| RFC 9411 | Benchmarking Network Security Devices | March 2023 |
| Balarajah, et al. | Informational | [Page] |
This document provides benchmarking terminology and methodology for next-generation network security devices, including next-generation firewalls (NGFWs) and next-generation intrusion prevention systems (NGIPSs). The main areas covered in this document are test terminology, test configuration parameters, and benchmarking methodology for NGFWs and NGIPSs. (It is assumed that readers have a working knowledge of these devices and the security functionality they contain.) This document aims to improve the applicability, reproducibility, and transparency of benchmarks and to align the test methodology with today's increasingly complex layer 7 security-centric network application use cases. As a result, this document makes RFC 3511 obsolete.¶
This document is not an Internet Standards Track specification; it is published for informational purposes.¶
This document is a product of the Internet Engineering Task Force (IETF). It represents the consensus of the IETF community. It has received public review and has been approved for publication by the Internet Engineering Steering Group (IESG). Not all documents approved by the IESG are candidates for any level of Internet Standard; see Section 2 of RFC 7841.¶
Information about the current status of this document, any errata, and how to provide feedback on it may be obtained athttps://www.rfc-editor.org/info/rfc9411.¶
Copyright (c) 2023 IETF Trust and the persons identified as the document authors. All rights reserved.¶
This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document. Code Components extracted from this document must include Revised BSD License text as described in Section 4.e of the Trust Legal Provisions and are provided without warranty as described in the Revised BSD License.¶
It has been 18 years since the IETF initially recommended test methodology and terminology for firewalls[RFC3511]. Firewalls have evolved significantly from the days of simple access control list (ACL) filters. As the underlying technology progresses and improves, recommending test methodology and terminology for firewalls, requirements, and expectations for network security elements has increased tremendously. Security function implementations have evolved and diversified into intrusion detection and prevention, threat management, analysis of encrypted traffic, and more. In an industry of growing importance, well-defined and reproducible key performance indicators (KPIs) are increasingly needed to enable fair and reasonable comparisons of network security functions. These reasons led to the creation of a new next-generation network security device benchmarking document, which makes[RFC3511] obsolete. The measurement of performance for processing IP-fragmented traffic (seeSection 5.9 of [RFC3511])is not included in this document since IP fragmentation does not commonly occur in traffic anymore, unlike how it might have at the time when[RFC3511] was written. It should also be noted that[RFC2647] retains significant value and was consulted frequently while creating this document.¶
For a more detailed explanation of what an NGFW is, see the Wikipedia article[Wiki-NGFW].¶
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14[RFC2119][RFC8174] when, and only when, they appear in all capitals, as shown here.¶
This document provides testing terminology and testing methodology for modern and next-generation network security devices that are configured in Active ("Inline", see Figures1 and2) mode. It covers the validation of security effectiveness configurations of network security devices, followed by performance benchmark testing. This document focuses on advanced, realistic, and reproducible testing methods. Additionally, it describes testbed environments, test tool requirements, and test result formats.¶
The performance testing methodology described in this document is not intended for security devices or systems that rely on machine learning or behavioral analysis. If such features are present in a Device Under Test / System Under Test (DUT/SUT), they should be disabled.¶
The test setup defined in this document applies to all benchmarking tests described inSection 7. The test setupMUST be contained within an isolated test environment (seeSection 3 of [RFC6815]).¶
Testbed configurationMUST ensure that any performance implications that are discovered during the benchmark testing aren't due to the inherent physical network limitations, such as the number of physical links and forwarding performance capabilities (throughput and latency) of the network devices in the testbed. For this reason, this document recommends avoiding external devices, such as switches and routers, in the testbed wherever possible.¶
