mirror of
https://github.com/Rain-kl/OpenFlare.git
synced 2026-10-07 08:06:37 +08:00
feat(clickhouse): wire batchwriter into business ingestion paths
Migrate risk_control audit logs to internal/db/batchwriter and add openflare/chwriter with per-table async flush for observability timeseries and node access logs. Replace single-row ClickHouse inserts and pre-insert SELECT count() dedup with repository BatchInsert* APIs, in-process TTL dedup for metric/report snapshots, and bootstrap initialization on API startup.
This commit is contained in:
@@ -5,88 +5,96 @@ package risk_control
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
"sync"
|
||||
|
||||
"github.com/Rain-kl/Wavelet/internal/config"
|
||||
"github.com/Rain-kl/Wavelet/internal/db/batchwriter"
|
||||
"github.com/Rain-kl/Wavelet/internal/model/analytics"
|
||||
analyticsrepo "github.com/Rain-kl/Wavelet/internal/repository/analytics"
|
||||
"github.com/Rain-kl/Wavelet/pkg/logger"
|
||||
)
|
||||
|
||||
var logChan chan *analytics.UserAccessLog
|
||||
|
||||
const (
|
||||
defaultQueueSize = 10000
|
||||
maxBatchSize = 1000
|
||||
flushInterval = 1 * time.Second
|
||||
var (
|
||||
logWriterMu sync.RWMutex
|
||||
logWriter *batchwriter.Writer[*analytics.UserAccessLog]
|
||||
)
|
||||
|
||||
// InitLogWriter 初始化日志写入通道和后台写入协程
|
||||
// InitLogWriter initializes the ClickHouse access-log batch writer.
|
||||
func InitLogWriter(ctx context.Context) {
|
||||
if !config.Config.ClickHouse.Enabled {
|
||||
return
|
||||
}
|
||||
|
||||
logChan = make(chan *analytics.UserAccessLog, defaultQueueSize)
|
||||
go startBatchWorker(context.WithoutCancel(ctx))
|
||||
}
|
||||
|
||||
// IsBufferFull 检查当前本地缓冲队列是否已满
|
||||
// 如果没有启用 ClickHouse,默认返回 false,不触发限流
|
||||
func IsBufferFull() bool {
|
||||
if !config.Config.ClickHouse.Enabled || logChan == nil {
|
||||
return false
|
||||
}
|
||||
return len(logChan) >= cap(logChan)
|
||||
}
|
||||
|
||||
// QueueAccessLog 异步非阻塞地将日志推入缓冲队列
|
||||
func QueueAccessLog(logItem *analytics.UserAccessLog) {
|
||||
if !config.Config.ClickHouse.Enabled || logChan == nil {
|
||||
logWriterMu.Lock()
|
||||
defer logWriterMu.Unlock()
|
||||
if logWriter != nil {
|
||||
return
|
||||
}
|
||||
|
||||
select {
|
||||
case logChan <- logItem:
|
||||
default:
|
||||
logger.WarnF(context.Background(), "[RiskControl] Log queue full, dropping log item for path: %s", logItem.Path)
|
||||
cfg := batchwriter.DefaultConfig()
|
||||
writer, err := batchwriter.New[*analytics.UserAccessLog](cfg, func(ctx context.Context, items []*analytics.UserAccessLog) error {
|
||||
rows := make([]analytics.UserAccessLog, 0, len(items))
|
||||
for _, item := range items {
|
||||
if item == nil {
|
||||
continue
|
||||
}
|
||||
rows = append(rows, *item)
|
||||
}
|
||||
return analyticsrepo.BatchInsert(ctx, rows)
|
||||
},
|
||||
batchwriter.WithDropHandler[*analytics.UserAccessLog](func(item *analytics.UserAccessLog) {
|
||||
path := ""
|
||||
if item != nil {
|
||||
path = item.Path
|
||||
}
|
||||
logger.WarnF(context.Background(), "[RiskControl] Log queue full, dropping log item for path: %s", path)
|
||||
}),
|
||||
batchwriter.WithFlushErrorHandler[*analytics.UserAccessLog](func(ctx context.Context, batchSize int, err error) {
|
||||
logger.ErrorF(ctx, "[RiskControl] Send ClickHouse batch failed (batch=%d): %v", batchSize, err)
|
||||
}),
|
||||
)
|
||||
if err != nil {
|
||||
logger.ErrorF(ctx, "[RiskControl] init log writer failed: %v", err)
|
||||
return
|
||||
}
|
||||
|
||||
writer.Start(ctx)
|
||||
logWriter = writer
|
||||
}
|
||||
|
||||
// IsBufferFull reports whether the access-log queue has no remaining capacity.
