didericis
2f8a7be1b1
netavark shells out to `nft` for the bridge network every compose file expects, and aardvark-dns serves name resolution inside nested containers. Neither arrives with the base image's `--no-install-recommends` podman, and each fails at a different and misleading layer: without nft containers are created but never start; without aardvark-dns DNS inside a container fails while the engine, the pulls, and the bridge all look healthy. That last one is the likeliest explanation for the "DNS inside nested containers fails entirely" note in #392 — a missing package, not a design gap. Verified on the macOS host: with passt alone, `docker run` reached netavark and died on "unable to execute nft". Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
97 lines
3.2 KiB
Bash
Executable File
97 lines
3.2 KiB
Bash
Executable File
#!/bin/sh
|
|
set -eu
|
|
|
|
uid="$(id -u)"
|
|
if [ "$uid" -eq 0 ]; then
|
|
echo "refusing to run the guest container engine as root" >&2
|
|
exit 1
|
|
fi
|
|
|
|
# Every piece of podman 5's networking stack is checked here, because each
|
|
# one fails at a different and misleading layer if it is absent: no pasta and
|
|
# nothing starts at all; no nft and netavark cannot build the bridge every
|
|
# compose file expects; no aardvark-dns and DNS inside nested containers fails
|
|
# while everything else looks healthy.
|
|
for command in podman docker fuse-overlayfs pasta nft slirp4netns; do
|
|
command -v "$command" >/dev/null 2>&1 || {
|
|
echo "missing nested-container prerequisite: $command" >&2
|
|
exit 1
|
|
}
|
|
done
|
|
|
|
# The inverse of the rootless-Docker check, and the whole point of the podman
|
|
# variant: a subordinate range would push podman onto newuidmap, which cannot
|
|
# write a multi-range uid_map without CAP_SYS_ADMIN in this guest. An empty
|
|
# range keeps it on the single-UID self-mapping an unprivileged process may
|
|
# write itself.
|
|
if grep -q "^$(id -un):" /etc/subuid 2>/dev/null; then
|
|
echo "unexpected subordinate UID range for $(id -un): podman would" >&2
|
|
echo "require CAP_SYS_ADMIN via newuidmap in this guest" >&2
|
|
exit 1
|
|
fi
|
|
|
|
for device in /dev/fuse /dev/net/tun; do
|
|
[ -r "$device" ] && [ -w "$device" ] || {
|
|
echo "device $device is not readable/writable by $(id -un)" >&2
|
|
exit 1
|
|
}
|
|
done
|
|
|
|
# Short by necessity, not by accident: conmon's attach socket lives under
|
|
# this directory and must fit in a 108-byte sun_path. See nested_containers.py.
|
|
export XDG_RUNTIME_DIR="${XDG_RUNTIME_DIR:-/tmp/bbp}"
|
|
config="$HOME/.config/containers"
|
|
mkdir -p "$XDG_RUNTIME_DIR" "$config"
|
|
chmod 700 "$XDG_RUNTIME_DIR"
|
|
|
|
# ignore_chown_errors is required, not incidental: with a single-UID mapping
|
|
# there is no second UID for image layers to be chowned to, so layers that
|
|
# record other owners would otherwise fail to extract.
|
|
cat > "$config/storage.conf" <<'CONF'
|
|
[storage]
|
|
driver="overlay"
|
|
[storage.options.overlay]
|
|
mount_program="/usr/bin/fuse-overlayfs"
|
|
ignore_chown_errors="true"
|
|
CONF
|
|
|
|
# No cgroup delegation reaches this guest, so asking podman to manage cgroups
|
|
# fails; events_logger=file avoids the journald socket that is equally absent.
|
|
cat > "$config/containers.conf" <<'CONF'
|
|
[containers]
|
|
cgroups="disabled"
|
|
[engine]
|
|
cgroup_manager="cgroupfs"
|
|
events_logger="file"
|
|
CONF
|
|
|
|
# Registry pulls egress through the bottle's proxy like everything else. The
|
|
# token-bearing proxy URL is already in the agent's environment; persisting it
|
|
# inside this disposable VM does not broaden its authority.
|
|
python3 - <<'PY'
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
|
|
proxy = os.environ.get("HTTPS_PROXY") or os.environ.get("https_proxy", "")
|
|
no_proxy = os.environ.get("NO_PROXY") or os.environ.get("no_proxy", "")
|
|
config = {"proxies": {"default": {
|
|
"httpProxy": proxy,
|
|
"httpsProxy": proxy,
|
|
"noProxy": no_proxy,
|
|
}}}
|
|
path = Path.home() / ".docker" / "config.json"
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
path.write_text(json.dumps(config), encoding="utf-8")
|
|
path.chmod(0o600)
|
|
PY
|
|
|
|
if docker info >/dev/null 2>&1; then
|
|
exit 0
|
|
fi
|
|
|
|
log=/tmp/bot-bottle-nested-containers.log
|
|
nohup podman system service --time=0 \
|
|
"unix://$XDG_RUNTIME_DIR/podman.sock" \
|
|
>"$log" 2>&1 </dev/null &
|