This is the multi-page printable view of this section. Click here to print.

Return to the regular view of this page.

Performance and scalability statistics of Dapr

Benchmarks and guidelines for Dapr building blocks

1: Longhaul performance and stability
2: Performance results

1 - Longhaul performance and stability

This article provides longhaul performance and stability benchmarks for Dapr on Kubernetes.

The longhaul tests are designed to run for a period of a week, validating the stability of Dapr and its components, while measuring resource utilization and performance over time.

Public Dashboard

You can access the live longhaul test results on the public Grafana dashboard. This dashboard is updated in near real-time, showing the latest results from the longhaul tests.

Dapr Longhaul Dashboard.

System overview

The longhaul environment is run on a 3 node managed Azure Kubernetes Service (AKS) cluster, using standard D2s_v5 nodes running 2 cores and 8GB of RAM, with network acceleration.

Test Applications

Feed generator
Hashtag Actor
Hashtag counter
Message Analyzer
Pubsub Workflow
Streaming Pubsub Publisher / Producer
Streaming Pubsub Subscriber / Consumer
Snapshot App
Validation Worker App
Scheduler Jobs App
Workflow Gen App
Scheduler Actor Reminders - Client
Scheduler Actor Reminders - Server
Scheduler Workflow App

Redeployments

The longhaul test environment is redeployed every 7 days (Fridays at 08:00 UTC).

Test Infrastructure

The test infrastructure is sourced from this GitHub repository.

It is a mixture of Bicep IaC templates and Helm charts to deploy the test applications and Dapr.

2 - Performance results

Performance benchmarks and charts for Dapr APIs

The charts below show the performance benchmarks for the Dapr APIs on this version of Dapr, per API. Each section leads with a throughput per resource table (iterations/sec against the CPU and memory consumed by the app and its Dapr sidecar combined) followed by the latency, throughput, resource and data-volume charts for every scenario.

To view the results for a different Dapr version, use the version selector at the top of the docs.

How this data is produced

Benchmarks run in the dapr-perf suite for each Dapr release. The raw report is the source of truth and is committed to the dapr/dapr repository; the rendered charts are published to the perf-charts branch and pulled into this page automatically. Nothing on this page is version-specific, the results shown always match the Dapr version you are viewing.

Test environment: Azure AKS, 3x Standard_D2s_v6 (2 vCPU, 8 GiB) Linux nodes. Results for Dapr v1.18.0.

Service invocation (2 scenarios)

HTTP

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestServiceInvocationHTTPPerformance	999.97	43	14	17	48	16666.1	16482.6

TestServiceInvocationHTTPPerformance (14 charts)

TestServiceInvocationHTTPPerformance_connection_stats.png

TestServiceInvocationHTTPPerformance_duration_breakdown.png

TestServiceInvocationHTTPPerformance_duration_requested_vs_actual.png

TestServiceInvocationHTTPPerformance_histogram_count.png

TestServiceInvocationHTTPPerformance_histogram_percent.png

TestServiceInvocationHTTPPerformance_resource_memory.png

gRPC

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestServiceInvocationGrpcPerformance	999.96	91	14	51	49	7042.0	16075.5

TestServiceInvocationGrpcPerformance (9 charts)

TestServiceInvocationGrpcPerformance_duration_breakdown.png

TestServiceInvocationGrpcPerformance_duration_requested_vs_actual.png

TestServiceInvocationGrpcPerformance_histogram_count.png

TestServiceInvocationGrpcPerformance_histogram_percent.png

TestServiceInvocationGrpcPerformance_resource_memory.png

State management (2 scenarios)

HTTP

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestStateGetHTTPPerformance	999.97	87	30	94	49	5524.7	13024.5

TestStateGetHTTPPerformance (14 charts)

TestStateGetHTTPPerformance_duration_requested_vs_actual.png

gRPC

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestStateGetGrpcPerformance	999.98	15	30	4	44	52630.7	13824.2

TestStateGetGrpcPerformance (9 charts)

TestStateGetGrpcPerformance_duration_requested_vs_actual.png

Publish and subscribe (14 scenarios)

HTTP

TestPubsubPublishHttpPerformance (6 charts)