|
||||
func IsBufferFull() bool {
|
||||
writer := currentLogWriter()
|
||||
if writer == nil {
|
||||
return false
|
||||
}
|
||||
return writer.IsFull()
|
||||
}
|
||||
|
||||
// QueueAccessLog enqueues an access log without blocking.
|
||||
func QueueAccessLog(logItem *analytics.UserAccessLog) {
|
||||
writer := currentLogWriter()
|
||||
if writer == nil || logItem == nil {
|
||||
return
|
||||
}
|
||||
writer.TryEnqueue(logItem)
|
||||
}
|
||||
|
||||
// SetLogWriterForTest swaps the access-log writer for unit tests.
|
||||
func SetLogWriterForTest(writer *batchwriter.Writer[*analytics.UserAccessLog]) func() {
|
||||
logWriterMu.Lock()
|
||||
previous := logWriter
|
||||
logWriter = writer
|
||||
logWriterMu.Unlock()
|
||||
return func() {
|
||||
logWriterMu.Lock()
|
||||
logWriter = previous
|
||||
logWriterMu.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
func startBatchWorker(ctx context.Context) {
|
||||
ticker := time.NewTicker(flushInterval)
|
||||
defer ticker.Stop()
|
||||
|
||||
var batch []*analytics.UserAccessLog
|
||||
|
||||
flush := func() {
|
||||
if len(batch) == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
items := make([]analytics.UserAccessLog, len(batch))
|
||||
for i, item := range batch {
|
||||
items[i] = *item
|
||||
}
|
||||
if err := analyticsrepo.BatchInsert(ctx, items); err != nil {
|
||||
logger.ErrorF(ctx, "[RiskControl] Send ClickHouse batch failed: %v", err)
|
||||
}
|
||||
batch = nil
|
||||
}
|
||||
|
||||
for {
|
||||
select {
|
||||
case item, ok := <-logChan:
|
||||
if !ok {
|
||||
flush()
|
||||
return
|
||||
}
|
||||
batch = append(batch, item)
|
||||
if len(batch) >= maxBatchSize {
|
||||
flush()
|
||||
}
|
||||
case <-ticker.C:
|
||||
flush()
|
||||
}
|
||||
}
|
||||
func currentLogWriter() *batchwriter.Writer[*analytics.UserAccessLog] {
|
||||
logWriterMu.RLock()
|
||||
defer logWriterMu.RUnlock()
|
||||
return logWriter
|
||||
}
|
||||
@@ -4,6 +4,7 @@
|
||||
package risk_control
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
@@ -12,6 +13,7 @@ import (
|
||||
|
||||
"github.com/Rain-kl/Wavelet/internal/apps/oauth"
|
||||
"github.com/Rain-kl/Wavelet/internal/config"
|
||||
"github.com/Rain-kl/Wavelet/internal/db/batchwriter"
|
||||
"github.com/Rain-kl/Wavelet/internal/model"
|
||||
"github.com/Rain-kl/Wavelet/internal/model/analytics"
|
||||
"github.com/Rain-kl/Wavelet/internal/testhelper"
|
||||
@@ -19,6 +21,35 @@ import (
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
const testLogQueueSize = 10_000
|
||||
|
||||
func newTestLogWriter(t *testing.T, queueSize int) (*batchwriter.Writer[*analytics.UserAccessLog], chan *analytics.UserAccessLog) {
|
||||
t.Helper()
|
||||
|
||||
received := make(chan *analytics.UserAccessLog, queueSize)
|
||||
cfg := batchwriter.Config{
|
||||
QueueSize: queueSize,
|
||||
MaxBatchSize: 1,
|
||||
FlushInterval: 5 * time.Millisecond,
|
||||
}
|
||||
writer, err := batchwriter.New[*analytics.UserAccessLog](cfg, func(_ context.Context, items []*analytics.UserAccessLog) error {
|
||||
for _, item := range items {
|
||||
if item != nil {
|
||||
received <- item
|
||||
}
|
||||
}
|
||||
return nil
|
||||
})
|
||||
assert.NoError(t, err)
|
||||
writer.Start(context.Background())
|
||||
t.Cleanup(func() {
|
||||
stopCtx, cancel := context.WithTimeout(context.Background(), time.Second)
|
||||
defer cancel()
|
||||
_ = writer.Stop(stopCtx)
|
||||
})
|
||||
return writer, received
|
||||
}
|
||||
|
||||
func TestRiskControlMiddleware(t *testing.T) {
|
||||
gin.SetMode(gin.TestMode)
|
||||
|
||||
