mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 13:07:57 +09:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
57a30979a7 | ||
|
|
70dd49da4a | ||
|
|
f26fb3fd85 |
No files matched your search
@@ -14,7 +14,7 @@ name: Build GHA Runner Images
|
||||
# 3. Stop the VM, snapshot its boot disk to a new image in the `gha-runner-<variant>`
|
||||
# image family with name gha-runner-<variant>-<timestamp>.
|
||||
# 4. Delete the build VM (boot disk auto-deletes).
|
||||
# 5. Deprecate older images in the family, keeping the newest 3 ACTIVE.
|
||||
# 5. Delete older images in the family, keeping the newest 2 (rollback = previous month).
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
@@ -24,7 +24,7 @@ on:
|
||||
required: false
|
||||
default: 'all'
|
||||
skip_prune:
|
||||
description: 'Skip deprecation of old images (debugging)'
|
||||
description: 'Skip pruning (deletion) of old images (debugging)'
|
||||
type: boolean
|
||||
required: false
|
||||
default: false
|
||||
@@ -41,7 +41,7 @@ env:
|
||||
BUILD_REGION: us-central1
|
||||
BUILD_ZONE: us-central1-a
|
||||
BASE_IMAGE: projects/debian-cloud/global/images/family/debian-12
|
||||
KEEP_IMAGES_PER_FAMILY: 3
|
||||
KEEP_IMAGES_PER_FAMILY: 2
|
||||
|
||||
jobs:
|
||||
resolve-matrix:
|
||||
@@ -271,7 +271,7 @@ jobs:
|
||||
run: |
|
||||
gcloud compute instances delete "$VM" --zone="$ZONE" --project="$PROJECT" --quiet || true
|
||||
|
||||
- name: Deprecate old images (keep newest ${{ env.KEEP_IMAGES_PER_FAMILY }})
|
||||
- name: Prune old images (keep newest ${{ env.KEEP_IMAGES_PER_FAMILY }})
|
||||
if: ${{ github.event.inputs.skip_prune != 'true' }}
|
||||
env:
|
||||
PROJECT: ${{ env.GCP_PROJECT }}
|
||||
@@ -279,20 +279,45 @@ jobs:
|
||||
KEEP: ${{ env.KEEP_IMAGES_PER_FAMILY }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# List ACTIVE images in this family, newest first, skip the top $KEEP.
|
||||
to_deprecate=$(gcloud compute images list \
|
||||
# DELETE (not deprecate — deprecated images still bill for storage)
|
||||
# every image in this family beyond the newest $KEEP. The dispatcher
|
||||
# boots from the family URL, which always resolves to the newest image,
|
||||
# so older ones are only rollback insurance (~$0.05/GB-mo; gpu images
|
||||
# are ~21 GB each). Previously this step used an invalid
|
||||
# `-deprecated.state:*` filter: gcloud errored to stderr, stdout was
|
||||
# empty, and it silently reported "Nothing to deprecate" every month
|
||||
# while images piled up (31 runner images, ~$18/mo, by 2026-09).
|
||||
# Match the family EXACTLY client-side: a gcloud `family=gha-runner-gpu`
|
||||
# filter is a word-boundary regex that ALSO matches gha-runner-gpu-windows.
|
||||
# Rank by ACTIVE (non-deprecated) images: the family URL skips deprecated
|
||||
# images, so the newest $KEEP active ones are the real rollback path.
|
||||
# Deprecated images never count toward $KEEP.
|
||||
rows=$(gcloud compute images list \
|
||||
--project="$PROJECT" \
|
||||
--filter="family=$FAMILY AND status=READY AND -deprecated.state:*" \
|
||||
--no-standard-images \
|
||||
--show-deprecated \
|
||||
--sort-by='~creationTimestamp' \
|
||||
--format='value(name)' | tail -n +$((KEEP+1)))
|
||||
if [[ -z "$to_deprecate" ]]; then
|
||||
echo "Nothing to deprecate."
|
||||
--format='value(name,family,deprecated.state)' | awk -v f="$FAMILY" '$2==f')
|
||||
active=$(echo "$rows" | awk 'NF==2 {print $1}')
|
||||
if [[ -z "$active" ]]; then
|
||||
echo "::error::No active images found in family $FAMILY (list failed?) — refusing to prune."
