<String, String> sslParameters = parseSSLConfig(config);
Expand All @@ -206,12 +219,10 @@ public JsonNode toDatabaseConfig(final JsonNode config) {
}

if (schemas != null && !schemas.isEmpty()) {
additionalParameters.add("currentSchema=" + String.join(",", schemas));
additionalParameters.add(CURRENT_SCHEMA.getName() + EQUALS + String.join(",", schemas));
}

additionalParameters.forEach(x -> jdbcUrl.append(x).append("&"));

jdbcUrl.append(toJDBCQueryParams(sslParameters));
additionalParameters.addAll(toJDBCQueryParams(sslParameters));
jdbcUrl.append(String.join(AMPERSAND, additionalParameters));
LOGGER.debug("jdbc url: {}", jdbcUrl);
final ImmutableMap.Builder<Object, Object> configBuilder = ImmutableMap.builder()
.put(JdbcUtils.USERNAME_KEY, config.get(JdbcUtils.USERNAME_KEY).asText())
Expand All @@ -225,8 +236,9 @@ public JsonNode toDatabaseConfig(final JsonNode config) {
return Jsons.jsonNode(configBuilder.build());
}

public String toJDBCQueryParams(final Map<String, String> sslParams) {
return Objects.isNull(sslParams) ? ""
public List<String> toJDBCQueryParams(final Map<String, String> sslParams) {
return Objects.isNull(sslParams)
? List.of()
: sslParams.entrySet()
.stream()
.map((entry) -> {
Expand All @@ -243,7 +255,7 @@ public String toJDBCQueryParams(final Map<String, String> sslParams) {
}
})
.filter(s -> Objects.nonNull(s) && !s.isEmpty())
.collect(Collectors.joining(JdbcUtils.AMPERSAND));
.toList();
}

@Override
Expand Down
25 changes: 25 additions & 0 deletions ...s/src/main/java/io/airbyte/integrations/source/postgres/PostgresStreamingQueryConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
/*
* Copyright (c) 2023 Airbyte, Inc., all rights reserved.
*/

package io.airbyte.integrations.source.postgres;

import io.airbyte.cdk.db.jdbc.streaming.JdbcStreamingQueryConfig;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import org.jetbrains.annotations.NotNull;

public class PostgresStreamingQueryConfig implements JdbcStreamingQueryConfig {

@Override
public void initialize(final Connection connection, final @NotNull Statement preparedStatement) throws SQLException {
connection.setAutoCommit(false);
// Nothing else to do, adaptive streaming is enabled via JDBC connection parameters.
}

@Override
public void accept(ResultSet resultSet, Object o) {}

}
15 changes: 13 additions & 2 deletions ...ce-postgres/src/test/java/io/airbyte/integrations/source/postgres/PostgresSourceTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -815,10 +815,21 @@ private ConfiguredAirbyteStream createTableWithInvalidCursorType(final Database
@Test
void testJdbcUrlWithEscapedDatabaseName() {
final JsonNode jdbcConfig = source().toDatabaseConfig(buildConfigEscapingNeeded());
assertEquals(EXPECTED_JDBC_ESCAPED_URL, jdbcConfig.get(JdbcUtils.JDBC_URL_KEY).asText());
assertEquals("jdbc:postgresql://localhost:1111/db%2Ffoo?" + EXPECTED_DEFAULT_PARAMS,
jdbcConfig.get(JdbcUtils.JDBC_URL_KEY).asText());
}

private static final String EXPECTED_JDBC_ESCAPED_URL = "jdbc:postgresql://localhost:1111/db%2Ffoo?prepareThreshold=0&";
@Test
void testJdbcUrlWithSchemas() {
final JsonNode sourceConfig = buildConfigEscapingNeeded();
((ObjectNode) sourceConfig).set("schemas", Jsons.arrayNode().add("bar").add("baz"));
final JsonNode jdbcConfig = source().toDatabaseConfig(sourceConfig);
assertEquals("jdbc:postgresql://localhost:1111/db%2Ffoo?" + EXPECTED_DEFAULT_PARAMS + "&currentSchema=bar,baz",
jdbcConfig.get(JdbcUtils.JDBC_URL_KEY).asText());
}

private static final String EXPECTED_DEFAULT_PARAMS =
"prepareThreshold=0&defaultRowFetchSize=1&adaptiveFetch=true&maxResultBuffer=10percent";

private JsonNode buildConfigEscapingNeeded() {
return Jsons.jsonNode(ImmutableMap.of(
Expand Down
57 changes: 29 additions & 28 deletions docs/integrations/sources/postgres.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,34 +308,35 @@ According to Postgres [documentation](https://www.postgresql.org/docs/14/datatyp

