UDR Benchmark Testing

3 UDR Benchmark Testing

This chapter describes UDR, SLF, and EIR test scenarios.

3.1 Test Scenario 1: SLF Call Model: 67K lookup + 1.44K Provisioning TPS (64M Subscribers)

This test scenario describes performance and capacity of SLF functionality offered by UDR and provides the benchmarking results for various deployment sizes.

The following features are enabled for SLF in this testcase:

Support for Default Group ID in SLF
Controlled Shutdown of an Instance
TLS 1.3 Support for Kubernetes API Server Communication
Error Logging Enhancement
Error Response Enhancement
OAuth2
Alternate Routing Service
Support for User-Agent Header
Overload Handling
Support for LCI and OCI Header
Network Function Scoring for a Site
Conflict Resolution
Ingress Gateway Pod Protection Using Rate Limiting

The following features are enabled for Provisioning Gateway in this testcase:

Auditor Service
Provgw global configuration

You can perform benchmark tests on SLF for compute and storage resources by considering the following conditions:

Signaling (SLF Look Up): 67K TPS
Provisioning: 1.44 K
Total Subscribers: 64 Million
Profile Size: 450 bytes

The following table describes the benchmarking parameters and their values:

Table 3-1 Traffic Model Details

Request Type	Details	TPS
Lookup 67k	SLF Lookup GET Requests	67K
Provisioning (1.44K using Provgw)	CREATE	210
	DELETE	210
	UPDATE	510
	GET	510

The following table describes the testcase parameters and their values:

Table 3-2 Testcase Parameters

Input Parameter Details	Configuration Values
SLF Version Tag	25.2.100
Target TPS	67K Lookup + 1.44K Provisioning
Traffic Profile	SLF 67K Profile
Notification Rate	OFF
SLF Response Timeout	900ms
Signaling Requests Latency Recorded	31ms
Provisioning Requests Latency Recorded	50ms

The following table describes consolidated resource requirement:

Table 3-3 Consolidated Resource Requirement per Site

Resource	CPU	Memory	Ephemeral Storage	PVC
cnDBTier	177	531 GB	69 GB	1094 GB
SLF	517	295 GB	67 GB	NA
ProvGw	39	39 GB	9 GB	5 GB
Buffer	50	50 GB	50 GB	50 GB
Total	783	915 GB	195 GB	1149 GB

Note:

All values are inclusive of ASM sidecar.

The following table provides OSO resources:

Table 3-4 OSO Resources (Retention period: 14 days)

Service	Replicas	CPU Limit	RAM Limit	PVC	Ephemeral storage
Prometheus (snapshot utility enabled)	1	4	8 GB	75 GB	12 GB
Prometheus AlertManager	2	4	4 GB	10 GB	1 GB
Total	3	12	16 GB	95 GB	14 GB

