kimchy
|
f4064038e4
|
improve load test
|
2010-07-20 20:53:14 +03:00 |
|
kimchy
|
b3b5c9b0cc
|
don't execute it on a thread pool
|
2010-07-20 18:34:01 +03:00 |
|
kimchy
|
553e8134ee
|
create a send transaction exception on the calling thread and fill its stack, so we know where its coming from
|
2010-07-20 18:33:44 +03:00 |
|
kimchy
|
07480846c3
|
fix logging to actually pass the actual logging parameters
|
2010-07-20 18:33:12 +03:00 |
|
kimchy
|
6915b39dc3
|
clean timeout listener task when removing the listener
|
2010-07-20 18:32:49 +03:00 |
|
kimchy
|
45e54c1705
|
add retry if master is not connected till master is connected or a timeout has passed to master based operations (like cluster health)
|
2010-07-20 18:32:21 +03:00 |
|
kimchy
|
45c821316b
|
no need for volatile on writer, its always accessed under a lock
|
2010-07-20 13:58:01 +03:00 |
|
kimchy
|
3c8cf68a17
|
improve timeout cluster service listener
|
2010-07-20 13:50:19 +03:00 |
|
kimchy
|
4ac1409afa
|
don't list connect exceptions
|
2010-07-20 11:01:08 +03:00 |
|
kimchy
|
679f3758b7
|
ignore a more genric exception
|
2010-07-20 09:29:10 +03:00 |
|
kimchy
|
3867591ffa
|
clean up the java api a bit
|
2010-07-20 09:18:16 +03:00 |
|
kimchy
|
2ee870e01e
|
nicer logging, append space before index + shard id logging
|
2010-07-20 08:53:57 +03:00 |
|
kimchy
|
6f2c0f4e55
|
spelling
|
2010-07-19 17:51:42 +03:00 |
|
kimchy
|
5f0470d68b
|
Support Cross-Origin resource in http/rest module, closes #218.
|
2010-07-19 15:06:13 +03:00 |
|
kimchy
|
e48b1d98db
|
more recovery under load tests, now with nodes shutdown, ignore node connected exception or retry when performing replicated operations
|
2010-07-19 11:33:21 +03:00 |
|
kimchy
|
9def68a733
|
add full rolling restart recvoery test
|
2010-07-19 10:08:12 +03:00 |
|
kimchy
|
df602054fb
|
fix relocation of primaries and perform the operation on the relocated primary replica as well
|
2010-07-19 09:54:52 +03:00 |
|
kimchy
|
0d20790ffe
|
when shutting down a node, close shard (and indices) in parallel
|
2010-07-19 02:17:59 +03:00 |
|
kimchy
|
d657d4447b
|
more shard relocation tests, create a cached executor that can be used to allocate threads that are not affected by the actual thread pool impl (can always fork, no blocking)
|
2010-07-19 01:45:09 +03:00 |
|
kimchy
|
f9cd7cb932
|
add a recovery test while under indexing load
|
2010-07-18 23:57:57 +03:00 |
|
kimchy
|
9c9dfe0b39
|
add a recovery test while under indexing load
|
2010-07-18 23:40:13 +03:00 |
|
kimchy
|
fefcfb5b5c
|
refactor recovery to be handled on the node level (and not per shard), with better retry mechanism when doing peer shard recovery
|
2010-07-18 22:54:21 +03:00 |
|
kimchy
|
8ac8dd818d
|
now that we have a file based transaction log, increate the memory clean threshold
|
2010-07-18 21:24:52 +03:00 |
|
kimchy
|
49f8501a5b
|
nicer serilization
|
2010-07-17 22:58:16 +03:00 |
|
kimchy
|
910ad2a408
|
fix optimization to not do sorting when searching with score "desc" sorting
|
2010-07-17 19:38:04 +03:00 |
|
kimchy
|
08ca383fd5
|
more work on cloud gateway
|
2010-07-17 15:20:13 +03:00 |
|
kimchy
|
6194b3ab0f
|
add NaN handling for specific hit score as well
|
2010-07-17 13:52:31 +03:00 |
|
kimchy
|
1fccaf06e9
|
start work on reimplementing cloud gateway
|
2010-07-17 13:12:53 +03:00 |
|
kimchy
|
e61dc78c21
|
max_score == NaN, closes #263.
