文章目录
一、 工具介绍
1.1 esrally简介
esrally 是 elastic 官方开源的一款基于 python3 实现的针对 es 的压测工具，esrally主要功能如下：
- 自动创建、压测和销毁 es 集群
- 可分 es 版本管理压测数据和方案
- 完善的压测数据展示，支持不同压测之间的数据对比分析，也可以将数据存储到指定的es中进行二次分析
- 支持收集 JVM 详细信息，比如内存、GC等数据来定位性能问题
1.2 测试结果
-
rally-metrics-*：记录race中所有的采样数据（性能报告数据都是基于采样数据汇总得出的结果），可以通过采样数据看到具体抖动情况进行具体分析
-
rally-results-*：基于上面的采样数据进行详细的数据汇总，针对每个指标进行汇总，可以针对每个指标进行最终的结果展示
-
rally-races-*：把最终性能压测结果（即我们看到的输出数据）展示出来，一个文档就是一次race压测
1.3 benchmarks目录
-
data":表示进行es测试时用的数据，默认是没有的，需要去下载，下载就到此文件夹
-
distributions: ES远程下载的目录
-
races: 目前有哪些压测试验
-
teams:要去进行的项目，进行压测比赛的考核项，系统已经准备
-
tracks：表示赛道，定义性能压测的规则、策略。这个非常重要
1.4 命令行解析
--pipeline：流水线
from-distribution：默认的，是指esrally在官方打好的包下载下来，解压运行
from-sources-complete：支持从源码本地编译、打包再运行，对于ES开发人员有用
benchmark-only：自定义集群时需要使用的pipeline，只进行压测而不去管理ES实例
from-sources-skip-build：与from-sources-complete相互呼应，利用源码方式但是跳过编译、打包
--target-hosts：执行集群的连接地址
--cluster-health：检查集群状态，根据设定的健康状态来判断是否进行压测，默认为Green，可以修改为Yellow
二、压测概要
2.1 测试背景
本次测试以esrally 标准测试得出ElasticSearch集群场景下性能数据以提供各类决策判断参考数据，进而预估当前环境是否可以满足目前需求。
2.2 测试环境
| OS版本 | Centos 6.10 |
|---|---|
| 压测机配置 | 8C16G |
| 数据库版本 | ElasticSearch 7.4 |
| ElasticSearch内存 | 8G |
| 压测软件版本 | esrally 1.4.1 |
| Python版本 | 3.7.7 |
| java版本 | 1.8 |
| git版本 | 1.9.5 |
esrally配置
[meta]
config.version = 17
[system]
env.name = local
[node]
root.dir = /home/elasticsearch/.rally/benchmarks
src.root.dir = /home/elasticsearch/.rally/benchmarks/src
[source]
remote.repo.url = https://github.com/elastic/elasticsearch.git
elasticsearch.src.subdir = elasticsearch
[benchmarks]
local.dataset.cache = /home/elasticsearch/.rally/benchmarks/data
[reporting]
datastore.type = elasticsearch
datastore.host = 172.32.1.59
datastore.port =9200
datastore.secure = False
datastore.user = elastic
datastore.password = elastic
[tracks]
\#default.url = https://github.com/elastic/rally-tracks
default.url = git://github.com/elastic/rally-tracks.git
[teams]
\#default.url = https://github.com/elastic/rally-teams
default.url = git://github.com/elastic/rally-teams.git
[defaults]
preserve_benchmark_candidate = False
[distributions]
release.cache = false
三、测试结果
3.1 表格展示
| Metric | Task | Value | Unit |
|---|---|---|---|
| Cumulative indexing time of primary shards | 418.085 | min | |
| Min cumulative indexing time across primary shards | 0 | min | |
| Median cumulative indexing time across primary shards | 1.97918 | min | |
| Max cumulative indexing time across primary shards | 75.682 | min | |
| Cumulative indexing throttle time of primary shards | 0 | min | |
| Min cumulative indexing throttle time across primary shards | 0 | min | |
| Median cumulative indexing throttle time across primary shards | 0 | min | |
| Max cumulative indexing throttle time across primary shards | 0 | min | |
| Cumulative merge time of primary shards | 59.458 | min | |
| Cumulative merge count of primary shards | 433 | ||
| Min cumulative merge time across primary shards | 0 | min | |
| Median cumulative merge time across primary shards | 0.162183 | min | |
| Max cumulative merge time across primary shards | 11.343 | min | |
| Cumulative merge throttle time of primary shards | 9.28582 | min | |
| Min cumulative merge throttle time across primary shards | 0 | min | |
| Median cumulative merge throttle time across primary shards | 0 | min | |
| Max cumulative merge throttle time across primary shards | 2.06697 | min | |
| Cumulative refresh time of primary shards | 9.17162 | min | |
| Cumulative refresh count of primary shards | 3732 | ||
| Min cumulative refresh time across primary shards | 0 | min | |
| Median cumulative refresh time across primary shards | 0.0840833 | min | |
| Max cumulative refresh time across primary shards | 1.57865 | min | |
| Cumulative flush time of primary shards | 10.9734 | min | |
| Cumulative flush count of primary shards | 142 | ||