Table 3-5 cnDBTier Resources

Microservice Name	Container Name	Number of Pods	CPU Allocation Per Pod (cnDBtier1)	Memory Allocation Per Pod (cnDBtier1)	Ephemeral Storage Per Pod	PVC Allocation Per Pod	Total Resources (cnDBtier)
Management node (ndbmgmd)	mysqlndbcluster	2	2 CPUs	12 GB	1 GB	16 GB	6 CPUs 26 GB Ephemeral Storage: 2 GB PVC Allocation: 32 GB
Management node (ndbmgmd)	istio-proxy	2	1 CPUs	1 GB	1 GB	16 GB
Data node (ndbmtd)	mysqlndbcluster	6	4 CPUs	50 GB	1 GB	65 GB (Backup: 63 GB)	42 CPUs 324 GB Ephemeral Storage: 6 GB PVC Allocation: 768 GB
	istio-proxy		2 CPUs	2 GB
	db-backup-executor-svc		1 CPU	2 GB
APP SQL node (ndbappmysqld)	mysqlndbcluster	10	6 CPUs	4 GB	1 GB	10 GB	90 CPUs 60 GB Ephemeral Storage: 10 GB PVC Allocation: 100 GB
APP SQL node (ndbappmysqld)	istio-proxy	10	3 CPUs	2 GB	1 GB	10 GB
SQL node (Used for Replication) (ndbmysqld)	mysqlndbcluster	4	4 CPUs	16 GB	1 GB	16 GB	25 CPUs 41 GB Ephemeral Storage: 2 GB PVC Allocation: 32 GB
	istio-proxy		2 CPUs	4 GB
	init-sidecar		100m CPU	256 MB
DB Monitor Service (db-monitor-svc)	db-monitor-svc	1	4 CPUs	4 GB	1 GB	NA	5 CPUs 5 GB Ephemeral Storage: 1 GB
DB Monitor Service (db-monitor-svc)	istio-proxy	1	1 CPUs	1 GB	1 GB	NA	5 CPUs 5 GB Ephemeral Storage: 1 GB
DB Backup Manager Service (backup-manager-svc)	backup-manager-svc	1	1 CPU	1 GB	1 GB	NA	2 CPUs 2 GB Ephemeral Storage: 1 GB
DB Backup Manager Service (backup-manager-svc)	istio-proxy	1	1 CPUs	1 GB	1 GB	NA	2 CPUs 2 GB Ephemeral Storage: 1 GB
Replication Service (db-replication-svc)	db-replication-svc	2	2 CPU	12 GB	1 GB	160 GB	4 CPUs 13 GB Ephemeral Storage: 1 GB PVC Allocation: 160 GB
Replication Service (db-replication-svc)	istio-proxy	2	200m CPU	500 MB	1 GB	160 GB

Additional cnDBTier configuration are as follows:

ndb:
  annotations:
    - sidecar.istio.io/inject: "true"
    - proxy.istio.io/config: "{concurrency: 8}"
    - sidecar.istio.io/proxyCPU: "2000m"
    - sidecar.istio.io/proxyCPULimit: "2000m"
    - sidecar.istio.io/proxyMemory: "4Gi"
    - sidecar.istio.io/proxyMemoryLimit: "4Gi"

mgm:
  annotations:
    - sidecar.istio.io/inject: "true"
    - proxy.istio.io/config: "{concurrency: 8}"
    - sidecar.istio.io/proxyCPU: "1000m"
    - sidecar.istio.io/proxyCPULimit: "1000m"
    - sidecar.istio.io/proxyMemory: "4Gi"
    - sidecar.istio.io/proxyMemoryLimit: "4Gi"
 
api:
  annotations:
    - sidecar.istio.io/inject: "true"
    - proxy.istio.io/config: "{concurrency: 8}"
    - sidecar.istio.io/proxyCPU: "2000m"
    - sidecar.istio.io/proxyCPULimit: "2000m"
    - sidecar.istio.io/proxyMemory: "4Gi"
    - sidecar.istio.io/proxyMemoryLimit: "4Gi"
  ndbapp:
    annotations:
      - sidecar.istio.io/inject: "true"
      - proxy.istio.io/config: "{concurrency: 8}"
      - sidecar.istio.io/proxyCPU: "3000m"
      - sidecar.istio.io/proxyCPULimit: "3000m"
      - sidecar.istio.io/proxyMemory: "4Gi"
      - sidecar.istio.io/proxyMemoryLimit: "4Gi"

The following table describes SLF resources (Lookup Latency: 31ms):