In some deployment scenarios, the network security devices (DUT/SUT) are connected to routers and switches, which will reduce the number of entries in MAC (Media Access Control) or Address Resolution Protocol / Neighbor Discovery (ARP/ND) tables of the DUT/SUT. If MAC or ARP/ND tables have many entries, this may impact the actual DUT/SUT performance due to MAC and ARP/ND table lookup processes. This document also recommends using test equipment with the capability of emulating layer 3 routing functionality instead of adding external routers in the testbed.¶
The testbed setup for Option 1 (Figure 1) is theRECOMMENDED testbed setup for the benchmarking test.¶
+-----------------------+ +-----------------------+| +-------------------+ | +-----------+ | +-------------------+ || | Emulated Router(s)| | | | | | Emulated Router(s)| || | (Optional) | +----- DUT/SUT +-----+ (Optional) | || +-------------------+ | | | | +-------------------+ || +-------------------+ | +-----------+ | +-------------------+ || | Clients | | | | Servers | || +-------------------+ | | +-------------------+ || | | || Test Equipment | | Test Equipment |+-----------------------+ +-----------------------+
If the test equipment used is not capable of emulating OSI layer 3 routing functionality or if the number of used ports is mismatched between the test equipment and the DUT/SUT (which is needed for test equipment port aggregation), the test setup can be configured as shown inFigure 2.¶
+-------------------+ +-----------+ +--------------------+ |Aggregation Switch/| | | | Aggregation Switch/| | Router +------+ DUT/SUT +------+ Router | | | | | | | +----------+--------+ +-----------+ +--------+-----------+ | | | |+-----------+-----------+ +-----------+-----------+| | | || +-------------------+ | | +-------------------+ || | Emulated Router(s)| | | | Emulated Router(s)| || | (Optional) | | | | (Optional) | || +-------------------+ | | +-------------------+ || +-------------------+ | | +-------------------+ || | Clients | | | | Servers | || +-------------------+ | | +-------------------+ || | | || Test Equipment | | Test Equipment |+-----------------------+ +-----------------------+
The same DUT/SUT configurationMUST be used for all benchmarking tests described inSection 7. Since each DUT/SUT will have its own unique configuration, usersMUST configure their devices with the same parameters and security features that would be used in the actual deployment of the device or a typical deployment. The DUT/SUTMUST be configured in "Inline" mode so that the traffic is actively inspected by the DUT/SUT.¶
Tables2 and3 below describe theRECOMMENDED andOPTIONAL sets of network security features for NGFWs and NGIPSs, respectively. If the recommended security features are not enabled in the DUT/SUT for any reason, the reasonMUST be reported with the benchmarking test results. For example, one reason for not enabling the anti-virus feature in an NGFW may be that this security feature was not required for a particular customer deployment scenario. ItMUST be also noted in the benchmarking test report that not enabling the specific recommended security features may impact the performance of the DUT/SUT. The selected security featuresMUST be consistently enabled on the DUT/SUT for all benchmarking tests described inSection 7.¶
To improve repeatability, a summary of the DUT/SUT configuration, including a description of all enabled DUT/SUT features,MUST be published with the benchmarking results.¶
The following table provides a brief description of the security feature; these are approximate taxonomies of features commonly found in currently deployed NGFWs and NGIPSs. The features provided by specific implementations may be named differently and not necessarily have configuration settings that align with the taxonomy.¶
| DUT/SUT Features | Description |
|---|---|
| TLS Inspection | The DUT/SUT intercepts and decrypts inbound HTTPS traffic between servers and clients. Once the content inspection has been completed, the DUT/SUT encrypts the HTTPS traffic with ciphers and keys used by the clients and servers. For TLS 1.3, the DUT works as a middlebox (proxy) and holds the certificates and Pre-Shared Keys (PSKs) that are trusted by the client and represent the identity of the real server. |
| IDS/IPS | The DUT/SUT detects and blocks exploits targeting known and unknown vulnerabilities across the monitored network. |
| Anti-Malware | The DUT/SUT detects and prevents the transmission of malicious executable code and any associated communications across the monitored network. This includes data exfiltration as well as command and control channels. |
| Anti-Spyware | Anti-Spyware is a subcategory of Anti-Malware. Spyware transmits information without the user's knowledge or permission. The DUT/SUT detects and blocks the initial infection or transmission of data. |
| Anti-Botnet | The DUT/SUT detects and blocks traffic to or from botnets. |
