113 Commits

Author SHA1 Message Date
Himanshu
3f82108d15 optionally enable coordinator auto kill tasks on all dataSources via dynamic config (#3250) 2016-07-17 18:47:52 -07:00
Fangjin Yang
8eeae2e844 remove bad docs on setting up clusters (#3188) 2016-07-01 15:41:40 -05:00
Gian Merlino
4cc39b2ee7 Alternative groupBy strategy. (#2998)
This patch introduces a GroupByStrategy concept and two strategies: "v1"
is the current groupBy strategy and "v2" is a new one. It also introduces
a merge buffers concept in DruidProcessingModule, to try to better
manage memory used for merging.

Both of these are described in more detail in #2987.

There are two goals of this patch:

1. Make it possible for historical/realtime nodes to return larger groupBy
   result sets, faster, with better memory management.
2. Make it possible for brokers to merge streams when there are no order-by
   columns, avoiding materialization.

This patch does not do anything to help with memory management on the broker
when there are order-by columns or when there are nested queries. That could
potentially be done in a future patch.
2016-06-24 18:06:09 -07:00
Gian Merlino
2db5f49f35 Fix JavaScriptConfig. (#3062) 2016-06-02 23:59:00 -07:00
Parag Jain
44237e25d9 fix duration format and number format (#3057) 2016-06-02 10:09:21 -07:00
David Lim
b489f63698 Supervisor for KafkaIndexTask (#2656)
* supervisor for kafka indexing tasks

* cr changes
2016-05-04 23:13:13 -07:00
Charles Allen
44e52acfc0 Link up metrics configuration to what they mean (#2921) 2016-05-04 10:30:02 -07:00
binlijin
9151099e08 add document for druid.segmentCache.numBootstrapThreads (#2872) 2016-04-22 12:06:08 +08:00
Himanshu
3cfd9c64c9 make singleThreaded groupBy query config overridable at query time (#2828)
* make isSingleThreaded groupBy query processing overridable at query time

* refactor code in GroupByMergedQueryRunner to make processing of single threaded and parallel merging of runners consistent
2016-04-21 17:12:58 -07:00
Gian Merlino
c74391e54c JavaScript: Ability to disable. (#2853)
Fixes #2852.
2016-04-21 09:43:15 -05:00
Nishant
dbf63f738f Add ability to filter segments for specific dataSources on broker without creating tiers (#2848)
* Add back FilteredServerView removed in a32906c7fd11c9a8554df2621a172353a523a9dd to reduce memory usage using watched tiers.

* Add functionality to specify "druid.broker.segment.watchedDataSources"
2016-04-19 10:10:06 -07:00
Nishant
deb6ecf919 handle review comments for PR 2784
https://github.com/druid-io/druid/pull/2784#discussion_r59062021
2016-04-12 21:52:00 +05:30
Nishant
edd74f2b67 Allow Lite DataSegment Announcements
separate config for each skipping dimensions, metrics and loadSpec

Add test

fix test comment

Add docs
2016-04-07 18:24:12 +05:30
Fangjin Yang
1e02eeab13 Merge pull request #2683 from metamx/default_retry
Better defaults for Retry policy for task actions
2016-03-29 08:02:59 -07:00
Fangjin Yang
9cb197adec Merge pull request #2722 from himanshug/fix_hadoop_jar_upload
config to explicitly specify classpath for hadoop container during hadoop ingestion
2016-03-28 14:49:03 -07:00
Himanshu Gupta
e78a469fb7 UTs for ExtensionsConfig 2016-03-25 10:51:28 -05:00
Himanshu Gupta
004b00bb96 config to explicitly specify classpath for hadoop container during hadoop ingestion 2016-03-25 10:51:28 -05:00
Bingkun Guo
0fa04305a6 refine description for mergeBytesLimit 2016-03-24 13:17:24 -05:00
Robin
448e0127b9 dynamic config endpoint is at coordinator 2016-03-23 17:22:19 -05:00
Gian Merlino
451c0bc6d8 Merge pull request #2702 from pjain1/improve_docs
how to query in the querying section, correct default for select strategy, formatting
2016-03-22 16:40:35 -07:00
Parag Jain
39ecb9929d how to query, correct default for select strategy, formatting 2016-03-22 17:06:15 -05:00
Nishant
ed8f39fcfe Better defaults for Retry policy for task actions
This PR changes the retry of task actions to be a bit more aggressive
by reducing the maxWait. Current defaults were 1 min to 10 mins, which
lead to a very delayed recovery in case there are any transient network
issues between the overlord and the peons.

