Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 6 additions & 0 deletions docs/content/configuration/broker.md
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,12 @@ The broker uses processing configs for nested groupBy queries. And, optionally,
|--------|-----------|-------|
|`druid.query.search.maxSearchLimit`|Maximum number of search results to return.|1000|

##### Segment Metadata Query Config

|Property|Description|Default|
|--------|-----------|-------|
|`druid.query.segmentMetadata.defaultHistory`|When no interval is specified in the query, use a default interval of defaultHistory before the end time of the most recent segment, specified in ISO8601 format. This property also controls the duration of the default interval used by GET /druid/v2/datasources/{dataSourceName} interactions for retrieving datasource dimensions/metrics.|P1W|

### Caching

You can optionally only configure caching to be enabled on the broker by setting caching configs here.
Expand Down
4 changes: 4 additions & 0 deletions docs/content/design/broker.md
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,10 @@ Returns a list of queryable datasources.

Returns the dimensions and metrics of the datasource. Optionally, you can provide request parameter "full" to get list of served intervals with dimensions and metrics being served for those intervals. You can also provide request param "interval" explicitly to refer to a particular interval.

If no interval is specified, a default interval spanning a configurable period before the current time will be used. The duration of this interval is specified in ISO8601 format via:

druid.query.segmentMetadata.defaultHistory

* `/druid/v2/datasources/{dataSourceName}/dimensions`

Returns the dimensions of the datasource.
Expand Down
9 changes: 8 additions & 1 deletion docs/content/querying/segmentmetadataquery.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ There are several main parts to a segment metadata query:
|--------|-----------|---------|
|queryType|This String should always be "segmentMetadata"; this is the first thing Druid looks at to figure out how to interpret the query|yes|
|dataSource|A String or Object defining the data source to query, very similar to a table in a relational database. See [DataSource](../querying/datasource.html) for more information.|yes|
|intervals|A JSON Object representing ISO-8601 Intervals. This defines the time ranges to run the query over.|yes|
|intervals|A JSON Object representing ISO-8601 Intervals. This defines the time ranges to run the query over.|no|
|toInclude|A JSON Object representing what columns should be included in the result. Defaults to "all".|no|
|merge|Merge all individual segment metadata results into a single result|no|
|context|See [Context](../querying/query-context.html)|no|
Expand All @@ -52,6 +52,13 @@ Timestamp column will have type `LONG`.

Only columns which are dimensions (ie, have type `STRING`) will have any cardinality. Rest of the columns (timestamp and metric columns) will show cardinality as `null`.

### intervals

If an interval is not specified, the query will use a default interval that spans a configurable period before the end time of the most recent segment.

The length of this default time period is set in the broker configuration via:
druid.query.segmentMetadata.defaultHistory

### toInclude

There are 3 types of toInclude objects.
Expand Down
3 changes: 2 additions & 1 deletion processing/src/main/java/io/druid/query/Druids.java
Original file line number Diff line number Diff line change
Expand Up @@ -876,7 +876,8 @@ public SegmentMetadataQuery build()
querySegmentSpec,
toInclude,
merge,
context
context,
false
);
}

Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,49 @@
/*
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@fjy header is changed

* Licensed to Metamarkets Group Inc. (Metamarkets) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Metamarkets licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/

package io.druid.query.metadata;

import com.fasterxml.jackson.annotation.JsonProperty;
import org.joda.time.Period;
import org.joda.time.format.ISOPeriodFormat;
import org.joda.time.format.PeriodFormatter;


public class SegmentMetadataQueryConfig
{
private static final String DEFAULT_PERIOD_STRING = "P1W";
private static final PeriodFormatter ISO_FORMATTER = ISOPeriodFormat.standard();

