---
type: configuration
title: Dankclaw Swap Configuration
description: The host swapfile on Dankclaw — 64 GiB at /swap.img on ext4, fstab-driven via the generated swap.img.swap unit. Covers why it was raised from 8 GiB, the safe resize ordering that avoids an OOM on a host whose MemAvailable is inflated by pinned model weights, and the swappiness caveat.
tags:
  - dankclaw
  - host
  - memory
  - swap
timestamp: 2026-09-12
---

# Dankclaw Swap Configuration

**Host:** Dankclaw (192.168.0.143) — **Filesystem:** ext4 on `/dev/nvme0n1p2`

| Item | Value |
| --- | --- |
| Swapfile | `/swap.img` |
| Size | **64 GiB** (raised from 8 GiB on 2026-09-12) |
| Filesystem | ext4 — swapfiles fully supported, no btrfs `nocow` handling needed |
| Allocation | `fallocate` (preallocated, hole-free; 530 extents) |
| Persistence | `/etc/fstab` line 12: `/swap.img none swap sw 0 0` |
| systemd unit | `swap.img.swap` — `loaded (/etc/fstab; generated)`, `active` |
| `vm.swappiness` | `60` (distro default, unchanged) |
| zswap | disabled (`/sys/module/zswap/parameters/enabled` = `N`) |
| Free on `/` after | 748 GiB of 1.9 TiB |

The unit is **generated from fstab**, not a hand-written unit file. fstab is the
only control point; `systemctl daemon-reload` re-reads it. Nothing in this
repository references the swapfile — it is host-level state, documented here so
it is not invisible.

## Why 64 GiB

Dankclaw is shared. `frank-dragoon` alone holds **103.5 GiB of the 121.2 GiB**
host (`68.0 weights + 14.4 KV pool + 21.1 working`), leaving roughly
**7.1 GiB** for 28 co-tenant containers whose working set is ~4.3 GiB. The
engine itself warns that when that runs out, frank-dragoon and its neighbours
"can stall for minutes at a time at full CPU with no disk activity and no
output". Swap is the valve that turns an OOM kill into slow paging.

Swap does **not** relieve the pinned-weights problem — see the caveat below.
It protects the *co-tenants* and buys headroom for burst allocation.

## The safe resize ordering

You cannot grow an active swapfile; it must be swapped off first. On a host
like this, **never `swapoff` before the replacement is online.** The old 8 GiB
held 4 GiB of live pages, and `MemAvailable` read 73 GiB while only ~5 GiB was
genuinely free — the pinned model weights are counted as reclaimable page
cache, so the headline number is a lie by roughly the size of the model
(see [[halogen-flash-server]]). Swapping off into that apparent space, with
nothing else to receive the pages, is how you invite the OOM killer.

The ordering that avoids it — create and enable the new swap **first**, so the
pages have somewhere to go:

```bash
# 1. Preallocate + format + enable the replacement, old swap still live
sudo fallocate -l 64G /swap2.img
sudo chmod 600 /swap2.img
sudo mkswap /swap2.img          # also rejects files with holes
sudo swapon /swap2.img          # total swap now 72 GiB

# 2. Only now drain the old one — pages migrate into /swap2.img, not into RAM
sudo swapoff /swap.img          # took 65 s for 4 GiB

# 3. Consolidate onto the conventional path so fstab needs no edit
sudo swapoff /swap2.img         # 725 MiB left, trivial
sudo mkdir -p ~/.AGENTTRASH/20260912-swapfile-8g
sudo mv /swap.img ~/.AGENTTRASH/20260912-swapfile-8g/swap.img
sudo mv /swap2.img /swap.img
sudo swapon /swap.img
```

Step 3 is chained tightly because it leaves the host with **zero swap** for a
few seconds. Do not leave that window open.

`mkswap` succeeding is itself a check: it refuses swapfiles containing holes,
so a `fallocate` that produced a sparse file fails here rather than at 3 a.m.
under memory pressure.

## Verification

```bash
swapon --show=NAME,TYPE,SIZE,USED,PRIO   # /swap.img file 64G
systemctl is-active swap.img.swap        # active
grep swap /etc/fstab                     # line 12 intact -> boot persistence
free -h | tail -2                        # Swap: 63Gi total
```

Then confirm the inference service is unaffected — a completion, not just
`/health`:

```bash
curl -s http://127.0.0.1:7770/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"frank-dragoon","messages":[{"role":"user","content":"Reply with exactly: SWAP64-OK"}],"max_tokens":48,"reasoning_effort":"low"}'
```

As run 2026-09-12: `finish_reason: stop`, `SWAP64-OK`, 28 containers up,
frank-dragoon `health=200` throughout.

## Caveats

- **Swap cannot help the pinned weights.** frank-dragoon's ~68 GiB of weights are
  held deliberately; paging them is a stall, not a relief. More swap does not
  make the doubled KV pool affordable — see the reserve/pool ceiling in
  [[halogen-flash-server]].
- **`vm.swappiness=60` is untested against this workload.** Under real
  pressure the kernel will happily page anonymous memory, and frank-dragoon's KV
  pool and working set *are* anonymous. Swapping the KV pool would be far worse
  than the OOM kill it prevents. If the box ever starts thrashing, lowering
  swappiness (or capping the engine's cgroup) is the knob, not more swap.
- **`free` still lies after the change.** `MemAvailable` reads ~70 GiB while
  the model is loaded. Trust the engine's `host memory left for everything
  else` line, not `free`.

- **Filesystem prerequisite (other hosts).** ext4 and xfs take swapfiles
  directly. btrfs needs `chattr +C` (NOCOW), no compression, and no
  snapshots in the swapfile path — check `df -T` before planning, or
  `mkswap` will reject the file.
- **Renaming an *active* swapfile works (inode-based) but leaves a stale
  path in `/proc/swaps`** — swap it off first, then rename, then `swapon`
  (which is exactly what the step-3 consolidation does). Migration is
  observable while it runs: in the 2026-09-12 run `swapoff` of 4 GiB took
  65 s and used-RAM rose only ~3 GiB (pages touched during migration), the
  rest relocating on disk. If used-RAM climbs toward the whole swapped
  amount, let it finish rather than aborting.

## Trash

The previous 8 GiB `/swap.img` (dated 2026-07-21) is staged, not deleted, at
`dankclaw:~/.AGENTTRASH/20260912-swapfile-8g/swap.img` (8.1 GiB). Purge
only on explicit approval.

## See Also

- [[halogen-flash-server]] — the memory model that motivated this
- [[Dankclaw System Specs]] — the Strix Halo box
- [[Dankclaw Improvements]] — other host-level changes