Hi Team,
ElasticSearch : 6.0.0
Operating System : CentOS 7
JVM arguments [-Xms4g, -Xmx4g, -XX:MaxMetaspaceSize=512m, -XX:+UseParNewGC, -XX:NewSize=128m, -XX:MaxNewSize=128m, -XX:SurvivorRatio=1024, -XX:MaxGCPauseMillis=1000, -XX:+UseCompressedOops, -XX:ParallelGCThreads=8, -XX:ConcGCThreads=8, -XX:+DisableExplicitGC, -XX:+UseConcMarkSweepGC, -XX:CMSInitiatingOccupancyFraction=50, -XX:+UseCMSInitiatingOccupancyOnly, -XX:+AlwaysPreTouch, -Xss1m, -Djava.awt.headless=true, -Dfile.encoding=UTF-8, -Djna.nosys=true, -XX:-OmitStackTraceInFastThrow, -Dio.netty.noUnsafe=true, -Dio.netty.noKeySetOptimization=true, -Dio.netty.recycler.maxCapacityPerThread=0, -Dlog4j.shutdownHookEnabled=false, -Dlog4j2.disable.jmx=true, -XX:+HeapDumpOnOutOfMemoryError, -XX:HeapDumpPath=/home/somasekhar.k/softwares/ES6/logs/ESHeapDump.hprof, -XX:+PrintGCDetails, -XX:+PrintGCTimeStamps, -Xloggc:/home/somasekhar.k/softwares/ES6/logs/gc.log, -XX:+UseGCLogFileRotation, -XX:NumberOfGCLogFiles=32, -XX:GCLogFileSize=128M, -Des.path.home=/home/somasekhar.k/softwares/ES6, -Des.path.conf=/home/somasekhar.k/softwares/ES6/config
Index Mapping Details :
{"2_1024": {"aliases": {},"mappings": {"2_1024": {"properties": {1: {"type": "text"},
2: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
4: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
5: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
6: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
7: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
8: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
9: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
10: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
11: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
12: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
13: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
14: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
15: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
16: {"type": "text","fields": {"exactMatch": {"type": "keyword"},"phoneticMatch": {"type": "text","analyzer": "phonetic_analyzer"},"subStringMatch": {"type": "text","analyzer": "substring_analyzer"}}},
"@timestamp": {"type": "date"},"@version": {"type": "text","fields": {"keyword": {"type": "keyword","ignore_above": 256}}},
"query": {"properties": {"term": {"properties": {7: {"properties": {"exactMatch": {"type": "text","fields": {"keyword": {"type": "keyword","ignore_above": 256}}}}}}}}},"size": {"type": "long"},"type": {"type": "text","fields": {"keyword": {"type": "keyword","ignore_above": 256}}}}}},"settings": {"index": {"number_of_shards": "1","provided_name": "2_1024","creation_date": "1541681596965","analysis": {"filter": {"phonetic_filter": {"type": "phonetic","encoder": "double_metaphone"}},"analyzer": {"phonetic_analyzer": {"filter": ["phonetic_filter","lowercase"],"tokenizer": "standard"},"substring_analyzer": {"filter": "lowercase","tokenizer": "substring_tokenizer"}},"tokenizer": {"substring_tokenizer": {"token_chars": ["letter","digit"],"min_gram": "3","type": "ngram","max_gram": "3"}}},"number_of_replicas": "0","uuid": "aFpNgjSXQA2eaepVYbjylg","version": {"created": "6000099"}}}}}
All search threads(13) are waiting same place.I taken jstack multiple times but every time showing same place.Please refer below Jstack snapshot
No of Nodes : 1
No of Index in ES : 2
Each Index Size : 1GB
No of Shards for Index : 1
No of Document in each Index : 1Million
No of search requests 1 Million using Low level rest client and doing exact match
Query : {"size":0,"_source":false,"query":{"term":{"7.exactMatch":"Subex__www200"}}}
I can't add more nodes to cluster.I increased no of shards to 2,3 and 5 but no improve on speed wise.
I checked Disk I/O statistics also but IOWaiting is o.13% only
Network Speed : 100M/sec
I tried Shard Request Cache,Indices queries Cache,Decreasing Semants from 15 to 1 and Pre-loading data into the file system cache but no improvement on search speed.
I need to know why search threads waiting same place and how to overcome this problem
I am try achieve latency and throughput using single client and single node.