|
||||
exit 1
|
||||
fi
|
||||
keep=$(echo "$active" | head -n "$KEEP")
|
||||
to_delete=$(echo "$rows" | awk '{print $1}' | grep -vxF "$keep" || true)
|
||||
if [[ -z "$to_delete" ]]; then
|
||||
echo "Nothing to prune (<= $KEEP images in $FAMILY)."
|
||||
exit 0
|
||||
fi
|
||||
for img in $to_deprecate; do
|
||||
echo "Deprecating $img"
|
||||
gcloud compute images deprecate "$img" \
|
||||
--project="$PROJECT" \
|
||||
--state=DEPRECATED \
|
||||
--replacement="projects/$PROJECT/global/images/family/$FAMILY"
|
||||
# Never delete an image some existing disk was created from (e.g. a
|
||||
# long-lived VM still on an older image).
|
||||
in_use=$(gcloud compute disks list --project="$PROJECT" \
|
||||
--format='value(sourceImage.basename())' | sort -u)
|
||||
for img in $to_delete; do
|
||||
if grep -qx "$img" <<<"$in_use"; then
|
||||
echo "Keeping $img (source image of an existing disk)"
|
||||
continue
|
||||
fi
|
||||
echo "Deleting $img"
|
||||
gcloud compute images delete "$img" --project="$PROJECT" --quiet
|
||||
done
|
||||
@@ -242,7 +242,13 @@ GitHub schedules onto any runner whose labels are a superset of the job's.
|
||||
Each image is tagged `gha-runner-<variant>-<YYYYMMDD-HHMMSS>` and joined to the
|
||||
matching image family. The dispatcher always selects from the family, so the
|
||||
newest non-deprecated image wins automatically. The build workflow keeps the
|
||||
newest 3 images per family and deprecates the rest.
|
||||
newest 2 images per family and **deletes** the rest (deprecated images still bill
|
||||
for storage; images that an existing disk was created from are never deleted).
|
||||
Until 2026-09-26 this step used an invalid gcloud filter and silently pruned
|
||||
nothing — 31 runner images (~360 GB archived, ~$18/mo) had accumulated; they were pruned by hand to
|
||||
2 per family when the step was fixed. Note a gcloud `family=gha-runner-gpu`
|
||||
filter also matches `gha-runner-gpu-windows` (word-boundary regex), so the step
|
||||
matches the family exactly client-side.
|
||||
|
||||
Build cadence: monthly cron (`0 2 1 * *` UTC) + `workflow_dispatch`. Manual:
|
||||
|
||||
|
||||
@@ -85,7 +85,8 @@ The `concurrency=1` setting may have been added deliberately for performance rea
|
||||
(c4d/c4/n4d/c2d/n2d/n2) for stockout resilience.
|
||||
- **Idle auto-shutdown is live** (JIT start on the lyrics-review page; a Cloud
|
||||
Function stops idle VMs after 15 min). When idle, cost is just boot disks
|
||||
(~$10/VM/mo); compute is billed only while encoding — so the historical
|
||||
(50 GB since 2026-09-26, ~$4-5/VM/mo; was 100 GB / ~$10 — see
|
||||
docs/archive/2026-09-26-encoding-worker-disk-cost.md); compute is billed only while encoding — so the historical
|
||||
"~$700/mo running 24/7" no longer applies.
|
||||
|
||||
**Opportunities (status):**
|
||||
|
||||
@@ -2033,3 +2033,20 @@ Also: colour-code the bars with the **exact** `HIGHLIGHT_CLASSES` tints the Adva
|
||||
pills use (not hand-picked solids) so the two views read identically, and persist the
|
||||
view mode under a new `lyricsReviewViewMode` enum that migrates the old
|
||||
`lyricsReviewAdvancedMode` boolean.
|
||||
|
||||
### Encoding-worker disks: shrink via in-place boot-disk swap, not Pulumi replace (2026-09-26)
|
||||
|
||||
- Workers used ~8-15 GB of their 100 GB boot disks. Shrunk to 50 GB (Packer image
|
||||
`disk_size` 100→30 — a disk can't be smaller than its source image).
|
||||
- Changing `boot_disk.initialize_params.size` in Pulumi means replace (or an
|
||||
impossible in-place shrink); replacing a c4d/n4d/c2d VM needs capacity that may be
|
||||
stocked out for hours. Instead: while TERMINATED, detach + delete the old boot disk,
|
||||
create a new one from the new image, attach `--boot --device-name=persistent-disk-0`,
|
||||
then `pulumi refresh --target` the instance → no diff. No compute allocation needed.