| Min cumulative flush time across primary shards | 0 | min | |
| Median cumulative flush time across primary shards | 0.00328333 | min | |
| Max cumulative flush time across primary shards | 2.17005 | min | |
| Total Young Gen GC | 247.611 | s | |
| Total Old Gen GC | 2.863 | s | |
| Store size | 21.266 | GB | |
| Translog size | 0.155841 | GB | |
| Heap used for segments | 98.5449 | MB | |
| Heap used for doc values | 1.39747 | MB | |
| Heap used for terms | 84.179 | MB | |
| Heap used for norms | 0.0130005 | MB | |
| Heap used for points | 5.75382 | MB | |
| Heap used for stored fields | 7.20159 | MB | |
| Segment count | 155 | ||
| Min Throughput | index-append | 98416.2 | docs/s |
| Median Throughput | index-append | 113464 | docs/s |
| Max Throughput | index-append | 128702 | docs/s |
| 50th percentile latency | index-append | 351.702 | ms |
| 90th percentile latency | index-append | 521.767 | ms |
| 99th percentile latency | index-append | 1002.35 | ms |
| 99.9th percentile latency | index-append | 6698.26 | ms |
| 99.99th percentile latency | index-append | 9180.18 | ms |
| 100th percentile latency | index-append | 10119.9 | ms |
| 50th percentile service time | index-append | 351.704 | ms |
| 90th percentile service time | index-append | 521.834 | ms |
| 99th percentile service time | index-append | 1002.35 | ms |
| 99.9th percentile service time | index-append | 6698.26 | ms |
| 99.99th percentile service time | index-append | 9180.18 | ms |
| 100th percentile service time | index-append | 10119.9 | ms |
| error rate | index-append | 0 | % |
| Min Throughput | default | 8.01 | ops/s |
| Median Throughput | default | 8.01 | ops/s |
| Max Throughput | default | 8.01 | ops/s |
| 50th percentile latency | default | 11.9403 | ms |
| 90th percentile latency | default | 15.8801 | ms |
| 99th percentile latency | default | 27.3298 | ms |
| 100th percentile latency | default | 34.0052 | ms |
| 50th percentile service time | default | 11.7154 | ms |
| 90th percentile service time | default | 15.6617 | ms |
| 99th percentile service time | default | 27.1083 | ms |
| 100th percentile service time | default | 33.8 | ms |
| error rate | default | 0 | % |
| Min Throughput | term | 50.04 | ops/s |
| Median Throughput | term | 50.04 | ops/s |
| Max Throughput | term | 50.04 | ops/s |
| 50th percentile latency | term | 11.8169 | ms |
| 90th percentile latency | term | 16.0652 | ms |
| 99th percentile latency | term | 35.3232 | ms |
| 100th percentile latency | term | 38.8156 | ms |
| 50th percentile service time | term | 11.6466 | ms |
| 90th percentile service time | term | 15.1945 | ms |
| 99th percentile service time | term | 29.1859 | ms |
| 100th percentile service time | term | 38.7171 | ms |
| error rate | term | 0 | % |
| Min Throughput | range | 1 | ops/s |
| Median Throughput | range | 1.01 | ops/s |
| Max Throughput | range | 1.01 | ops/s |
| 50th percentile latency | range | 26.2975 | ms |
| 90th percentile latency | range | 32.6228 | ms |
| 99th percentile latency | range | 88.2407 | ms |
| 100th percentile latency | range | 125.507 | ms |
| 50th percentile service time | range | 25.1863 | ms |
| 90th percentile service time | range | 31.5211 | ms |
| 99th percentile service time | range | 87.1588 | ms |
| 100th percentile service time | range | 124.409 | ms |
| error rate | range | 0 | % |
| Min Throughput | hourly_agg | 0.2 | ops/s |
| Median Throughput | hourly_agg | 0.2 | ops/s |
| Max Throughput | hourly_agg | 0.2 | ops/s |
| 50th percentile latency | hourly_agg | 2698.73 | ms |
| 90th percentile latency | hourly_agg | 2804.2 | ms |
| 99th percentile latency | hourly_agg | 2903.07 | ms |
| 100th percentile latency | hourly_agg | 2948.12 | ms |
| 50th percentile service time | hourly_agg | 2696.25 | ms |
