fix(esh): Plex hardware transcoding on the Arc A580, and the two ways it hid

Plex never hardware-transcoded on esh-pve-nas LXC 105 despite correct passthrough,
cgroups, group membership, authenticated HuC firmware, a lifetime Plex Pass,
HardwareAcceleratedCodecs=1, and the Arc already selected as HardwareDevicePath.

Root cause sat below all of that: intel-media-va-driver 22.3.1 (Apr 2023, stock
jammy) predates Arc/DG2 support and exports only __vaDriverInit_1_14, against the
libva 2.22 that Plex bundles and loads via RPATH rather than the system one. A
half-finished prior attempt at the same fix was also present -- libva and libva-drm
hand-installed at 2.22 with libva-x11 left at 2.14, breaking every X11 VA-API
consumer on va_fool_postp.

Fixed with Intel's client-GPU repo: iHD 24.3.4 (__vaDriverInit_1_22, an exact ABI
match) plus a consistent libva 2.22.0.2-87 set, which also brings the orphaned
manual install back under dpkg. The repo track is rolling, so the six packages are
pinned in /etc/apt/preferences.d/intel-gpu-pin and apt-mark held; verified by a
simulated upgrade that moves 152 packages and touches none of them.

Two findings worth more than the fix:

pct snapshot refuses on a guest with a bind mount and still exits 0, so a script
guarding a change with it proceeds without the rollback point it believes it has.
The ZFS dataset snapshot is the working path, verified by reading it back.

A synthetic Plex Transcoder invocation is not a valid test of Plex's transcode
path. Plex bundles its own libc among 61 libraries; the harness produced three
distinct failure modes that were artifacts of not reproducing that runtime, and it
failed identically before and after a fix that worked. With no positive control its
negatives carried no information. Only a forced transcode settles it, and PASS is
recognisable by Plex naming the device. The original empty decoder/encoder line was
an absence of evidence rather than evidence of failure -- TranscodeSession was 0.

