Related
I am trying to build a query to search for records in the following format: TR000002_1_2020.
Users should be able to search for results the following ways:
TR000002 or 2_1_2020 or TR000002_1_2020 or 2020. I figured an ngram tokenization query would be best suited for my needs. I am using Elasticsearch 6.8 so I cannot use the built in Search-As-You-Type introduced in E7.
Here's my implementation I followed from docs here. The only thing I modified was EdgeNGram -> NGram as the user can search from any point of the text.
My Analysis block looks like this:
.Analysis(a => a
.Analyzers(aa => aa
.Custom("autocomplete", ca => ca
.Tokenizer("autocomplete")
.Filters(new string[] {
"lowercase"
})
)
.Custom("autocomplete_search", ca => ca
.Tokenizer("lowercase")
)
)
.Tokenizers(t => t
.NGram("autocomplete", e => e
.MinGram(2)
.MaxGram(16)
.TokenChars(new TokenChar[] {
TokenChar.Letter,
TokenChar.Digit,
TokenChar.Punctuation,
TokenChar.Symbol
})
)
)
)
Then in my mapping I define:
.Text(t => t
.Name(tr => tr.TestRecordId)
.Analyzer("autocomplete")
.SearchAnalyzer("autocomplete_search")
)
When I search for TR000002, my query returns all results instead of just the records that contain those specific characters. What am I doing wrong? Is there a better tokenizer for this specific use case? Thanks!
EDIT: Here's a sample of what is returned:
{
"took" : 5,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : 27,
"max_score" : 0.105360515,
"hits" : [
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "3",
"_score" : 0.105360515,
"_source" : {
"id" : 3,
"testRecordId" : "TR000002_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 12,
"testStatus" : {
"testStatusId" : 12,
"name" : "Complete: Postponed Until Further Notice"
},
"discriminator" : "SingleEventEffectsRecord",
"testRecordServiceOrders" : [
{
"testRecordId" : 3,
"serviceOrderId" : 9,
"serviceOrder" : {
"serviceOrderId" : 9,
"serviceOrderNumber" : "105702"
}
}
],
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
},
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false,
"sEETestRates" : [ ]
}
},
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "11",
"_score" : 0.105360515,
"_source" : {
"id" : 11,
"testRecordId" : "TR000011_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 1,
"testStatus" : {
"testStatusId" : 1,
"name" : "Active"
},
"discriminator" : "TotalIonizingDoseRecord",
"creatorUsername" : "[REDACTED]",
"creator" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"testRecordServiceOrders" : [ ],
"partLDC" : "12",
"waferLot" : "1",
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false,
"testStartDate" : "2020-07-30T00:00:00",
"actualCompletionDate" : "2020-07-31T00:00:00"
}
},
{
"_index" : "test-records-development-09-09-2020-02-00-00",
"_type" : "testrecorddto",
"_id" : "17",
"_score" : 0.105360515,
"_source" : {
"id" : 17,
"testRecordId" : "TR000017_1_2020",
"type" : 0,
"typeName" : "TIDCo60",
"missionId" : 1,
"mission" : {
"missionId" : 1,
"name" : "[REDACTED]",
"mRPLUsername" : "[REDACTED]",
"missionRadiationPartsLead" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"missionInstruments" : [
{
"missionId" : 1,
"instrumentId" : 1,
"cognizantEngineerUsername" : "[REDACTED]",
"instrument" : {
"intstrumentId" : 1,
"name" : "Instrument"
},
"cognizantEngineer" : {
"username" : "lewallen",
"displayName" : "[REDACTED]"
}
},
{
"missionId" : 1,