Table 3-6 SLF Resources and Usage

Microservice name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources
Ingress-gateway-sig	ingressgateway-sig	26	6 CPUs	4 GB	1 GB	260 CPUs 156 GB Memory Ephemeral Storage: 26 GB
Ingress-gateway-sig	istio-proxy	26	4 CPUs	2 GB	1 GB	260 CPUs 156 GB Memory Ephemeral Storage: 26 GB
Ingress-gateway-prov	ingressgateway-prov	2	4 CPUs	4 GB	1 GB	12 CPUs 12 GB Ephemeral Storage: 2 GB
Ingress-gateway-prov	istio-proxy	2	2 CPUs	2 GB	1 GB	12 CPUs 12 GB Ephemeral Storage: 2 GB
Nudr-dr-service	nudr-drservice	22	6 CPUs	4 GB	1 GB	198 CPUs 132 GB Ephemeral Storage: 22 GB
Nudr-dr-service	istio-proxy	22	3 CPUs	2 GB	1 GB	198 CPUs 132 GB Ephemeral Storage: 22 GB
Nudr-dr-provservice	nudr-dr-provservice	2	4 CPUs	4 GB	1 GB	12 CPUs 12 GB Ephemeral Storage: 2 GB
Nudr-dr-provservice	istio-proxy	2	2 CPUs	2 GB	1 GB	12 CPUs 12 GB Ephemeral Storage: 2 GB
Nudr-nrf-client-nfmanagement	nrf-client-nfmanagement	2	1 CPU	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
Nudr-nrf-client-nfmanagement	istio-proxy	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
Nudr-egress-gateway	egressgateway	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
Nudr-egress-gateway	istio-proxy	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
Nudr-config	nudr-config	2	2 CPUs	2 GB	1 GB	6 CPUs 6 GB Ephemeral Storage: 2 GB
Nudr-config	istio-proxy	2	1 CPUs	1 GB	1 GB	6 CPUs 6 GB Ephemeral Storage: 2 GB
Nudr-config-server	nudr-config-server	2	2 CPUs	2 GB	1 GB	6 CPUs 6 GB Ephemeral Storage: 2 GB
Nudr-config-server	istio-proxy	2	1 CPUs	1 GB	1 GB	6 CPUs 6 GB Ephemeral Storage: 2 GB
alternate-route	alternate-route	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
alternate-route	istio-proxy	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
app-info	app-info	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
app-info	istio-proxy	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
perf-info	perf-info	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
perf-info	istio-proxy	2	1 CPUs	1 GB	1 GB	4 CPUs 4 GB Ephemeral Storage: 2 GB
Nudr-dbcr-auditor	nudr-dbcr-auditor-service	1	2 CPUs	2 GB	1 GB	3 CPUs 3 GB Ephemeral Storage: 1 GB
Nudr-dbcr-auditor	istio-proxy	1	1 CPUs	1 GB	1 GB	3 CPUs 3 GB Ephemeral Storage: 1 GB

Note:

The same resources and usage are used for all sites.

Table 3-7 Provision Gateway Resources (Provisioning Latency: 50 ms)

Microservice name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources
provgw-ingress-gateway	ingressgateway	2	4 CPUs	4 GB	1 GB	10 CPUs 12 GB Memory Ephemeral Storage: 2 GB
provgw-ingress-gateway	istio-proxy	2	1 CPUs	2 GB	1 GB	10 CPUs 12 GB Memory Ephemeral Storage: 2 GB
provgw-egress-gateway	egressgateway	2	4 CPUs	4 GB	1 GB	10 CPUs 12 GB Memory Ephemeral Storage: 2 GB
provgw-egress-gateway	istio-proxy	2	1 CPUs	2 GB	1 GB	10 CPUs 12 GB Memory Ephemeral Storage: 2 GB
provgw-service	provgw-service	2	4 CPUs	2 GB	1 GB	10 CPUs 8 GB Memory Ephemeral Storage: 2 GB
provgw-service	istio-proxy	2	1 CPUs	2 GB	1 GB	10 CPUs 8 GB Memory Ephemeral Storage: 2 GB
provgw-config	provgw-config	2	2 CPUs	2 GB	1 GB	6 CPUs 6 GB Memory Ephemeral Storage: 2 GB
provgw-config	istio-proxy	2	1 CPUs	1 GB	1 GB	6 CPUs 6 GB Memory Ephemeral Storage: 2 GB
provgw-auditor-service	auditor-service	1	2 CPUs	2 GB	1 GB	3 CPUs 4 GB Memory Ephemeral Storage: 1 GB
provgw-auditor-service	istio-proxy	1	1 CPU	2 GB	1 GB	3 CPUs 4 GB Memory Ephemeral Storage: 1 GB