|
2010-07-17 01:39:12 +03:00 |
|
kimchy
|
3006183191
|
fix a problem where max_score was NaN if there were no hits from a shard (though there are hits from other shards), it will still be NaN where there are no hits
|
2010-07-15 22:58:18 +03:00 |
|
kimchy
|
cf998e2f89
|
protected when not of the same type mapper when merging
|
2010-07-15 22:35:18 +03:00 |
|
kimchy
|
9f6fde9adb
|
better handling of failed merge because of different types
|
2010-07-15 20:40:40 +03:00 |
|
kimchy
|
cfa56cb3d6
|
Put Mapping: When updating existing mappings, the request returns with acknowledged `false`, closes #262.
|
2010-07-15 20:03:44 +03:00 |
|
kimchy
|
c987e8a534
|
Querying mapping on a non-master throws an error, closes #261.
|
2010-07-15 19:03:45 +03:00 |
|
kimchy
|
ee60d7dedc
|
better exception message when failing to parse a specific field
|
2010-07-15 18:46:12 +03:00 |
|
kimchy
|
ca8ad83092
|
only count data_nodes with recover_after_nodes parameter
|
2010-07-15 01:12:00 +03:00 |
|
kimchy
|
61fadb4dc0
|
use safe method (to get proper exception) to get shard injector
|
2010-07-14 23:39:19 +03:00 |
|
kimchy
|
f6fa056f1c
|
fix REST api for cluster state and the ability to filter parts of the data returned
|
2010-07-14 16:05:47 +03:00 |
|
kimchy
|
95ba62f83d
|
Translog: Implement a file system based translog and make it the default, closes #260.
|
2010-07-14 14:53:58 +03:00 |
|
kimchy
|
e7d80b8244
|
remove max_shards_per_node setting (actually, you could not set it even...), will be revisted when proper SLA based shard allocation will be implemented
|
2010-07-14 14:29:56 +03:00 |
|
kimchy
|
a6bd64f30d
|
Facet results vary depending on size, closes #259.
|
2010-07-14 11:30:39 +03:00 |
|
kimchy
|
2704ab3d69
|
improve join process in cluster, fetch the cluster meta-data on join and handle new meta data
|
2010-07-14 10:34:22 +03:00 |
|
kimchy
|
141506afc5
|
improve join process in cluster, fetch the cluster meta-data on join and handle new meta data
|
2010-07-14 09:28:56 +03:00 |
|
kimchy
|
2e2f22fbd6
|
nullify the updater on stop
|
2010-07-14 08:55:57 +03:00 |
|
kimchy
|
c4d6ccd07b
|
nicer logging
|
2010-07-14 08:41:42 +03:00 |
|
kimchy
|
234455530a
|
Make merging mappings smarter, closes #253.
|
2010-07-14 07:32:17 +03:00 |
|
kimchy
|
892dadca59
|
refactor meta data opertions into discrete services that do all operations within the cluster update process
|
2010-07-13 18:01:57 +03:00 |
|
kimchy
|
ed04721f08
|
doc
|
2010-07-13 10:19:57 +03:00 |
|
kimchy
|
f0cf552bc5
|
sorting breaks when sorting on a field that has no value in some documents
|
2010-07-13 09:38:55 +03:00 |
|
kimchy
|
e6bd3f2693
|
Put Mapping: Fail when an analyzer is specified that was not configured, closes #252.
|
2010-07-12 23:18:32 +03:00 |
|
kimchy
|
65dffdf9cf
|
throw a descriptive exception when trying to sort on multi token or multi values field per doc
|
2010-07-12 23:13:37 +03:00 |
|
kimchy
|
ff17183798
|
add more sort tests
|
2010-07-12 22:25:49 +03:00 |
|
kimchy
|
fe50a6f64e
|
improve allocation of shards based on existing work location, wait with index creation on other nodes, so listing their respective existing location will work
|
2010-07-12 01:33:38 +03:00 |
|
kimchy
|
6722e05418
|
only list unallocated shards on data nodes
|
2010-07-11 22:11:06 +03:00 |
|
kimchy
|
52ac24fa23
|
more debug statr on recovery from gateway
|
2010-07-11 21:51:45 +03:00 |
|
kimchy
|
e7a8da8236
|
do flush within the finalization of index shard recovery
|
2010-07-11 21:20:36 +03:00 |
|
kimchy
|
30b34b975c
|
fix spelling
|
2010-07-11 20:53:03 +03:00 |
|
kimchy
|
294f09a1d7
|
Shutdown API: Improve behavior when shutting down the whole cluster, closes #250.