| 90th percentile service time | hourly_agg | 2801.73 | ms |
| 99th percentile service time | hourly_agg | 2900.59 | ms |
| 100th percentile service time | hourly_agg | 2945.69 | ms |
| error rate | hourly_agg | 0 | % |
| Min Throughput | scroll | 25.01 | pages/s |
| Median Throughput | scroll | 25.03 | pages/s |
| Max Throughput | scroll | 25.08 | pages/s |
| 50th percentile latency | scroll | 713.475 | ms |
| 90th percentile latency | scroll | 763.469 | ms |
| 99th percentile latency | scroll | 833.412 | ms |
| 100th percentile latency | scroll | 862.202 | ms |
| 50th percentile service time | scroll | 713.065 | ms |
| 90th percentile service time | scroll | 763.003 | ms |
| 99th percentile service time | scroll | 833.002 | ms |
| 100th percentile service time | scroll | 861.829 | ms |
| error rate | scroll | 0 | % |
| Min Throughput | desc_sort_timestamp | 0.5 | ops/s |
| Median Throughput | desc_sort_timestamp | 0.5 | ops/s |
| Max Throughput | desc_sort_timestamp | 0.5 | ops/s |
| 50th percentile latency | desc_sort_timestamp | 1059.93 | ms |
| 90th percentile latency | desc_sort_timestamp | 1117.99 | ms |
| 99th percentile latency | desc_sort_timestamp | 1204.27 | ms |
| 100th percentile latency | desc_sort_timestamp | 1215.51 | ms |
| 50th percentile service time | desc_sort_timestamp | 1058.79 | ms |
| 90th percentile service time | desc_sort_timestamp | 1116.91 | ms |
| 99th percentile service time | desc_sort_timestamp | 1203.13 | ms |
| 100th percentile service time | desc_sort_timestamp | 1214.41 | ms |
| error rate | desc_sort_timestamp | 0 | % |
| Min Throughput | asc_sort_timestamp | 0.5 | ops/s |
| Median Throughput | asc_sort_timestamp | 0.5 | ops/s |
| Max Throughput | asc_sort_timestamp | 0.5 | ops/s |
| 50th percentile latency | asc_sort_timestamp | 1052.15 | ms |
| 90th percentile latency | asc_sort_timestamp | 1109.45 | ms |
| 99th percentile latency | asc_sort_timestamp | 1213.79 | ms |
| 100th percentile latency | asc_sort_timestamp | 1223.51 | ms |
| 50th percentile service time | asc_sort_timestamp | 1051.02 | ms |
| 90th percentile service time | asc_sort_timestamp | 1108.25 | ms |
| 99th percentile service time | asc_sort_timestamp | 1212.65 | ms |
| 100th percentile service time | asc_sort_timestamp | 1222.36 | ms |
| error rate | asc_sort_timestamp | 0 | % |
| Min Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.93 | ops/s |
| Median Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.93 | ops/s |
| Max Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.94 | ops/s |
| 50th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 143357 | ms |
| 90th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 165367 | ms |
| 99th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 170251 | ms |
| 100th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 170524 | ms |
| 50th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1058.98 | ms |
| 90th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1119.93 | ms |
| 99th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1188.45 | ms |
| 100th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1196.21 | ms |
| error rate | desc-sort-timestamp-after-force-merge-1-seg | 0 | % |
| Min Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.96 | ops/s |
| Median Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.97 | ops/s |
| Max Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.97 | ops/s |
| 50th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 134164 | ms |
| 90th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 155424 | ms |
| 99th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 160108 | ms |
| 100th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 160380 | ms |