|
||||
- New hyperdisks default to paid IOPS/throughput above the free 3000/140 baseline —
|
||||
always pass `--provisioned-iops=3000 --provisioned-throughput=140` (Pulumi doesn't
|
||||
set them because boot-disk init params force replacement).
|
||||
- A gcloud `family=X` filter is a word-boundary regex (`gha-runner-gpu` also matches
|
||||
`gha-runner-gpu-windows`), and an invalid filter errors to stderr with empty stdout
|
||||
— pipelines that treat empty output as "nothing to do" silently no-op. The runner
|
||||
image prune step did this for months (31 images, ~$18/mo).
|
||||
@@ -0,0 +1,116 @@
|
||||
# Encoding-worker disk cost reduction (2026-09-26)
|
||||
|
||||
## Problem
|
||||
|
||||
The 10 encoding-worker VMs (c4d primary pair + 8 stockout fallbacks) are stopped
|
||||
between jobs, so their cost is mostly their boot disks. Last-30-day billing:
|
||||
Hyperdisk Balanced capacity ~$48 (601 GiB-mo) + provisioned throughput ~$12 +
|
||||
provisioned IOPS ~$6; Balanced PD capacity ~$45 (includes 2 runner disks). Plus
|
||||
~$18/mo "Storage Image" for 39 custom images.
|
||||
|
||||
## Findings
|
||||
|
||||
- **Disks were ~85% empty.** `encoding-worker-b`, 8 months in service: 15 GB used
|
||||
of 99 GB (7 GB venv, 3 GB pip cache, 0.7 GB logs). Fresh disks from the current
|
||||
image use 8 GB.
|
||||
- **Scratch need is small.** Each `/encode` downloads its whole `jobs/<id>/` folder
|
||||
into `/tmp` on the boot disk. Across 1,904 job folders: median 0.43 GB, p99 1.3 GB,
|
||||
max 4.0 GB. Downloads happen before the (serialized) heavy lane, so queued jobs
|
||||
hold their inputs at the same time. The deepest queue seen in 30 days was 8.
|
||||
Realistic peak: ~8 GB base + ~10-15 GB scratch.
|
||||
- **Only two disks had paid IOPS/throughput.** `-c4a` and `-n4db`, created 2026-08-15
|
||||
after the June IOPS tune, got the Hyperdisk defaults of 3600 IOPS / 290 MB/s. The
|
||||
other hyperdisks were already on the free baseline of 3000 / 140.
|
||||
- **Image size set the disk floor.** Packer built the image with `disk_size = 100`.
|
||||
GCE cannot create a disk smaller than its source image, so every worker had to be
|
||||
at least 100 GB.
|
||||
- **Runner image pruning had never run.** The monthly `build-runner-images.yml`
|
||||
step used an invalid filter (`-deprecated.state:*`). gcloud wrote the error to
|
||||
stderr and the step printed "Nothing to deprecate". Deprecating wouldn't have
|
||||
saved money anyway, because deprecated images are still billed.
|
||||
|
||||
## Changes
|
||||
|
||||
| Lever | Change | Est. saving |
|
||||
|---|---|---|
|
||||
| Boot disk size | 100 GB to **50 GB** on all 10 workers (`DiskSizes.ENCODING_WORKER`); Packer image `disk_size` 100 to **30** | ~$44/mo |
|
||||
| Hyperdisk IOPS/throughput | `-c4a`/`-n4db` 3600/290 to 3000/140 (free baseline). New hyperdisks are created at 3000/140 explicitly | ~$18/mo |
|
||||
| Custom images | Deleted 23 old runner images (kept newest 2 per family). Fixed the prune step so it deletes beyond the newest 2, matches the family exactly, and skips images that are a disk's source | ~$13/mo |
|
||||
|
||||
**Total: ~$75/mo.**
|
||||
|
||||
Levers considered and **not** taken:
|
||||
- **Removing fallback VMs.** Not done. They are the stockout insurance, and machine-family diversity is deliberate.
|
||||
- **Ephemeral boot disks (create from image at start).** Not done. This adds disk-creation and hydration latency to every cold start, plus another failure mode during stockouts. The saving (~$4/VM/mo after the shrink) isn't worth that.
|
||||
- **pd-standard for the fallbacks.** Not done. A 50 GB pd-standard disk gets ~75 read IOPS, which would slow boot and pip installs badly. c4/c4d/n4d VMs require Hyperdisk anyway.