@@ -41,15 +72,15 @@ func TestRiskControlMiddleware(t *testing.T) {
|
||||
|
||||
t.Run("ClickHouse enabled - Normal Authenticated Request", func(t *testing.T) {
|
||||
config.Config.ClickHouse.Enabled = true
|
||||
logChan = make(chan *analytics.UserAccessLog, defaultQueueSize)
|
||||
writer, received := newTestLogWriter(t, testLogQueueSize)
|
||||
resetWriter := SetLogWriterForTest(writer)
|
||||
defer func() {
|
||||
config.Config.ClickHouse.Enabled = false
|
||||
logChan = nil
|
||||
resetWriter()
|
||||
}()
|
||||
|
||||
r := gin.New()
|
||||
r.Use(func(c *gin.Context) {
|
||||
// Mock authentication middleware placing user in context
|
||||
user := &model.User{ID: 12345}
|
||||
oauth.SetToContext(c, oauth.UserObjKey, user)
|
||||
c.Next()
|
||||
@@ -68,9 +99,8 @@ func TestRiskControlMiddleware(t *testing.T) {
|
||||
assert.Equal(t, http.StatusOK, w.Code)
|
||||
assert.Equal(t, "ok", w.Body.String())
|
||||
|
||||
// Verify log is enqueued
|
||||
select {
|
||||
case logItem := <-logChan:
|
||||
case logItem := <-received:
|
||||
assert.Equal(t, uint64(12345), logItem.UserID)
|
||||
assert.Equal(t, "/test", logItem.Path)
|
||||
assert.Equal(t, http.MethodGet, logItem.Method)
|
||||
@@ -78,17 +108,18 @@ func TestRiskControlMiddleware(t *testing.T) {
|
||||
assert.NotEmpty(t, logItem.Headers)
|
||||
assert.Contains(t, logItem.Headers, "X-Test-Header")
|
||||
assert.NotContains(t, logItem.Headers, "Cookie")
|
||||
case <-time.After(100 * time.Millisecond):
|
||||
t.Fatal("expected log item in logChan, but got none")
|
||||
case <-time.After(200 * time.Millisecond):
|
||||
t.Fatal("expected flushed log item, but got none")
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("ClickHouse enabled - Unauthenticated Request", func(t *testing.T) {
|
||||
config.Config.ClickHouse.Enabled = true
|
||||
logChan = make(chan *analytics.UserAccessLog, defaultQueueSize)
|
||||
writer, received := newTestLogWriter(t, testLogQueueSize)
|
||||
resetWriter := SetLogWriterForTest(writer)
|
||||
defer func() {
|
||||
config.Config.ClickHouse.Enabled = false
|
||||
logChan = nil
|
||||
resetWriter()
|
||||
}()
|
||||
|
||||
r := testhelper.NewTestGinEngine(RiskControlMiddleware())
|
||||
@@ -103,26 +134,24 @@ func TestRiskControlMiddleware(t *testing.T) {
|
||||
assert.Equal(t, http.StatusOK, w.Code)
|
||||
assert.Equal(t, "ok", w.Body.String())
|
||||
|
||||
// Verify no log is enqueued
|
||||
select {
|
||||
case <-logChan:
|
||||
case <-received:
|
||||
t.Fatal("expected no log item for unauthenticated request")
|
||||
case <-time.After(50 * time.Millisecond):
|
||||
// Success
|
||||
}
|
||||
})
|
||||
|
||||
t.Run("ClickHouse enabled - Buffer Full Rate Limiting", func(t *testing.T) {
|
||||
config.Config.ClickHouse.Enabled = true
|
||||
logChan = make(chan *analytics.UserAccessLog, 2) // small capacity for quick fill
|
||||
writer, _ := newTestLogWriter(t, 2)
|
||||
resetWriter := SetLogWriterForTest(writer)
|
||||
defer func() {
|
||||
config.Config.ClickHouse.Enabled = false
|
||||
logChan = nil
|
||||
resetWriter()
|
||||
}()
|
||||
|
||||
// fill logChan up to cap to simulate buffer full
|
||||
for len(logChan) < cap(logChan) {
|
||||
logChan <- &analytics.UserAccessLog{}
|
||||
for range 2 {
|
||||
assert.True(t, writer.TryEnqueue(&analytics.UserAccessLog{}))
|
||||
}
|
||||
|
||||
r := testhelper.NewTestGinEngine(RiskControlMiddleware())
|
||||
@@ -141,4 +170,4 @@ func TestRiskControlMiddleware(t *testing.T) {
|
||||
assert.NoError(t, err)
|
||||
assert.Contains(t, resp["error_msg"], "系统繁忙")
|
||||
})
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user