| Anti-Evasion | The DUT/SUT detects and mitigates attacks that have been obfuscated in some manner. |
| Web Filtering | The DUT/SUT detects and blocks malicious websites, including defined classifications of websites across the monitored network. |
| Data Loss Protection (DLP) | The DUT/SUT detects and prevents data breaches and data exfiltration, or it detects and blocks the transmission of sensitive data across the monitored network. |
| Certificate Validation | The DUT/SUT validates certificates used in encrypted communications across the monitored network. |
| Logging and Reporting | The DUT/SUT logs and reports all traffic at the flow level across the monitored network. |
| Application Identification | The DUT/SUT detects known applications as defined within the traffic mix selected across the monitored network. |
| Deep Packet Inspection (DPI) | The DUT/SUT inspects the content of the data packet. |
| DUT/SUT (NGFW) Features | RECOMMENDED | OPTIONAL |
|---|---|---|
| TLS Inspection | x | |
| IDS/IPS | x | |
| Anti-Spyware | x | |
| Anti-Virus | x | |
| Anti-Botnet | x | |
| Anti-Evasion | x | |
| Web Filtering | x | |
| Data Loss Protection (DLP) | x | |
| DDoS Protection | x | |
| Certificate Validation | x | |
| Application Identification | x |
| DUT/SUT (NGIPS) Features | RECOMMENDED | OPTIONAL |
|---|---|---|
| TLS Inspection | x | |
| Anti-Malware | x | |
| Anti-Spyware | x | |
| Anti-Botnet | x | |
| Application Identification | x | |
| Deep Packet Inspection (DPI) | x | |
| Anti-Evasion | x |
Note: With respect to TLS Inspection, there are scenarios where it will be optional.¶
Below is a summary of the DUT/SUT configuration:¶
In addition, a realistic number of access control lists (ACLs)SHOULD be configured on the DUT/SUT where ACLs are configurable and reasonable based on the deployment scenario. For example, it is acceptable not to configure ACLs in an NGIPS since NGIPS devices do not require the use of ACLs in most deployment scenarios. This document determines the number of access policy rules for four different classes of the DUT/SUT: Extra Small (XS), Small (S), Medium (M), and Large (L). A sample DUT/SUT classification is described inAppendix B.¶
The ACLs defined inTable 4MUST be configured from top to bottom in the correct order, as shown in the table. This is due to ACL types listed in specificity-decreasing order, with "block" first, followed by "allow", representing a typical ACL-based security policy. The ACL entriesMUST be configured with routable IP prefixes by the DUT/SUT, where applicable. (Note: There will be differences between how security vendors implement ACL decision making.) The configured ACLMUST NOT block the test traffic used for the benchmarking tests.¶
| DUT/SUT Classification # Rules | |||||||
|---|---|---|---|---|---|---|---|
| Rules Type | Match Criteria | Description | Action | XS | S | M | L |
| Application layer | Application | Any application not included in the measurement traffic | block | 5 | 10 | 20 | 50 |
| Transport layer | SRC IP and TCP/UDP DST ports | Any SRC IP prefix used and any DST ports not used in the measurement traffic | block | 25 | 50 | 100 | 250 |
| IP layer | SRC/DST IP | Any SRC/DST IP subnet not used in the measurement traffic | block | 25 | 50 | 100 | 250 |
| Application layer | Application | Half of the applications included in the measurement traffic (see the note below) | allow | 10 | 10 | 10 | 10 |
| Transport layer | SRC IP and TCP/UDP DST ports | Half of the SRC IPs used and any DST ports used in the measurement traffic (one rule per subnet) | allow | >1 | >1 | >1 | >1 |
| IP layer | SRC IP | The rest of the SRC IP prefix range used in the measurement traffic (one rule per subnet) | allow | >1 | >1 | >1 | >1 |
Note 1: Based on the test customer's specific use case, the testers can increase the number of rules.¶
Note 2: If half of the applications included in the test traffic are less than 10, the missing number of ACL entries (placeholder rules) can be configured for any application traffic not included in the test traffic.¶
Note 3: In the event that the DUT/SUT is designed to not use ACLs, it is acceptable to conduct tests without them. However, thisMUST be noted in the test report.¶
The selected security features (defined in Tables2 and3) of the DUT/SUTMUST be configured effectively to detect, prevent, and report the defined security vulnerability sets. This section defines the selection of the security vulnerability sets from the Common Vulnerabilities and Exposures (CVEs) list[CVE] for testing. The vulnerability set should reflect a minimum of 500 CVEs from no older than 10 calendar years to the current year. These CVEs should be selected with a focus on in-use software commonly found in business applications, with a Common Vulnerability Scoring System (CVSS) Severity of High (7-10).¶
