#!/usr/bin/env bash
# Readiness check: is this machine ready to run rig? Reports and instructs; never fixes.
# Usage: check.sh [all | mem [status|push|all|backup|restore]]   (all = every detail)
# Notes: docs/notes/check.md
set -euo pipefail
cd "$(dirname "$0")"

# `check mem` goes deeper on memory than the summary below: how far allocation
# really climbs, and the WSL .wslconfig backup/restore.
if [ "${1:-}" = mem ]; then
    shift
    exec bash ./mem.sh "${@:-status}"
fi

# Compact by default: facts only with `all`; problems (!) always print.
VERBOSE=""
if [ "${1:-}" = all ]; then VERBOSE=1; fi
fact() { if [ -n "$VERBOSE" ]; then echo "$@"; fi; }

bash ./deps.sh detect ${VERBOSE:+all}

source ./lib/config.sh
load_config

# A /proc/meminfo field in MB, 0 if absent. MEMINFO/OVERCOMMIT_FILE override for testing.
mb_of() {
    awk -v k="$1:" '$1 == k { printf "%d", $2 / 1024; found = 1 }
                    END      { if (!found) printf "0" }' "${MEMINFO:-/proc/meminfo}"
}

# NODE_MB (cost of one node) comes from load_config in lib/config.sh; do not copy it here.

# Every running container's working set in MB, tagged with its kind cluster ('-' if none).
container_mb() {
    docker info >/dev/null 2>&1 || return 0
    awk -F'\t' '
        FILENAME == ARGV[1] { cl[$1] = ($2 == "" ? "-" : $2); if ($2 != "") isc[$2] = 1; next }
        {
            grp = ($1 in cl ? cl[$1] : "-")
            # A kind cluster'"'"'s local registry is a plain container with no kind
            # label, named <cluster>-registry, so on its own it would read as a
            # stranger. It belongs to its cluster — but only if that cluster exists:
            # a registry whose cluster is gone is a genuine stray, and says so.
            if (grp == "-" && $1 ~ /-registry$/) {
                base = $1; sub(/-registry$/, "", base)
                if (base in isc) grp = base
            }
            split($2, u, " "); v = u[1]; mb = 0
            if      (v ~ /GiB$/) { sub(/GiB$/, "", v); mb = v * 1024 }
            else if (v ~ /MiB$/) { sub(/MiB$/, "", v); mb = v }
            else if (v ~ /KiB$/) { sub(/KiB$/, "", v); mb = v / 1024 }
            else if (v ~ /B$/)   { sub(/B$/,   "", v); mb = v / 1048576 }
            printf "%d\t%s\t%s\n", mb, grp, $1
        }
    ' <(docker ps --format '{{.Names}}\t{{.Label "io.x-k8s.kind.cluster"}}' 2>/dev/null) \
      <(docker stats --no-stream --format '{{.Name}}\t{{.MemUsage}}' 2>/dev/null)
}

port_busy() {
    if command -v ss >/dev/null 2>&1; then
        ss -ltn "sport = :$1" 2>/dev/null | grep -q LISTEN && return 0 || return 1
    fi
    # iproute2 is absent from a minimal Debian, so fall back to procfs rather
    # than silently reporting everything as free.
    local hex; hex=$(printf ':%04X' "$1")
    grep -qi "^ *[0-9]*: [0-9A-F]*$hex " /proc/net/tcp /proc/net/tcp6 2>/dev/null
}

echo
echo "rig"
echo "  cluster     ${CLUSTER} (${KUBECONTEXT})  profile ${PROFILE_NAME}, ${NODES} node(s), registry ${REGISTRY_MODE}"
fact "  ingress     ${INGRESS_MODE}"
if [ ! -f ./.env ]; then
    fact "  .env        none — built-in defaults (cp ctrl/.env.example ctrl/.env to set values)"
fi

# ── memory: does this cluster fit right now? Warns; never blocks. ──────────
total_mb=$(mb_of MemTotal)
avail_mb=$(mb_of MemAvailable)
swap_used_mb=$(( $(mb_of SwapTotal) - $(mb_of SwapFree) ))
overcommit=$(cat "${OVERCOMMIT_FILE:-/proc/sys/vm/overcommit_memory}" 2>/dev/null || echo '?')
need_mb=$(( NODES * NODE_MB ))

rows=$(container_mb)
# If our cluster is already up, its memory is already out of MemAvailable: need nothing more.
ours_mb=$(awk -F'\t' -v c="$CLUSTER" '$2 == c { s += $1 } END { print s + 0 }' <<< "$rows")
still_mb=$(( ours_mb > 0 ? 0 : need_mb ))
headroom=$(( avail_mb - still_mb ))