The following table provides observation data for the performance test that can be used for the benchmark testing to scale up SLF performance:

Table 3-8 Result and Observation

Parameter	Values
TPS Achieved	67K SLF Lookup + 1.44K Provisioning
Success Rate	100%
Average SLF processing time for signaling requests	19ms
Average SLF processing time for provisioning requests	42ms

3.2 Test Scenario 2: EIR 10K TPS and 10k Diameter S13 Interface TPS (600 K Subscribers)

This test scenario describes performance and capacity improvements of EIR functionality offered by UDR and provides the benchmarking results for various deployment sizes.

The following features are enabled for this testcase:

Support for EIR International Mobile Equipment Identity Software Version (IMEISV) Fallback
Overload Handling
Ingress Gateway Pod Protection Using Rate Limiting
Auto Create
Diameter S13 Interface
International Mobile Subscriber Identity (IMSI) Fallback Lookup

EIR is benchmarked for compute and storage resources under the following conditions:

EIR Look Up: 20K
Total Subscribers: 600 K
Profile Size: 130 bytes

The following table describes the benchmarking parameters and their values:

Table 3-9 Traffic Model Details

Request Type	Details	TPS
EIR GET	N17 GET Request	10K
ECR message	Diameter S13 Interface ECR	10K

The following table describes the testcase parameters and their values:

Table 3-10 Testcase Parameters

Input Parameter Details	Configuration Values
UDR Version Tag	25.2.100
Target TPS	20K Lookup
Traffic Profile	20K
EIR Response Timeout	2.7s
Client Timeout	10s
N17 Latency:	6 ms
S13 Latency	7 ms

The following table describes the consolidated resource requirements:

Table 3-11 Consolidated Resource Requirement per Site

Resource	CPUs	Memory	Ephemeral Storage	PVC
cnDBTier	55	141 GB	16 GB	516 GB
EIR	131	97 GB	34 GB	NA GB
Buffer	50	50 GB	20 GB	50 GB
Total	236	288 GB	70 GB	566 GB

The following table describes cnDBTier resources:

Table 3-12 cnDBTier Resources

Micro service name	Container name	Number of Pods (cnDBTier1)	CPU Allocation Per Pod (cnDBTier1)	Memory Allocation Per Pod (cnDBTier1)	PVC Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources (cnDBTier1)
Management node	mysqlndbcluster	2	2 CPUs	12 GB	16 GB	1 GB	4 CPU 24 GB Memory Ephemeral Storage: 2 GB PVC Allocation: 32 GB
Data node	mysqlndbcluster	4	4 CPUs	20 GB	28 GB Backup: 56 GB	1 GB	16 CPU 80 GB Memory Ephemeral Storage: 4 GB PVC Allocation: 336 GB
APP SQL node	mysqlndbcluster	5	4 CPUs	4 GB	10 GB	1 GB	20 CPU 20 GB Memory Ephemeral Storage: 5 GB PVC Allocation: 50 GB
SQL node (Used for Replication)	mysqlndbcluster	2	4 CPUs	5 GB	16 GB	1 GB	8 CPU 10 GB Memory Ephemeral Storage: 2 GB PVC Allocation: 32 GB
DB Monitor Service (db-monitor-svc)	db-monitor-svc	1	4 CPUs	4 GB	NA	1 GB	4 CPUs 4 GB Memory Ephemeral Storage: 1 GB
DB Backup Manager Service (backup-manager-svc)	backup-manager-svc	1	100m CPUs	128 MB	NA	1 GB	100m CPUs 128 MB Memory Ephemeral Storage: 1 GB
Replication Service (db-replication-svc)	db-replication-svc	1	2 CPU	2 GB	NA	1 GB	2 CPUs 2 MB Memory Ephemeral Storage: 1 GB PVC Allocation: 66 GB

