Files
pangolin/server/internal/nodes/load.go
T
wangjia 605bfa1ec9 feat(nodes): gRPC server + Hub + Redis pub/sub cross-instance delivery (tsk__58l3wTLvaSn)
Implements AgentService gRPC server with all 6 RPCs (Enroll/Register/Heartbeat/
Subscribe/Ack/ReportUsage), Hub command routing with Redis ZSET at-least-once
persistence and cross-instance pub/sub delivery, LoadCache for node:load metrics,
NodeStore SQL interface + MySQL implementation, and full mTLS gRPC listener in main.

Integration tests: 18 tests covering full Enroll→Register→Heartbeat→Subscribe→Ack
flow, reconnect resume with last_command_id, and cross-instance pub/sub delivery
via bufconn + miniredis + mockNodeStore + real mTLS certificates.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-13 17:30:42 +08:00

84 lines
2.3 KiB
Go

package nodes
import (
"context"
"fmt"
"time"
"github.com/redis/go-redis/v9"
)
const (
// nodeLoadKeyPrefix is the Redis HASH key prefix for per-node runtime load metrics.
// Full key: node:load:{node_uuid} (doc/03 §4)
nodeLoadKeyPrefix = "node:load:"
// nodeLoadTTL is the TTL on each node:load hash. A node that stops sending
// heartbeats has its entry automatically evicted after 90 seconds.
nodeLoadTTL = 90 * time.Second
)
// NodeLoad holds the runtime metrics reported in each heartbeat.
type NodeLoad struct {
OnlineCount int64
BandwidthUpBps int64
BandwidthDownBps int64
CPUPercent float64
}
// LoadCache reads and writes node:load Redis hashes.
// It accepts redis.Cmdable so it can be used with a *redis.Client or pipeline.
type LoadCache struct {
rdb redis.Cmdable
}
// NewLoadCache creates a LoadCache backed by rdb.
func NewLoadCache(rdb redis.Cmdable) *LoadCache {
return &LoadCache{rdb: rdb}
}
// Set writes nodeUUID's current load metrics to Redis and refreshes the TTL.
// The hash fields match the names in doc/03 §4: online_count, bw_up, bw_down, cpu.
func (c *LoadCache) Set(ctx context.Context, nodeUUID string, load NodeLoad) error {
key := nodeLoadKeyPrefix + nodeUUID
pipe := c.rdb.Pipeline()
pipe.HSet(ctx, key,
"online_count", load.OnlineCount,
"bw_up", load.BandwidthUpBps,
"bw_down", load.BandwidthDownBps,
"cpu", load.CPUPercent,
)
pipe.Expire(ctx, key, nodeLoadTTL)
if _, err := pipe.Exec(ctx); err != nil {
return fmt.Errorf("nodes.LoadCache.Set: %w", err)
}
return nil
}
// Get reads nodeUUID's last-known load. Returns (nil, false, nil) if the key has
// expired or was never set. Fields missing from the hash default to zero.
func (c *LoadCache) Get(ctx context.Context, nodeUUID string) (*NodeLoad, bool, error) {
key := nodeLoadKeyPrefix + nodeUUID
vals, err := c.rdb.HGetAll(ctx, key).Result()
if err != nil {
return nil, false, fmt.Errorf("nodes.LoadCache.Get: %w", err)
}
if len(vals) == 0 {
return nil, false, nil
}
var l NodeLoad
if v, ok := vals["online_count"]; ok {
_, _ = fmt.Sscan(v, &l.OnlineCount)
}
if v, ok := vals["bw_up"]; ok {
_, _ = fmt.Sscan(v, &l.BandwidthUpBps)
}
if v, ok := vals["bw_down"]; ok {
_, _ = fmt.Sscan(v, &l.BandwidthDownBps)
}
if v, ok := vals["cpu"]; ok {
_, _ = fmt.Sscan(v, &l.CPUPercent)
}
return &l, true, nil
}