|
||||
- **Smaller than 50 GB.** Not done. It saves only ~$1/disk/mo per 10 GB, and a disk-full error during a bulk-queue encode costs far more than that.
|
||||
|
||||
## Performance
|
||||
|
||||
pd-balanced performance scales with size: 100 GB gives 3600 IOPS / 168 MB/s, and
|
||||
50 GB gives 3300 / 154. Hyperdisk Balanced at 3000 / 140 is the same at any size.
|
||||
Encoding is CPU-bound: a full 4K finalization writes ~200 MB of outputs in ~2 min.
|
||||
|
||||
Real full `/encode` of the same job (`bench/disk-swap-input`, the Aug-2026 benchmark
|
||||
song; formats 4k lossless + 4k lossy + 720p), wall time in seconds:
|
||||
|
||||
| VM | CPU platform | Before (100 GB, old image) | After (50 GB, new image) | start to healthy |
|
||||
|---|---|---|---|---|
|
||||
| fallback-c2df (pd-balanced) | AMD Milan | 142.6, 138.9 | 142.2, 136.9 | 34.9 s to 33.5 s |
|
||||
| fallback-c4a (hyperdisk) | Intel Emerald Rapids | 132.1, 121.4 | 147.4, 144.5, then a re-run of 143.9, 138.7, 138.6 | 39.1 s to 50-53 s |
|
||||
| fallback-n2da (pd-balanced) | AMD Milan | failed: transient metadata-server SSL error (pre-existing, see v0.217.0) | 155.7 | to 41.7 s |
|
||||
| fallback-n2f (pd-balanced) | Intel Cascade Lake | 247.2 (Aug benchmark) | 246.8 | to 39.7 s |
|
||||
| fallback-a (hyperdisk) | AMD Turin (c4d) | n/a | 99.0 | to 42.3 s |
|
||||
| fallback-b (hyperdisk) | AMD Turin (c4d) | n/a | 105.4 | to 52.5 s |
|
||||
| encoding-worker-b (hyperdisk) | AMD Turin (c4d) | n/a | 100.8 | to 35.9 s |
|
||||
| encoding-worker-a (hyperdisk, primary) | AMD Turin (c4d) | n/a | 98.9 | to 36.9 s |
|
||||
|
||||
On c4a the after-median of 139 s is exactly the 138.6 s August median, which was
|
||||
measured on the old 100 GB disk. The two "before" samples today were at the fast
|
||||
end of the ~35% run-to-run noise the August benchmark documented. Hyperdisk
|
||||
performance at 3000/140 doesn't depend on disk size, so the disk change can't
|
||||
explain the difference.
|
||||
|
||||
## Rollout procedure: in-place boot-disk swap
|
||||
|
||||
Changing `boot_disk.initialize_params.size` makes Pulumi either replace the VM or
|
||||
try an in-place resize. An in-place resize can't shrink a disk, and a replacement
|
||||
has to re-allocate the VM, which for c4d/n4d/c2d can be blocked for hours by a
|
||||
stockout. Each VM was left in place and only its boot disk was swapped, while the
|
||||
VM was `TERMINATED`. No compute capacity is needed for this.
|
||||
|
||||
```bash
|
||||
# Per VM, only if status == TERMINATED and config/encoding-worker.deploy_in_progress is false
|
||||
gcloud compute instances detach-disk $VM --zone=$Z --disk=$VM
|
||||
gcloud compute disks delete $VM --zone=$Z --quiet
|
||||
# hyperdisk-balanced (c4d/c4/n4d):
|
||||
gcloud compute disks create $VM --zone=$Z --image=$NEW_IMAGE --image-project=nomadkaraoke \
|
||||
--size=50GB --type=hyperdisk-balanced --provisioned-iops=3000 --provisioned-throughput=140
|
||||
# pd-balanced (n2/n2d/c2d):
|
||||
gcloud compute disks create $VM --zone=$Z --image=$NEW_IMAGE --image-project=nomadkaraoke \
|
||||
--size=50GB --type=pd-balanced
|
||||
gcloud compute instances attach-disk $VM --zone=$Z --disk=$VM --boot --device-name=persistent-disk-0
|
||||
gcloud compute instances set-disk-auto-delete $VM --zone=$Z --disk=$VM --auto-delete
|
||||
# then: pulumi refresh --target <instance urn> → state picks up size 50 / new image;
|
||||
# pulumi preview shows no diff for that VM (the family-image URL diff-suppresses).
|
||||
```
|
||||
|
||||
The old disk is deleted without a snapshot on purpose. Worker boot disks hold no
|
||||
state that can't be rebuilt: the image, the wheel downloaded at boot, and caches.
