fix(ha/deploy): remove _patch_targetctl — iscsi-target.nix now correct
Check NixOS configurations / eval-hosts (push) Successful in 10m23s

The _patch_targetctl runtime dropin was a workaround for the wrong targetctl
binary path in the original iscsi-target.nix (used pkgs.targetcli-fb, but
targetctl is in rtslib-fb's python3 env).  The module is now fixed to use
\${python3}/bin/targetctl, so new VM images have the correct ExecStart/ExecStop
baked in and the patch finds nothing — failing with exit 1 and killing the deploy.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HaH1cSGvhogRP5ExoF6nD8
This commit is contained in:
2026-07-28 19:41:20 +10:00
co-authored by Claude Sonnet 4.6
parent 7417cc1b0a
commit 1ce4589830
-52
View File
@@ -355,58 +355,6 @@ if ! $SKIP_CLUSTER_INIT; then
"sudo mkdir -p /root/.ssh && sudo cp /tmp/cluster-init-key /root/.ssh/cluster-init-key && \ "sudo mkdir -p /root/.ssh && sudo cp /tmp/cluster-init-key /root/.ssh/cluster-init-key && \
sudo chmod 600 /root/.ssh/cluster-init-key && rm -f /tmp/cluster-init-key" sudo chmod 600 /root/.ssh/cluster-init-key && rm -f /tmp/cluster-init-key"
# Fix targetctl.service on both nodes: the iscsi-target.nix module bakes
# pkgs.targetcli-fb for the targetctl binary, but targetctl is actually in
# rtslib-fb (a different store path). Apply a runtime dropin that corrects
# both ExecStart and ExecStop before Pacemaker ever touches the service.
# The fixed iscsi-target.nix module will make this redundant on next rebuild.
logn "Patching targetctl.service on both nodes..."
_patch_targetctl() {
local ip="$1"
ssh -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no "${HA_USER}@${ip}" sudo bash << 'PATCH'
set -euo pipefail
TC=$(find /nix/store -maxdepth 4 -path '*/python3*env/bin/targetctl' 2>/dev/null | head -1)
PY=$(find /nix/store -maxdepth 4 -path '*/python3*env/bin/python3' -name 'python3' 2>/dev/null | \
while IFS= read -r p; do "$p" -c "import rtslib_fb" 2>/dev/null && echo "$p" && break; done | head -1)
[[ -n "$TC" && -n "$PY" ]] || { echo "targetctl or python3+rtslib_fb not found"; exit 1; }
# Write stop script that saves LIO config then tears down kernel state
"$PY" - "$TC" "$PY" << 'PYEOF'
import sys, os, stat
tc, py = sys.argv[1], sys.argv[2]
script = f"""#!{py}
import subprocess, sys, rtslib_fb
root = rtslib_fb.RTSRoot()
targets = list(root.targets)
if targets:
r = subprocess.run(["{tc}", "save", "/etc/target/saveconfig.json"], capture_output=True)
print(f"saved {{len(targets)}} target(s); rc={{r.returncode}}")
else:
print("no active LIO targets")
for t in targets:
try:
for tpg in list(t.tpgs): tpg.enable = False
t.delete()
except Exception as e: print(f"warn: {{e}}", file=sys.stderr)
for so in list(root.storage_objects):
try: so.delete()
except Exception as e: print(f"warn: {{e}}", file=sys.stderr)
print("LIO kernel target cleared")
"""
path = "/run/ha-targetctl-stop.py"
with open(path, "w") as f: f.write(script)
os.chmod(path, 0o755)
print(f"wrote {path}")
PYEOF
mkdir -p /run/systemd/system/targetctl.service.d
printf '[Service]\nExecStart=\nExecStart=%s restore /etc/target/saveconfig.json\nExecStop=\nExecStop=/run/ha-targetctl-stop.py\n' \
"$TC" > /run/systemd/system/targetctl.service.d/fix-exec.conf
systemctl daemon-reload
echo "patched on $(hostname)"
PATCH
}
_patch_targetctl "${NODE1_IP}"
_patch_targetctl "${NODE2_IP}"
logn "Uploading cluster-init.sh to ${NODE1_HOST}..." logn "Uploading cluster-init.sh to ${NODE1_HOST}..."
scp -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \ scp -i ~/.ssh/id_ed25519 -o StrictHostKeyChecking=no \
"$CLUSTER_INIT" "${HA_USER}@${NODE1_IP}:/tmp/cluster-init.sh" "$CLUSTER_INIT" "${HA_USER}@${NODE1_IP}:/tmp/cluster-init.sh"