The following table describes EIR resources:

Table 3-13 EIR Resources

Micro service name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources
Ingress-gateway-sig	Ingress-gateway-sig	4	6 CPUs	4 GB	1 GB	24 CPUs 16 GB Memory Ephemeral Storage: 4 GB
Ingress-gateway-prov	Ingress-gateway-prov	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Memory Ephemeral Storage: 2 GB
Nudr-dr-service	nudr-drservice	3	6 CPUs	4 GB	1 GB	18 CPUs 12 GB Memory Ephemeral Storage: 3 GB
Nudr-dr-provservice	nudr-dr-provservice	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Memory Ephemeral Storage: 2 GB
Nudr-diam-gateway	nudr-diam-gateway	2	6 CPUs	4 GB	1 GB	12 CPUs 8 GB Memory Ephemeral Storage: 2 GB
Nudr-diameterproxy	nudr-diameterproxy	8	6 CPUs	4 GB	1 GB	48 CPUs 32 GB Memory Ephemeral Storage: 8 GB
Nudr-config	nudr-config	2	1 CPUs	1 GB	1 GB	2 CPUs 2 GB Memory Ephemeral Storage: 2 GB
Nudr-config-server	nudr-config-server	2	1 CPUs	1 GB	1 GB	2 CPU 2 GB Memory Ephemeral Storage: 2 GB
Alternate-route	alternate-route	2	1 CPUs	1 GB	1 GB	2 CPU 2 GB Memory Ephemeral Storage: 2 GB
Nudr-nrf-client-nfmanagement-service	nrf-client-nfmanagement	2	1 CPUs	1 GB	1 GB	2 CPU 2 GB Memory Ephemeral Storage: 2 GB
App-info	app-info	2	1 CPUs	1 GB	1 GB	2 CPU 2 GB Memory Ephemeral Storage: 2 GB
Perf-info	perf-info	2	1 CPUs	1 GB	1 GB	2 CPU 2 GB Memory Ephemeral Storage: 2 GB
Nudr-dbcr-auditor-service	nudr-dbcr-auditor-service	1	1 CPUs	1 GB	1 GB	1 CPU 1 GB Memory Ephemeral Storage: 1 GB

The following table provides observation data for the performance test that can be used for the benchmark testing to scale up EIR performance:

Table 3-14 Result and Observation

Parameter	Values
TPS Achieved	20K
Success Rate	100%
Average EIR processing time (Request and Response)	9 ms

3.3 Test Scenario 3: 25K N36 and 600 Provisioning (SOAP) Profile (35M Subscribers)

You can perform benchmark tests on UDR for compute and storage resources by considering the following conditions:

Signaling: 25K TPS
Provisioning: 600 TPS
Total Subscribers: 35 Million

The following features are enabled for this testcase:

Auto Enrollment and Auto Create Features
Overload Handling
ETag (Entity Tag)
Ingress Gateway Pod Protection Using Rate Limiting
Support for User-Agent Header
3gpp-Sbi-Correlation-Info Header
Suppress Notification
Support for Post Operation for an Existing Subscription
Subscriber Activity Logging

The following table describes the benchmarking parameters and their values:

Table 3-15 Traffic Model Details

Request Type	Details	TPS
N36 traffic 25K TPS	subs-to-notify POST	5K (20%)
	sm-data GET	5K (20%)
	subs-to-notify DELETE	5K (20%
	sm-data PATCH	10K (40%)
SOAP PROVISIONING 600 TPS	GET	100
	UPDATE QUOTA	50
	UPDATE DYNAMIC QUOTA	50
	UPDATE STATE	100
	UPDATE SUBSCRIBER	100
	CREATE SUBSCRIBER	100
	DELETE SUBSCRIBER	100