|
||||
Jobs live in GCS and Firestore.
|
||||
|
||||
Rollback: repeat the swap using the previous image. `encoding-worker-1786843294`
|
||||
is kept for this.
|
||||
|
||||
Verification per VM: start it, check `/health` (wheel version), run a real `/encode`,
|
||||
check `df`, then stop it. VMs that hit a stockout at start were swapped but could
|
||||
only be verified later.
|
||||
|
||||
## Status
|
||||
|
||||
All 10 workers were swapped to 50 GB on `encoding-worker-1790444464` and their
|
||||
Pulumi state was refreshed, and `pulumi preview` shows no encoding-VM diff. The old
|
||||
encoding-worker images were deleted, keeping `encoding-worker-1786843294` for
|
||||
rollback. Custom images went from 39 to 10. `-n4db` (n4d, us-central1-b) and `-n2c`
|
||||
(n2, us-central1-c) couldn't be boot-verified because both zones were stocked out
|
||||
during the rollout. They got the same swap as the 8 verified VMs.
|
||||
@@ -173,7 +173,7 @@ gcloud compute ssh github-runner-1 --zone=us-central1-a -- \
|
||||
|
||||
High-performance VM for video encoding:
|
||||
- Machine: c4-standard-8 (8 vCPU, 32GB RAM)
|
||||
- Disk: 100GB hyperdisk-balanced
|
||||
- Disk: 50GB boot disk (hyperdisk-balanced at the free 3000 IOPS / 140 MB/s baseline; pd-balanced on c2d/n2/n2d fallbacks). See docs/archive/2026-09-26-encoding-worker-disk-cost.md
|
||||
- Pre-installed: FFmpeg (static build), Python 3.13, Noto fonts
|
||||
|
||||
**API Endpoints:**
|
||||
|
||||
@@ -122,7 +122,7 @@ def create_encoding_worker_fallback_vms(
|
||||
every lane at once (incident 2026-08-12). Each entry's machine_type and
|
||||
disk_type come from EncodingWorkerConfig.FALLBACKS — n2 uses pd-balanced
|
||||
because it does not support hyperdisk-balanced. Cost when stopped is just
|
||||
the boot disk (~$10/mo each).
|
||||
the 50 GB boot disk (~$4-5/mo each).
|
||||
"""
|
||||
startup_script = read_script("encoding_worker.sh")
|
||||
custom_image = f"projects/{PROJECT_ID}/global/images/family/encoding-worker"
|
||||
|
||||
@@ -71,7 +71,18 @@ class DiskSizes:
|
||||
"""Disk size configurations in GB."""
|
||||
|
||||
GITHUB_RUNNER = 200 # Large for Docker builds/caches
|
||||
ENCODING_WORKER = 100 # For temp video files during encoding
|
||||
# Encoding-worker boot disk (OS + baked venv ~12-15 GB, plus per-job scratch in
|
||||
# /tmp: each queued /encode downloads its whole jobs/<id>/ folder — p99 ~1.3 GB,
|
||||
# max seen ~4 GB — and up to ~9 jobs have been queued on one worker at once).
|
||||
# Was 100 GB, but a worker 8 months into service used only 15 GB of it; 50 GB
|
||||
# keeps >3x headroom over realistic peak while halving the 10-VM disk bill.
|
||||
# Must be >= the Packer image's disk_size (infrastructure/packer/
|
||||
# encoding-worker.pkr.hcl), since GCE cannot create a disk smaller than its
|
||||
# source image. Changing this forces VM *replacement* in Pulumi — see
|
||||
# docs/archive/2026-09-26-encoding-worker-disk-cost.md for the in-place
|
||||
# boot-disk swap procedure that avoids re-allocating (possibly stocked-out) VMs.
|
||||
ENCODING_WORKER = 50
|
||||
ENCODING_WORKER_IMAGE = 30 # Packer image disk_size (keep in sync with .pkr.hcl)
|
||||
FLACFETCH = 30 # For torrent storage
|
||||
|
||||
|
||||
@@ -306,7 +317,7 @@ class EncodingWorkerConfig:
