mkdir /mnt/memory_storage
mount -t tmpfs -o size=800G tmpfs /mnt/memory_storage
儲存空間會按需使用,也就是使用100G 儲存時才會佔用100G 記憶體。主機節點上有 2T 內存,這裡分配 800G 內存用於儲存 Elasticsearch 資料。
mkdir /mnt/memory_storage/elasticsearch-data-es-jfs-prod-es-default-0mkdir /mnt/memory_storage/elasticsearch-data-es-jfs-prod-es-default-1mkdir /mnt/memory_storage/elasticsearch-data-es-jfs-prod-es-default-2
如果沒有事先建立好目錄,並賦予讀寫權限,會導致Elasticsearch 元件起不來,提示多個節點使用了相同的資料目錄。
chmod -R 777 /mnt/memory_storage
dd if=/dev/zero of=/mnt/memory_storage/dd.txt bs=4M count=25002500+0 records in2500+0 records out10485760000 bytes (10 GB, 9.8 GiB) copied, 3.53769 s, 3.0 GB/s
rm -rf /mnt/memory_storage/dd.txt
fio --name=test --filename=/mnt/memory_storage/fio_test_file --size=10G --rw=write --bs=4M --numjobs=1 --runtime=60 --time_basedRun status group 0 (all jobs):WRITE: bw=2942MiB/s (3085MB/s), 2942MiB/s-2942MiB/s (3085MB/s-3085MB/s), io=172GiB (185GB), run=60001-60001msec
rm -rf /mnt/memory_storage/fio_test_file
mbw 10000Long uses 8 bytes. Allocating 2*1310720000 elements = 20971520000 bytes of memory.Using 262144 bytes as blocks for memcpy block copy test.Getting down to business... Doing 10 runs per test.0 Method: MEMCPY Elapsed: 1.62143 MiB: 10000.00000 Copy: 6167.380 MiB/s1 Method: MEMCPY Elapsed: 1.63542 MiB: 10000.00000 Copy: 6114.656 MiB/s2 Method: MEMCPY Elapsed: 1.63345 MiB: 10000.00000 Copy: 6121.997 MiB/s3 Method: MEMCPY Elapsed: 1.63715 MiB: 10000.00000 Copy: 6108.161 MiB/s4 Method: MEMCPY Elapsed: 1.64429 MiB: 10000.00000 Copy: 6081.667 MiB/s5 Method: MEMCPY Elapsed: 1.62772 MiB: 10000.00000 Copy: 6143.574 MiB/s6 Method: MEMCPY Elapsed: 1.60684 MiB: 10000.00000 Copy: 6223.379 MiB/s7 Method: MEMCPY Elapsed: 1.62499 MiB: 10000.00000 Copy: 6153.876 MiB/s8 Method: MEMCPY Elapsed: 1.63967 MiB: 10000.00000 Copy: 6098.770 MiB/s9 Method: MEMCPY Elapsed: 2.97213 MiB: 10000.00000 Copy: 3364.588 MiB/sAVG Method: MEMCPY Elapsed: 1.76431 MiB: 10000.00000 Copy: 5667.937 MiB/s0 Method: DUMB Elapsed: 1.01521 MiB: 10000.00000 Copy: 9850.140 MiB/s1 Method: DUMB Elapsed: 0.85378 MiB: 10000.00000 Copy: 11712.605 MiB/s2 Method: DUMB Elapsed: 0.82487 MiB: 10000.00000 Copy: 12123.167 MiB/s3 Method: DUMB Elapsed: 0.84520 MiB: 10000.00000 Copy: 11831.463 MiB/s4 Method: DUMB Elapsed: 0.83050 MiB: 10000.00000 Copy: 12040.968 MiB/s5 Method: DUMB Elapsed: 0.84932 MiB: 10000.00000 Copy: 11774.194 MiB/s6 Method: DUMB Elapsed: 0.82491 MiB: 10000.00000 Copy: 12122.505 MiB/s7 Method: DUMB Elapsed: 1.44235 MiB: 10000.00000 Copy: 6933.144 MiB/s8 Method: DUMB Elapsed: 2.68656 MiB: 10000.00000 Copy: 3722.225 MiB/s9 Method: DUMB Elapsed: 8.44667 MiB: 10000.00000 Copy: 1183.898 MiB/sAVG Method: DUMB Elapsed: 1.86194 