"instrumentId" : 2,
"instrument" : {
"intstrumentId" : 2,
"name" : "Instrument 2"
}
}
]
},
"procurementPartId" : 2,
"procurementPart" : {
"procurementPartId" : 2,
"partNumber" : "procurement part",
"part" : {
"partId" : 1,
"manufacturer" : "Texas Instruments",
"genericPartNumber" : "123",
"description" : "description",
"partTechnology" : "Part Tech"
}
},
"testStatusId" : 1,
"testStatus" : {
"testStatusId" : 1,
"name" : "Active"
},
"discriminator" : "TotalIonizingDoseRecord",
"creatorUsername" : "[REDACTED]",
"creator" : {
"username" : "[REDACTED]",
"displayName" : "[REDACTED]"
},
"testRecordServiceOrders" : [ ],
"rtdbFiles" : [ ],
"personnelGroups" : [
{
"personnelGroupUsers" : [ ]
}
],
"testRecordTestSubTypes" : [ ],
"testRecordTestFacilityConditions" : [ ],
"testRecordFollowers" : [ ],
"isDeleted" : false
}
},
Also here's what shows for mapping:
"testRecordId" : {
"type" : "text",
"analyzer" : "autocomplete",
"search_analyzer" : "autocomplete_search"
},
I guess I should also mention, I've been testing this query in the console like so:
GET test-records-development/_search
{
"query": {
"match": {
"testRecordId": {
"query": "TR000002_1_2020"
}
}
}
}
EDIT 2: Added API response from index _settings endpoint:
{
"test-records-development-09-09-2020-02-00-00" : {
"settings" : {
"index" : {
"number_of_shards" : "5",
"provided_name" : "test-records-development-09-09-2020-02-00-00",
"creation_date" : "1599617013874",
"analysis" : {
"analyzer" : {
"autocomplete" : {
"filter" : [
"lowercase"
],
"type" : "custom",
"tokenizer" : "autocomplete"
},
"autocomplete_search" : {
"type" : "custom",
"tokenizer" : "lowercase"
}
},
"tokenizer" : {
"autocomplete" : {
"token_chars" : [
"letter",
"digit",
"punctuation",
"symbol"
],
"min_gram" : "2",
"type" : "ngram",
"max_gram" : "16"
}
}
},
"number_of_replicas" : "0",
"uuid" : "FSeCa0YwRCOJVbjfxYGkig",
"version" : {
"created" : "6080199"
}
}
}
}
}
As I don't have the analyzer setting access in JSON format,I can't confirm it but most probably issue is with your search analyzer autocomplete_search which is creating search time tokens which are matching the index time tokens.
For example: you are searching for TR000002_1_2020 and if it creates 2020 as a token and for document containing TR000011_1_2020 also creates a 2020 token than your query will match it.
You can use the analyze API to check the generated tokens based on a analyzer and as mentioned earlier mostly there is some tokens which are matching as shown above.
I'm using Elasticsearch 6.6 and have an index (1 shard, 1 replica) with the geonames (https://www.geonames.org/) dataset indexed (indexsize =1.3 gb, 11.8 mio geopoints).
I was playing around a bit with the geo distance sorting query, sorting the whole index for some origin points. So after some testing I saw that sorting ascending is always faster than sorting descending. here is an example query (i also tested with bigger "size"-parameter):
POST /geonames/_search?request_cache=false
{
"size":1,
"sort" : [
{
"_geo_distance" : {
"location" : [8, 49],
"order" : "asc",
"unit" : "m",
"mode" : "min",
"distance_type" : "arc",
"ignore_unmapped": true
}
}
]
}
Here is the answer for ascending sorting (with explain and profile True):
{
"took" : 1374,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : 11858060,
"max_score" : null,
"hits" : [
{
"_shard" : "[geonames][0]",