The following table describes the test case parameters and their values:

Table 3-16 Testcase Parameters

Input Parameter Details	Configuration Values
UDR Version Tag	25.2.100
Target TPS	25K TPS Signaling + 600 SOAP
Notification Rate	300
UDR Response Timeout	2.7s
Signaling Requests Latency Recorded	25ms
Provisioning Requests Latency Recorded	40ms

Table 3-17 Consolidated Resource Requirement per Site

Resource	CPU	Memory	Ephemeral Storage	PVC
cnDBTier	163 CPUs	640 GB	29 GB	1955 GB
UDR	257 CPUs	184 GB	55 GB	NA
PROVGW	28	28	10	NA
Buffer	50 CPUs	50 GB	20 GB	200 GB
Total	498 CPUs	902 GB	114 GB	2155 GB

The following table describes cnDBTier resources:

Table 3-18 cnDBTier Resources

Microservice name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	PVC Allocation Per Pod	Total Resources
Management node (ndbmgmd)	mysqlndbcluster	2	2 CPUs	9 GB	1 GB	15 GB	4 CPUs 18 GB Ephemeral Storage: 2 GB PVC Allocation: 30 GB
Data node (ndbmtd)	mysqlndbcluster	4	9 CPUs	124 GB	1 GB	132 GB Backup: 220 GB	36 CPUs 496 GB Ephemeral Storage: 4 GB PVC Allocation: 1408 GB
APP SQL node (ndbappmysqld)	mysqlndbcluster	18	6 CPUs	4 GB	1 GB	4 GB	108 CPUs 72 GB Ephemeral Storage: 18 GB PVC Allocation: 72 GB
SQL node (ndbmysqld,used for replication)	mysqlndbcluster	2	4 CPUs	24 GB	1 GB	110 GB	8 CPUs 48 GB Ephemeral Storage: 2 GB PVC Allocation: 220 GB
DB Monitor Service (db-monitor-svc)	db-monitor-svc	1	4 CPUs	4 GB	1 GB	NA	4 CPU 4 MB Ephemeral Storage: 1 GB
DB Backup Manager Service (backup-manager-svc)	backup-manager-svc	1	100 millicores CPUs	128 MB	1 GB	NA	1 CPU 128 MB Ephemeral Storage: 1 GB
Replication service (Multi site cases)	replication-svc	1	2 CPUs	2 GB	1 GB	225 GB	2 CPUs 2 GB Ephemeral Storage: 1 GB PVC Allocation: 225 GB

The following table describes UDR resources:

Table 3-19 UDR Resources (Average Latency: 33ms (N36/PROV) and N36: 25ms / PROV: 40ms

Micro service name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources
Ingress-gateway-sig	ingressgateway-sig	13	6 CPUs	4 GB	1 GB	78 CPUs 52 GB Ephemeral Storage: 13 GB
Ingress-gateway-prov	ingressgateway-prov	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-dr-service	nudr-drservice	20	6 CPUs	4 GB	1 GB	120 CPUs 80 GB Ephemeral Storage: 20 GB
Nudr-dr-provservice	nudr-dr-provservice	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-notify-service	nudr-notify-service	3	6 CPUs	5 GB	1 GB	18 CPUs 15 GB Ephemeral Storage: 3 GB
Nudr-egress-gateway	egressgateway	2	6 CPUs	4 GB	1 GB	12 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-config	nudr-config	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-config-server	nudr-config-server	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Alternate-route	alternate-route	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-nrf-client-nfmanagement-service	nrf-client-nfmanagement	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
App-info	app-info	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Perf-info	perf-info	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-dbcr-auditor-service	nudr-dbcr-auditor-service	1	1 CPU	1 GB	1 GB	1 CPU 1 GB Ephemeral Storage: 1 GB

