Elasticsearch指标监控说明
Posted 顧棟
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了Elasticsearch指标监控说明相关的知识，希望对你有一定的参考价值。
Elasticsearch指标监控说明
指标维度
可以把指标分为6个维度。
下面的表格总结了上一篇文章中提到搜索性能，索引性能，内存性能，网络性能对应的ES API。其中有些性能数据是从多个维度描述的，比如搜索性能在节点维度和索引维度都有提供。
| Metric category | Availability | Description |
|---|---|---|
| Search performance metrics | Node Stats API, Index Stats API | 查询性能指标 |
| Indexing performance metrics | Node Stats API, Index Stats API | 写入性能指标 |
| Memory and garbage collection | Node Stats API, Cluster Stats API | 内存与GC性能指标 |
| Network metrics | Node Stats API | 网络情况 |
| Cluster health and node availability | Cluster Health API | 集群健康和节点的可用性指标 |
| Resource saturation and errors | Node Stats API, Index Stats API, Cluster Stats API, Pending Tasks API | 资源状态和错误信息指标 |
指标分级
Elasticsearch集群监控状态指标分三个级别
集群级别
集群级别的监控主要是针对整个Elasticsearch集群来说，包括集群的健康状况、集群的状态等。
节点级别
节点级别的监控主要是针对每个Elasticsearch实例的监控，其中包括每个实例的查询索引指标和物理资源使用指标。
索引级别
索引级别的监控主要是针对每个索引来说，主要包括每个索引的性能指标。
指标分布如图
API使用示例
主要有五个HTTP REST API可用于采集Elasticsearch监控指标：
- Cluster Health API
- Cluster Stats API
- Node Stats API
- Index Stats API
- Pending Tasks API
集群健康情况
GET /_cluster/health?human&pretty
结果示例
{
"cluster_name": "es-platform-log",
"status": "green",
"timed_out": false,
"number_of_nodes": 9,
"number_of_data_nodes": 6,
"active_primary_shards": 80,
"active_shards": 166,
"relocating_shards": 0,
"initializing_shards": 0,
"unassigned_shards": 0,
"delayed_unassigned_shards": 0,
"number_of_pending_tasks": 0,
"number_of_in_flight_fetch": 0,
"task_max_waiting_in_queue": "0s",
"task_max_waiting_in_queue_millis": 0,
"active_shards_percent": "100.0%",
"active_shards_percent_as_number": 100
}
统计集群信息
GET /_cluster/stats?human&pretty
结果示例
{
"_nodes": {
"total": 9,
"successful": 9,
"failed": 0
},
"cluster_name": "es-platform-log",
"cluster_uuid": "M0qBb884SWCYd8KjQcpFQg",
"timestamp": 1625657783874,
"status": "green",
"indices": {
"count": 34,
"shards": {
"total": 166,
"primaries": 80,
"replication": 1.075,
"index": {
"shards": {
"min": 2,
"max": 20,
"avg": 4.882352941176471
},
"primaries": {
"min": 1,
"max": 5,
"avg": 2.3529411764705883
},
"replication": {
"min": 0,
"max": 3,
"avg": 1
}
}
},
"docs": {
"count": 794178337,
"deleted": 8595881
},
"store": {
"size": "813.1gb",
"size_in_bytes": 873069900311
},
"fielddata": {
"memory_size": "1.7kb",
"memory_size_in_bytes": 1840,
"evictions": 0
},
"query_cache": {
"memory_size": "1gb",
"memory_size_in_bytes": 1099581304,
"total_count": 3012012,
"hit_count": 2854064,
"miss_count": 157948,
"cache_size": 3570,
"cache_count": 5415,
"evictions": 1845
},
"completion": {
"size": "0b",
"size_in_bytes": 0
},
"segments": {
"count": 659,
"memory": "898.8mb",
"memory_in_bytes": 942513495,
"terms_memory": "387.5mb",
"terms_memory_in_bytes": 406388453,
"stored_fields_memory": "483.7mb",
"stored_fields_memory_in_bytes": 507295448,
"term_vectors_memory": "0b",
"term_vectors_memory_in_bytes": 0,
"norms_memory": "18kb",
"norms_memory_in_bytes": 18432,
"points_memory": "22.9mb",
"points_memory_in_bytes": 24036474,
"doc_values_memory": "4.5mb",
"doc_values_memory_in_bytes": 4774688,
"index_writer_memory": "9.7mb",
"index_writer_memory_in_bytes": 10228272,
"version_map_memory": "260b",
"version_map_memory_in_bytes": 260,
"fixed_bit_set": "733.2kb",
"fixed_bit_set_memory_in_bytes": 750848,
"max_unsafe_auto_id_timestamp": 1625616004589,