This document is primarily focused on performance benchmarking. However, it isRECOMMENDED to validate the security features configuration of the DUT/SUT by evaluating the security effectiveness as a prerequisite for performance benchmarking tests defined inSection 7. In case the benchmarking tests are performed without evaluating security effectiveness, the test reportMUST explain the implications of this. The methodology for evaluating security effectiveness is defined inAppendix A.¶
In general, test equipment allows configuring parameters in different protocol layers. Extensive proof-of-concept tests conducted to support preparation of this document showed that benchmarking results are strongly affected by the choice of protocol stack parameters, especially OSI layer 4 transport protocol parameters. For more information on how TCP and QUIC parameters will impact performance, review[fastly]. To achieve reproducible results that will be representative of real deployment scenarios, careful specification and documentation of the parameters are required.¶
This section specifies common test equipment configuration parameters applicable for all benchmarking tests defined inSection 7. Any benchmarking-test-specific parameters are described under the test setup section of each benchmarking test individually.¶
This section specifies which parameters should be considered while configuring emulated client endpoints in the test equipment. Also, this section specifies theRECOMMENDED values for certain parameters. The values are the defaults typically used in most of the client operating system types.¶
Pre-standard evaluations have shown that it is possible to set a wide range of arbitrary parameters for OSI layer 4 transport protocols on test equipment leading to optimization of client-specific results; however, only well-defined common parameter sets help to establish meaningful and comparable benchmarking results. For these reasons, this document recommends specific sets of transport protocol parameters to be configured on test equipment used for benchmarking.¶
The TCP stack of the emulated client endpointsMUST fulfill the TCP requirements defined inAppendix B of [RFC9293]. In addition, this section specifies theRECOMMENDED values for TCP parameters configured using the parameters described below.¶
The IPv4 and IPv6 Maximum Segment Sizes (MSSs) are set to 1460 bytes and 1440 bytes, respectively. TX and RX initial receive window sizes are set to 65535 bytes. The client's initial congestion window should not exceed 10 times the MSS. Delayed ACKs are permitted, and the maximum client delayed ACK should not exceed 10 times of the MSS before a forced ACK; also, the maximum delayed ACK timer is allowed to be set to 200 ms. Up to three retries are allowed before a timeout event is declared. The TCP PSH flag is set to high in all traffic. The source port range is 1024-65535. The clients initiate TCP connections via a three-way handshake (SYN, SYN/ACK, ACK) and close TCP connections via either a TCP three-way close (FIN, FIN/ACK, ACK) or a TCP four-way close (FIN, ACK, FIN, ACK).¶
QUIC stack emulation on the test equipmentMUST conform to[RFC9000] and[RFC9001]. This section specifies theRECOMMENDED values for certain QUIC parameters to be configured on test equipment used for benchmarking purposes only. The QUIC stream type (defined inSection 2.1 of [RFC9000]) is set to "Client-Initiated, Bidirectional". 0-RTT and early data are disabled. The QUIC connection termination method is an immediate close (Section 10.2 of [RFC9000]). Flow control is enabled. UDP payloads are set to the datagram size of 1232 bytes for IPv6 and 1252 bytes for IPv4. In addition, transport parameters and default values defined inSection 18.2 of [RFC9000] areRECOMMENDED to configure on test equipment. Also, this document references AppendicesB.1 andB.2 of[RFC9002] for congestion-control-related constants and variables. Any configured QUIC and UDP parameterMUST be documented in the test report.¶
The client IP space contains the following attributes.¶
The following equation can be used to define the total number of client IP addresses that need to be configured on the test equipment.¶
Desired total number of client IP addresses = Target throughput [Mbit/s] / Average throughput per IP address [Mbit/s]¶
As shown in the example list below, the value for "Average throughput per IP address" can be varied depending on the deployment and use case scenario.¶
Client IP addressesMUST be distributed between IPv4 and IPv6 based on the deployment and use case scenario. The following optionsMAY be considered for a selection of ratios for both IP addresses and traffic load distribution.¶
Note: IANA has assigned IP address ranges for testing purposes, as described inSection 8. If the test scenario requires more IP addresses or subnets than IANA has assigned, this document recommends using private IPv4 address ranges or Unique Local Address (ULA) IPv6 address ranges for the testing.¶