"_node" : "qXTymyB9QLmxhPtGEtA_mA",
"_index" : "geonames",
"_type" : "doc",
"_id" : "L781LmkBrQo0YN4qP48D",
"_score" : null,
"_source" : {
"id" : "3034701",
"name" : "Forêt de Wissembourg",
"location" : {
"lat" : "49.00924",
"lon" : "8.01542"
}
},
"sort" : [
1523.4121312414704
],
"_explanation" : {
"value" : 1.0,
"description" : "*:*",
"details" : [ ]
}
}
]
},
"profile" : {
"shards" : [
{
"id" : "[qXTymyB9QLmxhPtGEtA_mA][geonames][0]",
"searches" : [
{
"query" : [
{
"type" : "MatchAllDocsQuery",
"description" : "*:*",
"time_in_nanos" : 265223567,
"breakdown" : {
"score" : 0,
"build_scorer_count" : 54,
"match_count" : 0,
"create_weight" : 10209,
"next_doc" : 253091268,
"match" : 0,
"create_weight_count" : 1,
"next_doc_count" : 11858087,
"score_count" : 0,
"build_scorer" : 263948,
"advance" : 0,
"advance_count" : 0
}
}
],
"rewrite_time" : 1097,
"collector" : [
{
"name" : "CancellableCollector",
"reason" : "search_cancelled",
"time_in_nanos" : 1044167746,
"children" : [
{
"name" : "SimpleFieldCollector",
"reason" : "search_top_hits",
"time_in_nanos" : 508296683
}
]
}
]
}
],
"aggregations" : [ ]
}
]
}
}
and here for descending, just switched the parameter from asc to desc (also with profile and explain):
{
"took" : 2226,
"timed_out" : false,
"_shards" : {
"total" : 1,
"successful" : 1,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : 11858060,
"max_score" : null,
"hits" : [
{
"_shard" : "[geonames][0]",
"_node" : "qXTymyB9QLmxhPtGEtA_mA",
"_index" : "geonames",
"_type" : "doc",
"_id" : "Mq80LmkBrQo0YN4q11bA",
"_score" : null,
"_source" : {
"id" : "4036351",
"name" : "Bollons Seamount",
"location" : {
"lat" : "-49.66667",
"lon" : "-176.16667"
}
},
"sort" : [
1.970427111052182E7
],
"_explanation" : {
"value" : 1.0,
"description" : "*:*",
"details" : [ ]
}
}
]
},
"profile" : {
"shards" : [
{
"id" : "[qXTymyB9QLmxhPtGEtA_mA][geonames][0]",
"searches" : [
{
"query" : [
{
"type" : "MatchAllDocsQuery",
"description" : "*:*",
"time_in_nanos" : 268521404,
"breakdown" : {
"score" : 0,
"build_scorer_count" : 54,
"match_count" : 0,
"create_weight" : 9333,
"next_doc" : 256458664,
"match" : 0,
"create_weight_count" : 1,
"next_doc_count" : 11858087,
"score_count" : 0,
"build_scorer" : 195265,
"advance" : 0,
"advance_count" : 0
}
}
],
"rewrite_time" : 1142,
"collector" : [
{
"name" : "CancellableCollector",
"reason" : "search_cancelled",
"time_in_nanos" : 1898324618,
"children" : [
{
"name" : "SimpleFieldCollector",
"reason" : "search_top_hits",
"time_in_nanos" : 1368306442
}
]
}
]
}
],
"aggregations" : [ ]
}
]
}
}
So my question is, why is it like this ? As I understood Es calculates the distance from the origin point to every other point and then sorts them. So why is the descending sorting so much slower ?
Asking the same question on the Elasticsearch board and getting an answer.
So apparantly Elasticsearch uses differnt searching strategies/algorithms for ascending end descending distance sorting.
For the descending sorting it calculates the distance from the origin to every point end then sorts.
For the ascending sorting it uses boundingboxes to filter points near the origin and only calculate the distances for points inside the boundingboxes.
I need to have average of cpuload on specific nodetype. For example if I give nodetype as tpt it should give the average of cpuload of nodetype's of all tpt available. I tried different methods but vain...