TestPubsubPublishHttpPerformance_duration_breakdown.png

gRPC

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestPubsubPublishGrpcPerformance	999.98	86	33	106	51	5208.3	12113.4

TestPubsubPublishGrpcPerformance (9 charts)

TestPubsubPublishGrpcPerformance_duration_breakdown.png

TestPubsubPublishGrpcPerformance_duration_requested_vs_actual.png

Bulk / HTTP

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestPubsubBulkPublishSubscribeHttpPerformance_kafka-messagebus	67.55	24	19	2	37	2598.2	1230.4

TestPubsubBulkPublishBulkSubscribeHttpPerformance_kafka-messagebus (8 charts)

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk (6 charts)

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_data_volume.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_duration_breakdown.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_duration_low.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_summary.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_tail_latency.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_bulk_throughput.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal (6 charts)

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_data_volume.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_duration_breakdown.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_duration_low.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_summary.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_tail_latency.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b100_s1KB_normal_throughput.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk (6 charts)

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_data_volume.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_duration_breakdown.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_duration_low.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_summary.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_tail_latency.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_bulk_throughput.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal (6 charts)

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_data_volume.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_duration_breakdown.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_duration_low.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_summary.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_tail_latency.png

TestPubsubBulkPublishHttpPerformance_memory-broker_b10_s1KB_normal_throughput.png

TestPubsubBulkPublishHttpPerformance_variants_duration (1 chart)

TestPubsubBulkPublishHttpPerformance_variants_duration.png

TestPubsubBulkPublishSubscribeHttpPerformance_kafka-messagebus (8 charts)

Bulk / gRPC

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event	199.94	476	41	1126	77	124.8	1726.1
TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)	199.95	372	44	1000	76	145.7	1701.8
TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event	199.94	564	42	1676	94	89.3	1497.7
TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)	199.94	758	43	1545	94	86.8	1493.1

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event (9 charts)

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_duration_breakdown.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_duration_requested_vs_actual.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_histogram_count.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_histogram_percent.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_qps.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_resource_cpu.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_resource_memory.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_summary.png

TestBulkPubsubPublishGrpcPerformance_In-memory_with_with_cloud_event_tail_latency.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload) (9 charts)

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_duration_breakdown.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_duration_requested_vs_actual.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_histogram_count.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_histogram_percent.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_qps.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_resource_cpu.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_resource_memory.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_summary.png

TestBulkPubsubPublishGrpcPerformance_In-memory_without_cloud_event_(raw_payload)_tail_latency.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event (9 charts)

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_duration_breakdown.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_duration_requested_vs_actual.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_histogram_count.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_histogram_percent.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_qps.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_resource_cpu.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_resource_memory.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_summary.png

TestBulkPubsubPublishGrpcPerformance_Kafka_with_cloud_event_tail_latency.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload) (9 charts)

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_duration_breakdown.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_duration_requested_vs_actual.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_histogram_count.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_histogram_percent.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_qps.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_resource_cpu.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_resource_memory.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_summary.png

TestBulkPubsubPublishGrpcPerformance_Kafka_without_cloud_event_(raw_payload)_tail_latency.png

TestBulkPubsubPublishGrpcPerformance_variants_duration (1 chart)

TestBulkPubsubPublishGrpcPerformance_variants_duration.png

Actors (5 scenarios)

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestActorActivate	499.98	662	891	106	65	651.0	535.6
TestActorDoubleActivation	770.87	206	14	419	204	1233.4	3614.8
TestActorIdStress	13497.43	101	35	413	241	26259.6	49935.8
TestActorReminderRegistrationPerformance	1415.09	1	8	29	56	47169.8	22794.7
TestActorTimerWithStatePerformance	219.98	138	1192	155	65	750.8	179.2

TestActorActivate (13 charts)

TestActorDoubleActivation (8 charts)

TestActorIdStress (8 charts)

TestActorReminderRegistrationPerformance (14 charts)