The client (emulated web browser) contains attributes that will materially affect the traffic load. The objective is to emulate modern, typical browser attributes to improve the relevance of the result set for typical deployment scenarios.¶
The emulated browserMUST negotiate HTTP version 1.1 or higher. The emulated browserSHOULD advertise a User-Agent header. The emulated browserMUST enforce content length validation. HTTP header compressionMAY be set to enable. If HTTP header compression is configurable in the test equipment, itMUST be documented if it was enabled or disabled. Depending on test scenarios and the chosen HTTP version, the emulated browserMAY open multiple TCP or QUIC connections per server endpoint IP at any time, depending on how many sequential transactions need to be processed.¶
For HTTP/2 traffic emulation, the emulated browser opens multiple concurrent streams per connection (multiplexing). For HTTPS requests, the emulated browserMUST send an "h2" protocol identifier using the TLS extension Application-Layer Protocol Negotiation (ALPN). The following default values (see[Undertow]) are theRECOMMENDED settings for certain HTTP/2 parameters to be configured on test equipment used for benchmarking purposes only:¶
This document refers to[RFC9113] for further details of HTTP/2. If any additional parameters are used to configure the test equipment, theyMUST be documented.¶
For HTTP/3 traffic emulation, the emulated browsers initiate secure QUIC connections using TLS 1.3 ([RFC9001] describes how TLS is used to secure QUIC). This document refers to[RFC9114] for HTTP/3 specifications. The specification for transport protocol parameters is defined inSection 4.3.1.2. QPACK configuration settings, such as MAX_TABLE_CAPACITY and QPACK_BLOCKED_STREAMS, are set to zero (default), as defined in[RFC9204]. Any HTTP/3 parameters used for test equipment configurationMUST be documented.¶
For encrypted traffic, the following attributes are defined as the negotiated encryption parameters. The test clientsMUST use TLS version 1.2 or higher. The TLS record sizeMAY be optimized for the HTTPS response object size, up to a record size of 16 KB. If Server Name Indication (SNI) is required (especially if the server is identified by a domain name), the client endpointMUST send TLS extension SNI information when opening a security tunnel. Each client connectionMUST perform a full TLS handshake, and session reuse or resumptionMUST be disabled. (Note: Real web browsers use session reuse or resumption. However, for testing purposes, this feature must not be used to measure the DUT/SUT performance in the worst-case scenario.)¶
The following ciphers and keys supported by TLS 1.2 areRECOMMENDED for the HTTPS-based benchmarking tests defined inSection 7.¶
Note: The above ciphers and keys were those commonly used for enterprise-grade encryption cipher suites for TLS 1.2 at of the time of publication (2023). Individual certification bodies should use ciphers and keys that reflect evolving use cases. These choicesMUST be documented in the resulting test reports with detailed information on the ciphers and keys used, along with reasons for the choices.¶
IANA recommends the following cipher suites for use with TLS 1.3, as defined in[RFC8446].¶
This section specifies which parameters should be considered while configuring emulated backend servers using test equipment.¶
The TCP stack on the server-sideMUST be configured similarly to the client-side configuration described inSection 4.3.1.1.¶
The QUIC parameters on the server-sideMUST be configured similarly to the client-side configuration. Any configured QUIC parameterMUST be documented in the report.¶
The sum of the server IP spaceMUST contain the following attributes.¶
Note: IANA has assigned IP address blocks for the testing purpose described inSection 8. If the test scenario requires more IP addresses or address blocks than IANA has assigned, this document recommends using private IPv4 address ranges or Unique Local Address (ULA) IPv6 address ranges for the testing.¶
The HTTP 1.1 and HTTP/2 server pools listen on TCP ports 80 and 443 for HTTP and HTTPS. The HTTP/3 server pool listens on any UDP port. The serverMUST emulate the same HTTP version (HTTP 1.1, HTTP/2, or HTTP/3) and settings chosen by the client (emulated web browser). For the HTTPS server, TLS version 1.2 or higherMUST be used with a maximum record size of 16 KB. Ticket resumption or session ID reuseMUST NOT be used for TLS 1.2; also, session ticket or session cacheMUST NOT be used for TLS 1.3. The serverMUST serve a certificate to the client. The cipher suite and key size on the server-sideMUST be configured similarly to the client-side configuration described inSection 4.3.1.4.¶
