host
a55d2bcf4b
One-off worker verification passed before this flip (2026-10-26): production-shaped docker task (apparmor=docker-codex, pids-limit 512, tenant isolation, egress proxy 8888, --docker-runtime runsc) completed in 60s with gpt-6.1-sol, worktree quadruple + proof verified, template and tenant repo copies clean. README now states the production state.
26 lines
2.0 KiB
Desktop File
26 lines
2.0 KiB
Desktop File
[Unit]
|
||
Description=Codex cloud autoscaler (scales worker processes by queue depth)
|
||
After=codex-cloud-server.service
|
||
Wants=codex-cloud-server.service
|
||
|
||
[Service]
|
||
Type=simple
|
||
User=codexsvc
|
||
Group=codexsvc
|
||
WorkingDirectory=/opt/codex-app-server
|
||
EnvironmentFile=/etc/codex-app-server/env
|
||
# scaler 自身参数在前，`--` 之后是传给 cloud.worker 的参数。
|
||
# 不要在这里写 --worker-id / --worker-capacity / --loop，
|
||
# scaler 会按实例强制追加；--db 只给 scaler，scaler 会补给 worker。
|
||
# 注意：启用 autoscaler 后必须停掉静态 codex-cloud-worker，
|
||
# 否则两边同时派任务（scaler 只管理 autoscale-* 实例）。
|
||
ExecStart=/usr/bin/python3 -m cloud.autoscaler --db /var/lib/codex-app-server/control.db --interval 30 --min-workers 1 --max-workers 2 --per-worker-capacity 2 --scale-down-after 3 --drain-timeout 60 --state-file /var/lib/codex-app-server/autoscaler-state.json --log-dir /var/lib/codex-app-server/autoscaler-logs -- --interval 10 --config /opt/codex-app-server/host-config-docker.json --executor docker --docker-image codex-app-server:latest --docker-user 1003:1004 --docker-cpus 2 --docker-memory 2g --docker-extra-mounts /opt/codex-app-server/work:/app/work,/var/lib/codex-app-server/codex-home:/var/lib/codex-app-server/codex-home,/var/lib/codex-app-server/repos:/var/lib/codex-app-server/repos,/var/lib/codex-app-server/test-repo:/var/lib/codex-app-server/test-repo --repos-dir /var/lib/codex-app-server/repos --tenant-isolation --tenants-root /var/lib/codex-app-server/tenants --tenant-template-home /var/lib/codex-app-server/codex-home --tenant-template-repo /var/lib/codex-app-server/test-repo --docker-security-opt apparmor=docker-codex --docker-pids-limit 512 --egress-proxy-port 8888 --docker-runtime runsc
|
||
Restart=on-failure
|
||
RestartSec=10
|
||
# 停 scaler 时要等它把 worker 优雅排空（drain 60 秒 + 缓冲），
|
||
# 默认 90 秒不够，放到 180 秒；超时后 systemd 再 SIGKILL。
|
||
TimeoutStopSec=180
|
||
|
||
[Install]
|
||
WantedBy=multi-user.target
|