My data in elasticsearch is below:
{
"took" : 5,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"failed" : 0
},
"hits" : {
"total" : 4,
"max_score" : 1.0,
"hits" : [
{
"_index" : "kpi",
"_type" : "kpi",
"_id" : "\u0003",
"_score" : 1.0,
"_source" : {
"kpi" : {
"CpuAverageLoad" : 13,
"NodeId" : "kishan",
"NodeType" : "Tpt",
"State" : "online",
"Static_limit" : 0
}
}
},
{
"_index" : "kpi",
"_type" : "kpi",
"_id" : "\u0005",
"_score" : 1.0,
"_source" : {
"kpi" : {
"CpuAverageLoad" : 15,
"NodeId" : "kishan1",
"NodeType" : "tpt",
"State" : "online",
"Static_limit" : 0
}
}
},
{
"_index" : "kpi",
"_type" : "kpi",
"_id" : "\u0004",
"_score" : 1.0,
"_source" : {
"kpi" : {
"MaxLbCapacity" : "700000",
"NodeId" : "kishan2",
"NodeType" : "bang",
"OnlineCSCF" : [
"001",
"002"
],
"State" : "Online",
"TdbGroup" : 1,
"TdGroup" : 0
}
}
},
{
"_index" : "kpi",
"_type" : "kpi",
"_id" : "\u0002",
"_score" : 1.0,
"_source" : {
"kpi" : {
"MaxLbCapacity" : "700000",
"NodeId" : "kishan3",
"NodeType" : "bang",
"OnlineCSCF" : [
"001",
"002"
],
"State" : "Online",
"TdLGroup" : 1,
"TGroup" : 0
}
}
}
]
}
}
And my query is
curl -XGET 'localhost:9200/_search?pretty' -H 'Content-Type: application/json' -d'
{
"query": {
"bool" : {
"must" : {
"script" : {
"script" : {
"source" : "kpi[CpuAverageLoad].value > params.param1",
"lang" : "painless",
"params" : {
"param1" : 5
}
}
}
}
}
}
}'
but is falling as it is unable to find the exact source.
{
"error" : {
"root_cause" : [
{
"type" : "illegal_argument_exception",
"reason" : "[script] unknown field [source], parser not found"
}
],
"type" : "illegal_argument_exception",
"reason" : "[script] unknown field [source], parser not found"
},
"status" : 400
}
I need sumttf of ONE document in a field. However I can get sumttf of all documents only...
I need to be able to access the variable in script like _index['field'].sumttf() of that particular document. This is what I've got so far.
Mapping:
{"document2" : {
"mappings" : {
"document2" : {
"_all" : {
"enabled" : false
},
"properties" : {
"content" : {
"type" : "string",
"term_vector" : "yes",
"fields" : {
"with_shingles" : {
"type" : "string",
"analyzer" : "my_shingle_analyzer"
}
}
},
...
Term vector:
"_index" : "document2",
"_type" : "document2",
"_id" : "709718",
"_version" : 1,
"term_vectors" : {
"content" : {
"field_statistics" : {
"sum_doc_freq" : 60676474,
"doc_count" : 198373,
"sum_ttf" : 224960172
},
terms" : {
"0" : {
"term_freq" : 8
},
"0.5" : {
"term_freq" : 1
},
"003a0e45ea07a" : {
"term_freq" : 1
},
"005" : {
"term_freq" : 1
},
"0081989" : {
"term_freq" : 1
},
"01" : {
"term_freq" : 1
},
"01.08.2002" : {
"term_freq" : 1
},
...
I have setup a cluster with 3 elasticsearch instances and they are being feed with documents provided by logstash (~165K docs per minute). I have those 3 machines with 16Gb RAM and each instance is started up with 8Gb.
The indexing works quite well, and I'm able to perform all required search operations I was expecting. The thing now is that I want to make it general available, but unfortunately depending on the queries that are executed (i.e. range facets over all indexes) it freezes the entire cluster and ends up in a split-brain state.
I already limited some things like:
indices.memory.index_buffer_size: 30%
indices.memory.min_shard_index_buffer_size: 12mb
indices.memory.min_index_buffer_size: 96mb
indices.fielddata.cache.size: 15%
indices.fielddata.cache.expire: 6h
indices.cache.filter.size: 15%
indices.cache.filter.expire: 6h
My entire config file looks like:
index.number_of_shards: 10
index.number_of_replicas: 0
bootstrap.mlockall: true
# Indices settings
indices.memory.index_buffer_size: 30%
indices.memory.min_shard_index_buffer_size: 12mb
indices.memory.min_index_buffer_size: 96mb
# Cache Sizes
indices.fielddata.cache.size: 15%
indices.fielddata.cache.expire: 6h
indices.cache.filter.size: 15%
indices.cache.filter.expire: 6h
# Indexing Settings for Writes
index.refresh_interval: 30s
index.translog.flush_threshold_ops: 50000
Is there something else I could improve here to avoid such freeze and split brain state?