| 50th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1020.59 | ms |
| 90th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1092.2 | ms |
| 99th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1136.68 | ms |
| 100th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1139.94 | ms |
| error rate | asc-sort-timestamp-after-force-merge-1-seg | 0 | % |
3.2 图形展示
四、附录
4.1 测试结果
esrally --target-hosts=172.32.1.59:9200,172.32.1.91:9200,172.32.1.140:9200 --pipeline=benchmark-only --track=http_logs --client-options="use_ssl:false,verify_certs:true,basic_auth_user:'elastic',basic_auth_password:'elastic'"
____ ____
/ __ \____ _/ / /_ __
/ /_/ / __ `/ / / / / /
/ _, _/ /_/ / / / /_/ /
/_/ |_|\__,_/_/_/\__, /
/____/
[INFO] You did not provide an explicit timeout in the client options. Assuming default of 10 seconds.
************************************************************************
************** WARNING: A dark dungeon lies ahead of you **************
************************************************************************
Rally does not have control over the configuration of the benchmarked
Elasticsearch cluster.
Be aware that results may be misleading due to problems with the setup.
Rally is also not able to gather lots of metrics at all (like CPU usage
of the benchmarked cluster) or may even produce misleading metrics (like
the index size).
************************************************************************
****** Use this pipeline only if you are aware of the tradeoffs. ******
*************************** Watch your step! ***************************
************************************************************************
[WARNING] Could not update tracks. Continuing with your locally available state.
[WARNING] Could not update tracks. Continuing with your locally available state.
[INFO] Racing on track [http_logs], challenge [append-no-conflicts] and car ['external'] with version [7.4.0].
[WARNING] merges_total_time is 20335 ms indicating that the cluster is not in a defined clean state. Recorded index time metrics may be misleading.
[WARNING] indexing_total_time is 11316 ms indicating that the cluster is not in a defined clean state. Recorded index time metrics may be misleading.
[WARNING] refresh_total_time is 16501 ms indicating that the cluster is not in a defined clean state. Recorded index time metrics may be misleading.
[WARNING] flush_total_time is 127 ms indicating that the cluster is not in a defined clean state. Recorded index time metrics may be misleading.
Running delete-index [100% done]
Running create-index [100% done]
Running check-cluster-health [100% done]
Running index-append [100% done]
Running refresh-after-index [100% done]
Running force-merge [100% done]
Running refresh-after-force-merge [100% done]
Running wait-until-merges-finish [100% done]
Running default [100% done]
Running term [100% done]
Running range [100% done]
Running hourly_agg [100% done]
Running scroll [100% done]
Running desc_sort_timestamp [100% done]
Running asc_sort_timestamp [100% done]
Running force-merge-1-seg [100% done]
Running refresh-after-force-merge-1-seg [100% done]
Running wait-until-merges-1-seg-finish [100% done]
Running desc-sort-timestamp-after-force-merge-1-seg [100% done]
Running asc-sort-timestamp-after-force-merge-1-seg [100% done]
\------------------------------------------------------
_______ __ _____
/ ____(_)___ ____ _/ / / ___/_________ ________
/ /_ / / __ \/ __ `/ / \__ \/ ___/ __ \/ ___/ _ \
/ __/ / / / / / /_/ / / ___/ / /__/ /_/ / / / __/
/_/ /_/_/ /_/\__,_/_/ /____/\___/\____/_/ \___/
\------------------------------------------------------
| Metric | Task | Value | Unit |
|---------------------------------------------------------------:|--------------------------------------------:|-----------:|--------:|