TestActorReminderRegistrationPerformance_connection_stats.png

TestActorReminderRegistrationPerformance_data_volume.png

TestActorReminderRegistrationPerformance_duration_breakdown.png

TestActorReminderRegistrationPerformance_duration_requested_vs_actual.png

TestActorReminderRegistrationPerformance_header_size.png

TestActorReminderRegistrationPerformance_histogram_count.png

TestActorReminderRegistrationPerformance_histogram_percent.png

TestActorReminderRegistrationPerformance_payload_size.png

TestActorReminderRegistrationPerformance_resource_cpu.png

TestActorReminderRegistrationPerformance_resource_memory.png

TestActorReminderRegistrationPerformance_tail_latency.png

TestActorReminderRegistrationPerformance_throughput.png

TestActorTimerWithStatePerformance (14 charts)

TestActorTimerWithStatePerformance_connection_stats.png

TestActorTimerWithStatePerformance_duration_breakdown.png

TestActorTimerWithStatePerformance_duration_requested_vs_actual.png

TestActorTimerWithStatePerformance_histogram_percent.png

Workflows (6 scenarios)

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestDelayWorkflowsAtScale	35.58	402	939	162	101	63.1	35.0
TestParallelWorkflowWithMaxVUs	110.24	14	608	2	36	6890.0	175.3
TestSeriesWorkflowWithMaxVUs	92.97	13	610	2	39	6197.7	146.7
TestWorkflowWithConstantIterations	62.62	14	608	2	37	3834.1	99.5
TestWorkflowWithConstantVUs	53.41	58	626	3	49	875.6	81.0
TestWorkflowWithDifferentPayloads	9.29	19	616	2	35	442.6	14.6

TestDelayWorkflowsAtScale (8 charts)

TestParallelWorkflowWithMaxVUs (8 charts)

TestSeriesWorkflowWithMaxVUs (8 charts)

TestWorkflowWithConstantIterations (9 charts)

TestWorkflowWithConstantIterations_avg_duration_breakdown.png

TestWorkflowWithConstantIterations_avg_duration_comparison.png

TestWorkflowWithConstantIterations_avg_duration_low.png

TestWorkflowWithConstantIterations_avg_resource_cpu.png

TestWorkflowWithConstantIterations_avg_resource_memory.png

TestWorkflowWithConstantIterations_avg_tail_latency.png

TestWorkflowWithConstantVUs (9 charts)

TestWorkflowWithConstantVUs_avg_duration_comparison.png

TestWorkflowWithDifferentPayloads (9 charts)

TestWorkflowWithDifferentPayloads_avg_duration_breakdown.png

TestWorkflowWithDifferentPayloads_avg_duration_comparison.png

TestWorkflowWithDifferentPayloads_avg_resource_memory.png

Jobs (1 scenario)

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestJobSchedulingPerformance	870.79	62	27	102	80	5309.7	8344.7

TestJobSchedulingPerformance (14 charts)

TestJobSchedulingPerformance_duration_requested_vs_actual.png

Configuration (4 scenarios)

HTTP

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestConfigurationGetHTTPPerformance	9697.99	1	39	2	35	3232664.4	132479.0
TestConfigurationSubscribeHTTPPerformance	2074.52	1	73	57	87	35767.6	13307.4

TestConfigurationGetHTTPPerformance (8 charts)

TestConfigurationGetHTTPPerformance_duration_breakdown.png

TestConfigurationGetHTTPPerformance_resource_memory.png

TestConfigurationSubscribeHTTPPerformance (8 charts)

gRPC

Throughput per resource

Iterations/sec relative to the CPU and memory consumed by the app and its Dapr sidecar combined. Resource figures are point-in-time samples taken at the end of each run.

Test	Iterations/sec	App CPU (m)	App Mem (MB)	Sidecar CPU (m)	Sidecar Mem (MB)	Iter/s per core	Iter/s per GB
TestConfigurationGetGRPCPerformance	14369.91	1	73	1	76	7184956.9	99023.6
TestConfigurationSubscribeGRPCPerformance	4038.77	1	83	2	75	1346257.7	26268.1

TestConfigurationGetGRPCPerformance (8 charts)

TestConfigurationGetGRPCPerformance_duration_breakdown.png

TestConfigurationGetGRPCPerformance_resource_memory.png

TestConfigurationSubscribeGRPCPerformance (8 charts)