Jellyfin LXC 107 has the same stale stack and the same Arc available; left alone
per the operator, and it ships its own ffmpeg so this may not transfer verbatim.
This commit is contained in:
vh
2026-09-11 22:03:52 -07:00
parent e01484f6d0
commit 88e171bea6
3 changed files with 204 additions and 0 deletions
+122
View File
@@ -0,0 +1,122 @@
# Plex hardware transcoding on the Arc A580 (esh-pve-nas, LXC 105)
**Fixed 2026-09-11.** Plex never hardware-transcoded on the Arc A580 despite every
setting being correct. The fault was one layer below the settings, and the whole
diagnosis is reusable for any Intel-GPU VA-API consumer on Ubuntu 22.04.
## The symptom, and why it misleads
Plex logged, on every transcode decision:
TPU: hardware transcoding: final decoder: , final encoder:
Both fields empty. That reads like "hardware transcoding failed", but on its own it is
**also** what you get when nothing transcoded at all — and `TranscodeSession` count was
zero, so the log was not evidence of failure. Twenty of those lines landed inside one
second on one thread: a capability probe loop, not twenty sessions.
⚠ **Do not diagnose this from configuration.** Every one of these read correct while
hardware transcoding was dead:
| checked | state |
|---|---|
| Arc A580 present, DMC/GuC/HuC firmware | ✅ HuC "authenticated for all workloads" |
| LXC passthrough: both render nodes + cgroup allows | ✅ |
| `plex` user in `video(44)` + `render(104)` | ✅ |
| Plex 1.43.2, lifetime Plex Pass | ✅ |
| `HardwareAcceleratedCodecs=1` (via API, not the file) | ✅ |
| `HardwareDevicePath` = `…@0000:03:00.0` (the Arc) | ✅ already selected |
⚠ `HardwareAcceleratedCodecs` is **absent from `Preferences.xml` when enabled** — Plex
only persists non-defaults. Read it from the API, never from the file:
curl -s "http://127.0.0.1:32400/:/prefs?X-Plex-Token=$TOKEN"
## Root cause
`intel-media-va-driver` **22.3.1** (Apr 2023, stock jammy) — predates Arc/DG2 support
entirely, and exports only `__vaDriverInit_1_14` against Plex's **bundled** libva 2.22
(`/usr/lib/plexmediaserver/lib/libva.so.2`, loaded via RPATH, not the system one).
Compounding it: someone had previously hand-installed libva 2.22 over the packaged
2.14 and left `libva-x11` behind at 2.14, so `vainfo` died with
`undefined symbol: va_fool_postp` — a half-finished run at this same fix.
## The fix
```bash
# 1. Snapshot. `pct snapshot` REFUSES on a guest with a bind mount (mp0: /tank/media)
# AND STILL EXITS 0 — snapshot the ZFS dataset directly and read it back.
zfs snapshot nvme/subvol-105-disk-0@pre-vaapi-20260911
zfs list -t snapshot nvme/subvol-105-disk-0@pre-vaapi-20260911 # VERIFY, don't trust rc
# 2. Intel client-GPU repo (inside LXC 105)
curl -fsS https://repositories.intel.com/gpu/intel-graphics.key \
| gpg --yes --dearmor -o /usr/share/keyrings/intel-graphics.gpg
echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] \
https://repositories.intel.com/gpu/ubuntu jammy client" \
> /etc/apt/sources.list.d/intel-gpu-jammy.list
apt-get update
# 3. Consistent set — the driver AND all four libva packages together
apt-get install -y intel-media-va-driver-non-free libva2 libva-drm2 libva-x11-2
# 4. Pinned + held, because `jammy client` is a ROLLING track
# /etc/apt/preferences.d/intel-gpu-pin + apt-mark hold
systemctl restart plexmediaserver
```
Landed: iHD **24.3.4** (`__vaDriverInit_1_22`), libva set **2.22.0.2-87**, libigdgmm12
22.5.2 — and the orphaned manual libva is now dpkg-owned.
## Verification — behaviour, not config
⚠ **A synthetic `Plex Transcoder` invocation is not a valid test.** Running it from a
shell produced three different failure modes (`unknown libva error`, then a libstdc++
`__wmemmove_chk` relocation error) that were **artifacts of not reproducing Plex's
bundled Conan runtime** — Plex ships its own libc among 61 bundled libraries. It failed
identically before and after a fix that worked. No positive control existed, so its
negatives were worthless.
Force a real transcode and read Plex's own log:
```bash
TOKEN=$(sed -n 's/.*PlexOnlineToken="\([^"]*\)".*/\1/p' \
"/var/lib/plexmediaserver/Library/Application Support/Plex Media Server/Preferences.xml")
KEY=<a ratingKey from /library/sections/<n>/all>
curl -s -o /dev/null "http://127.0.0.1:32400/video/:/transcode/universal/start.m3u8\
?path=%2Flibrary%2Fmetadata%2F$KEY&mediaIndex=0&partIndex=0&protocol=hls\
&directPlay=0&directStream=0&videoQuality=20&maxVideoBitrate=1500\
&X-Plex-Token=$TOKEN&X-Plex-Client-Identifier=vaapi-verify&session=vaapiverify1"
sleep 12
grep -i "hardware transcoding: testing API" "…/Logs/Plex Media Server.log" | tail -3
curl -s -o /dev/null "http://127.0.0.1:32400/video/:/transcode/universal/stop\
?session=vaapiverify1&X-Plex-Token=$TOKEN"
```
PASS looks like this — the device is **named**, and both encoder and decoder are tested:
Codecs: testing h264_vaapi (encoder)
Codecs: hardware transcoding: testing API vaapi for device '/dev/dri/renderD129' (Intel DG2 [Arc A580])
Codecs: testing h264 (decoder) with hwdevice vaapi
followed by `[FFMPEG] - Format 0x… -> bgra` surface enumeration, which only occurs
after a successful `vaInitialize`. FAIL is the empty `final decoder: , final encoder:`.
`vainfo --display drm --device /dev/dri/renderD129` is a useful *secondary* check (it
now reports iHD 24.3.4 with H.264/HEVC VLD **and** EncSliceLP) but it exercises the
system libva, not Plex's bundled one — so it can pass while Plex fails.
## Rollback
pct stop 105
zfs rollback nvme/subvol-105-disk-0@pre-vaapi-20260911
pct start 105
## Not done
- **Jellyfin (LXC 107)** on the same host has the same stale stack and the same Arc
available. Left alone 2026-09-11 — operator: not actively used. It ships its own
ffmpeg, so this fix may not transfer verbatim.
- LXC 105 has **152 packages pending upgrade** unrelated to this work.