At the beginning of the test (the init phase; seeSection 4.3.4), the server endpoint initializes, and the server endpoint will be ready to accept TCP or QUIC connections as well as inbound HTTP and HTTPS requests. The client endpoints initialize and are given attributes such as a MAC and IP address. After the init phase of the test, each client sweeps through the given server IP space, generating a service recognizable by the DUT. Sequential and pseudorandom sweep methods are acceptable. The method usedMUST be stated in the final report. Thus, a balanced mesh between client endpoints and server endpoints will be generated in a client IP and port to server IP and port combination. Each client endpoint performs the same actions as other endpoints, with the difference being the source IP of the client endpoint and the target server IP pool. The clientMUST use the server IP address or FQDN in the host header.¶
Client endpoints are independent of other clients that are concurrently executing. When a client endpoint initiates traffic, this section describes how the client steps through different services. Once the test is initialized, the client endpoints randomly hold (perform no operation) for a few milliseconds for better randomization of the start of client traffic. Each client (HTTP 1.1 or HTTP/2) will either open a new TCP connection or connect to an HTTP persistent connection that is still open to that specific server. HTTP/3 clients will open UDP streams within QUIC connections. At any point that the traffic profile may require encryption, a TLS encryption tunnel will form, presenting the URL or IP address request to the server. If using SNI, the serverMUST then perform an SNI name check by comparing the proposed FQDN to the domain embedded in the certificate. Only when correct will the server process the HTTPS response object. The initial response object to the server is based on benchmarking tests described inSection 7. Multiple additional sub-URLs (response objects on the service page)MAY be requested simultaneously. ThisMAY be to the same server IP as the initial URL. Each sub-object will also use a canonical FQDN and URL path.¶
The loading of traffic is described in this section. The loading of a traffic load profile has five phases: Init, ramp up, sustain, ramp down, and collection.¶
This section describes steps for a reference test (pre-test) that controls the test environment, including test equipment, focusing on physical and virtualized environments and test equipment. Below are theRECOMMENDED steps for the reference test.¶
The reference testMUST be performed before the benchmarking tests (described inSection 7) start.¶
This section describes how the benchmarking test report should be formatted and presented. It isRECOMMENDED to include two main sections in the report: the introduction and the detailed test results sections.¶
The following attributes should be present in the introduction section of the test report.¶
Summary of testbed software and hardware details¶
DUT/SUT hardware/virtual configuration¶
DUT/SUT software¶
DUT-/SUT-enabled features¶
Test equipment hardware and software¶
Key test parameters¶
Details of the application traffic mix used in the benchmarking testThroughput Performance with Application Traffic Mix (Section 7.1)¶
Results Summary / Executive Summary¶
In the results section of the test report, the following attributes should be present for each benchmarking test.¶
This section lists key performance indicators (KPIs) for overall benchmarking tests. All KPIsMUST be measured during the sustain phase of the traffic load profile described inSection 4.3.4. Also, the KPIsMUST be measured from the result output of test equipment.¶
The average number of successfully established QUIC connections per second between hosts across the DUT/SUT. As described inSection 4.3.1.2, the QUIC connections are initiated by clients. Then, the data is sent, and then the QUIC sessions are closed by the "immediate close" method.¶
Since the QUIC specification defined inSection 4.3.1.2 recommends disabling 0-RTT and early data, this KPI is focused on the 1-RTT handshake. If required, 0-RTT can be also measured in separate test runs while enabling 0-RTT and early data in the test equipment.¶
The average number of successfully established TLS connections per second between hosts across the DUT/SUT or between hosts and the DUT/SUT.¶
For TLS 1.3, the handshake rate can be measured with the 0-RTT or 1-RTT handshake. The transport protocol can be either TCP or QUIC.¶
This section mainly focuses on the benchmarking tests with HTTP/1.1 or HTTP/2 traffic, which uses TCP as the transport protocol. In particular, this section does not define specific benchmarking tests for KPIs related to QUIC or HTTP/3. However, the test methodology defined in the benchmarking testsTCP or QUIC connections per second with HTTPS traffic (Section 7.6),HTTPS transaction latency (Section 7.8),HTTPS throughput (Section 7.7), andconcurrent TCP or QUIC connection capacity with HTTPS traffic (Section 7.9) can be used to test KPIs related to QUIC or HTTP/3. The throughput performance test with the application traffic mix defined inSection 7.1 can be performed with any other application traffic, including HTTP/3.¶