| Cumulative indexing time of primary shards | | 418.085 | min |
| Min cumulative indexing time across primary shards | | 0 | min |
| Median cumulative indexing time across primary shards | | 1.97918 | min |
| Max cumulative indexing time across primary shards | | 75.682 | min |
| Cumulative indexing throttle time of primary shards | | 0 | min |
| Min cumulative indexing throttle time across primary shards | | 0 | min |
| Median cumulative indexing throttle time across primary shards | | 0 | min |
| Max cumulative indexing throttle time across primary shards | | 0 | min |
| Cumulative merge time of primary shards | | 59.458 | min |
| Cumulative merge count of primary shards | | 433 | |
| Min cumulative merge time across primary shards | | 0 | min |
| Median cumulative merge time across primary shards | | 0.162183 | min |
| Max cumulative merge time across primary shards | | 11.343 | min |
| Cumulative merge throttle time of primary shards | | 9.28582 | min |
| Min cumulative merge throttle time across primary shards | | 0 | min |
| Median cumulative merge throttle time across primary shards | | 0 | min |
| Max cumulative merge throttle time across primary shards | | 2.06697 | min |
| Cumulative refresh time of primary shards | | 9.17162 | min |
| Cumulative refresh count of primary shards | | 3732 | |
| Min cumulative refresh time across primary shards | | 0 | min |
| Median cumulative refresh time across primary shards | | 0.0840833 | min |
| Max cumulative refresh time across primary shards | | 1.57865 | min |
| Cumulative flush time of primary shards | | 10.9734 | min |
| Cumulative flush count of primary shards | | 142 | |
| Min cumulative flush time across primary shards | | 0 | min |
| Median cumulative flush time across primary shards | | 0.00328333 | min |
| Max cumulative flush time across primary shards | | 2.17005 | min |
| Total Young Gen GC | | 247.611 | s |
| Total Old Gen GC | | 2.863 | s |
| Store size | | 21.266 | GB |
| Translog size | | 0.155841 | GB |
| Heap used for segments | | 98.5449 | MB |
| Heap used for doc values | | 1.39747 | MB |
| Heap used for terms | | 84.179 | MB |
| Heap used for norms | | 0.0130005 | MB |
| Heap used for points | | 5.75382 | MB |
| Heap used for stored fields | | 7.20159 | MB |
| Segment count | | 155 | |
| Min Throughput | index-append | 98416.2 | docs/s |
| Median Throughput | index-append | 113464 | docs/s |
| Max Throughput | index-append | 128702 | docs/s |
| 50th percentile latency | index-append | 351.702 | ms |
| 90th percentile latency | index-append | 521.767 | ms |
| 99th percentile latency | index-append | 1002.35 | ms |
| 99.9th percentile latency | index-append | 6698.26 | ms |
| 99.99th percentile latency | index-append | 9180.18 | ms |
| 100th percentile latency | index-append | 10119.9 | ms |
| 50th percentile service time | index-append | 351.704 | ms |
| 90th percentile service time | index-append | 521.834 | ms |
| 99th percentile service time | index-append | 1002.35 | ms |
| 99.9th percentile service time | index-append | 6698.26 | ms |
| 99.99th percentile service time | index-append | 9180.18 | ms |
| 100th percentile service time | index-append | 10119.9 | ms |
| error rate | index-append | 0 | % |
| Min Throughput | default | 8.01 | ops/s |
| Median Throughput | default | 8.01 | ops/s |
| Max Throughput | default | 8.01 | ops/s |
| 50th percentile latency | default | 11.9403 | ms |
| 90th percentile latency | default | 15.8801 | ms |
| 99th percentile latency | default | 27.3298 | ms |
| 100th percentile latency | default | 34.0052 | ms |
| 50th percentile service time | default | 11.7154 | ms |
| 90th percentile service time | default | 15.6617 | ms |
| 99th percentile service time | default | 27.1083 | ms |
| 100th percentile service time | default | 33.8 | ms |