MiB: 10000.00000 Copy: 5370.750 MiB/s0 Method: MCBLOCK Elapsed: 4.52486 MiB: 10000.00000 Copy: 2210.013 MiB/s1 Method: MCBLOCK Elapsed: 4.82467 MiB: 10000.00000 Copy: 2072.683 MiB/s2 Method: MCBLOCK Elapsed: 0.84797 MiB: 10000.00000 Copy: 11792.870 MiB/s3 Method: MCBLOCK Elapsed: 0.84980 MiB: 10000.00000 Copy: 11767.516 MiB/s4 Method: MCBLOCK Elapsed: 0.87665 MiB: 10000.00000 Copy: 11407.113 MiB/s5 Method: MCBLOCK Elapsed: 0.85952 MiB: 10000.00000 Copy: 11634.468 MiB/s6 Method: MCBLOCK Elapsed: 0.84132 MiB: 10000.00000 Copy: 11886.154 MiB/s7 Method: MCBLOCK Elapsed: 0.84970 MiB: 10000.00000 Copy: 11768.915 MiB/s8 Method: MCBLOCK Elapsed: 0.86918 MiB: 10000.00000 Copy: 11505.150 MiB/s9 Method: MCBLOCK Elapsed: 0.85996 MiB: 10000.00000 Copy: 11628.434 MiB/sAVG Method: MCBLOCK Elapsed: 1.62036 MiB: 10000.00000 Copy: 6171.467 MiB/s看起來將記憶體掛載為檔案系統的IO頻寬只能達到記憶體的IO 頻寬的一半。 2. 在Kubernetes 叢集上建立PVC
export NAMESPACE=data-centerexport PVC_NAME=elasticsearch-data-es-jfs-prod-es-default-0建立PV 與PVC
kubectl create -f - <<EOFapiVersion: v1kind: PersistentVolumemetadata:name: ${PVC_NAME}namespace: ${NAMESPACE}spec:accessModes:- ReadWriteManycapacity:storage: 800GihostPath:path: /mnt/memory_storage/${PVC_NAME}---apiVersion: v1kind: PersistentVolumeClaimmetadata:name: ${PVC_NAME}namespace: ${NAMESPACE}spec:accessModes:- ReadWriteManyresources:requests:storage: 800GiEOF
3. 部署 Elasticsearch 相關元件
cat <<EOF | kubectl apply -f -apiVersion: elasticsearch.k8s.elastic.co/v1kind: Elasticsearchmetadata:namespace: $NAMESPACEname: es-jfs-prodspec:version: 8.3.2image: hubimage/elasticsearch:8.3.2http:tls:selfSignedCertificate:disabled: truenodeSets:- name: defaultcount: 3config:node.store.allow_mmap: falseindex.store.type: niofspodTemplate:spec:nodeSelector:servertype: Ascend910B-24initContainers:- name: sysctlsecurityContext:privileged: truerunAsUser: 0command: ['sh', '-c', 'sysctl -w vm.max_map_count=262144']- name: install-pluginscommand:- sh- -c- |bin/elasticsearch-plugin install --batch https://get.infini.cloud/elasticsearch/analysis-ik/8.3.2securityContext:runAsUser: 0runAsGroup: 0containers:- name: elasticsearchreadinessProbe:exec:command:- bash- -c- /mnt/elastic-internal/scripts/readiness-probe-script.shfailureThreshold: 10initialDelaySeconds: 30periodSeconds: 30successThreshold: 1timeoutSeconds: 30env:- name: "ES_JAVA_OPTS"value: "-Xms31g -Xmx31g"- name: "NSS_SDB_USE_CACHE"value: "no"resources:requests:cpu: 8memory: 64GiEOF
kubectl -n $NAMESPACE get secret es-jfs-prod-es-elastic-user -o go-template='{{.data.elastic | base64decode}}'xxx
部署Metricbeat
