Slurm's shared files and users: one path everywhere, accounts as Linux users
CI / test (push) Failing after 7m1s
CI / test (push) Failing after 7m1s
slurm.shared mounts the site's NFS export, has an llmgw node export the path over NFS to the Slurm machines alone (2049 in the firewall), or looks for a file system the site mounts. slurm.users "llmgw" makes each active account a Linux user on every Slurm machine: login from its e-mail, a UID from 200000 kept in slurm_users and never reused, its home on the shared path, its SSH keys from the portal's Profile (or ctl slurm users keys) read by sshd from /etc/llmgw/ssh-keys. server init --slurm chooses /shared from the first machine and llmgw's users; --slurm-shared and --slurm-users change that. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed
1 parent
b9d20e7bba
commit
d8ce573bdb
45 files changed
+2505
-79
No files matched your search
@@ -5109,6 +5109,89 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/slurm/users": {
|
||||
"get": {
|
||||
"operationId": "getSlurmUsers",
|
||||
"summary": "The Linux users made from llmgw's accounts for the Slurm cluster",
|
||||
"description": "Every active account, with its login, UID and SSH keys; an account is given its login and UID the first time it is listed. The machines have them when slurm.users is \"llmgw\".",
|
||||
"tags": [
|
||||
"slurm"
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/slurmsvc.User"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/Error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/slurm/users/{user}/ssh-keys": {
|
||||
"put": {
|
||||
"operationId": "putSlurmUsersUserSshKeys",
|
||||
"summary": "Replace an account's SSH public keys",
|
||||
"description": "{user} is an ID or e-mail. keys is OpenSSH public keys, one a line, without options; empty takes them all away. The machines have them within a minute.",
|
||||
"tags": [
|
||||
"slurm"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
"name": "user",
|
||||
"in": "path",
|
||||
"required": true,
|
||||
"description": "The person's ID or email.",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/parameters/Actor"
|
||||
}
|
||||
],
|
||||
"requestBody": {
|
||||
"required": true,
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/SlurmKeysRequest"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/slurmsvc.User"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"401": {
|
||||
"$ref": "#/components/responses/Unauthorized"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/Error"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/summary": {
|
||||
"get": {
|
||||
"operationId": "getSummary",
|
||||
@@ -9401,6 +9484,15 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"SlurmKeysRequest": {
|
||||
"type": "object",
|
||||
"description": "SlurmKeysRequest is a person's SSH public keys, one a line, as authorized_keys has them; empty takes them all away.",
|
||||
"properties": {
|
||||
"keys": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"StoreMember": {
|
||||
"type": "object",
|
||||
"description": "StoreMember is one member of a replicated store, as its Patroni reports it.",
|
||||
@@ -10785,6 +10877,24 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"config.SharedStorage": {
|
||||
"type": "object",
|
||||
"description": "SharedStorage is where the Slurm cluster's shared files come from: the site's NFS export (NFS), an NFS export llmgw keeps on one of its nodes (Server), or, with neither, a file system the site mounts itself (Lustre, BeeGFS, GPFS), which llmgw only looks for.",
|
||||
"properties": {
|
||||
"Path": {
|
||||
"type": "string",
|
||||
"description": "Path is where every machine sees it, as /shared."
|
||||
},
|
||||
"NFS": {
|
||||
"type": "string",
|
||||
"description": "NFS is the site's export, host:/path, mounted at Path on every machine of the Slurm cluster."
|
||||
},
|
||||
"Server": {
|
||||
"type": "string",
|
||||
"description": "Server is the llmgw node, the controller or one of the nodes, that exports Path over NFS to the others: for a site with no storage of its own. One machine: not highly available, and no faster than its disk and network."
|
||||
}
|
||||
}
|
||||
},
|
||||
"control.Activity": {
|
||||
"type": "object",
|
||||
"description": "Activity is what a standby's router reports back: when it last sent each replica a request, and the on-demand models it was asked for. The leader evicts and loads by these, and without them a replica busy behind a standby looks idle to the one machine that decides.",
|
||||
@@ -12249,6 +12359,14 @@
|
||||
"slurmdbd_running": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"shared": {
|
||||
"type": "string",
|
||||
"description": "Shared is the shared path here: \"mounted\", \"exported\", \"missing\"."
|
||||
},
|
||||
"users": {
|
||||
"type": "integer",
|
||||
"description": "Users is how many of llmgw's users the machine has."
|
||||
},
|
||||
"state": {
|
||||
"type": "string"
|
||||
},
|
||||
@@ -12301,6 +12419,40 @@
|
||||
"type": "string"
|
||||
},
|
||||
"description": "Waiting are nodes left out of slurm.conf until they report their hardware."
|
||||
},
|
||||
"shared": {
|
||||
"$ref": "#/components/schemas/config.SharedStorage",
|
||||
"description": "Shared is where the shared files are and come from; Users who keeps the users, and how many llmgw has."
|
||||
},
|
||||
"users": {
|
||||
"type": "string"
|
||||
},
|
||||
"user_count": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
},
|
||||
"slurmsvc.User": {
|
||||
"type": "object",
|
||||
"description": "User is a Linux user made from an llmgw account.",
|
||||
"properties": {
|
||||
"login": {
|
||||
"type": "string"
|
||||
},
|
||||
"uid": {
|
||||
"type": "integer"
|
||||
},
|
||||
"name": {
|
||||
"type": "string"
|
||||
},
|
||||
"email": {
|
||||
"type": "string"
|
||||
},
|
||||
"ssh_keys": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
Reference in new issue
Block a user