|
2010-07-11 20:41:58 +03:00 |
|
kimchy
|
09493691a7
|
nicer serializtion
|
2010-07-11 15:41:12 +03:00 |
|
kimchy
|
671a14ce87
|
freq is always positive int
|
2010-07-11 15:35:53 +03:00 |
|
kimchy
|
a6ef805aa8
|
add doc
|
2010-07-11 00:40:29 +03:00 |
|
kimchy
|
ef369fc40f
|
javadoc
|
2010-07-10 23:21:34 +03:00 |
|
kimchy
|
d0cdbeffba
|
only send intiial state recived after sending join request, just when we actually get a new cluster state that includes us. Also, handle no nodes to send to with generic transport nodes action.
|
2010-07-10 15:43:49 +03:00 |
|
kimchy
|
a0ead02299
|
Don't create / use the work directory if not needed (for example, on client / non data) nodes, closes #249.
|
2010-07-10 14:29:39 +03:00 |
|
kimchy
|
7ba3b3a9eb
|
Zen Discovery: Control which nodes are allowed to become masters, closes #248.
|
2010-07-09 04:27:13 +03:00 |
|
kimchy
|
b657ffc5e7
|
Zen Discovery: Control which nodes are allowed to become masters, closes #248.
|
2010-07-09 04:22:03 +03:00 |
|
kimchy
|
d1f5577c40
|
add channel based read from fs snapshot, reusing the same file descriptor with direct position based reads
|
2010-07-09 03:51:36 +03:00 |
|
kimchy
|
6cdd6a015c
|
reuse file buffer
|
2010-07-09 03:24:31 +03:00 |
|
kimchy
|
d531d82cfb
|
Zen Discovery: A node might get into an infinite state of trying to find a master (when client / non_master) nodes exists, closes #247.
|
2010-07-09 00:43:06 +03:00 |
|
kimchy
|
87eb6bed8f
|
nicer logging
|
2010-07-08 22:53:41 +03:00 |
|
kimchy
|
720e6a6d5b
|
nicer logging
|
2010-07-08 22:52:03 +03:00 |
|
kimchy
|
be6aaa157f
|
fixed a bug in fs translog where it wasn't seeking correctly, and not counting the number of operations
|
2010-07-08 22:18:26 +03:00 |
|
kimchy
|
ef148077fc
|
better logging
|
2010-07-08 21:37:10 +03:00 |
|
kimchy
|
84af9f5681
|
improve handling of translog snapshotting
|
2010-07-08 20:51:37 +03:00 |
|
kimchy
|
4429a61528
|
better cleanup on shard startup failure
|
2010-07-08 19:20:03 +03:00 |
|
kimchy
|
b69fc265c5
|
index writer ram buffer size can only be 2G, make sure not to set an illegal value
|
2010-07-08 19:03:55 +03:00 |
|
kimchy
|
400ec7b8d1
|
index writer ram buffer size can only be 2G, make sure not to set an illegal value
|
2010-07-08 18:58:04 +03:00 |
|
kimchy
|
63deef42cf
|
add a help appendable blob store based on immutable one
|
2010-07-08 18:53:40 +03:00 |
|
kimchy
|
8d669ff54e
|
move sorting to be done using the new fielddata cache, and not using lucene built in FieldCache
|
2010-07-08 14:42:35 +03:00 |
|
kimchy
|
97b5b41522
|
enable eager cache eviction based on readers, requires a nasty hack to Lucene, basically overriding two classes to hook into when a reader actually gets closed (and only enabled when elasticsearch is before lucene in the classpath, which we take for in the startup scripts)
|
2010-07-07 17:15:26 +03:00 |
|
kimchy
|
a36b06c682
|
ignore failed snapshot on a non started index
|
2010-07-07 16:59:33 +03:00 |
|
kimchy
|
a8c317e355
|
fix terms facets test to take into account distributed terms request
|
2010-07-07 16:33:39 +03:00 |
|
kimchy
|
5ff46911b6
|
ignore recovery when no node to recover from (it has disconnected, for example)
|
2010-07-07 16:30:28 +03:00 |
|
kimchy
|
3fb68c52da
|
ignore snapshot on a shard thas has just been created
|
2010-07-07 16:30:17 +03:00 |
|
kimchy
|
11a8d637c0
|
ignore snapshot on a shard thas has just been created
|
2010-07-07 16:26:19 +03:00 |
|
kimchy
|
e40aa540fe
|
ignore recovery when no node to recover from (it has disconnected, for example)
|
2010-07-07 16:25:55 +03:00 |
|
kimchy
|
9578ad3ef1
|
Terms Facets: Allow to specify a set of terms to exclude in the request, closes #246.
