Closed zhengkang2020 closed 2 weeks ago
第4步已经解决!
## 1、修改grpc的版本,将1.55修改为1.64
vim go.mod
google.golang.org/grpc v1.64.0
## 2、更新版本
go mod tidy
## 3、重新构建
make build
但是使用新构建的scow-slurm-adapter-amd64
问题仍未解决!
重新配置scow,初始化时提示当前正在访问的集群不可用或没有可用集群。请稍后再试或联系管理员。
[root@scow scow]# ./cli compose ps
INFO: Loaded plugins: []
WARN[0000] /scow/docker-compose-1718865568980.yml: `version` is obsolete
NAME IMAGE COMMAND SERVICE CREATED STATUS PORTS
scow-audit-db-1 mysql:8 "docker-entrypoint.s…" audit-db About a minute ago Up About a minute 3306/tcp, 33060/tcp
scow-audit-server-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" audit-server About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-auth-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" auth About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-db-1 mysql:8 "docker-entrypoint.s…" db About a minute ago Up About a minute 3306/tcp, 33060/tcp
scow-gateway-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" gateway About a minute ago Up About a minute 3000/tcp, 0.0.0.0:80->80/tcp, :::80->80/tcp, 5000/tcp
scow-log-1 fluentd:v1.14.0-1.0 "tini -- /bin/entryp…" log About a minute ago Up About a minute 5140/tcp, 0.0.0.0:24224->24224/tcp, 0.0.0.0:24224->24224/udp, :::24224->24224/tcp, :::24224->24224/udp
scow-mis-server-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" mis-server About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-mis-web-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" mis-web About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-novnc-1 ghcr.io/pkuhpc/novnc-client-docker:master "/docker-entrypoint.…" novnc About a minute ago Up About a minute 80/tcp
scow-portal-server-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" portal-server About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-portal-web-1 mirrors.pku.edu.cn/pkuhpc-icode/scow:master "./entrypoint.sh" portal-web About a minute ago Up About a minute 80/tcp, 3000/tcp, 5000/tcp
scow-redis-1 redis:alpine "docker-entrypoint.s…" redis About a minute ago Up About a minute 6379/tcp
mis-server
的日志有报错信息:
[root@scow scow]# ./cli compose logs mis-server
INFO: Loaded plugins: []
WARN[0000] /scow/docker-compose-1718875515775.yml: `version` is obsolete
mis-server-1 |
mis-server-1 | > @scow/mis-server@1.5.2 serve
mis-server-1 | > node build/index.js
mis-server-1 |
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:44.986Z","pid":17,"hostname":"bc7a670af1a1","msg":"Hook is not configured."}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:46.011Z","pid":17,"hostname":"bc7a670af1a1","version":{"commit":"6bde35bd1fc62b5e2187123cbe09cc1227a8ef10"},"msg":"@scow/mis-server: "}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:46.012Z","pid":17,"hostname":"bc7a670af1a1","config":{"HOST":"0.0.0.0","PORT":5000,"LOG_LEVEL":"info","LOG_PRETTY":false,"SSH_PRIVATE_KEY_PATH":"/root/.ssh/id_rsa","SSH_PUBLIC_KEY_PATH":"/root/.ssh/id_rsa.pub","AUTH_URL":"","DB_PASSWORD":"must!chang3this"},"msg":"Loaded env config"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:46.981Z","pid":17,"hostname":"bc7a670af1a1","msg":"Checking if root can login to hpc-test by login node login"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:47.149Z","pid":17,"hostname":"bc7a670af1a1","msg":"Root can login to hpc-test by login node login"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:47.155Z","pid":17,"hostname":"bc7a670af1a1","msg":"Update cluster entity started."}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:47.226Z","pid":17,"hostname":"bc7a670af1a1","plugin":"price","msg":"Default Price Map: {}"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:47.226Z","pid":17,"hostname":"bc7a670af1a1","plugin":"price","msg":"Tenant specific prices {}"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.382Z","pid":17,"hostname":"bc7a670af1a1","plugin":"price","msg":"Executing on hpc01 success"}
mis-server-1 | {"level":40,"time":"2024-06-20T09:22:48.383Z","pid":17,"hostname":"bc7a670af1a1","plugin":"price","msg":"\n The following price items are missing in platform scope: [\"hpc01.compute.normal\",\"hpc01.compute.low\",\"hpc01.compute.high\"].\n An error will be thrown when such a job is fetched.\n "}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.573Z","pid":17,"hostname":"bc7a670af1a1","plugin":"fetch","msg":"Fetch info started."}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.723Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"misConfig.periodicSyncStatus?.cron: 0 4 * * *"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.725Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Sync block status started."}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.729Z","pid":17,"hostname":"bc7a670af1a1","plugin":"cache","msg":"Cache clear scheduled task started."}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.785Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Current clusters list: (Cluster ID: hpc01) : ACTIVATED"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.802Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated block status in slurm of the following accounts: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.802Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated block status failed in slurm of the following accounts: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.802Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated block status in slurm of the following user account: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.803Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated block status failed in slurm of the following user account: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.819Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Current clusters list: (Cluster ID: hpc01) : ACTIVATED"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.820Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated unblock status in slurm of the following accounts: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.821Z","pid":17,"hostname":"bc7a670af1a1","plugin":"syncBlockStatus","msg":"Updated unblock status failed in slurm of the following accounts: []"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:22:48.883Z","pid":17,"hostname":"bc7a670af1a1","msg":"Listening at 5000"}
mis-server-1 | (node:17) DeprecationWarning: Calling start() is no longer necessary. It can be safely omitted.
mis-server-1 | (Use `node --trace-deprecation ...` to show where the warning was created)
mis-server-1 | {"level":30,"time":"2024-06-20T09:23:09.743Z","pid":17,"hostname":"bc7a670af1a1","req":"1","path":"/scow.server.InitService/QuerySystemInitialized","msg":"Starting request"}
mis-server-1 | {"level":30,"time":"2024-06-20T09:23:09.753Z","pid":17,"hostname":"bc7a670af1a1","req":"1","path":"/scow.server.InitService/QuerySystemInitialized","msg":"Request completed."}
麻烦看下是哪里的问题?
使用master分支为以上情况,使用1.5.2分支正常!
cli更新到1.6后正常!
升级cli到1.6版本后正常!
发生了什么
执行
./cli compose pull && ./cli compose down && ./cli compose up -d
后 1、主页提示没有可用集群 2、创建作业报错,提示404 3、集群管理中正常 4、尝试编译最新版本的适配器,但是按文档编译报错之前运行正常吗?
./cli compose pull
之前运行正常!运行环境 | Environment