#!/usr/bin/env bash
# spdk-release.sh — add/remove a rootfs RELEASE on the long-lived nvmf_tgt
# ONLINE, via JSON-RPC, WITHOUT restarting the target. The target process holds
# every running host's NVMe/TCP root connection, so restarting it tears down the
# whole fleet's root at once (see docs/TODO.md #6). Routine rollouts therefore
# never restart SPDK: this script adds the new version's bdevs + subsystem +
# namespaces live (existing connections untouched) and removes an old version
# live once it has drained.
#
# ONE SUBSYSTEM PER VERSION (distinct NQN): adding a release as a NEW subsystem
# never disturbs the subsystem running hosts are attached to (adding a namespace
# to a SHARED subsystem would fire an AER + rescan at every host). It also gives
# clean per-release drain + per-release hostNQN allow-listing.
#
# Each release lives under $RELEASES_DIR/<version>/ as rootfs.erofs + rootfs.hash
# + verity.json. verity.json is the single source of truth for that version's
# namespace UUIDs + subsystem NQN (written by scripts/extract-artifacts.sh) — so
# the host's by-id verity refs and the target's namespace UUIDs always agree.
#
# Usage:
#   spdk-release add   <version>            # idempotent; live, no restart
#   spdk-release remove <version> [--force] # DRAIN-GATED unless --force
#   spdk-release list                       # served versions + connected hosts
#   spdk-release drain-status <version>     # connected controller count
#   spdk-release reconcile                  # add every release under $RELEASES_DIR
set -euo pipefail

RELEASES_DIR="${RELEASES_DIR:-/releases}"
TADDR="${TARGET_ADDR:-0.0.0.0}"
TPORT="${TARGET_PORT:-4420}"
SUBNQN_BASE="${SUBNQN_BASE:-nqn.2026-06.org.example.fleet:rootfs}"
DISCOVERY_NQN="nqn.2014-08.org.nvmexpress.discovery"
RPC=$(command -v rpc.py || echo /usr/libexec/spdk/scripts/rpc.py)

die()  { echo "ERROR: $*" >&2; exit 1; }
rpc()  { "$RPC" "$@"; }
# bdev names must be filesystem/identifier-safe; sanitise the version.
san()  { printf '%s' "$1" | tr -c 'A-Za-z0-9' '_'; }

# Read a field from a release's verity.json (empty if missing).
vfield() {
    local v=$1 path=$2
    jq -r "$path // empty" "$RELEASES_DIR/$v/verity.json" 2>/dev/null || true
}

# Per-version subsystem NQN: prefer the one baked into verity.json; otherwise
# derive it the same way extract-artifacts.sh does (base-<version>).
release_nqn() {
    local v=$1 nqn
    nqn=$(vfield "$v" .subnqn)
    [ -n "$nqn" ] || nqn="${SUBNQN_BASE}-${v}"
    printf '%s' "$nqn"
}

subsys_exists() {
    rpc nvmf_get_subsystems 2>/dev/null \
        | jq -e --arg n "$1" 'any(.[]; .nqn==$n)' >/dev/null 2>&1
}

# Connected controllers on a subsystem (the drain gate). 0 if absent/none.
ctrl_count() {
    local n
    n=$(rpc nvmf_subsystem_get_controllers "$1" 2>/dev/null | jq 'length' 2>/dev/null || echo 0)
    printf '%s' "${n:-0}"
}

cmd_add() {
    local v=${1:?usage: add <version>}
    local dir="$RELEASES_DIR/$v"
    [ -s "$dir/rootfs.erofs" ] || die "$dir/rootfs.erofs missing/empty"
    [ -s "$dir/rootfs.hash" ]  || die "$dir/rootfs.hash missing/empty"

    local nqn du hu s
    nqn=$(release_nqn "$v")
    du=$(vfield "$v" .data_ns_uuid)
    hu=$(vfield "$v" .hash_ns_uuid)
    [ -n "$du" ] && [ -n "$hu" ] \
        || die "$dir/verity.json lacks data_ns_uuid/hash_ns_uuid (rebuild with the per-version UUID extract-artifacts.sh)"

    if subsys_exists "$nqn"; then
        echo "release $v already served ($nqn) — nothing to do"
        return 0
    fi

