Skip to content

History backfill rate limiter #8645

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

History backfill rate limiter #8645

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c8b5527
Add a limiter for the history replicator persistence layer.
robholland Nov 13, 2025
b057280
Set unlimited by default.
robholland Nov 14, 2025
5b5ade0
Merge branch 'main' into rh-backfill-limiter
robholland Nov 14, 2025
170174c
0 is not unlimited for QPS limiting. Set a high value.
robholland Nov 14, 2025
26deef2
Wire into FX.
robholland Nov 20, 2025
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
5 changes: 5 additions & 0 deletions common/dynamicconfig/constants.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2387,6 +2387,11 @@ the number of children greater than or equal to this threshold`,
30,
`ReplicationTaskProcessorShardQPS is the qps of task processing rate limiter on shard level`,
)
ReplicationTaskProcessorApplyPersistenceQPS = NewGlobalFloatSetting(
"history.ReplicationTaskProcessorApplyPersistenceQPS",
10000,
`ReplicationTaskProcessorApplyPersistenceQPS is the qps of task processing rate limiter on persistence level`,
)
ReplicationEnableDLQMetrics = NewGlobalBoolSetting(
"history.ReplicationEnableDLQMetrics",
true,
Expand Down
2 changes: 2 additions & 0 deletions service/history/configs/config.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,6 +266,7 @@ type Config struct {
ReplicationTaskProcessorCleanupJitterCoefficient dynamicconfig.FloatPropertyFnWithShardIDFilter
ReplicationTaskProcessorHostQPS dynamicconfig.FloatPropertyFn
ReplicationTaskProcessorShardQPS dynamicconfig.FloatPropertyFn
ReplicationTaskProcessorApplyPersistenceQPS dynamicconfig.FloatPropertyFn
ReplicationEnableDLQMetrics dynamicconfig.BoolPropertyFn
ReplicationEnableUpdateWithNewTaskMerge dynamicconfig.BoolPropertyFn
ReplicationMultipleBatches dynamicconfig.BoolPropertyFn
Expand Down Expand Up @@ -556,6 +557,7 @@ func NewConfig(
ReplicatorProcessorMaxSkipTaskCount: dynamicconfig.ReplicatorMaxSkipTaskCount.Get(dc),
ReplicationTaskProcessorHostQPS: dynamicconfig.ReplicationTaskProcessorHostQPS.Get(dc),
ReplicationTaskProcessorShardQPS: dynamicconfig.ReplicationTaskProcessorShardQPS.Get(dc),
ReplicationTaskProcessorApplyPersistenceQPS: dynamicconfig.ReplicationTaskProcessorApplyPersistenceQPS.Get(dc),
ReplicationEnableDLQMetrics: dynamicconfig.ReplicationEnableDLQMetrics.Get(dc),
ReplicationEnableUpdateWithNewTaskMerge: dynamicconfig.ReplicationEnableUpdateWithNewTaskMerge.Get(dc),
ReplicationStreamSyncStatusDuration: dynamicconfig.ReplicationStreamSyncStatusDuration.Get(dc),
Expand Down
12 changes: 11 additions & 1 deletion service/history/ndc/history_replicator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import (
"go.temporal.io/server/common/persistence/transitionhistory"
"go.temporal.io/server/common/persistence/versionhistory"
"go.temporal.io/server/common/primitives/timestamp"
"go.temporal.io/server/common/quotas"
serviceerrors "go.temporal.io/server/common/serviceerror"
"go.temporal.io/server/service/history/consts"
historyi "go.temporal.io/server/service/history/interfaces"
Expand Down Expand Up @@ -104,6 +105,7 @@ type (
workflowCache wcache.Cache
eventsReapplier EventsReapplier
transactionMgr TransactionManager
rateLimiter quotas.RateLimiter
logger log.Logger

mutableStateMapper *MutableStateMapperImpl
Expand Down Expand Up @@ -137,7 +139,10 @@ func NewHistoryReplicator(
workflowCache: workflowCache,
transactionMgr: transactionMgr,
eventsReapplier: eventsReapplier,
logger: logger,
rateLimiter: quotas.NewDefaultOutgoingRateLimiter(
func() float64 { return shardContext.GetConfig().ReplicationTaskProcessorApplyPersistenceQPS() },
),
logger: logger,

mutableStateMapper: NewMutableStateMapping(
shardContext,
Expand Down Expand Up @@ -192,6 +197,7 @@ func (r *HistoryReplicatorImpl) ApplyEvents(
ctx context.Context,
request *historyservice.ReplicateEventsV2Request,
) (retError error) {
_ = r.rateLimiter.Wait(ctx) // WaitN(ctx, tokens) based on the request events size?

task, err := newReplicationTaskFromRequest(
r.clusterMetadata,
Expand All @@ -210,6 +216,8 @@ func (r *HistoryReplicatorImpl) BackfillHistoryEvents(
ctx context.Context,
request *historyi.BackfillHistoryEventsRequest,
) error {
_ = r.rateLimiter.Wait(ctx) // WaitN(ctx, tokens) based on the request events size?

task, err := newReplicationTaskFromBatch(
r.clusterMetadata,
r.logger,
Expand Down Expand Up @@ -404,6 +412,8 @@ func (r *HistoryReplicatorImpl) ReplicateHistoryEvents(
newEvents []*historypb.HistoryEvent,
newRunID string,
) error {
_ = r.rateLimiter.Wait(ctx) // WaitN(ctx, tokens) based on the request events size?

task, err := newReplicationTaskFromBatch(
r.clusterMetadata,
r.logger,
Expand Down
Loading