Output of my nodes info:
{
"cluster_name" : "elasticsearch",
"nodes" : {
"7i5sZj_jT_qe6HNESfzO3A" : {
"name" : "Captain Fate",
"transport_address" : "inet[/192.168.0.83:9300]",
"host" : "esserver02",
"ip" : "192.168.0.83",
"version" : "1.1.1",
"build" : "f1585f0",
"http_address" : "inet[/192.168.0.83:9200]",
"settings" : {
"index" : {
"number_of_replicas" : "0",
"translog" : {
"flush_threshold_ops" : "50000"
},
"number_of_shards" : "40",
"refresh_interval" : "30s"
},
"bootstrap" : {
"mlockall" : "true"
},
"transport" : {
"tcp" : {
"port" : "9300"
}
},
"http" : {
"port" : "9200"
},
"name" : "Captain Fate",
"path" : {
"logs" : "/opt/as/es/logs",
"home" : "/opt/as/es"
},
"cluster" : {
"name" : "elasticsearch"
},
"indices" : {
"memory" : {
"index_buffer_size" : "50%",
"min_shard_index_buffer_size" : "12mb",
"min_index_buffer_size" : "96mb"
}
},
"discovery" : {
"zen" : {
"minimum_master_nodes" : "1",
"ping" : {
"unicast" : {
"hosts" : [ "esserver02", "esserver03", "esserver04" ]
},
"multicast" : {
"enabled" : "false"
},
"timeout" : "30s"
}
}
}
},
"os" : {
"refresh_interval" : 1000,
"available_processors" : 16
},
"process" : {
"refresh_interval" : 1000,
"id" : 8482,
"max_file_descriptors" : 128000,
"mlockall" : false
},
"jvm" : {
"pid" : 8482,
"version" : "1.7.0_45",
"vm_name" : "Java HotSpot(TM) 64-Bit Server VM",
"vm_version" : "24.45-b08",
"vm_vendor" : "Oracle Corporation",
"start_time" : 1411976625093,
"mem" : {
"heap_init_in_bytes" : 2147483648,
"heap_max_in_bytes" : 12771524608,
"non_heap_init_in_bytes" : 24313856,
"non_heap_max_in_bytes" : 136314880,
"direct_max_in_bytes" : 12771524608
},
"gc_collectors" : [ "ParNew", "ConcurrentMarkSweep" ],
"memory_pools" : [ "Code Cache", "Par Eden Space", "Par Survivor Space", "CMS Old Gen", "CMS Perm Gen" ]
},
"thread_pool" : {
"generic" : {
"type" : "cached",
"keep_alive" : "30s"
},
"index" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "200"
},
"get" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"snapshot" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"merge" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"suggest" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"bulk" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "50"
},
"optimize" : {
"type" : "fixed",
"min" : 1,
"max" : 1
},
"warmer" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"flush" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"search" : {
"type" : "fixed",
"min" : 48,
"max" : 48,
"queue_size" : "1k"
},
"percolate" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"management" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"refresh" : {
"type" : "scaling",
"min" : 1,
"max" : 8,
"keep_alive" : "5m"
}
},
"network" : {
"refresh_interval" : 5000
},
"transport" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0:9300]",
"publish_address" : "inet[/192.168.0.83:9300]"
},
"http" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0:9200]",
"publish_address" : "inet[/192.168.0.83:9200]",
"max_content_length_in_bytes" : 104857600
},
"plugins" : [ {
"name" : "head",
"version" : "NA",
"description" : "No description found.",
"url" : "/_plugin/head/",
"jvm" : false,
"site" : true
} ]
},
"0OaMqY6IR1SYeL6rd6P61Q" : {
"name" : "Blonde Phantom",
"transport_address" : "inet[/192.168.0.100:9300]",
"host" : "esserver03",
"ip" : "192.168.0.100",
"version" : "1.1.1",
"build" : "f1585f0",
"http_address" : "inet[/192.168.0.100:9200]",
"settings" : {
"index" : {
"number_of_replicas" : "0",
"translog" : {
"flush_threshold_ops" : "50000"
},
"number_of_shards" : "40",
"refresh_interval" : "30s"
},
"bootstrap" : {