|
||||
# Capacity-resilience fallback fleet. Each VM is provisioned STOPPED in an
|
||||
# alternate zone / machine family and is started on demand only when the
|
||||
# primary zone rejects a start with ZONE_RESOURCE_POOL_EXHAUSTED. Cost when
|
||||
# stopped is just the boot disk (~$10/mo each).
|
||||
# stopped is just the 50 GB boot disk (~$4-5/mo each).
|
||||
#
|
||||
# Machine-family diversity is DELIBERATE. The primary pair and the two c4d
|
||||
# fallbacks are all c4d-highcpu-32, so a region-wide c4d stockout (observed
|
||||
|
||||
@@ -94,6 +94,16 @@ Rebuild the image when:
|
||||
- Font packages change
|
||||
- bootstrap.sh changes (extremely rare)
|
||||
|
||||
**Image disk size:** `disk_size` in the template (30 GB) is the *minimum* boot-disk
|
||||
size of any VM created from the image — GCE cannot create a disk smaller than its
|
||||
source image. Keep it ≤ `DiskSizes.ENCODING_WORKER` in `infrastructure/config.py`
|
||||
(50 GB); `infrastructure/test_encoding_worker_config.py` enforces this.
|
||||
|
||||
**After a rebuild, existing VMs keep their old disks** (Pulumi only uses the new
|
||||
image when a VM/disk is recreated). To roll a new image onto the stopped workers
|
||||
without re-allocating VMs (stockout-safe), use the in-place boot-disk swap in
|
||||
`docs/archive/2026-09-26-encoding-worker-disk-cost.md`.
|
||||
|
||||
**No rebuild needed** for:
|
||||
- Application code changes (wheel downloaded at runtime)
|
||||
- Startup logic changes (startup.sh downloaded from GCS)
|
||||
|
||||
@@ -44,7 +44,12 @@ source "googlecompute" "encoding-worker" {
|
||||
# Use n2 machine type for building (c4 requires hyperdisk which isn't supported by Packer)
|
||||
# The resulting image will work on c4-standard-8 in production
|
||||
machine_type = "n2-standard-8"
|
||||
disk_size = 100
|
||||
# Image disk size = the MINIMUM boot-disk size any VM created from this image
|
||||
# can have (GCE cannot create a disk smaller than its source image). Keep it
|
||||
# small (the provisioned OS + venv is ~12 GB) so the worker boot disk size is
|
||||
# decided by infrastructure/config.py::DiskSizes.ENCODING_WORKER (50 GB), not
|
||||
# pinned here. Was 100, which forced every worker onto a 100 GB disk.
|
||||
disk_size = 30
|
||||
disk_type = "pd-ssd" # Use SSD for faster builds
|
||||
|
||||
# Image naming - uses timestamp for versioning, family for latest
|
||||
|
||||
@@ -112,3 +112,24 @@ def test_original_c4d_fallbacks_unchanged():
|
||||
"machine_type": MachineTypes.ENCODING_WORKER, "disk_type": "hyperdisk-balanced"}
|
||||
assert b == {"suffix": "b", "zone_suffix": "b",
|
||||
"machine_type": MachineTypes.ENCODING_WORKER, "disk_type": "hyperdisk-balanced"}
|
||||
|
||||
|
||||
def test_worker_boot_disk_fits_packer_image_size():
|
||||
"""GCE cannot create a boot disk smaller than its source image's disk size.
|
||||
The Packer image's `disk_size` must stay <= DiskSizes.ENCODING_WORKER, or
|
||||
every worker (re)creation from the new image fails. Also keeps the
|
||||
ENCODING_WORKER_IMAGE mirror constant honest."""
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
from config import DiskSizes
|
||||
|
||||
hcl = (Path(__file__).parent / "packer" / "encoding-worker.pkr.hcl").read_text()
|
||||
match = re.search(r"^\s*disk_size\s*=\s*(\d+)", hcl, re.MULTILINE)
|
||||
assert match, "disk_size not found in encoding-worker.pkr.hcl"
|
||||
image_size = int(match.group(1))
|
||||
assert image_size == DiskSizes.ENCODING_WORKER_IMAGE
|
||||
assert image_size <= DiskSizes.ENCODING_WORKER
|
||||
# Headroom floor: OS + baked venv is ~12-15 GB and per-job scratch lives in
|
||||
# /tmp on the boot disk. Don't let a future "cost cut" starve encodes.
|
||||
assert DiskSizes.ENCODING_WORKER >= 40
|
||||
Reference in new issue
Block a user