# The biggest things holding memory, other than this cluster: kind clusters summed, the rest by name.
others=$(awk -F'\t' -v c="$CLUSTER" '
            $2 != c && $2 != "-" && $2 != "" { k["kind cluster \x27" $2 "\x27"] += $1 }
            $2 == "-"                         { k["container \x27" $3 "\x27"]    += $1 }
            END { for (n in k) printf "%d\t%s\n", k[n], n }' <<< "$rows" | sort -rn)

if [ "$still_mb" -eq 0 ] && [ "$headroom" -ge 512 ]; then
    printf "  memory      up, holding %d MB — %d MB headroom for what you deploy\n" "$ours_mb" "$headroom"
elif [ "$still_mb" -eq 0 ]; then
    printf "  ! memory    up, but only %d MB headroom for anything you deploy\n" "$headroom"
elif [ "$headroom" -ge 512 ]; then
    printf "  memory      fits — ~%d MB for %s node(s), %d MB headroom\n" "$need_mb" "$NODES" "$headroom"
elif [ "$headroom" -ge 0 ]; then
    printf "  ! memory    fits, but only %d MB headroom (~%d MB for %s node(s))\n" "$headroom" "$need_mb" "$NODES"
else
    printf "  ! memory    does not fit: ~%d MB needed, %d MB available\n" "$still_mb" "$avail_mb"
    # Two failures with opposite fixes, and telling them apart is the point.
    if [ "$still_mb" -le "$total_mb" ]; then
        echo "              something else holds it (below) — stopping that helps, a bigger VM would not."
        if grep -q 'kind cluster' <<< "$others"; then
            echo "              'make cluster free' stops the other kind clusters. It stops, never deletes."
        fi
    else
        echo "              the machine itself is too small: ${total_mb} MB total."
    fi
fi
if [ -n "$others" ] && { [ -n "$VERBOSE" ] || [ "$headroom" -lt 512 ]; }; then
    echo "              held elsewhere:"
    head -6 <<< "$others" | awk -F'\t' '{ printf "              %6d MB  %s\n", $1, $2 }'
    n_others=$(wc -l <<< "$others")
    if [ "$n_others" -gt 6 ]; then
        echo "              ... and $((n_others - 6)) more"
    fi
fi
if [ "$swap_used_mb" -gt 0 ]; then
    fact "              ${swap_used_mb} MB already in swap, which 'available' does not count: expect slow before failing"
fi
if [ "$overcommit" = "1" ]; then
    fact "              overcommit=1: allocations never fail, so read 'fits' as a ceiling (OOM killer settles up)"
fi

# ── ports: checked before creation; docker reports a clash only halfway through. ──
# Ports held by our own cluster are not clashes. Second grep, not `tr -d ':->'` (a tr range).
ours=$(docker ps --filter "label=io.x-k8s.kind.cluster=${CLUSTER}" \
        --format '{{.Ports}}' 2>/dev/null | tr ',' '\n' \
        | grep -oE ':[0-9]+->' | grep -oE '[0-9]+' || true)

clash=0 list="" mine=0
for entry in "HTTP:${HTTP_PORT}" "HTTPS:${HTTPS_PORT}" \
             "TILT:${TILT_PORT}" "REGISTRY:${REGISTRY_PORT}"; do
    name="${entry%%:*}"; p="${entry#*:}"
    [ -n "$p" ] || continue
    list+="$p "
    if ! port_busy "$p"; then
        fact "$(printf "    %-9s %-6s free" "$name" "$p")"
    elif echo "$ours" | grep -qx "$p"; then
        mine=1
        fact "$(printf "    %-9s %-6s in use by this environment's cluster" "$name" "$p")"
    else
        printf "  ! ports     %s %s IN USE by something else\n" "$name" "$p"
        clash=1
    fi
done
if [ "$clash" -eq 1 ]; then
    echo "              override it in ctrl/.env (e.g. HTTP_PORT=21080), or rename this directory"
elif [ "$mine" -eq 1 ]; then
    echo "  ports       ${list% }  held by this cluster"
else
    echo "  ports       ${list% }  free"
fi
fact "              derived from the directory name; pin them: bash ctrl/ports.sh persist"

# ── what `make cluster up` wires in beside the cluster ─────────────────────
REG_NAME="${CLUSTER}-registry"
if state=$(docker inspect -f '{{.State.Status}}' "$REG_NAME" 2>/dev/null); then
    echo "  registry    localhost:${REGISTRY_PORT}  ($state)"
else
    fact "  registry    no container yet — 'make cluster up' starts it"
fi
echo "  addons      ${ADDONS:-none}"
fact "              available: $(ls addons/*.sh 2>/dev/null | xargs -n1 basename | sed 's/\.sh$//' | tr '\n' ' ')"

# The CA reaches three places and only one of them is ours. Report the other two.
if [ -n "${REGISTRY_CA_FILE:-}" ]; then
    if [ ! -r "$REGISTRY_CA_FILE" ]; then
        echo "  ! CA        REGISTRY_CA_FILE not readable: $REGISTRY_CA_FILE"
    else
        fact "  CA          $REGISTRY_CA_FILE"
        host="${REGISTRY_REMOTE_URL#*://}"; host="${host%%/*}"
        if [ -n "$host" ] && [ ! -f "/etc/docker/certs.d/${host}/ca.crt" ]; then
            echo "  ! CA        the HOST docker daemon does not trust it yet:"
            echo "                sudo mkdir -p /etc/docker/certs.d/${host}"
            echo "                sudo cp ${REGISTRY_CA_FILE} /etc/docker/certs.d/${host}/ca.crt"
            echo "              (kind nodes are handled by registry.sh; in-cluster clients are the workload's job)"
        fi
    fi
fi