"mlockall" : "true"
},
"transport" : {
"tcp" : {
"port" : "9300"
}
},
"http" : {
"port" : "9200"
},
"name" : "Blonde Phantom",
"path" : {
"logs" : "/opt/as/es/logs",
"home" : "/opt/as/es"
},
"cluster" : {
"name" : "elasticsearch"
},
"indices" : {
"memory" : {
"index_buffer_size" : "50%",
"min_shard_index_buffer_size" : "12mb",
"min_index_buffer_size" : "96mb"
}
},
"discovery" : {
"zen" : {
"minimum_master_nodes" : "1",
"ping" : {
"unicast" : {
"hosts" : [ "esserver02", "esserver03", "esserver04" ]
},
"multicast" : {
"enabled" : "false"
},
"timeout" : "30s"
}
}
}
},
"os" : {
"refresh_interval" : 1000,
"available_processors" : 16
},
"process" : {
"refresh_interval" : 1000,
"id" : 98772,
"max_file_descriptors" : 128000,
"mlockall" : false
},
"jvm" : {
"pid" : 98772,
"version" : "1.7.0_45",
"vm_name" : "Java HotSpot(TM) 64-Bit Server VM",
"vm_version" : "24.45-b08",
"vm_vendor" : "Oracle Corporation",
"start_time" : 1414657551806,
"mem" : {
"heap_init_in_bytes" : 2147483648,
"heap_max_in_bytes" : 12771524608,
"non_heap_init_in_bytes" : 24313856,
"non_heap_max_in_bytes" : 136314880,
"direct_max_in_bytes" : 12771524608
},
"gc_collectors" : [ "ParNew", "ConcurrentMarkSweep" ],
"memory_pools" : [ "Code Cache", "Par Eden Space", "Par Survivor Space", "CMS Old Gen", "CMS Perm Gen" ]
},
"thread_pool" : {
"generic" : {
"type" : "cached",
"keep_alive" : "30s"
},
"index" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "200"
},
"get" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"snapshot" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"merge" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"suggest" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"bulk" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "50"
},
"optimize" : {
"type" : "fixed",
"min" : 1,
"max" : 1
},
"warmer" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"flush" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"search" : {
"type" : "fixed",
"min" : 48,
"max" : 48,
"queue_size" : "1k"
},
"percolate" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"management" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"refresh" : {
"type" : "scaling",
"min" : 1,
"max" : 8,
"keep_alive" : "5m"
}
},
"network" : {
"refresh_interval" : 5000,
"primary_interface" : {
"address" : "",
"name" : "",
"mac_address" : ""
}
},
"transport" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0%0:9300]",
"publish_address" : "inet[/192.168.0.100:9300]"
},
"http" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0%0:9200]",
"publish_address" : "inet[/192.168.0.100:9200]",
"max_content_length_in_bytes" : 104857600
},
"plugins" : [ {
"name" : "head",
"version" : "NA",
"description" : "No description found.",
"url" : "/_plugin/head/",
"jvm" : false,
"site" : true
} ]
},
"H2h01oNGSuCL0uu8J3SF6w" : {
"name" : "Dakimh the Enchanter",
"transport_address" : "inet[/192.168.0.101:9300]",
"host" : "esserver04",
"ip" : "192.168.0.101",
"version" : "1.1.1",
"build" : "f1585f0",
"http_address" : "inet[/192.168.0.101:9200]",
"settings" : {
"index" : {
"number_of_replicas" : "0",
"translog" : {
"flush_threshold_ops" : "50000"
},
"number_of_shards" : "40",
"refresh_interval" : "30s"
},
"bootstrap" : {
"mlockall" : "true"
},
"transport" : {
"tcp" : {
"port" : "9300"
}
},
"http" : {
"port" : "9200"
},
"name" : "Dakimh the Enchanter",
"path" : {
"logs" : "/opt/as/es/logs",
"home" : "/opt/as/es"
},
"cluster" : {
"name" : "elasticsearch"
},
"indices" : {
"memory" : {
"index_buffer_size" : "50%",
"min_shard_index_buffer_size" : "12mb",
"min_index_buffer_size" : "96mb"
}
},
"discovery" : {
"zen" : {