"file_sizes": {}
}
},
"nodes": {
"count": {
"total": 9,
"data": 6,
"coordinating_only": 0,
"master": 3,
"ingest": 9
},
"versions": [
"6.7.2"
],
"os": {
"available_processors": 360,
"allocated_processors": 360,
"names": [
{
"name": "Linux",
"count": 9
}
],
"pretty_names": [
{
"pretty_name": "CentOS Linux 7 (Core)",
"count": 9
}
],
"mem": {
"total": "1.1tb",
"total_in_bytes": 1211755806720,
"free": "21.7gb",
"free_in_bytes": 23325560832,
"used": "1tb",
"used_in_bytes": 1188430245888,
"free_percent": 2,
"used_percent": 98
}
},
"process": {
"cpu": {
"percent": 0
},
"open_file_descriptors": {
"min": 869,
"max": 1000,
"avg": 948
}
},
"jvm": {
"max_uptime": "297.7d",
"max_uptime_in_millis": 25724732930,
"versions": [
{
"version": "1.8.0_161",
"vm_name": "Java HotSpot(TM) 64-Bit Server VM",
"vm_version": "25.161-b12",
"vm_vendor": "Oracle Corporation",
"count": 9
}
],
"mem": {
"heap_used": "135.7gb",
"heap_used_in_bytes": 145777776144,
"heap_max": "279gb",
"heap_max_in_bytes": 299573968896
},
"threads": 2654
},
"fs": {
"total": "43tb",
"total_in_bytes": 47300324622336,
"free": "42.6tb",
"free_in_bytes": 46859340689408,
"available": "42.1tb",
"available_in_bytes": 46376411246592
},
"plugins": [
{
"name": "analysis-pinyin",
"version": "6.7.2.4",
"elasticsearch_version": "6.7.2",
"java_version": "1.8",
"description": "Pinyin Analysis for Elasticsearch",
"classname": "org.elasticsearch.plugin.analysis.pinyin.AnalysisPinyinPlugin",
"extended_plugins": [],
"has_native_controller": false
},
{
"name": "analysis-dynamic-synonym",
"version": "6.7.2.4",
"elasticsearch_version": "6.7.2",
"java_version": "1.8",
"description": "Analysis-plugin for synonym",
"classname": "com.bellszhu.elasticsearch.plugin.DynamicSynonymPlugin",
"extended_plugins": [],
"has_native_controller": false
},
{
"name": "repository-sdoss",
"version": "6.7.2.4",
"elasticsearch_version": "6.7.2",
"java_version": "1.8",
"description": "The Sdoss repository plugin adds support for SDFS or other sdoss server repositories.",
"classname": "org.elasticsearch.repositories.sdoss.SdossPlugin",
"extended_plugins": [],
"has_native_controller": false
},
{
"name": "analysis-ik",
"version": "6.7.2.4",
"elasticsearch_version": "6.7.2",
"java_version": "1.8",
"description": "IK Analyzer for Elasticsearch",
"classname": "org.elasticsearch.plugin.analysis.ik.AnalysisIkPlugin",
"extended_plugins": [],
"has_native_controller": false
}
],
"network_types": {
"transport_types": {
"netty4": 9
},
"http_types": {
"netty4": 9
}
}
}
}
统计索引信息
GET /_stats
或
GET /index1,index2/_stats
可以在URL中增减参数，进行部分指标的统计 ，如GET /_stats/merge,refresh。
| 参数值 | 说明 |
|---|---|
docs | The number of docs / deleted docs (docs not yet merged out). Note, affected by refreshing the index. |
store | The size of the index. |
indexing | Indexing statistics, can be combined with a comma separated list of types to provide document type level stats. |
get | Get statistics, including missing stats. |
search | Search statistics including suggest statistics. You can include statistics for custom groups by adding an extra groups parameter (search operations can be associated with one or more groups). The groups parameter accepts a comma separated list of group names. Use _all to return statistics for all groups. |