| error rate | default | 0 | % |
| Min Throughput | term | 50.04 | ops/s |
| Median Throughput | term | 50.04 | ops/s |
| Max Throughput | term | 50.04 | ops/s |
| 50th percentile latency | term | 11.8169 | ms |
| 90th percentile latency | term | 16.0652 | ms |
| 99th percentile latency | term | 35.3232 | ms |
| 100th percentile latency | term | 38.8156 | ms |
| 50th percentile service time | term | 11.6466 | ms |
| 90th percentile service time | term | 15.1945 | ms |
| 99th percentile service time | term | 29.1859 | ms |
| 100th percentile service time | term | 38.7171 | ms |
| error rate | term | 0 | % |
| Min Throughput | range | 1 | ops/s |
| Median Throughput | range | 1.01 | ops/s |
| Max Throughput | range | 1.01 | ops/s |
| 50th percentile latency | range | 26.2975 | ms |
| 90th percentile latency | range | 32.6228 | ms |
| 99th percentile latency | range | 88.2407 | ms |
| 100th percentile latency | range | 125.507 | ms |
| 50th percentile service time | range | 25.1863 | ms |
| 90th percentile service time | range | 31.5211 | ms |
| 99th percentile service time | range | 87.1588 | ms |
| 100th percentile service time | range | 124.409 | ms |
| error rate | range | 0 | % |
| Min Throughput | hourly_agg | 0.2 | ops/s |
| Median Throughput | hourly_agg | 0.2 | ops/s |
| Max Throughput | hourly_agg | 0.2 | ops/s |
| 50th percentile latency | hourly_agg | 2698.73 | ms |
| 90th percentile latency | hourly_agg | 2804.2 | ms |
| 99th percentile latency | hourly_agg | 2903.07 | ms |
| 100th percentile latency | hourly_agg | 2948.12 | ms |
| 50th percentile service time | hourly_agg | 2696.25 | ms |
| 90th percentile service time | hourly_agg | 2801.73 | ms |
| 99th percentile service time | hourly_agg | 2900.59 | ms |
| 100th percentile service time | hourly_agg | 2945.69 | ms |
| error rate | hourly_agg | 0 | % |
| Min Throughput | scroll | 25.01 | pages/s |
| Median Throughput | scroll | 25.03 | pages/s |
| Max Throughput | scroll | 25.08 | pages/s |
| 50th percentile latency | scroll | 713.475 | ms |
| 90th percentile latency | scroll | 763.469 | ms |
| 99th percentile latency | scroll | 833.412 | ms |
| 100th percentile latency | scroll | 862.202 | ms |
| 50th percentile service time | scroll | 713.065 | ms |
| 90th percentile service time | scroll | 763.003 | ms |
| 99th percentile service time | scroll | 833.002 | ms |
| 100th percentile service time | scroll | 861.829 | ms |
| error rate | scroll | 0 | % |
| Min Throughput | desc_sort_timestamp | 0.5 | ops/s |
| Median Throughput | desc_sort_timestamp | 0.5 | ops/s |
| Max Throughput | desc_sort_timestamp | 0.5 | ops/s |
| 50th percentile latency | desc_sort_timestamp | 1059.93 | ms |
| 90th percentile latency | desc_sort_timestamp | 1117.99 | ms |
| 99th percentile latency | desc_sort_timestamp | 1204.27 | ms |
| 100th percentile latency | desc_sort_timestamp | 1215.51 | ms |
| 50th percentile service time | desc_sort_timestamp | 1058.79 | ms |
| 90th percentile service time | desc_sort_timestamp | 1116.91 | ms |
| 99th percentile service time | desc_sort_timestamp | 1203.13 | ms |
| 100th percentile service time | desc_sort_timestamp | 1214.41 | ms |
| error rate | desc_sort_timestamp | 0 | % |
| Min Throughput | asc_sort_timestamp | 0.5 | ops/s |
| Median Throughput | asc_sort_timestamp | 0.5 | ops/s |
| Max Throughput | asc_sort_timestamp | 0.5 | ops/s |
| 50th percentile latency | asc_sort_timestamp | 1052.15 | ms |
| 90th percentile latency | asc_sort_timestamp | 1109.45 | ms |
| 99th percentile latency | asc_sort_timestamp | 1213.79 | ms |
| 100th percentile latency | asc_sort_timestamp | 1223.51 | ms |
| 50th percentile service time | asc_sort_timestamp | 1051.02 | ms |
| 90th percentile service time | asc_sort_timestamp | 1108.25 | ms |