"minimum_master_nodes" : "1",
"ping" : {
"unicast" : {
"hosts" : [ "esserver02", "esserver03", "esserver04" ]
},
"multicast" : {
"enabled" : "false"
},
"timeout" : "30s"
}
}
}
},
"os" : {
"refresh_interval" : 1000,
"available_processors" : 16
},
"process" : {
"refresh_interval" : 1000,
"id" : 88019,
"max_file_descriptors" : 128000,
"mlockall" : false
},
"jvm" : {
"pid" : 88019,
"version" : "1.7.0_45",
"vm_name" : "Java HotSpot(TM) 64-Bit Server VM",
"vm_version" : "24.45-b08",
"vm_vendor" : "Oracle Corporation",
"start_time" : 1414657560829,
"mem" : {
"heap_init_in_bytes" : 2147483648,
"heap_max_in_bytes" : 12771524608,
"non_heap_init_in_bytes" : 24313856,
"non_heap_max_in_bytes" : 136314880,
"direct_max_in_bytes" : 12771524608
},
"gc_collectors" : [ "ParNew", "ConcurrentMarkSweep" ],
"memory_pools" : [ "Code Cache", "Par Eden Space", "Par Survivor Space", "CMS Old Gen", "CMS Perm Gen" ]
},
"thread_pool" : {
"generic" : {
"type" : "cached",
"keep_alive" : "30s"
},
"index" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "200"
},
"get" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"snapshot" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"merge" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"suggest" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"bulk" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "50"
},
"optimize" : {
"type" : "fixed",
"min" : 1,
"max" : 1
},
"warmer" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"flush" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"search" : {
"type" : "fixed",
"min" : 48,
"max" : 48,
"queue_size" : "1k"
},
"percolate" : {
"type" : "fixed",
"min" : 16,
"max" : 16,
"queue_size" : "1k"
},
"management" : {
"type" : "scaling",
"min" : 1,
"max" : 5,
"keep_alive" : "5m"
},
"refresh" : {
"type" : "scaling",
"min" : 1,
"max" : 8,
"keep_alive" : "5m"
}
},
"network" : {
"refresh_interval" : 5000,
"primary_interface" : {
"address" : "",
"name" : "",
"mac_address" : ""
}
},
"transport" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0%0:9300]",
"publish_address" : "inet[/192.168.0.101:9300]"
},
"http" : {
"bound_address" : "inet[/0:0:0:0:0:0:0:0%0:9200]",
"publish_address" : "inet[/192.168.0.101:9200]",
"max_content_length_in_bytes" : 104857600
},
"plugins" : [ {
"name" : "head",
"version" : "NA",
"description" : "No description found.",
"url" : "/_plugin/head/",
"jvm" : false,
"site" : true
} ]
}
}
}
My old configuration:
index.number_of_shards: 40
index.number_of_replicas: 0
bootstrap.mlockall: true
## Threadpool Settings ##
# Indices settings
indices.memory.index_buffer_size: 50%
indices.memory.min_shard_index_buffer_size: 12mb
indices.memory.min_index_buffer_size: 96mb
# Indexing Settings for Writes
index.refresh_interval: 30s
index.translog.flush_threshold_ops: 50000
Your indices.fielddata.cache.size is set to 15% only. Why?
These data are used for aggregations/facets so it could be related. You should remove indices.fielddata.cache.expire ASAP : this setting is really not recommended at all, as evictions are really costful and it schedules evictions for fielddata values, even if they are used. Could you give us the result of a node stats API ?
Update 1 :
I see minimum_master_nodes is set to 1, but you say you have 3 nodes. This should be set to 2 according to the equation generally used (number of nodes/2 + 1, documentation)
Update 2 :
Do you still experience split-brains with the updated configuration?
Depending on your cluster ES version (> 1.0) , you might want to tune the fielddata circuit-breaker to prevent the most costly requests to be done : take a look here.