Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: refresh connections to avoid hotspotting of load distribution #5227

Closed
wants to merge 3 commits into from
Closed

fix: refresh connections to avoid hotspotting of load distribution #5227

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
12a8e21
fix: refresh connections to avoid hotspotting of load distribution
snarkychef Oct 24, 2024
679daa9
fixes
snarkychef Oct 24, 2024
b3cd6ea
Implemented for processor transformations
snarkychef Oct 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 16 additions & 13 deletions processor/transformer/transformer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ import (
backendconfig "github.com/rudderlabs/rudder-server/backend-config"
"github.com/rudderlabs/rudder-server/processor/integrations"
"github.com/rudderlabs/rudder-server/utils/httputil"
"github.com/rudderlabs/rudder-server/utils/sysUtils"
"github.com/rudderlabs/rudder-server/utils/types"
warehouseutils "github.com/rudderlabs/rudder-server/warehouse/utils"
)
Expand Down Expand Up @@ -136,7 +137,7 @@ type Opt func(*handle)

func WithClient(client *http.Client) Opt {
return func(s *handle) {
s.client = client
s.recycledClient = sysUtils.NewRecycledHTTPClient(func() *http.Client { return client }, 0)
}
}

Expand All @@ -157,7 +158,7 @@ type handle struct {
logger logger.Logger
stat stats.Stats

client *http.Client
recycledClient *sysUtils.RecycledHTTPClient

guardConcurrency chan struct{}

Expand Down Expand Up @@ -209,16 +210,18 @@ func NewTransformer(conf *config.Config, log logger.Logger, stat stats.Stats, op

trans.guardConcurrency = make(chan struct{}, trans.config.maxConcurrency)

if trans.client == nil {
trans.client = &http.Client{
Transport: &http.Transport{
DisableKeepAlives: trans.config.disableKeepAlives,
MaxConnsPerHost: trans.config.maxHTTPConnections,
MaxIdleConnsPerHost: trans.config.maxHTTPIdleConnections,
IdleConnTimeout: trans.config.maxIdleConnDuration,
},
Timeout: trans.config.timeoutDuration,
}
if trans.recycledClient == nil {
trans.recycledClient = sysUtils.NewRecycledHTTPClient(func() *http.Client {
return &http.Client{
Transport: &http.Transport{
DisableKeepAlives: trans.config.disableKeepAlives,
MaxConnsPerHost: trans.config.maxHTTPConnections,
MaxIdleConnsPerHost: trans.config.maxHTTPIdleConnections,
IdleConnTimeout: trans.config.maxIdleConnDuration,
},
Timeout: trans.config.timeoutDuration,
}
}, config.GetDuration("Transformer.Client.ttl", 120, time.Second))
}

for _, opt := range opts {
Expand Down Expand Up @@ -472,7 +475,7 @@ func (trans *handle) doPost(ctx context.Context, rawJSON []byte, url, stage stri
// Header to let transformer know that the client understands event filter code
req.Header.Set("X-Feature-Filter-Code", "?1")

resp, reqErr = trans.client.Do(req)
resp, reqErr = trans.recycledClient.GetClient().Do(req)
})
trans.stat.NewTaggedStat("processor.transformer_request_time", stats.TimerType, tags).SendTiming(time.Since(requestStartTime))
if reqErr != nil {
Expand Down
11 changes: 6 additions & 5 deletions processor/transformer/transformer_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ import (
"github.com/rudderlabs/rudder-server/testhelper/backendconfigtest"
warehouseutils "github.com/rudderlabs/rudder-server/warehouse/utils"

"github.com/rudderlabs/rudder-server/utils/sysUtils"
"github.com/rudderlabs/rudder-server/utils/types"