segments | Retrieve the memory use of the open segments. Optionally, setting the include_segment_file_sizes flag, report the aggregated disk usage of each one of the Lucene index files. |
completion | Completion suggest statistics. |
fielddata | Fielddata statistics. |
flush | Flush statistics. |
merge | Merge statistics. |
request_cache | Shard request cache statistics. |
refresh | Refresh statistics. |
warmer | Warmer statistics. |
translog | Translog statistics. |
结果示例
{
"_shards": {
"total": 4,
"successful": 4,
"failed": 0
},
"_all": {
"primaries": {
"docs": {
"count": 791173931,
"deleted": 8580767
},
"store": {
"size_in_bytes": 437042050823
},
"indexing": {
"index_total": 1005140339,
"index_time_in_millis": 234948689,
"index_current": 0,
"index_failed": 0,
"delete_total": 458968359,
"delete_time_in_millis": 90953371,
"delete_current": 0,
"noop_update_total": 0,
"is_throttled": false,
"throttle_time_in_millis": 0
},
"get": {
"total": 0,
"time_in_millis": 0,
"exists_total": 0,
"exists_time_in_millis": 0,
"missing_total": 0,
"missing_time_in_millis": 0,
"current": 0
},
"search": {
"open_contexts": 0,
"query_total": 527285,
"query_time_in_millis": 38479084,
"query_current": 0,
"fetch_total": 307477,
"fetch_time_in_millis": 7206781,
"fetch_current": 0,
"scroll_total": 51,
"scroll_time_in_millis": 358349299,
"scroll_current": 0,
"suggest_total": 0,
"suggest_time_in_millis": 0,
"suggest_current": 0
},
"merges": {
"current": 0,
"current_docs": 0,
"current_size_in_bytes": 0,
"total": 2973208,
"total_time_in_millis": 972619673,
"total_docs": 14744942732,
"total_size_in_bytes": 7712062295680,
"total_stopped_time_in_millis": 0,
"total_throttled_time_in_millis": 530615641,
"total_auto_throttle_in_bytes": 10485760
},
"refresh": {
"total": 26691087,
"total_time_in_millis": 474628597,
"listeners": 0
},
"flush": {
"total": 3305,
"periodic": 3301,
"total_time_in_millis": 1497051
},
"warmer": {
"current": 0,
"total": 26662293,
"total_time_in_millis": 493330
},
"query_cache": {
"memory_size_in_bytes": 443995504,
"total_count": 2037568,
"hit_count": 1964092,
"miss_count": 73476,
"cache_size": 1436,
"cache_count": 2735,
"evictions": 1299
},
"fielddata": {
"memory_size_in_bytes": 0,
"evictions": 0
},
"completion": {
"size_in_bytes": 0
},
"segments": {
"count": 138,
"memory_in_bytes": 467411612,
"terms_memory_in_bytes": 202202784,
"stored_fields_memory_in_bytes": 254003248,
"term_vectors_memory_in_bytes": 0,
"norms_memory_in_bytes": 8832,
"points_memory_in_bytes": 11182860,
"doc_values_memory_in_bytes": 13888,
"index_writer_memory_in_bytes": 665540,
"version_map_memory_in_bytes": 0,
"fixed_bit_set_memory_in_bytes": 0,
"max_unsafe_auto_id_timestamp": 1619778779940,
"file_sizes": {}
},
"translog": {
"operations": 639821,
"size_in_bytes": 1156652496,
"uncommitted_operations": 297497,
"uncommitted_size_in_bytes": 619765088,
"earliest_last_modified_age": 0
},
"request_cache": {
"memory_size_in_bytes": 0,
"evictions": 0,
"hit_count": 39,
"miss_count": 90
},
"recovery": {
"current_as_source": 0,
"current_as_target": 0,
"throttle_time_in_millis": 1331100
}
},
"total": {
"docs": {
"count": 1582347865,
"deleted": 14594676
},
"store": {
"size_in_bytes": 869264426131
},
"indexing": {
"index_total": 2014175604,
"index_time_in_millis": 479642467,
"index_current": 0,
"index_failed": 0,
"delete_total": 754975511,
"delete_time_in_millis": 169701198,
"delete_current"MetricBeat + Elasticsearch + Kibana 实现监控指标可视化