kubectl apply -f - <<EOFapiVersion: beat.k8s.elastic.co/v1beta1kind: Beatmetadata:name: es-jfs-prodnamespace: $NAMESPACEspec:type: metricbeatversion: 8.3.2elasticsearchRef:name: es-jfs-prodconfig:metricbeat:autodiscover:providers:- type: kubernetesscope: clusterhints.enabled: truetemplates:- config:- module: kubernetesmetricsets:- eventperiod: 10sprocessors:- add_cloud_metadata: {}logging.json: truedeployment:podTemplate:spec:serviceAccountName: metricbeatautomountServiceAccountToken: true# required to read /etc/beat.ymlsecurityContext:runAsUser: 0EOF#部署Kibana
cat <<EOF | kubectl apply -f -apiVersion: kibana.k8s.elastic.co/v1kind: Kibanametadata:namespace: $NAMESPACEname: es-jfs-prodspec:version: 8.3.2count: 1image: hubimage/kibana:8.3.2elasticsearchRef:name: es-jfs-prodhttp:tls:selfSignedCertificate:disabled: trueEOF檢視Elasticsearch 叢集資訊
PUT /bayou_tt_articles{"settings": {"index": {"number_of_shards": 30,"number_of_replicas": 1,"refresh_interval": "120s","translog.durability": "async","translog.sync_interval": "120s","translog.flush_threshold_size": "2048M"}},"mappings": {"properties": {"text": {"type": "text","analyzer": "ik_smart"}}}}有兩個注意事項:
apt-get install npm -y######
npm install elasticdump -g#########匯入資料#########
export DATAPATH=./bayou_tt_articles_0.jsonlnohup elasticdump --limit 20000 --input=${DATAPATH} --output=http://elastic:xxx@x.x.x.x:31391/ --output-index=bayou_tt_articles --type=data --transform="doc._source=Object.assign({},doc)" > elasticdump-${DATAPATH}.log 2>&1 &###
limit 表示每次导入的数据条数,默认值是 100 太小,建议在保障导入成功的前提下尽可能大一点。
图片
索引速率达到 1w+/s,但上限远不止于此。因为,根据社区文档的压力测试结果显示,单个节点至少能提供 2W/s 的索引速率。
图片
上图是使用 JuiceFS 存储的全文检索速度为 18s,使用 SSD 节点的 Elasticsearch 的全文检索速度为 5s。下图是使用内存存储的 Elasticsearch 的全文检索速度为 100ms 左右。
图片
之前给 Elasticsearch Pod 分配的 CPU 和 Memory 太多,调整为 CPU 32C,Memory 64 GB。在滚动更新过程中,Elasticsearch 始终可用,并且数据没有丢失。
但务必注意设置 replicas > 1,尽量不要自行重启 Pod,虽然 Pod 是原节点更新。
图片
由于业务总的 Elasticsearch 存储需求是 10T 左右,我继续增加节点到 10 个,Elasticsearch 的索引分片会自动迁移,均匀分布在这些节点上。
docker run --rm -ti elasticdump/elasticsearch-dump --limit 10000 --input=http://elastic:xxx@x.x.x.x:31391/bayou_tt_articles --output=/data/es-bayou_tt_articles-output.json --type=data
Wed, 29 May 2024 01:41:23 GMT | got 10000 objects from source elasticsearch (offset: 0)Wed, 29 May 2024 01:41:23 GMT | sent 10000 objects to destination file, wrote 10000Wed, 29 May 2024 01:41:24 GMT | got 10000 objects from source elasticsearch (offset: 10000)Wed, 29 May 2024 01:41:24 GMT | sent 10000 objects to destination file, wrote 10000Wed, 29 May 2024 01:41:25 GMT | got 10000 objects from source elasticsearch (offset: 20000)Wed, 29 May 2024 01:41:25 GMT | sent 10000 objects to destination file, wrote 10000Wed, 29 May 2024 01:41:25 GMT | got 10000 objects from source elasticsearch (offset: 30000)