|
2010-07-07 14:41:34 +03:00 |
|
kimchy
|
2b5458daf6
|
implement a simple file system based translog, not the defeault yet, should provide better memory management
|
2010-07-07 09:30:07 +03:00 |
|
kimchy
|
b2bdb149f9
|
log shard close failure when closing an index
|
2010-07-06 22:50:40 +03:00 |
|
kimchy
|
6aa9be238c
|
use the atomic integer counter to represent the size
|
2010-07-06 18:45:19 +03:00 |
|
kimchy
|
267016758d
|
improve handling of memory caching with file system, only force compound file when really needed (when an extension that exists within the compound file is part of the memory cached extensions)
|
2010-07-06 18:21:36 +03:00 |
|
kimchy
|
ac01bb86e8
|
clean lock only before opening an index writer
|
2010-07-06 18:13:05 +03:00 |
|
kimchy
|
2908418d37
|
checn the default byte buffer cache to 200mb, now that its global per node
|
2010-07-06 17:58:30 +03:00 |
|
kimchy
|
070cb5b295
|
allocate replica shards (backups) only after the primaries have been allocated, this results in better theoretical shard allocation, and the ability to reuse local storage index files (comared against the backup)
|
2010-07-06 17:58:05 +03:00 |
|
kimchy
|
1d39bb4d51
|
cache md5 computation for unallocated shard and reused it
|
2010-07-06 09:00:24 +03:00 |
|
kimchy
|
d4f86899e3
|
more work on reuse work dir, improved transaction log to move to stream based
|
2010-07-06 00:12:40 +03:00 |
|
kimchy
|
b078c9206a
|
more work on reuse work dir, added md5 logic to identify what need to be recovered or not, note, requires reindexing
|
2010-07-05 14:13:55 +03:00 |
|
kimchy
|
79b69764e0
|
doc
|
2010-07-01 15:03:11 +03:00 |
|
kimchy
|
e8b261c165
|
better shutdown handling
|
2010-07-01 10:28:57 +03:00 |
|
kimchy
|
ad5525f575
|
fix unwrapping of exceptions
|
2010-07-01 10:27:53 +03:00 |
|
kimchy
|
f6c9c49645
|
better logging when failing to read full content of a transport message
|
2010-07-01 03:00:57 +03:00 |
|
kimchy
|
c75a56ca17
|
better shutdown handling
|
2010-07-01 02:41:00 +03:00 |
|
kimchy
|
c2d02e4e3a
|
wrong serialization of shardId
|
2010-07-01 02:18:35 +03:00 |
|
kimchy
|
d848ab3df3
|
rename executors to esexecutors
|
2010-07-01 00:06:34 +03:00 |
|
kimchy
|
b0d736b489
|
make the shard routing an actual component
|
2010-06-30 23:39:27 +03:00 |
|
kimchy
|
811559f393
|
add another test if the pool size is greater than the core pool size before a worker can exit
|
2010-06-30 23:08:05 +03:00 |
|
kimchy
|
6709518c4e
|
add the ability to list shard index blobs without actually having one created
|
2010-06-30 22:54:59 +03:00 |
|
kimchy
|
66096e97f2
|
Remove the terms API (replaced by facets in search), closes #242.
|
2010-06-30 19:49:41 +03:00 |
|
kimchy
|
df7e3f55a4
|
improve cluster blocks data structures for simpler usage
|
2010-06-30 16:06:31 +03:00 |
|
kimchy
|
4049da97fb
|
time value to support parsing days as well
|
2010-06-30 13:00:25 +03:00 |
|
kimchy
|
088e0b5a64
|
Automatic management of indexing buffer size, closes #241.
|
2010-06-30 01:46:57 +03:00 |
|
kimchy
|
fdb2eff998
|
Automatic management of indexing buffer size, closes #241.