| Version | Date | Pull Request | Subject |
|---------|------------|----------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 3.4.4 | 2024-05-15 | [38208](https://github.com/airbytehq/airbyte/pull/38208) | disable counts in full refresh stream in state message. |
| 3.4.3 | 2024-05-13 | [38104](https://github.com/airbytehq/airbyte/pull/38104) | Handle transient error messages. |
| 3.4.2 | 2024-05-10 | [38171](https://github.com/airbytehq/airbyte/pull/38171) | Bug fix on final state setup. |
| 3.4.1 | 2024-05-10 | [38130](https://github.com/airbytehq/airbyte/pull/38130) | Bug fix on old PG where ctid column not found when stream is a view. |
| 3.4.0 | 2024-04-29 | [37112](https://github.com/airbytehq/airbyte/pull/37112) | resumeable full refresh. |
| 3.3.33 | 2024-05-07 | [38030](https://github.com/airbytehq/airbyte/pull/38030) | Mark PG hot standby error as transient. |
| 3.3.32 | 2024-04-30 | [37758](https://github.com/airbytehq/airbyte/pull/37758) | Correct previous release to disable debezium retries |
| 3.3.31 | 2024-04-30 | [37754](https://github.com/airbytehq/airbyte/pull/37754) | Add CDC logs |
| 3.3.30 | 2024-04-30 | [37726](https://github.com/airbytehq/airbyte/pull/37726) | Remove debezium retries |
| 3.3.29 | 2024-04-23 | [37509](https://github.com/airbytehq/airbyte/pull/37509) | remove excessive logs |
| 3.3.28 | 2024-04-23 | [37509](https://github.com/airbytehq/airbyte/pull/37509) | Better error messages on switching between sync modes. |
| 3.3.27 | 2024-04-22 | [37441](https://github.com/airbytehq/airbyte/pull/37441) | Remove legacy bad values handling code. |
| 3.3.26 | 2024-04-10 | [36982](https://github.com/airbytehq/airbyte/pull/36982) | Populate airyte_meta.changes for xmin path |
| 3.3.25 | 2024-04-10 | [36981](https://github.com/airbytehq/airbyte/pull/36981) | Track latest CDK |
| 3.3.24 | 2024-04-10 | [36865](https://github.com/airbytehq/airbyte/pull/36865) | Track latest CDK |
| 3.3.23 | 2024-04-02 | [36759](https://github.com/airbytehq/airbyte/pull/36759) | Track latest CDK |
| 3.3.22 | 2024-04-01 | [36739](https://github.com/airbytehq/airbyte/pull/36739) | Fix useLocalCdk flag. |
| 3.3.21 | 2024-03-25 | [36584](https://github.com/airbytehq/airbyte/pull/36584) | Adopt Kotlin CDK. |
| 3.3.20 | 2024-03-25 | [36432](https://github.com/airbytehq/airbyte/pull/36432) | Failure to serialize values from Postgres DB shouldn't fail sync. |
| 3.3.19 | 2024-03-12 | [36333](https://github.com/airbytehq/airbyte/pull/36333) | Use newest CDK - deprecate dbz iterator |
| 3.3.18 | 2024-03-12 | [35599](https://github.com/airbytehq/airbyte/pull/35599) | Use newest CDK |
| 3.3.17 | 2024-03-12 | [35939](https://github.com/airbytehq/airbyte/pull/35939) | Use lsn_commit value instead of lsn_proc for CDC checkpointing logic. |
| 3.3.16 | 2024-03-11 | [35904](https://github.com/airbytehq/airbyte/pull/35904) | Adopt Java CDK 0.23.1- debezium retries. |
| 3.3.15 | 2024-02-29 | [34724](https://github.com/airbytehq/airbyte/pull/34724) | Add record count in state message. |
| 3.3.14 | 2024-03-06 | [35842](https://github.com/airbytehq/airbyte/pull/35842) | Add logging to understand cases with a large number of records with the same LSN. |
| 3.3.13 | 2024-02-27 | [35675](https://github.com/airbytehq/airbyte/pull/35675) | Fix invalid cdc error message. |
| 3.3.12 | 2024-02-22 | [35569](https://github.com/airbytehq/airbyte/pull/35569) | Fix logging bug. |
| 3.3.11 | 2024-02-20 | [35304](https://github.com/airbytehq/airbyte/pull/35304) | Add config to throw an error on invalid CDC position and enable it by default. |
| 3.4.5 | 2024-05-16 | [38289](https://github.com/airbytehq/airbyte/pull/38289) | Connect with adaptiveFetch=true |
