// Copyright (c) 2026, Pim van Pelt <pim@ipng.ch>

package vpp

import (
	"context"
	"fmt"
	"log/slog"
	"time"

	"go.fd.io/govpp/adapter"

	"git.ipng.ch/ipng/vpp-maglev/internal/metrics"
)

// lbStatsInterval is how often lbStatsLoop scrapes per-VIP and per-backend
// counters from the VPP stats segment. Hard-coded for now; the scrape
// feeds both slog.Debug lines and the Prometheus collector.
const lbStatsInterval = 5 * time.Second

// LB VIP counter names as they appear in the VPP stats segment. These
// come from lb_foreach_vip_counter in src/plugins/lb/lb.h — the plugin
// passes them through vlib_simple_counter_main_t with only .name set
// (.stat_segment_name unset), so vlib_validate_simple_counter /
// vlib_stats_add_counter_vector register them under the name verbatim
// with no leading slash. Contrast with /net/route/to below, which IS
// registered with stat_segment_name="/net/route/to" in
// src/vnet/dpo/load_balance.c. Replace if the VPP plugin renames them
// or starts setting stat_segment_name.
const (
	lbStatNextPacket   = "packet from existing sessions"
	lbStatFirstPacket  = "first session packet"
	lbStatUntrackedPkt = "untracked packet"
	lbStatNoServer     = "no server configured"
)

// lbStatPatterns is the full list of anchored regexes passed to DumpStats
// for one scrape cycle: the four LB-plugin SimpleCounters plus the FIB
// CombinedCounter for per-VIP packet+byte totals. Doing it in a single
// DumpStats avoids walking the stats segment twice.
var lbStatPatterns = []string{
	`^packet from existing sessions$`,
	`^first session packet$`,
	`^untracked packet$`,
	`^no server configured$`,
	`^/net/route/to$`,
}

// lbStatsLoop periodically scrapes the LB plugin's per-VIP counters and
// the FIB's /net/route/to combined counter for both VIPs and backends,
// publishes the results to the atomic snapshots read by Prometheus, and
// emits one slog.Debug line per VIP and per backend. Exits when ctx is
// cancelled.
func (c *Client) lbStatsLoop(ctx context.Context) {
	ticker := time.NewTicker(lbStatsInterval)
	defer ticker.Stop()
	for {
		select {
		case <-ctx.Done():
			return
		case <-ticker.C:
		}
		if err := c.scrapeLBStats(); err != nil {
			slog.Debug("vpp-lb-stats-error", "err", err)
		}
	}
}

// scrapeLBStats runs one full scrape cycle: discover VIPs via cli_inband,
// look up the FIB stats_index for every VIP via ip_route_lookup, dump
// all five stats-segment paths in one DumpStats call, and reduce the
// counters into the per-VIP snapshot.
//
// NOTE: there is no per-backend counter here. The LB plugin's forwarding
// node (src/plugins/lb/node.c) sets adj_index[VLIB_TX] to the AS's DPO
// directly and enqueues into the lb*-gre* encap node, bypassing
// ip6_lookup_inline / ip4_lookup_inline entirely. Since
// lbm_to_counters is only incremented in those lookup paths (see
// ip6_forward.h / ip4_forward.h), the backend's FIB-entry
// load_balance stats_index never ticks for LB-forwarded traffic —
// /net/route/to at that index would always report zero. Per-backend
// packet/byte counters would need a new counter inside the LB plugin
// itself (e.g. a vlib_combined_counter_main_t keyed by AS index
// incremented in lb4-gre4 / lb6-gre6 / etc.). Until that lands
// upstream we simply don't expose per-backend rates; the VIP-level
// counters tell the dataplane story on the granularity VPP actually
// provides today.
func (c *Client) scrapeLBStats() error {
	if !c.IsConnected() {
		return nil
	}
	ch, err := c.apiChannel()
	if err != nil {
		return err
	}
	defer ch.Close()

	snap, err := queryLBVIPSnapshot(ch)
	if err != nil {
		return fmt.Errorf("query vip snapshot: %w", err)
	}

	// Resolve FIB stats_indices for every VIP. The LB plugin installs a
	// host-prefix FIB entry per VIP (lb.c:990), so the exact=0 lookup
	// lands on it in the common case. See fibStatsIndex for the exact=0
	// caveat when a covering route shadows the host prefix.
	vipStatsIdx := make(map[vipKey]uint32, len(snap))
	for k := range snap {
		addr, _, err := vipKeyToIP(k)
		if err != nil {
			continue
		}
		idx, err := fibStatsIndex(ch, addr)
		if err != nil {
			slog.Debug("vpp-vip-route-lookup-failed",
				"prefix", k.prefix, "err", err)
			continue
		}
		vipStatsIdx[k] = idx
	}

	c.mu.Lock()
	sc := c.statsClient
	c.mu.Unlock()
	if sc == nil {
		return nil
	}
	entries, err := sc.DumpStats(lbStatPatterns...)
	if err != nil {
		return fmt.Errorf("dump stats: %w", err)
	}

	nextPkt := findSimpleCounter(entries, lbStatNextPacket)
	firstPkt := findSimpleCounter(entries, lbStatFirstPacket)
	untracked := findSimpleCounter(entries, lbStatUntrackedPkt)
	noServer := findSimpleCounter(entries, lbStatNoServer)
	routeTo := findCombinedCounter(entries, routeToStatPath)

	// ---- VIP snapshot ----
	vipOut := make([]metrics.VIPStatEntry, 0, len(snap))
	for key, info := range snap {
		lbIdx := int(info.index)
		entry := metrics.VIPStatEntry{
			Prefix:    key.prefix,
			Protocol:  protocolName(key.protocol),
			Port:      key.port,
			NextPkt:   reduceSimpleCounter(nextPkt, lbIdx),
			FirstPkt:  reduceSimpleCounter(firstPkt, lbIdx),
			Untracked: reduceSimpleCounter(untracked, lbIdx),
			NoServer:  reduceSimpleCounter(noServer, lbIdx),
		}
		if fibIdx, ok := vipStatsIdx[key]; ok {
			entry.Packets, entry.Bytes = reduceCombinedCounter(routeTo, int(fibIdx))
		}
		vipOut = append(vipOut, entry)
		slog.Debug("vpp-vip-stats",
			"prefix", entry.Prefix,
			"protocol", entry.Protocol,
			"port", entry.Port,
			"next-packet", entry.NextPkt,
			"first-packet", entry.FirstPkt,
			"untracked", entry.Untracked,
			"no-server", entry.NoServer,
			"packets", entry.Packets,
			"bytes", entry.Bytes,
		)
	}
	c.lbStatsSnap.Store(&vipOut)
	return nil
}

// findSimpleCounter returns the SimpleCounterStat matching name, or nil if
// not found. Stats segment names are byte slices, so we compare as string.
func findSimpleCounter(entries []adapter.StatEntry, name string) adapter.SimpleCounterStat {
	for _, e := range entries {
		if string(e.Name) != name {
			continue
		}
		if s, ok := e.Data.(adapter.SimpleCounterStat); ok {
			return s
		}
	}
	return nil
}

// reduceSimpleCounter sums per-worker values at column i. It tolerates a
// short per-worker vector (which can happen right after a VIP is added,
// before a worker has observed it) by skipping out-of-range rows.
func reduceSimpleCounter(s adapter.SimpleCounterStat, i int) uint64 {
	var sum uint64
	for _, thread := range s {
		if i >= 0 && i < len(thread) {
			sum += uint64(thread[i])
		}
	}
	return sum
}