"github.com/stretchr/testify/require"
Expand Down Expand Up @@ -173,7 +174,7 @@ func TestTransformer(t *testing.T) {
tr.stat = statsStore
tr.logger = logger.NOP
tr.conf = config.Default
tr.client = srv.Client()
tr.recycledClient = sysUtils.NewRecycledHTTPClient(srv.Client, 0)
tr.guardConcurrency = make(chan struct{}, 200)
tr.sentStat = tr.stat.NewStat("transformer_sent", stats.CountType)
tr.receivedStat = tr.stat.NewStat("transformer_received", stats.CountType)
Expand Down Expand Up @@ -359,7 +360,7 @@ func TestTransformer(t *testing.T) {
tr.stat = stats.Default
tr.logger = logger.NOP
tr.conf = config.Default
tr.client = client
tr.recycledClient = sysUtils.NewRecycledHTTPClient(func() *http.Client { return client }, 0)
tr.config.maxRetry = config.SingleValueLoader(tc.retries)
tr.config.failOnUserTransformTimeout = config.SingleValueLoader(tc.failOnUserTransformTimeout)
tr.cpDownGauge = tr.stat.NewStat("control_plane_down", stats.GaugeType)
Expand Down Expand Up @@ -422,7 +423,7 @@ func TestTransformer(t *testing.T) {
tr.stat = stats.Default
tr.logger = logger.NOP
tr.conf = config.Default
tr.client = srv.Client()
tr.recycledClient = sysUtils.NewRecycledHTTPClient(srv.Client, 0)
tr.config.maxRetry = config.SingleValueLoader(1)
tr.config.maxRetryBackoffInterval = config.SingleValueLoader(1 * time.Second)
tr.config.timeoutDuration = 1 * time.Second
Expand Down Expand Up @@ -553,7 +554,7 @@ func TestTransformer(t *testing.T) {
tr.stat = stats.Default
tr.logger = logger.NOP
tr.conf = config.Default
tr.client = srv.Client()
tr.recycledClient = sysUtils.NewRecycledHTTPClient(srv.Client, 0)
tr.config.failOnUserTransformTimeout = config.SingleValueLoader(false)
tr.config.maxRetry = config.SingleValueLoader(tc.retries)
tr.config.failOnError = config.SingleValueLoader(tc.failOnError)
Expand Down Expand Up @@ -653,7 +654,7 @@ func TestTransformer(t *testing.T) {
defer srv.Close()

tr := handle{}
tr.client = srv.Client()
tr.recycledClient = sysUtils.NewRecycledHTTPClient(srv.Client, 0)
tr.stat = stats.Default
tr.conf = config.Default
tr.logger = logger.NOP
Expand Down
11 changes: 7 additions & 4 deletions router/transformer/transformer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,8 @@ const (
// handle is the handle for this class
type handle struct {
tr *http.Transport
// http client for router transformation request
client *http.Client
// http recycledClient for router transformation request
recycledClient *sysUtils.RecycledHTTPClient
// Mockable http.client for transformer proxy request
proxyClient sysUtils.HTTPClientI
// http client timeout for transformer proxy request
Expand Down Expand Up @@ -179,7 +179,7 @@ func (trans *handle) Transform(transformType string, transformMessage *types.Tra
req = req.WithContext(cntx.CtxWithDestInfo(req.Context(), destinationInfo))
resp, err = trans.clientOAuthV2.Do(req)
} else {
resp, err = trans.client.Do(req)
resp, err = trans.recycledClient.GetClient().Do(req)
}

if err == nil {
Expand Down Expand Up @@ -500,7 +500,10 @@ func (trans *handle) setup(destinationTimeout, transformTimeout time.Duration, c
// Basically this timeout we will configure when we make final call to destination to send event
trans.destinationTimeout = destinationTimeout
// This client is used for Router Transformation
trans.client = &http.Client{Transport: trans.tr, Timeout: trans.transformTimeout}
trans.recycledClient = sysUtils.NewRecycledHTTPClient(
func() *http.Client {
return &http.Client{Transport: trans.tr.Clone(), Timeout: trans.transformTimeout}
}, config.GetDuration("Transformer.Client.ttl", 120, time.Second))
optionalArgs := &oauthv2httpclient.HttpClientOptionalArgs{
Locker: locker,
Augmenter: extensions.RouterBodyAugmenter,
Expand Down
31 changes: 31 additions & 0 deletions utils/sysUtils/httpclient.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,40 @@ package sysUtils

import (
"net/http"
"sync"
"time"
)

// HTTPClient interface
type HTTPClientI interface {
Do(req *http.Request) (*http.Response, error)
}

type RecycledHTTPClient struct {
client *http.Client
lastRefreshTime time.Time
ttl time.Duration
clientFunc func() *http.Client
lock sync.Mutex
}

func NewRecycledHTTPClient(_clientFunc func() *http.Client, _ttl time.Duration) *RecycledHTTPClient {
return &RecycledHTTPClient{
client: _clientFunc(),
clientFunc: _clientFunc,
ttl: _ttl,
lastRefreshTime: time.Now(),
}
}

func (r *RecycledHTTPClient) GetClient() *http.Client {
r.lock.Lock()
defer r.lock.Unlock()

if r.ttl > 0 && time.Since(r.lastRefreshTime) > r.ttl {
r.client.CloseIdleConnections()
r.client = r.clientFunc()
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what if 1 goroutine comes and gets a http client and make a http-request and while that request is in flight another go routine comes and ttl is passed we closed all the ideal conns(conn made by the 1st goroutine is still not closed as the req is in flight) and recycle the http client. But since first req is already in flight can this cause some resource to leak?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thats true. We should combine this with: IdleConnTimeout (can be equal to r.lastRefreshTime) Eventually resources would freed up.

r.lastRefreshTime = time.Now()
}
return r.client
}
Loading