The following table describes Provisioning Gateway resources:

Table 3-20 Provisioning Gateway Resources

Micro service name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Total Resources
provgw-ingress-gateway	ingressgateway	2	4 CPUs	4 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
provgw-egress-gateway	egressgateway	2	4 CPUs	4 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
provgw-service	provgw-service	4	2 CPUs	2 GB	8 CPUs 8 GB Ephemeral Storage: 4 GB
provgw-config	provgw-config	2	2 CPUs	2 GB	4 CPUs 4 GB Memory Ephemeral Storage: 2 GB

The following table provides observation data for the performance test that can be used for the benchmark testing to scale up UDR performance:

Table 3-21 Result and Observation

Parameter	Values
TPS Achieved	25K Signaling + 600
UDR Request Average Latency	33ms
Success rate	100%

3.4 Test Scenario 4: 17.2K N36 + 10K SH and 600 Provisioing (SOAP) Profile (35M Subscribers)

You can perform benchmark tests on UDR for compute and storage resources by considering the following conditions:

Signaling : 17.2K N36 + 10K SH
Provisioning: 600 TPS
Total Subscribers: 35 Million

The following features are enabled for this testcase:

Auto Enrollment and Auto Create Features
Overload Handling
ETag (Entity Tag)
Ingress Gateway Pod Protection Using Rate Limiting
Support for User-Agent Header
3gpp-Sbi-Correlation-Info Header
Suppress Notification
Subscriber Activity Logging
Diameter Gateway Pod Congestion Control
Support for Post Operation for an Existing Subscription

The following table describes the benchmarking parameters and their values:

Table 3-22 Traffic Model Details

Request Type	Details	TPS
N36 17.2K TPS	subs-to-notify POST	5K (20%)
	sm-data GET	5K (20%)
	subs-to-notify DELETE	5K (20%)
	sm-data PATCH	5K (20%)
SH 10K TPS	UDR	4K
	PUR	1.2K
	SNR	4.8K
SH PNR 1.2K TPS	PNR	1.2K
SOAP PROVISIONING 600 TPS	GET	100
	UPDATE QUOTA	50
	UPDATE DYNAMIC QUOTA	50
	UPDATE STATE	100
	UPDATE SUBSCRIBER	100
	CREATE SUBSCRIBER	100
	DELETE SUBSCRIBER	100

The following table describes the test case parameters and their values:

Table 3-23 Testcase Parameters

Input Parameter Details	Configuration Values
UDR Version Tag	25.2.100
Target TPS	17.2K N36 + 10K SH + 600 SOAP
Notification Rate	1.2K
UDR Response Timeout	2.7s
Signaling Requests Latency Recorded	25ms
Provisioning Requests Latency Recorded	30ms
Diameter (SH) Requests Latency Recorded	18ms

Table 3-24 Consolidated Resource Requirement per Site

Resource	CPU	Memory	Ephemeral Storage	PVC
cnDBTier	139 CPUs	625 GB	25 GB	1939
UDR	281 CPUs	201 GB	60 GB	NA
PROVGW	28	28	10	NA
Buffer	50 CPUs	50 GB	20 GB	200 GB
Total	498 CPUs	901 GB	115 GB	2139 GB

The following table describes cnDBTier resources:

Table 3-25 cnDBTier Resource

Microservice name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	PVC Allocation Per Pod	Total Resources
Management node (ndbmgmd)	mysqlndbcluster	2	2 CPUs	9 GB	1 GB	15 GB	4 CPUs 18 GB Ephemeral Storage: 2 GB PVC Allocation: 30 GB
Data node (ndbmtd)	mysqlndbcluster	4	9 CPUs	124 GB	1 GB	132 GB Backup: 220 GB	36 CPUs 496 GB Ephemeral Storage: 4 GB PVC Allocation: 1408 GB
APP SQL node (ndbappmysqld)	mysqlndbcluster	14	6 CPUs	4 GB	1 GB	4 GB	84 CPUs 56 GB Ephemeral Storage: 14 GB PVC Allocation: 56 GB
SQL node (ndbmysqld,used for replication)	mysqlndbcluster	2	4 CPUs	24 GB	1 GB	110 GB	8 CPUs 48 GB Ephemeral Storage: 2 GB PVC Allocation: 220 GB
DB Monitor Service	db-monitor-svc	1	4 CPUs	4 GB	1 GB	NA	4 CPU 4 MB Ephemeral Storage: 1 GB
DB Backup Manager Service	backup-manager-svc	1	100 millicores CPUs	128 MB	1 GB	NA	1 CPU 128 MB Ephemeral Storage: 1 GB
Replication service (Multi site cases)	replication-svc	1	2 CPUs	2 GB	1 GB	225 GB	2 CPUs 2 GB Ephemeral Storage: 1 GB PVC Allocation: 225 GB

The following table describes UDR resources:

Table 3-26 UDR Resources (Average Latency: 25ms [25ms (N36) / 18ms (SH) / 30ms Provisioning]).

Micro service name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Ephemeral Storage Per Pod	Total Resources
Ingress-gateway-sig	ingressgateway-sig	9	6 CPUs	4 GB	1 GB	54 CPUs 36 GB Ephemeral Storage: 9 GB
Ingress-gateway-prov	ingressgateway-prov	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-dr-service	nudr-drservice	17	6 CPUs	4 GB	1 GB	102 CPUs 68 GB Ephemeral Storage: 17 GB
Nudr-dr-provservice	nudr-dr-provservice	2	4 CPUs	4 GB	1 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-notify-service	nudr-notify-service	3	6 CPUs	5 GB	1 GB	18 CPUs 15 GB Ephemeral Storage: 3 GB
Nudr-egress-gateway	egressgateway	2	6 CPUs	4 GB	1 GB	12 CPUs 8 GB Ephemeral Storage: 2 GB
Nudr-diam-gateway	nudr-diam-gateway	2	6 CPUs	5 GB	1 GB	12 CPUs 10 GB Ephemeral Storage: 2 GB
Nudr-diameterproxy	nudr-diameterproxy	9	6 CPUs	4 GB	1 GB	54 CPUs 36 GB Ephemeral Storage: 9 GB
Nudr-config	nudr-config	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-config-server	nudr-config-server	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Alternate-route	alternate-route	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-nrf-client-nfmanagement-service	nrf-client-nfmanagement	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
App-info	app-info	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Perf-info	perf-info	2	1 CPU	1 GB	1 GB	2 CPUs 2 GB Ephemeral Storage: 2 GB
Nudr-dbcr-auditor-service	nudr-dbcr-auditor-service	1	1 CPU	1 GB	1 GB	1 CPU 1 GB Ephemeral Storage: 1 GB

The following table describes Provisioning Gateway resources:

Table 3-27 Provisioning Gateway Resources

Micro service name	Container name	Number of Pods	CPU Allocation Per Pod	Memory Allocation Per Pod	Total Resources
provgw-ingress-gateway	ingressgateway	2	4 CPUs	4 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
provgw-egress-gateway	egressgateway	2	4 CPUs	4 GB	8 CPUs 8 GB Ephemeral Storage: 2 GB
provgw-service	provgw-service	4	2 CPUs	2 GB	8 CPUs 8 GB Ephemeral Storage: 4 GB
provgw-config	provgw-config	2	2 CPUs	2 GB	4 CPUs 4 GB Memory Ephemeral Storage: 2 GB

The following table provides observation data for the performance test that can be used for the benchmark testing to scale up UDR performance:

Table 3-28 Result and Observation

Parameter	Values
TPS Achieved	17.2K N36 + 10K SH + 600
UDR Request Average Latency	25ms
Success rate	100%