fjy
c22e5b7ee0
[maven-release-plugin] prepare release druid-0.5.27
2013-08-05 18:26:10 -07:00
fjy
d1b2a5a4b3
fix indexer console serde of running tasks
2013-08-05 18:22:12 -07:00
fjy
8ff0b53df4
[maven-release-plugin] prepare for next development iteration
2013-08-05 18:00:46 -07:00
fjy
1d3729906d
[maven-release-plugin] prepare release druid-0.5.26
2013-08-05 18:00:36 -07:00
fjy
479f0cefca
fix bug with RTR not assigning tasks when a new worker is available
2013-08-05 17:57:59 -07:00
fjy
90e082463b
[maven-release-plugin] prepare for next development iteration
2013-08-05 16:10:19 -07:00
fjy
eb276d34d7
[maven-release-plugin] prepare release druid-0.5.25
2013-08-05 16:10:11 -07:00
fjy
626cf14a6e
fix bug where the curator config name was changed in one place but not another; make some info msgs into debug msgs; fix zkworker serialization
2013-08-05 16:02:26 -07:00
fjy
a95d9c46e2
[maven-release-plugin] prepare for next development iteration
2013-08-05 14:47:35 -07:00
fjy
8e1f4d3256
[maven-release-plugin] prepare release druid-0.5.24
2013-08-05 14:47:26 -07:00
fjy
66c658305f
Merge branch 'master' of github.com:metamx/druid
2013-08-05 14:44:09 -07:00
fjy
35f89d7232
make RTR idempotent to multiple run requests for same task, because higher level things in the indexing service require this behaviour
2013-08-05 14:44:01 -07:00
Gian Merlino
efd34f3a8b
TaskRunner: Fix comment
2013-08-05 14:20:31 -07:00
fjy
fbb1211cbc
[maven-release-plugin] prepare for next development iteration
2013-08-05 11:44:36 -07:00
fjy
22a90d36b7
[maven-release-plugin] prepare release druid-0.5.23
2013-08-05 11:44:28 -07:00
cheddar
3c808b15c3
1) Fix HadoopDruidIndexerConfigTest to actually verify the current correct behavior.
2013-08-05 11:37:20 -07:00
cheddar
d6ac75cff5
Merge branch 'master' of github.com:metamx/druid
2013-08-05 11:22:37 -07:00
cheddar
2b71505421
1) Fix HadoopDruidIndexerConfig to no longer replace ":" with "_" on the segmentOutputDir. The segmentOutputDir is user-supplied so they should have the ability to just not set a bad directory.
2013-08-05 11:22:26 -07:00
cheddar
e1d65e736c
Merge pull request #203 from metamx/worker-resource
...
Remove retry logic out of the Remote Task Runner and introduce Task resources
2013-08-05 11:11:21 -07:00
fjy
c33f2f06ff
fix logic of how to assign tasks to workers
2013-08-02 09:01:02 -07:00
fjy
584ccac833
move scanning of workers and tasks into RTR start, simplify bootstrap, make tests better
2013-08-01 17:50:05 -07:00
cheddar
fba2bc9623
Merge pull request #204 from metamx/close-handle
...
add the ability to unmap mmapped files
2013-08-01 14:09:46 -07:00
fjy
8f39db7804
more data to exception msgs
2013-08-01 14:04:27 -07:00
fjy
6d54ae9f81
more unit tests to test for multiple closes in different threads
2013-08-01 13:51:56 -07:00
fjy
dc169d9fcd
hide decrement and update close logic to call decrement
2013-08-01 13:24:56 -07:00
fjy
e92e0c35a4
put all concurrency test back into server manager test, introduce better concurrency for reference counting
2013-08-01 13:13:03 -07:00
fjy
b86258cc14
fix broken master UT based on changes that were discarded as part of a pull req
2013-08-01 10:44:39 -07:00
fjy
2f8351b314
fix broken ut
2013-08-01 09:41:36 -07:00
fjy
a4edc2221d
fix RTR comments
2013-07-31 15:28:52 -07:00
fjy
215d147a69
Merge branch 'worker-resource' of github.com:metamx/druid into worker-resource
2013-07-31 15:23:49 -07:00
fjy
e2b5cd6067
Merge branch 'master' of github.com:metamx/druid into worker-resource
...
Conflicts:
indexing-service/src/main/java/com/metamx/druid/indexing/worker/executor/ExecutorNode.java
2013-07-31 15:23:13 -07:00
fjy
f76540c16c
move reference counting classes out of server manager and more tests for concurrency
2013-07-31 15:14:39 -07:00
fjy
5d1fe50703
additional ut for reference counting
2013-07-30 17:55:57 -07:00
fjy
404b84823e
reference count to make sure we arent accessing any instances of a closed mmapped segment
2013-07-30 17:36:56 -07:00
Gian Merlino
eaddce06d5
Call TaskRunner.bootstrap immediately after starting it
2013-07-30 15:26:11 -07:00
cheddar
843b6650a2
Merge pull request #206 from metamx/peontimeout
...
Add a timeout in LoadQueuePeon to fail an assign if it takes too long
2013-07-30 15:08:46 -07:00
fjy
e7c6dd8112
get and reset failed assign count
2013-07-30 14:50:24 -07:00
fjy
35d8a82879
move the close method to the segment object
2013-07-30 12:24:01 -07:00
cheddar
1c5c2e0ef5
Merge pull request #205 from metamx/compress-curator
...
Toggle between compressed and non compressed service discovery
2013-07-30 11:33:43 -07:00
cheddar
66adef5d64
Merge pull request #179 from zanox/master
...
Fix path used when storing segments to HDFS
2013-07-30 11:13:29 -07:00
fjy
f55e12040f
fix according to code review
2013-07-29 18:39:14 -07:00
fjy
6a96c1fb76
fix according to code review comments
2013-07-29 17:56:19 -07:00
fjy
af6db21264
fix configs based on code review
2013-07-29 17:04:27 -07:00
fjy
091dce11c8
Add a timeout in LQP to fail an assign if it takes too long
2013-07-29 15:47:05 -07:00
fjy
50836798fa
toggle between compressed and non compressed service discovery
2013-07-29 15:40:45 -07:00
fjy
1226190279
add the ability to close mmapped files
2013-07-29 15:22:34 -07:00
fjy
ad65c8111d
fix logs
2013-07-29 11:41:42 -07:00
fjy
4ae8395538
1) on bootstrap, load all initial data and do a compare with bootstrapped tasks, delete any that are extra out there
...
2) change autoscaling logic such that it only works with remote task runnrs
3) zk workers use their own status caches to determine what they are running
2013-07-26 14:32:08 -07:00
fjy
a1262760b2
Merge branch 'master' into worker-resource
2013-07-26 10:02:15 -07:00
fjy
b0090a1de6
[maven-release-plugin] prepare for next development iteration
2013-07-25 17:26:44 -07:00