@JsonProperty
private Period defaultHistory = ISO_FORMATTER.parsePeriod(DEFAULT_PERIOD_STRING);

public SegmentMetadataQueryConfig(String period)
{
defaultHistory = ISO_FORMATTER.parsePeriod(period);
}

public SegmentMetadataQueryConfig()
{
}

public Period getDefaultHistory()
{
return defaultHistory;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,13 @@
import com.fasterxml.jackson.core.type.TypeReference;
import com.google.common.base.Function;
import com.google.common.base.Functions;
import com.google.common.base.Predicate;
import com.google.common.collect.Iterables;
import com.google.common.collect.Lists;
import com.google.common.collect.Maps;
import com.google.common.collect.Ordering;
import com.google.common.collect.Sets;
import com.google.inject.Inject;
import com.metamx.common.ISE;
import com.metamx.common.guava.MergeSequence;
import com.metamx.common.guava.Sequence;
Expand All @@ -41,6 +44,8 @@
import io.druid.query.metadata.metadata.ColumnAnalysis;
import io.druid.query.metadata.metadata.SegmentAnalysis;
import io.druid.query.metadata.metadata.SegmentMetadataQuery;
import io.druid.timeline.LogicalSegment;
import org.joda.time.DateTime;
import org.joda.time.Interval;

import javax.annotation.Nullable;
Expand All @@ -56,6 +61,16 @@ public class SegmentMetadataQueryQueryToolChest extends QueryToolChest<SegmentAn
};
private static final byte[] SEGMENT_METADATA_CACHE_PREFIX = new byte[]{0x4};

private final SegmentMetadataQueryConfig config;

@Inject
public SegmentMetadataQueryQueryToolChest(
SegmentMetadataQueryConfig config
)
{
this.config = config;
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Storing either the config or the defaultHistory period should be enough- doesn't look like there's a need to store both

}

@Override
public QueryRunner<SegmentAnalysis> mergeResults(final QueryRunner<SegmentAnalysis> runner)
{
Expand Down Expand Up @@ -216,6 +231,37 @@ public Sequence<SegmentAnalysis> mergeSequences(Sequence<Sequence<SegmentAnalysi
};
}

@Override
public <T extends LogicalSegment> List<T> filterSegments(SegmentMetadataQuery query, List<T> segments)
{
if (!query.isUsingDefaultInterval()) {
return segments;
}

if (segments.size() <= 1) {
return segments;
}

final T max = segments.get(segments.size() - 1);

DateTime targetEnd = max.getInterval().getEnd();
final Interval targetInterval = new Interval(config.getDefaultHistory(), targetEnd);

return Lists.newArrayList(
Iterables.filter(
segments,
new Predicate<T>()
{
@Override
public boolean apply(T input)
{
return (input.getInterval().overlaps(targetInterval));
}
}
)
);
}

private Ordering<SegmentAnalysis> getOrdering()
{
return new Ordering<SegmentAnalysis>()
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -20,33 +20,57 @@
import com.fasterxml.jackson.annotation.JsonCreator;
import com.fasterxml.jackson.annotation.JsonProperty;
import com.google.common.base.Preconditions;
import io.druid.common.utils.JodaUtils;
import io.druid.query.BaseQuery;
import io.druid.query.DataSource;
import io.druid.query.Query;
import io.druid.query.TableDataSource;
import io.druid.query.spec.MultipleIntervalSegmentSpec;
import io.druid.query.spec.QuerySegmentSpec;
import org.joda.time.Interval;

import java.util.Arrays;
import java.util.Map;

public class SegmentMetadataQuery extends BaseQuery<SegmentAnalysis>
{
public static final Interval DEFAULT_INTERVAL = new Interval(
JodaUtils.MIN_INSTANT, JodaUtils.MAX_INSTANT
);

private final ColumnIncluderator toInclude;
private final boolean merge;
private final boolean usingDefaultInterval;

@JsonCreator
public SegmentMetadataQuery(
@JsonProperty("dataSource") DataSource dataSource,
@JsonProperty("intervals") QuerySegmentSpec querySegmentSpec,
@JsonProperty("toInclude") ColumnIncluderator toInclude,
@JsonProperty("merge") Boolean merge,
@JsonProperty("context") Map<String, Object> context
@JsonProperty("context") Map<String, Object> context,
@JsonProperty("usingDefaultInterval") Boolean useDefaultInterval
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

does this flag needs part of the json ?
I believe this can just be derived from whether the querySegmentSpec is not or not ?

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The querySegmentSpec is always going to be set after the first object construction (constructor sets it to DEFAULT_INTERVAL if it's null) so this needs to be part of the json if the query is ever going to be constructed and then re-serialized. That could potentially happen if someone creates the Query object locally and then serializes it to send to the broker.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The flag needs to be in the constructor, in the situations where a query object is generated from an existing object, e.g. query.withOverriddenContext, query.withQuerySegmentSpec, the querySegmentSpec will not be null.