| 3.4.4 | 2024-05-15 | [38208](https://github.com/airbytehq/airbyte/pull/38208) | disable counts in full refresh stream in state message. |
| 3.4.3 | 2024-05-13 | [38104](https://github.com/airbytehq/airbyte/pull/38104) | Handle transient error messages. |
| 3.4.2 | 2024-05-10 | [38171](https://github.com/airbytehq/airbyte/pull/38171) | Bug fix on final state setup. |
| 3.4.1 | 2024-05-10 | [38130](https://github.com/airbytehq/airbyte/pull/38130) | Bug fix on old PG where ctid column not found when stream is a view. |
| 3.4.0 | 2024-04-29 | [37112](https://github.com/airbytehq/airbyte/pull/37112) | resumeable full refresh. |
| 3.3.33 | 2024-05-07 | [38030](https://github.com/airbytehq/airbyte/pull/38030) | Mark PG hot standby error as transient. |
| 3.3.32 | 2024-04-30 | [37758](https://github.com/airbytehq/airbyte/pull/37758) | Correct previous release to disable debezium retries |
| 3.3.31 | 2024-04-30 | [37754](https://github.com/airbytehq/airbyte/pull/37754) | Add CDC logs |
| 3.3.30 | 2024-04-30 | [37726](https://github.com/airbytehq/airbyte/pull/37726) | Remove debezium retries |
| 3.3.29 | 2024-04-23 | [37509](https://github.com/airbytehq/airbyte/pull/37509) | remove excessive logs |
| 3.3.28 | 2024-04-23 | [37509](https://github.com/airbytehq/airbyte/pull/37509) | Better error messages on switching between sync modes. |
| 3.3.27 | 2024-04-22 | [37441](https://github.com/airbytehq/airbyte/pull/37441) | Remove legacy bad values handling code. |
| 3.3.26 | 2024-04-10 | [36982](https://github.com/airbytehq/airbyte/pull/36982) | Populate airyte_meta.changes for xmin path |
| 3.3.25 | 2024-04-10 | [36981](https://github.com/airbytehq/airbyte/pull/36981) | Track latest CDK |
| 3.3.24 | 2024-04-10 | [36865](https://github.com/airbytehq/airbyte/pull/36865) | Track latest CDK |
| 3.3.23 | 2024-04-02 | [36759](https://github.com/airbytehq/airbyte/pull/36759) | Track latest CDK |
| 3.3.22 | 2024-04-01 | [36739](https://github.com/airbytehq/airbyte/pull/36739) | Fix useLocalCdk flag. |
| 3.3.21 | 2024-03-25 | [36584](https://github.com/airbytehq/airbyte/pull/36584) | Adopt Kotlin CDK. |
| 3.3.20 | 2024-03-25 | [36432](https://github.com/airbytehq/airbyte/pull/36432) | Failure to serialize values from Postgres DB shouldn't fail sync. |
| 3.3.19 | 2024-03-12 | [36333](https://github.com/airbytehq/airbyte/pull/36333) | Use newest CDK - deprecate dbz iterator |
| 3.3.18 | 2024-03-12 | [35599](https://github.com/airbytehq/airbyte/pull/35599) | Use newest CDK |
| 3.3.17 | 2024-03-12 | [35939](https://github.com/airbytehq/airbyte/pull/35939) | Use lsn_commit value instead of lsn_proc for CDC checkpointing logic. |
| 3.3.16 | 2024-03-11 | [35904](https://github.com/airbytehq/airbyte/pull/35904) | Adopt Java CDK 0.23.1- debezium retries. |
| 3.3.15 | 2024-02-29 | [34724](https://github.com/airbytehq/airbyte/pull/34724) | Add record count in state message. |
| 3.3.14 | 2024-03-06 | [35842](https://github.com/airbytehq/airbyte/pull/35842) | Add logging to understand cases with a large number of records with the same LSN. |
| 3.3.13 | 2024-02-27 | [35675](https://github.com/airbytehq/airbyte/pull/35675) | Fix invalid cdc error message. |
| 3.3.12 | 2024-02-22 | [35569](https://github.com/airbytehq/airbyte/pull/35569) | Fix logging bug. |
| 3.3.11 | 2024-02-20 | [35304](https://github.com/airbytehq/airbyte/pull/35304) | Add config to throw an error on invalid CDC position and enable it by default. |
| 3.3.10 | 2024-02-13 | [35036](https://github.com/airbytehq/airbyte/pull/34751) | Emit analytics message for invalid CDC cursor. |
| 3.3.9 | 2024-02-13 | [35224](https://github.com/airbytehq/airbyte/pull/35224) | Adopt CDK 0.20.4 |
| 3.3.8 | 2024-02-08 | [34751](https://github.com/airbytehq/airbyte/pull/34751) | Adopt CDK 0.19.0 |
Expand Down
Loading