即使我使用ES群集更新了每个节点的文件限制，我也遇到了这个错误。我的设置是一个6节点的集群，有大约6.3亿个文档被索引。
在我重新启动群集的过程中发生了此错误：
[2013-11-11 00:00:21,087][WARN ][index.engine.robin ] [rap-es-3] [zt_2012][11] failed to read latest segment infos on flush
java.io.FileNotFoundException: /data/elasticsearch/data/Odine/nodes/0/indices/zt_2012/11/index/segments_e (Too many open files)
at java.io.RandomAccessFile.open(Native Method)
at java.io.RandomAccessFile.<init>(Unknown Source)
at org.apache.lucene.store.FSDirectory$FSIndexInput.<init>(FSDirectory.java:410)
at org.apache.lucene.store.NIOFSDirectory$NIOFSIndexInput.<init>(NIOFSDirectory.java:123)
at org.apache.lucene.store.NIOFSDirectory.openInput(NIOFSDirectory.java:80)
at org.apache.lucene.store.RateLimitedFSDirectory.openInput(RateLimitedFSDirectory.java:99)
at org.elasticsearch.index.store.Store$StoreDirectory.openInput(Store.java:436)
at org.apache.lucene.index.SegmentInfos.read(SegmentInfos.java:318)
at org.apache.lucene.index.SegmentInfos$1.doBody(SegmentInfos.java:380)
at org.apache.lucene.index.SegmentInfos$FindSegmentsFile.run(SegmentInfos.java:812)
at org.apache.lucene.index.SegmentInfos$FindSegmentsFile.run(SegmentInfos.java:663)
at org.apache.lucene.index.SegmentInfos.read(SegmentInfos.java:376)
at org.elasticsearch.index.engine.robin.RobinEngine.flush(RobinEngine.java:947)
at org.elasticsearch.index.shard.service.InternalIndexShard.flush(InternalIndexShard.java:502)
at org.elasticsearch.index.translog.TranslogService$TranslogBasedFlush$1.run(TranslogService.java:186)
at java.util.concurrent.ThreadPoolExecutor$Worker.runTask(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
以下是我的节点API的输出：
{
"ok" : true,
"cluster_name" : "Odine",
"nodes" : {
"J_vVn1gKQMmcDYADbcPlfw" : {
"name" : "rap-es-1",
"transport_address" : "inet[/141.161.88.174:9300]",
"hostname" : "rap-es-1.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.174:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 31729,
"max_file_descriptors" : 65535
}
},
"hT_Z-JneS6uCem0M-7nTEQ" : {
"name" : "rap-es",
"transport_address" : "inet[/141.161.88.169:9300]",
"hostname" : "rap-es.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.169:9200]",
"attributes" : {
"data" : "false"
},
"os" : {
"refresh_interval" : 1000,
"available_processors" : 2,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 2,
"total_sockets" : 2,
"cores_per_socket" : 1,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255303680
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 10282,
"max_file_descriptors" : 500000
}
},
"-76vB5ISTUq4M7ESizP7og" : {
"name" : "rap-es-4",
"transport_address" : "inet[/141.161.88.177:9301]",
"hostname" : "rap-es-4.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.177:9201]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 2462,
"max_file_descriptors" : 65535
}
},
"xssBGLKITpicDcxdeEjr4A" : {
"name" : "rap-es-6",
"transport_address" : "inet[/141.161.88.179:9300]",
"hostname" : "rap-es-6.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.179:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 2608,
"max_file_descriptors" : 65535
}
},
"wg_I5wBfRxqs6kdH-S_kww" : {
"name" : "rap-es-6",
"transport_address" : "inet[/141.161.88.179:9301]",
"hostname" : "rap-es-6.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.179:9201]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 2570,
"max_file_descriptors" : 65535
}
},
"lG0sqr95Q02Lt-iTCcg6qg" : {
"name" : "rap-es-5",
"transport_address" : "inet[/141.161.88.178:9300]",
"hostname" : "rap-es-5.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.178:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 22580,
"max_file_descriptors" : 65535
}
},
"biDQwwn4R9GTkesZUlNW1g" : {
"name" : "rap-es-2",
"transport_address" : "inet[/141.161.88.175:9300]",
"hostname" : "rap-es-2.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.175:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 5190,
"max_file_descriptors" : 65535
}
},
"A7E7I7R5SIib6RJPA3RNug" : {
"name" : "rap-es-4",
"transport_address" : "inet[/141.161.88.177:9300]",
"hostname" : "rap-es-4.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.177:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 2500,
"max_file_descriptors" : 65535
}
},
"oQG-yfURTTWZiFC6eOwjAg" : {
"name" : "rap-es-3",
"transport_address" : "inet[/141.161.88.176:9300]",
"hostname" : "rap-es-3.uis.georgetown.edu",
"version" : "0.90.3",
"http_address" : "inet[/141.161.88.176:9200]",
"os" : {
"refresh_interval" : 1000,
"available_processors" : 4,
"cpu" : {
"vendor" : "Intel",
"model" : "Xeon",
"mhz" : 1995,
"total_cores" : 4,
"total_sockets" : 1,
"cores_per_socket" : 4,
"cache_size" : "18kb",
"cache_size_in_bytes" : 18432
},
"mem" : {
"total" : "7.6gb",
"total_in_bytes" : 8255045632
},
"swap" : {
"total" : "7.9gb",
"total_in_bytes" : 8589926400
}
},
"process" : {
"refresh_interval" : 1000,
"id" : 1291,
"max_file_descriptors" : 65535
}
}
}
}
我知道为什么在将文件限制更新为65535 / node（测试时为500,000）后仍然出现错误。
答案 0 :(得分：0)
问题是每个节点有太多分片。我将它们从12减少到6，它解决了这个问题。