)
{
super(dataSource, querySegmentSpec, context);
super(
dataSource,
(querySegmentSpec == null) ? new MultipleIntervalSegmentSpec(Arrays.asList(DEFAULT_INTERVAL))
: querySegmentSpec,
context
);

if (querySegmentSpec == null) {
this.usingDefaultInterval = true;
} else {
this.usingDefaultInterval = useDefaultInterval == null ? false : useDefaultInterval;
}

this.toInclude = toInclude == null ? new AllColumnIncluderator() : toInclude;
this.merge = merge == null ? false : merge;
Preconditions.checkArgument(dataSource instanceof TableDataSource, "SegmentMetadataQuery only supports table datasource");
Preconditions.checkArgument(
dataSource instanceof TableDataSource,
"SegmentMetadataQuery only supports table datasource"
);
}

@JsonProperty
Expand All @@ -61,6 +85,12 @@ public boolean isMerge()
return merge;
}

@JsonProperty
public boolean isUsingDefaultInterval()
{
return usingDefaultInterval;
}

@Override
public boolean hasFilters()
{
Expand All @@ -78,7 +108,11 @@ public Query<SegmentAnalysis> withOverriddenContext(Map<String, Object> contextO
{
return new SegmentMetadataQuery(
getDataSource(),
getQuerySegmentSpec(), toInclude, merge, computeOverridenContext(contextOverride)
getQuerySegmentSpec(),
toInclude,
merge,
computeOverridenContext(contextOverride),
usingDefaultInterval
);
}

Expand All @@ -87,7 +121,12 @@ public Query<SegmentAnalysis> withQuerySegmentSpec(QuerySegmentSpec spec)
{
return new SegmentMetadataQuery(
getDataSource(),
spec, toInclude, merge, getContext());
spec,
toInclude,
merge,
getContext(),
usingDefaultInterval
);
}

@Override
Expand All @@ -98,22 +137,34 @@ public Query<SegmentAnalysis> withDataSource(DataSource dataSource)
getQuerySegmentSpec(),
toInclude,
merge,
getContext());
getContext(),
usingDefaultInterval
);
}

@Override
public boolean equals(Object o)
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This should include the new field - you can regenerate this and hashCode with IntelliJ

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@gianm functions regenerated

{
if (this == o) return true;
if (o == null || getClass() != o.getClass()) return false;
if (!super.equals(o)) return false;
if (this == o) {
return true;
}
if (o == null || getClass() != o.getClass()) {
return false;
}
if (!super.equals(o)) {
return false;
}

SegmentMetadataQuery that = (SegmentMetadataQuery) o;

if (merge != that.merge) return false;
if (toInclude != null ? !toInclude.equals(that.toInclude) : that.toInclude != null) return false;
if (merge != that.merge) {
return false;
}
if (usingDefaultInterval != that.usingDefaultInterval) {
return false;
}
return !(toInclude != null ? !toInclude.equals(that.toInclude) : that.toInclude != null);

return true;
}

@Override
Expand All @@ -122,6 +173,7 @@ public int hashCode()
int result = super.hashCode();
result = 31 * result + (toInclude != null ? toInclude.hashCode() : 0);
result = 31 * result + (merge ? 1 : 0);
result = 31 * result + (usingDefaultInterval ? 1 : 0);
return result;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -99,13 +99,13 @@ private List<SegmentAnalysis> getSegmentAnalysises(Segment index)
{
final QueryRunner runner = QueryRunnerTestHelper.makeQueryRunner(
(QueryRunnerFactory) new SegmentMetadataQueryRunnerFactory(
new SegmentMetadataQueryQueryToolChest(),
new SegmentMetadataQueryQueryToolChest(new SegmentMetadataQueryConfig()),
QueryRunnerTestHelper.NOOP_QUERYWATCHER
), index
);

final SegmentMetadataQuery query = new SegmentMetadataQuery(
new LegacyDataSource("test"), QuerySegmentSpecs.create("2011/2012"), null, null, null
new LegacyDataSource("test"), QuerySegmentSpecs.create("2011/2012"), null, null, null, false
);
HashMap<String,Object> context = new HashMap<String, Object>();
return Sequences.toList(query.run(runner, context), Lists.<SegmentAnalysis>newArrayList());
Expand Down
Loading