edc1acbb7e
The EC_DOMAIN_LINK MariaDB table stores links between domains. This is problematic, as both updating and querying this table is very slow in relation to how small the data is (~10 GB). This slowness is largely caused by the database enforcing ACID guarantees we don't particularly need. This changeset replaces the EC_DOMAIN_LINK table with a file in each index node containing 32 bit integer pairs corresponding to links between two domains. This file is loaded in memory in each node, and can be queried via the Query Service. A migration step is needed before this file is created in each node. Until that happens, the actual data is loaded from the EC_DOMAIN_LINK table, but accessed as though it was a file. The changeset also migrates/renames the links.db file to documents.db to avoid naming confusion between the two.
73 lines
2.2 KiB
Groovy
73 lines
2.2 KiB
Groovy
plugins {
|
|
id 'java'
|
|
|
|
id 'com.palantir.docker' version '0.35.0'
|
|
id 'application'
|
|
id 'jvm-test-suite'
|
|
}
|
|
|
|
application {
|
|
mainClass = 'nu.marginalia.executor.ExecutorMain'
|
|
applicationName = 'executor-service'
|
|
}
|
|
|
|
tasks.distZip.enabled = false
|
|
|
|
apply from: "$rootProject.projectDir/docker-service-with-dist.gradle"
|
|
|
|
java {
|
|
toolchain {
|
|
languageVersion.set(JavaLanguageVersion.of(21))
|
|
}
|
|
}
|
|
|
|
dependencies {
|
|
implementation project(':code:common:config')
|
|
implementation project(':code:common:model')
|
|
implementation project(':code:common:process')
|
|
implementation project(':code:common:db')
|
|
implementation project(':code:common:linkdb')
|
|
|
|
implementation project(':code:common:service')
|
|
implementation project(':code:common:service-client')
|
|
implementation project(':code:common:service-discovery')
|
|
|
|
implementation project(':third-party:commons-codec')
|
|
|
|
implementation project(':code:libraries:message-queue')
|
|
|
|
implementation project(':code:process-models:crawl-spec')
|
|
implementation project(':code:process-models:crawling-model')
|
|
implementation project(':code:features-crawl:link-parser')
|
|
implementation project(':code:features-index:index-journal')
|
|
implementation project(':code:api:index-api')
|
|
implementation project(':code:api:query-api')
|
|
implementation project(':code:api:process-mqapi')
|
|
implementation project(':code:api:executor-api')
|
|
|
|
implementation libs.bundles.slf4j
|
|
|
|
implementation libs.spark
|
|
implementation libs.gson
|
|
implementation libs.prometheus
|
|
implementation libs.notnull
|
|
implementation libs.guice
|
|
implementation libs.trove
|
|
implementation libs.protobuf
|
|
implementation libs.rxjava
|
|
implementation libs.zstd
|
|
implementation libs.jsoup
|
|
implementation libs.commons.io
|
|
implementation libs.commons.lang3
|
|
implementation libs.bundles.mariadb
|
|
|
|
testImplementation libs.bundles.slf4j.test
|
|
testImplementation libs.bundles.junit
|
|
testImplementation libs.mockito
|
|
|
|
testImplementation platform('org.testcontainers:testcontainers-bom:1.17.4')
|
|
testImplementation 'org.testcontainers:mariadb:1.17.4'
|
|
testImplementation 'org.testcontainers:junit-jupiter:1.17.4'
|
|
|
|
|
|
} |