| 99th percentile service time | asc_sort_timestamp | 1212.65 | ms |
| 100th percentile service time | asc_sort_timestamp | 1222.36 | ms |
| error rate | asc_sort_timestamp | 0 | % |
| Min Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.93 | ops/s |
| Median Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.93 | ops/s |
| Max Throughput | desc-sort-timestamp-after-force-merge-1-seg | 0.94 | ops/s |
| 50th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 143357 | ms |
| 90th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 165367 | ms |
| 99th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 170251 | ms |
| 100th percentile latency | desc-sort-timestamp-after-force-merge-1-seg | 170524 | ms |
| 50th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1058.98 | ms |
| 90th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1119.93 | ms |
| 99th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1188.45 | ms |
| 100th percentile service time | desc-sort-timestamp-after-force-merge-1-seg | 1196.21 | ms |
| error rate | desc-sort-timestamp-after-force-merge-1-seg | 0 | % |
| Min Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.96 | ops/s |
| Median Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.97 | ops/s |
| Max Throughput | asc-sort-timestamp-after-force-merge-1-seg | 0.97 | ops/s |
| 50th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 134164 | ms |
| 90th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 155424 | ms |
| 99th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 160108 | ms |
| 100th percentile latency | asc-sort-timestamp-after-force-merge-1-seg | 160380 | ms |
| 50th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1020.59 | ms |
| 90th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1092.2 | ms |
| 99th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1136.68 | ms |
| 100th percentile service time | asc-sort-timestamp-after-force-merge-1-seg | 1139.94 | ms |
| error rate | asc-sort-timestamp-after-force-merge-1-seg | 0 | % |
\----------------------------------
[INFO] SUCCESS (took 6784 seconds)
\----------------------------------
4.2 结果参数说明
Metric：具体指标
Task：操作名称
Value：数值
Unit：单位
注意：在Task当中，有空和具体操作名称的区分，如果是空的则表示总计的果，如果有具体操作名称的则是记录该次操作的结果
Mertic具体指标详解
time：Index | Merge | Refresh | Flush => 对应操作花费的总时间
GC：Young | Total => GC花费的时间
Index size | Total written => 最终索引总大小和实际写入处理的大小
Heap：doc values | terms | norms => 堆内存占用情况
Operation：
Throughput => 当前操作的吞吐情况
Latency => 当前操作的延迟时长（请求到达ES，然后从ES返回的时间，包含了排队的时间）
Service Time => 当前操作的服务时间（ES开始执行请求到结束的时间）
具体指标说明
Cumulative indexing time of primary shards：主分片的累计索引时间，用于索引的累积时间
Cumulative indexing time across primary shards：跨主分片的累计索引时间，跨主碎片建立索引的最小、中值和最大累计时间
Cumulative indexing throttle time across primary shards：跨主分片的累计索引节流时间，已限制索引的累积时间
Cumulative merge time of primary shards：主分片的累计合并时间
Cumulative merge count of primary shards：主分片的累计合并个数
Cumulative merge time across primary shards：跨主分片的累计合并时间
Cumulative merge throttle time of primary shards：跨主分片的累计节流时间
Cumulative refresh time of primary shards：主分片的累计刷新时间
Cumulative refresh count of primary shards：主分片的累计刷新次数
Cumulative refresh time across primary shards：跨主分片的累计刷新时间
Cumulative flush time of primary shards：主分片的累计冲洗时间
Cumulative flush count of primary shards：主分片的累计冲洗次数
Cumulative flush time across primary shards：跨主分片的累计冲洗时间
Total Young Gen GC：整个集群中Young Gen GC的总运行时间
Total Old Gen GC：整个集群中Old Gen GC的总运行时间
Store size：索引大小（不包括事务日志），以字节为单位
Translog size：事务日志的大小（以字节为单位）
Index size：索引大小
Total written：总共写入
Heap used for *：堆用于相应项目的字节数
Segment count：细分总数
Throughput：吞吐量
Latency：延迟，提交请求到接收完整响应之间的时间段。它还包括等待时间，即请求花费等待直到准备好由Elasticsearch服务的时间。
Service Time：服务时间，ES处理请求的时间
error rate：错误率，错误响应相对于响应总数的比率。Python Elasticsearch客户端抛出的任何异常都被认为是错误的（例如HTTP响应代码4xx，5xx或网络错误（网络不可达））。