dtoro
b87735a111
Graph view: raise the node cap 500 -> 2000 and exclude execution/task audit rows from the default whole-graph view so the cap is spent on actual topology rather than ~380 cognition records that crowded out every host/lxc/service. dns-zone monitoring [dns] -> none: no dns checker exists, so the declaration only produced unresolvable `unmonitored` noise (requires ontology re-ingest; coverageSweep now auto-clears the stale signals). Flip back to [dns] when a checker lands. Operator tooling: tools/deploy-checks.sh pushes check scripts into guests via pct push (a pct-exec-routed check runs the script INSIDE the guest), wired into the post-pull setup-checks hook so guests stay in sync on Proxmox hosts; scripts/cleanup-orphan-checks.sh (dry-run by default) and report-stray-test-lxcs.sh retire legacy cruft. VERSION 0.13.0 -> 0.14.0. Plan: plans/2026-07-29-health-check-reality-and-knowledge-graph.md.
95 lines
3.7 KiB
Bash
Executable File
95 lines
3.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# deploy-checks.sh — push the check scripts into every monitored target.
|
|
#
|
|
# Background: an ssh-script check runs the script INSIDE the target, so the
|
|
# script must exist at /opt/oikos/checks/ on the target itself — not just on
|
|
# the proxmox host. The scheduler routes LXC/VM checks through the host via
|
|
# `pct exec`/`qm guest exec`, so it never SSHes a guest directly, but the
|
|
# script still has to be present inside the guest. This script deploys them.
|
|
#
|
|
# Run from a Proxmox host (it uses `pct`/`qm`) to populate every local guest,
|
|
# and/or pass --host to install on a host/workstation over SSH.
|
|
#
|
|
# Usage:
|
|
# deploy-checks.sh # on a proxmox host: push to every LXC/VM here
|
|
# deploy-checks.sh --host ws:mac-mini # ssh-install scripts on a host/workstation
|
|
# deploy-checks.sh --checks /path # override the source checks dir
|
|
#
|
|
# Idempotent: skips a script whose deployed copy is byte-identical.
|
|
set -euo pipefail
|
|
|
|
CHECKS_DIR="${OIKOS_CHECK_DIR:-${HOMELAB_CONTEXT_DIR:-/opt/homelab}/checks}"
|
|
DEST=/opt/oikos/checks
|
|
|
|
die() { echo "deploy-checks: $*" >&2; exit 1; }
|
|
|
|
deploy_to_guest() {
|
|
local id="$1" vm="$2" # vm=0 for LXC, 1 for VM
|
|
local kind=pct; [ "$vm" = "1" ] && kind=qm
|
|
echo "[deploy-checks] $kind $id"
|
|
# Ensure the destination dir exists inside the guest.
|
|
if [ "$kind" = "pct" ]; then
|
|
pct exec "$id" -- mkdir -p "$DEST" 2>/dev/null || { echo " skip (pct exec failed)"; return; }
|
|
else
|
|
# qm guest exec returns JSON; best-effort for VMs (guest agent required).
|
|
qm guest exec "$id" -- mkdir -p "$DEST" >/dev/null 2>&1 || { echo " skip (qm guest exec failed)"; return; }
|
|
fi
|
|
local pushed=0 skipped=0
|
|
for script in "$CHECKS_DIR"/*.sh; do
|
|
local name; name=$(basename "$script")
|
|
[ "$name" = "deploy-checks.sh" ] && continue
|
|
[ "$name" = "install.sh" ] && continue
|
|
if [ "$kind" = "pct" ]; then
|
|
pct push "$id" "$script" "$DEST/$name" --perms 755 2>/dev/null && pushed=$((pushed+1)) || skipped=$((skipped+1))
|
|
else
|
|
# qm has no push; copy via the guest agent file write if available.
|
|
qm guest exec "$id" -- /bin/sh -c "cat > $DEST/$name" < "$script" >/dev/null 2>&1 && pushed=$((pushed+1)) || skipped=$((skipped+1))
|
|
fi
|
|
done
|
|
echo " pushed=$pushed skipped=$skipped"
|
|
}
|
|
|
|
deploy_to_host() {
|
|
local target="$1" # user@ip or slug resolved by caller
|
|
echo "[deploy-checks] host $target"
|
|
ssh -o BatchMode=yes -o StrictHostKeyChecking=no "$target" "bash -s" < "$CHECKS_DIR/install.sh" \
|
|
|| echo " WARNING: install on $target failed"
|
|
}
|
|
|
|
if [ ! -d "$CHECKS_DIR" ]; then die "checks dir not found: $CHECKS_DIR"; fi
|
|
|
|
# Host/workstation install mode.
|
|
if [ "${1:-}" = "--host" ]; then
|
|
[ $# -ge 2 ] || die "--host needs a target (user@ip)"
|
|
deploy_to_host "$2"
|
|
exit 0
|
|
fi
|
|
|
|
# Proxmox-host mode: push to every local LXC and VM.
|
|
if command -v pct >/dev/null 2>&1; then
|
|
# LXC containers: ID and status. Skip stopped ones.
|
|
while IFS= read -r line; do
|
|
[ -z "$line" ] && continue
|
|
id=$(awk '{print $1}' <<<"$line")
|
|
status=$(awk '{print $2}' <<<"$line")
|
|
[ "$status" = "running" ] || { echo "[deploy-checks] skip LXC $id ($status)"; continue; }
|
|
deploy_to_guest "$id" 0
|
|
done < <(pct list 2>/dev/null | tail -n +2)
|
|
else
|
|
echo "deploy-checks: 'pct' not found — not a Proxmox host."
|
|
echo " On a host/workstation, use: deploy-checks.sh --host user@ip"
|
|
exit 0
|
|
fi
|
|
|
|
if command -v qm >/dev/null 2>&1; then
|
|
while IFS= read -r line; do
|
|
[ -z "$line" ] && continue
|
|
id=$(awk '{print $1}' <<<"$line")
|
|
status=$(awk '{print $2}' <<<"$line")
|
|
[ "$status" = "running" ] || continue
|
|
deploy_to_guest "$id" 1
|
|
done < <(qm list 2>/dev/null | tail -n +2)
|
|
fi
|
|
|
|
echo "[deploy-checks] done"
|