    s=$(san "$v")
    echo "==> adding release $v as subsystem $nqn (data uuid $du, hash uuid $hu)"
    # -r opens the backing file read-only where the SPDK build supports it.
    rpc bdev_aio_create "$dir/rootfs.erofs" "rootfs_$s" 4096 -r \
        || rpc bdev_aio_create "$dir/rootfs.erofs" "rootfs_$s" 4096
    rpc bdev_aio_create "$dir/rootfs.hash" "roothash_$s" 4096 -r \
        || rpc bdev_aio_create "$dir/rootfs.hash" "roothash_$s" 4096
    # Serial must be <=20 chars; derive a stable, version-tagged one.
    rpc nvmf_create_subsystem "$nqn" -a -s "SPDK$(printf '%s' "$s" | cut -c1-16)" -d "FleetRootfs"
    rpc nvmf_subsystem_add_ns "$nqn" "rootfs_$s"   -u "$du"
    rpc nvmf_subsystem_add_ns "$nqn" "roothash_$s" -u "$hu"
    rpc nvmf_subsystem_add_listener "$nqn" -t tcp -a "$TADDR" -s "$TPORT"
    # Register the listener on the discovery subsystem too (best-effort; older
    # SPDK answers discovery implicitly but logs a deprecation warning).
    rpc nvmf_subsystem_add_listener "$DISCOVERY_NQN" -t tcp -a "$TADDR" -s "$TPORT" 2>/dev/null || true
    echo "==> release $v ONLINE (existing connections untouched)"
}

cmd_remove() {
    local force=0 v=""
    local a
    for a in "$@"; do
        case "$a" in
            --force) force=1 ;;
            *)       v="$a" ;;
        esac
    done
    [ -n "$v" ] || die "usage: remove <version> [--force]"

    local nqn n
    nqn=$(release_nqn "$v")
    if ! subsys_exists "$nqn"; then
        echo "release $v not served ($nqn) — nothing to remove"
        return 0
    fi
    n=$(ctrl_count "$nqn")
    if [ "$n" -gt 0 ] && [ "$force" -ne 1 ]; then
        die "release $v still has $n connected controller(s) — refusing to remove. Drain first (reboot/migrate those hosts), or pass --force to EVICT them (they lose root I/O)."
    fi
    [ "$n" -gt 0 ] && echo "WARNING: --force removing $v with $n connected controller(s) — those hosts lose root I/O"

    local s
    s=$(san "$v")
    echo "==> removing release $v ($nqn)"
    rpc nvmf_delete_subsystem "$nqn" || true
    rpc bdev_aio_delete "rootfs_$s"   2>/dev/null || true
    rpc bdev_aio_delete "roothash_$s" 2>/dev/null || true
    echo "==> release $v removed (other versions + their connections untouched)"
}

cmd_list() {
    local nqn n ver
    printf '%-26s %-7s %s\n' VERSION CONNS NQN
    rpc nvmf_get_subsystems 2>/dev/null \
        | jq -r '.[] | select(.nqn | test("discovery") | not) | .nqn' \
        | while read -r nqn; do
              n=$(ctrl_count "$nqn")
              ver="${nqn##*:}"           # strip the nqn.*: prefix for readability
              printf '%-26s %-7s %s\n' "$ver" "$n" "$nqn"
          done
}

cmd_drain_status() {
    local v=${1:?usage: drain-status <version>}
    local nqn
    nqn=$(release_nqn "$v")
    echo "$(ctrl_count "$nqn") connected controller(s) on $nqn"
}

cmd_reconcile() {
    [ -d "$RELEASES_DIR" ] || { echo "no $RELEASES_DIR — nothing to reconcile"; return 0; }
    local d any=0
    for d in "$RELEASES_DIR"/*/; do
        [ -e "${d}verity.json" ] || continue
        any=1
        cmd_add "$(basename "$d")" || echo "WARNING: failed to add release $(basename "$d")" >&2
    done
    [ "$any" -eq 1 ] || echo "no releases found under $RELEASES_DIR"
}

case "${1:-}" in
    add)                   shift; cmd_add "$@" ;;
    remove|rm)             shift; cmd_remove "$@" ;;
    list|ls)               shift; cmd_list "$@" ;;
    drain-status|status)   shift; cmd_drain_status "$@" ;;
    reconcile)             shift; cmd_reconcile "$@" ;;
    *) echo "usage: spdk-release {add <ver>|remove <ver> [--force]|list|drain-status <ver>|reconcile}" >&2; exit 2 ;;
esac