mirror of
https://github.com/kevinveenbirkenbach/computer-playbook.git
synced 2026-11-06 10:59:59 +00:00
kevinveenbirkenbachandClaude Opus 5
eef3c3be71
A wedged LM Studio daemon cost CI job 105558224377 three hours: three kills at the global 60-minute `CONTAINER_EXEC_TIMEOUT`, for a 531 MB model that a healthy node pulls in 27 seconds. Nothing in the path was sized against the thing being fetched, and nothing checked whether it could land at all. Size. Each model now declares `bytes`, taken from the value the deploy already printed as "OK (531068224 bytes)", and the pre-pull derives its own timeout per model: max(preload_floor_seconds, bytes / preload_min_bytes_per_second). The floor of 600s protects a small model from a brief stall; the rate of 1 MB/s sits twenty times below the 21.98 MB/s a healthy pull reached and seven thousand times above the 142 B/s the wedged one managed, so it separates the two without guessing. Evaluated against ansible-core's filters: 531 MB and 10 MB both land on the floor, 4 GB gives 4000s. Disk. The seed measures free space with `df -P -B1` before fetching and refuses with a message naming both figures in GiB, the factor and the file to edit. The factor is three because the node cache, the staging copy inside the container and the models volume all exist at once during the import; that is measured, not padding. Fallback. A model may list `mirrors`, extra bases tried after the source. The mirror task is a no-op once the source delivered, because get_url skips a dest whose checksum already matches: measured at 145.24s for the first pass against 0.64s for the second. The list ships empty, because the obvious candidate is not one: hf-mirror.com answers 206 but resolves to us.aws.cdn.hf.co, so it is a front end for HuggingFace and adds no redundancy against a HuggingFace outage. The mechanism is here; an independent copy is the operator's to name. The external check grew with the declaration: `bytes` is compared against the size the API publishes, and every declared mirror must still serve the pinned file, or it is redundancy on paper only. 01_manager_ops.yml's rescue rationale claimed that restarting the container clears a wedged transfer. Job 105558224377 shows the restart returning rc 0 without clearing it, so the claim now says what was measured instead. Residual: the mirror path has never run in a deploy, since no mirror is declared. Its loop expression is verified against ansible-core's subelements over four shapes, including the zero-iteration case when nothing is mirrored. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
37 lines
850 B
YAML
37 lines
850 B
YAML
---
|
|
lmstudio:
|
|
modes:
|
|
compose:
|
|
enabled: true
|
|
swarm:
|
|
enabled: true
|
|
bond: 1
|
|
enabled: true
|
|
shared: true
|
|
backup:
|
|
no_stop_required: true
|
|
image: lmstudio/llmster-preview
|
|
# nocheck: docker-version -- the repository publishes 2 tags and neither is a version; 'cpu' selects the backend, not a release
|
|
version: cpu
|
|
name: lmstudio
|
|
platform_arch: x86_64
|
|
min_storage: 588MB
|
|
cpus: "4.0"
|
|
mem_reservation: 6g
|
|
mem_limit: 8g
|
|
pids_limit: 2048
|
|
ports:
|
|
internal:
|
|
http: 1234
|
|
preload_models: "{{ AI_LOCAL_MODELS }}"
|
|
preload_async_time: 3600
|
|
preload_floor_seconds: 600
|
|
preload_min_bytes_per_second: 1000000
|
|
lifecycle: beta
|
|
|
|
# nocheck: playwright-service-flag, dynamic-flag
|
|
container_backup: # nocheck: bond-baseline
|
|
bond: 1
|
|
enabled: "{{ 'svc-bkp-volume-2-local' in group_names }}"
|
|
shared: true
|