|
2010-06-29 22:54:54 +03:00 |
|
kimchy
|
03ac38fdba
|
better benchmark on memory monitor
|
2010-06-29 22:12:43 +03:00 |
|
kimchy
|
3f6cd46736
|
allow to configure tcp network modules (transport, memcached and http) to use blocking io (just enabling it to do some performance tests)
|
2010-06-29 21:07:38 +03:00 |
|
kimchy
|
01ff81fa89
|
fix log message
|
2010-06-29 19:49:28 +03:00 |
|
kimchy
|
bc803b4fcf
|
close the thread pool on test
|
2010-06-29 18:35:03 +03:00 |
|
kimchy
|
703657699a
|
refactor new thread pools in, remove dynamic ones
|
2010-06-29 18:20:31 +03:00 |
|
kimchy
|
de4b21e986
|
backups don't become primaries on node failures, primaries are first allocated and then start initializing from gateway
|
2010-06-29 18:20:13 +03:00 |
|
kimchy
|
514df4ee3f
|
refactor the shard routing abstraction, no need for it
|
2010-06-29 18:02:10 +03:00 |
|
kimchy
|
fe5e5a073b
|
work on scaling and blocking thread pool
|
2010-06-29 18:01:54 +03:00 |
|
kimchy
|
9051ae3a65
|
work on scaling and blocking thread pool
|
2010-06-29 17:50:05 +03:00 |
|
kimchy
|
297001de53
|
update benchmark code
|
2010-06-29 08:59:28 +03:00 |
|
kimchy
|
aa5791a14f
|
move block metadata checks to the transport level
|
2010-06-29 08:51:36 +03:00 |
|
kimchy
|
a82bf74c1c
|
expose blocks in the cluster state rest api
|
2010-06-29 01:00:07 +03:00 |
|
kimchy
|
5f538b1ba3
|
Block operation performed on cluster until it recovered from the gateway, closes #239.
|
2010-06-28 22:53:13 +03:00 |
|
kimchy
|
b970f0dcc2
|
fix toString of bytes value
|
2010-06-28 17:53:07 +03:00 |
|
kimchy
|
63523f4525
|
Query DSL: field query does not take into account `allow_leading_wildcards`, closes #236.
|
2010-06-28 12:33:36 +03:00 |
|
kimchy
|
cb9be9973b
|
add the ability to define meta _attributes for mapping, basically a place to store additional unstructured data on the mapping
|
2010-06-28 09:10:08 +03:00 |
|
kimchy
|
3770924300
|
allow to control the buffer size of the gateway blob container
|
2010-06-27 23:26:32 +03:00 |
|
kimchy
|
a7c13826da
|
more work on reusing work directory, clean unallocated shards when they are not needed
|
2010-06-27 18:19:12 +03:00 |
|
kimchy
|
b43f0f5965
|
add streamable to stores files metadata
|
2010-06-27 14:18:14 +03:00 |
|
kimchy
|
4ae45946a2
|
nicer logging
|
2010-06-27 13:50:27 +03:00 |
|
kimchy
|
fc7392a98b
|
fix logging
|
2010-06-27 13:07:21 +03:00 |
|
kimchy
|
90c995dda5
|
add todo
|
2010-06-27 12:28:30 +03:00 |
|
kimchy
|
1e7481d5ab
|
fix logging
|
2010-06-27 12:15:58 +03:00 |
|
kimchy
|
c56609a0ad
|
fix default merge size to not truncate on long
|
2010-06-27 12:14:38 +03:00 |
|
kimchy
|
bbb9c3883f
|
fix jdoc
|
2010-06-27 12:05:30 +03:00 |
|
kimchy
|
f1f695b4d9
|
fix logging
|
2010-06-27 09:39:07 +03:00 |
|
kimchy
|
b9590b5ed6
|
fix logging
|
2010-06-27 09:37:44 +03:00 |
|
kimchy
|
edd8786a81
|
close open index input on failure
|
2010-06-27 02:13:59 +03:00 |
|
kimchy
|
33d357dbb4
|
Memory Store / FS Memory: Create a node level memory store cache and allocator, closes #235.
|
2010-06-26 22:34:30 +03:00 |
|
kimchy
|
00d2abef40
|
refactor facets builder API to make it more manageable
|
2010-06-26 01:36:42 +03:00 |
|
kimchy
|
5df2257319
|
add test for facets with search size 0
|
2010-06-25 22:46:07 +03:00 |
|
kimchy
|
83010f7ee1
|
more apis on the index level store to help clean unused work shards when needed
|
2010-06-25 03:39:42 +03:00 |
|
kimchy
|
811856e1f8
|
better method name
|
2010-06-25 01:41:06 +03:00 |
|
kimchy
|
98e93322ae
|
use java user.dir as the default "path.home" location
|
2010-06-24 22:11:13 +03:00 |
|
kimchy
|
4709f00790
|
add to index store the ability to get the backing store free / total space
|
2010-06-24 18:05:21 +03:00 |
|
kimchy
|
edf0075025
|
more work on reusing work node level data, now when recovering from peers
|
2010-06-24 15:34:02 +03:00 |
|
kimchy
|
57169d4233
|
initial work on reusing work node level data when recovering from gateway
|
2010-06-24 00:32:05 +03:00 |
|
kimchy
|
0d7cebbaf0
|
upgrade to async http client 1.0.0
|
2010-06-23 21:51:29 +03:00 |