Track zram-generator config; correct STATUS.md/README.md staleness — zram was implemented after these docs were originally written

README.md

@@ -196,14 +196,15 @@ bigboy-alma-deploy/
 
 ### Next Steps (current priority)
 
-1. Commit tracked template files for the systemd unit, nginx config, and
-   firewall rules currently only configured live on BigBoy
+1. Confirm the tracked templates (`ansible/templates/llama-server.service.j2`,
+   `llama.conf.j2`, `zram-generator.conf`) and the firewall script
+   (`scripts/configure-llama-firewall.sh`) all match what's actually
+   configured live on BigBoy — they were written to match the live
+   system, not the other way around, so worth a direct diff
 2. Record the actual NVIDIA driver version in `group_vars/bigboy.yml`
    (placeholder currently reads `CHECK-WITH-nvidia-smi`)
-3. Implement zram alongside the existing swapfile (decision made
-   2026-07-19, not yet acted on)
-4. Decide Phase 8 (Open WebUI) — build or drop
-5. Complete the physical case move to Modcase HYPER, then proceed with
+3. Decide Phase 8 (Open WebUI) — build or drop
+4. Complete the physical case move to Modcase HYPER, then proceed with
    Phases 6–7, 9, 11–12, 14
 
 ---

ansible/templates/zram-generator.conf

@@ -0,0 +1,21 @@
+# zram-generator.conf — BigBoy's compressed-RAM swap tier
+#
+# Implemented 2026-07-19, alongside the existing NVMe swapfile — not a
+# replacement for it. zram is the fast, first-preference tier (default
+# priority 100, well above the swapfile's -2); the swapfile is the
+# larger, slower fallback that actually resolved the original OOM kill
+# during the llama.cpp CUDA build. Both are active simultaneously,
+# by decision — see CLAUDE.md / group_vars/bigboy.yml (zram_percentage).
+#
+# Deploy: copy to /etc/systemd/system/zram-generator.conf... actually to
+# /etc/systemd/zram-generator.conf, then:
+#   sudo systemctl daemon-reload
+#   sudo systemctl start systemd-zram-setup@zram0.service
+# (or just reboot — the generator runs automatically at boot from here on)
+#
+# Confirm with: swapon --show
+#   Expect two entries: zram0 (priority 100) and /swapfile (priority -2)
+
+[zram0]
+zram-size = ram / 2
+compression-algorithm = zstd

planning/STATUS.md

@@ -128,7 +128,10 @@ decided deliberately, see `CLAUDE.md` for the full rationale.
   against memory-hungry CUDA source files with zero swap configured.
   Fixed with a 16GB NVMe swapfile (persistent via fstab) plus dropping to
   `-j2`. zram was separately decided as a complementary fast-swap tier
-  (2026-07-19) — **not yet implemented**, tracked as open work.
+  (2026-07-19) and **implemented the same day** — both are now active
+  simultaneously (`zram0` at priority 100, `/swapfile` at priority -2,
+  confirmed via `swapon --show`). See
+  `ansible/templates/zram-generator.conf` for the tracked config.
 - Two rounds of missing baseline utilities discovered mid-deployment
   (`tar`, `which`, then nine more via a proactive `utility-recon.sh`
   scan) — all now added to the kickstart's `%packages` list for future
@@ -325,12 +328,13 @@ Parallel: Phase 13 (home LAN) — network migration done, physical case move in
 ## Blockers & Decisions Needed
 
 ### Immediate
-- **Real gap:** systemd unit, nginx config, and firewall rules for
-  `llama-server` exist only on BigBoy — need tracked template files in
-  the repo for actual reproducibility
+- **Real gap:** firewall rich-rules script now tracked
+  (`scripts/configure-llama-firewall.sh`); systemd/nginx/zram configs
+  now tracked (`ansible/templates/`) — confirm all four are actually
+  applied identically on BigBoy vs. what's committed, since the live
+  system was configured first and the templates written to match it
+  afterward
 - **Action:** record actual NVIDIA driver version in `group_vars/bigboy.yml`
-- **Action:** implement zram alongside the existing swapfile (decision
-  already made 2026-07-19, not yet acted on)
 
 ### Medium Term
 - **Decision:** Phase 8 (Open WebUI) — build or drop? (leaning drop)