导出速度能达到 1w 条每秒,一亿条数据大约需要 3h,基本也能满足索引的备份、迁移需求。
更新之前的 Pod 分布节点如下:
NAME READY STATUSRESTARTSAGE IP NODE NOMINATED NODE READINESS GATESes-jfs-prod-beat-metricbeat-7fbdd657c4-djgg6 1/1 Running 6 (32m ago) 18h 10.244.54.5ascend-01 <none> <none>es-jfs-prod-es-default-0 1/1 Running 0 28m 10.244.46.82 ascend-07 <none> <none>es-jfs-prod-es-default-1 1/1 Running 0 29m 10.244.23.77 ascend-53 <none> <none>es-jfs-prod-es-default-2 1/1 Running 0 31m 10.244.49.65 ascend-20 <none> <none>es-jfs-prod-es-default-3 1/1 Running 0 32m 10.244.54.14 ascend-01 <none> <none>es-jfs-prod-es-default-4 1/1 Running 0 34m 10.244.100.239 ascend-40 <none> <none>es-jfs-prod-es-default-5 1/1 Running 0 35m 10.244.97.201ascend-39 <none> <none>es-jfs-prod-es-default-6 1/1 Running 0 37m 10.244.101.156 ascend-38 <none> <none>es-jfs-prod-es-default-7 1/1 Running 0 39m 10.244.19.101ascend-49 <none> <none>es-jfs-prod-es-default-8 1/1 Running 0 40m 10.244.16.109ascend-46 <none> <none>es-jfs-prod-es-default-9 1/1 Running 0 41m 10.244.39.119ascend-15 <none> <none>es-jfs-prod-kb-75f7bbd96-6tcrn 1/1 Running 0 18h 10.244.1.164 ascend-22 <none> <none>
更新之后的 Pod 分布节点如下:
NAME READY STATUSRESTARTSAGE IP NODE NOMINATED NODE READINESS GATESes-jfs-prod-beat-metricbeat-7fbdd657c4-djgg6 1/1 Running 6 (50m ago) 18h 10.244.54.5ascend-01 <none> <none>es-jfs-prod-es-default-0 1/1 Running 0 72s 10.244.46.83 ascend-07 <none> <none>es-jfs-prod-es-default-1 1/1 Running 0 2m35s 10.244.23.78 ascend-53 <none> <none>es-jfs-prod-es-default-2 1/1 Running 0 3m59s 10.244.49.66 ascend-20 <none> <none>es-jfs-prod-es-default-3 1/1 Running 0 5m34s 10.244.54.15 ascend-01 <none> <none>es-jfs-prod-es-default-4 1/1 Running 0 7m21s 10.244.100.240 ascend-40 <none> <none>es-jfs-prod-es-default-5 1/1 Running 0 8m44s 10.244.97.202ascend-39 <none> <none>es-jfs-prod-es-default-6 1/1 Running 0 10m 10.244.101.157 ascend-38 <none> <none>es-jfs-prod-es-default-7 1/1 Running 0 11m 10.244.19.102ascend-49 <none> <none>es-jfs-prod-es-default-8 1/1 Running 0 13m 10.244.16.110ascend-46 <none> <none>es-jfs-prod-es-default-9 1/1 Running 0 14m 10.244.39.120ascend-15 <none> <none>es-jfs-prod-kb-75f7bbd96-6tcrn 1/1 Running 0 18h 10.244.1.164 ascend-22 <none> <none>
这点打消了我的一个顾虑, Elasticsearch 的 Pod 重启时,发生了漂移,那么节点上是否会残留分片的数据,导致内存使用不断膨胀?答案是,不会。ECK Operator 似乎能让 Pod 在原节点进行重启,挂载的 Hostpath 数据依然对新的 Pod 有效,仅当主机节点发生重启时,才会丢失数据。
AI 的算力节点有大量空闲的 CPU 和 Memory 资源,使用这些大内存的主机节点,部署一些短生命周期的基于内存存储的高性能应用,有利于提高资源的使用效率。
本篇主要介绍了借助于 Hostpath 的内存存储部署 Elasticsearch 提供高性能查询能力的方案,具体内容如下:
[1]使用 JuiceFS 存储 Elasticsearch 数据: https://www.chenshaowen.com/blog/store-elasticsearch-data-in-juicefs.html
以上是部署基於記憶體儲存的 Elasticsearch - 一億+條數據,全文檢索 100ms 回應的詳細內容。更多資訊請關注PHP中文網其他相關文章!