doc changes.
2016-03-18 11:59:55 -07:00
Charles Allen
5da9a280b6 Query Time Lookup - Dynamic Configuration 2016-03-18 09:45:05 -07:00
Jonathan Wei
5ec5ac92c6 Merge pull request #2382 from himanshug/broker_segment_tier_selection
at broker, if configured, only add segments from specific tiers to the timeline
2016-03-14 16:53:06 -07:00
Bingkun Guo
96c981cd0a fix broken link for Tasks 2016-03-11 11:36:34 -06:00
Himanshu Gupta
ca5de3f583 only allow lowering maxResults and maxIntermediateRows from groupBy query context 2016-03-08 15:03:59 -06:00
Himanshu Gupta
099acb4966 allow groupBy max[Intermediate]Rows limit be overridable by context 2016-03-07 15:22:41 -06:00
jisookim
177b575d41 fix default number of connections on broker config documentation 2016-03-03 13:50:48 -08:00
Björn Zettergren
2462c82c0e New defaults for maxRowsInMemory rowFlushBoundary
To bring consistency to docs and source this commit changes the default
values for maxRowsInMemory and rowFlushBoundary to 75000 after
discussion in PR https://github.com/druid-io/druid/pull/2457.

The previous default was 500000 and it's lower now on the grounds that
it's better for a default to be somewhat less efficient, and work,
than to reach for the stars and possibly result in
"OutOfMemoryError: java heap space" errors.
2016-03-01 13:50:28 +01:00
Charles Allen
c6803c4364 Allow specifying peon javaOpts as an array 2016-02-26 13:24:35 -08:00
Gian Merlino
eb13d7afe3 Merge pull request #2521 from himanshug/fix_2497
RTR has multiple threads for assignment of pending tasks now
2016-02-26 08:14:15 -08:00
Nishant
9f8faabddb Merge pull request #2469 from pdeva/patch-10
correct service names
2016-02-26 21:15:58 +05:30
Himanshu Gupta
bc156effe7 RTR has multiple threads for assignment of pending tasks now. 2016-02-26 09:27:03 -06:00
Gian Merlino
23c993c9e7 Add druid.indexer.server.maxChatRequests for QoS; deprecate separate ports.
- Add druid.indexer.server.maxChatRequests, which sets up a QoSFilter on the main Jetty server.
- Deprecate druid.indexer.runner.separateIngestionEndpoint
- Deprecate druid.indexer.server.chathandler.*
2016-02-19 13:36:09 -08:00
pdeva
dd81b5ebe4 correct service names
use a `/` instead of `:` cause thats how the service names are declared in the respective config files of coordinator and overlord
2016-02-13 15:26:19 -08:00
Gian Merlino
e0c049c0b0 Make startup properties logging optional.
Off by default, but enabled in the example config files. See also #2452.
2016-02-12 14:12:16 -08:00
Charles Allen
3a6452c6d4 Make QuotableWhiteSpaceSplitter able to take json
* Fixes #2435
2016-02-10 16:42:14 -08:00
Himanshu Gupta
d1cb17d3f7 at broker - only add segments from specific tiers to the timeline 2016-02-09 22:33:22 -06:00
Robin
1d57e3267d some minor doc changes 2016-02-09 08:20:53 -06:00
Himanshu Gupta
b40c342cd1 make Global stupid pool cache size configurable 2016-02-05 14:18:06 -06:00
fjy
9e2295aa61 whitespace fixes 2016-02-04 16:25:51 -08:00
fjy
003f54e268 add doc rendering 2016-02-04 14:21:59 -08:00
fjy
1aa363cea7 new quickstart 2016-02-04 09:37:38 -08:00
Charles Allen
c9393e5289 Add more docs around timezone handling
* Fixes #2356
2016-02-01 08:51:07 -08:00
Bingkun Guo
b07db4089c fix doc: Setting druid.coordinator.merge.on will trigger an Append Task instead of Merge Task. 2016-01-26 10:20:32 -06:00
Slim Bouguerra
e0d90f875c Graphite emitter 2016-01-21 13:43:37 -06:00
Robin
c9368702fa do some editing of the instructions for using mysql for metadata 2016-01-21 10:37:30 -06:00
Fangjin Yang
2e54553a8f Merge pull request #1990 from himanshug/schedule_kill_task
support periodic hard delete of segments
2016-01-15 15:22:33 -06:00
Nikita Geer
1908d63162 acl for zookeeper is added 2016-01-13 14:56:05 -08:00
Himanshu Gupta
eb2d251ac8 support periodic hard delete of segments 2016-01-12 16:55:05 -06:00