# Set a host-wide docker nofile floor on corviduo-dev. # # WHY: Worldtree #401 — a slow fd accrual in worldtree-personal hit the 1024 # soft nofile ceiling and converted into a hard deadlock. Raising the floor # turns any recurrence into observable degradation instead of a wedge. # Operator authorized the raise 2026-08-17 (relayed via worldtree-dev, # thread 01M08QQ655XD6VKEV7MA9GX0NS); sizing 65536 agreed with worldtree-dev. # # WHY THE DAEMON LAYER: /opt/worldtree-*/compose.yaml on this host is written # by the team's CI `deploy` identity, so a host-side compose edit reverts on # the next deploy. Daemon config is infra-ops-owned, survives every CI deploy, # and covers all containers on the box — not just worldtree. worldtree-dev # ALSO shipped an explicit compose-level pin (e41b139) as the belt to this # braces; the two are deliberately redundant. # # ACTIVATION — READ THIS BEFORE ASSUMING THE FLOOR IS LIVE. # `default-ulimits` is NOT in dockerd's SIGHUP-reloadable set. Measured on # Docker 29.4.3 (corviduo-dev, 2026-08-17): after `systemctl reload docker` the # daemon's own "Reloaded configuration" log line enumerates the live config and # `default-ulimits` is ABSENT from it, and a freshly created container still # reports `ulimit -n` = 1024. The reload step below is therefore harmless but # insufficient on its own. # # So this playbook STAGES the floor; it does not activate it. Activation needs a # full `systemctl restart docker`, which with live-restore unset BOUNCES EVERY # CONTAINER on the host (13 of them here, including all three worldtree # instances) — deliberately not taken here, because #401 is not urgent at fd # ~100 and worldtree-dev's explicit compose-level pin (e41b139) already covers # the worldtree services on their next recreate. Expect verify step 3 to FAIL # until a dockerd restart or a host reboot happens. # # If you want it live without a bounce, add `"live-restore": true` to # daemon.json FIRST (that one IS reloadable), then restart — containers survive # the daemon going away. That is a separate change with its own blast radius; # it was not in scope for #401. # # FOOT-GUN: an invalid daemon.json does not break a reload (dockerd logs and # keeps the old config) but WILL break the next dockerd *start*. The playbook # validates the JSON before reloading and refuses to proceed otherwise. vars: nofile: "65536" daemon_json: /etc/docker/daemon.json steps: - name: Back up an existing daemon.json (no-op when absent) sudo: true shell: | if [ -f {{ daemon_json }} ] && [ ! -f {{ daemon_json }}.bak-401-ulimits ]; then cp -a {{ daemon_json }} {{ daemon_json }}.bak-401-ulimits echo backed-up else echo no-backup-needed fi changed_when: "false" - name: Write daemon.json with the nofile floor sudo: true shell: | set -e tmp=$(mktemp) if [ -f {{ daemon_json }} ]; then python3 - "$tmp" <<'PY' import json, sys p = "/etc/docker/daemon.json" cfg = json.load(open(p)) cfg.setdefault("default-ulimits", {})["nofile"] = { "Name": "nofile", "Soft": 65536, "Hard": 65536} json.dump(cfg, open(sys.argv[1], "w"), indent=2) PY else cat > "$tmp" <<'JSON' { "default-ulimits": { "nofile": { "Name": "nofile", "Soft": 65536, "Hard": 65536 } } } JSON fi python3 -m json.tool "$tmp" > /dev/null install -m 0644 -o root -g root "$tmp" {{ daemon_json }} rm -f "$tmp" # Skip entirely when the floor is already recorded at the right size. when: "! sudo python3 -c \"import json;c=json.load(open('{{ daemon_json }}'));u=c.get('default-ulimits',{}).get('nofile',{});raise SystemExit(0 if u.get('Soft')=={{ nofile }} and u.get('Hard')=={{ nofile }} else 1)\" 2>/dev/null" - name: Reload dockerd (SIGHUP — does NOT restart containers) sudo: true shell: systemctl reload docker when: "! sudo docker run --rm --entrypoint sh busybox -c 'ulimit -n' 2>/dev/null | grep -qx '{{ nofile }}'" verify: - name: daemon.json is valid JSON sudo: true shell: python3 -m json.tool {{ daemon_json }} > /dev/null changed_when: "false" - name: daemon.json records the nofile floor at the agreed size sudo: true shell: | python3 -c "import json;u=json.load(open('{{ daemon_json }}'))['default-ulimits']['nofile'];assert u['Soft']=={{ nofile }} and u['Hard']=={{ nofile }}, u" changed_when: "false" - name: A NEWLY created container actually gets the floor (the real proof) sudo: true shell: | out=$(docker run --rm --entrypoint sh busybox -c 'ulimit -n') [ "$out" = "{{ nofile }}" ] || { echo "got $out want {{ nofile }}"; exit 1; } changed_when: "false" - name: dockerd is still running and containers were not bounced sudo: true shell: systemctl is-active --quiet docker && test "$(docker ps -q | wc -l)" -ge 13 changed_when: "false"