Using a relevant application traffic mix, determine the sustainable inspected throughput supported by the DUT/SUT.¶
Based on the test customer's specific use case, testers can choose the relevant application traffic mix for this test. The details about the traffic mixMUST be documented in the report. At least, the following traffic mix detailsMUST be documented and reported together with the test results:¶
The testbed setupMUST be configured as defined inSection 4. Any benchmarking-test-specific testbed configuration changesMUST be documented.¶
In this section, the benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented. If the DUT/SUT is configured without TLS inspection, the test reportMUST explain how this impacts the encrypted traffic of the relevant application traffic mix.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial throughput: 10% of the "Target inspected throughput"¶
Note: Initial throughput is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.1.4.¶
This testMUST be run with a relevant application traffic mix profile.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
The following KPI metricsMUST be reported for this benchmarking test:¶
Mandatory KPIs (benchmarks): inspected throughput and application transactions per second¶
Note: The TTLBMUST be reported along with the object size used in the traffic profile.¶
The test procedures are designed to measure the inspected throughput performance of the DUT/SUT at the sustaining period of the traffic load profile. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (initial throughput) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IP types: IPv4 only, IPv6 only, and IPv4 and IPv6 mixed traffic distribution.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to generate test traffic at the "initial throughput" rate, as described inSection 7.1.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4. The DUT/SUTMUST reach the "initial throughput" during the sustain phase. Measure all KPIs, as defined inSection 7.1.3.5. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.1.3.4.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to generate traffic at the "Target inspected throughput" rate defined inSection 7.1.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4. The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective ("Target inspected throughput") in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable average inspected throughput within the test results validation criteria. The final test iterationMUST be performed for the test duration defined inSection 4.3.4.¶
Using HTTP traffic, determine the sustainable TCP connection establishment rate supported by the DUT/SUT under different throughput load conditions.¶
To measure connections per second, test iterationsMUST use different fixed HTTP response object sizes (the different load conditions) defined inSection 7.2.3.2.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial connections per second: 10% of "Target connections per second"¶
Note: Initial connections per second is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.2.4.¶
The clientMUST negotiate HTTP and close the connection with FIN immediately after the completion of one transaction. In each test iteration, the clientMUST send a GET request requesting a fixed HTTP response object size.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
TCP connections per secondMUST be reported for each test iteration (for each object size).¶
The test procedure is designed to measure the DUT/SUT's rate of TCP connections per second during the sustaining period of the traffic load profile. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (Initial connections per second) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IP types: IPv4 only, IPv6 only, and IPv4 and IPv6 mixed traffic distribution.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish "Initial connections per second", as defined inSection 7.2.3.2. The traffic load profileMUST be defined as described inSection 4.3.4.¶
The DUT/SUTMUST reach the "Initial connections per second" before the sustain phase. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.2.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT continue to Step 2.¶
Configure test equipment to establish the target objective ("Target connections per second") defined inSection 7.2.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4.¶
During the ramp up and sustain phases of each test iteration, other KPIs, such as inspected throughput, concurrent TCP connections, and application transactions per second,MUST NOT reach the maximum value the DUT/SUT can support. The test results for specific test iterationsMUST NOT be reported as valid results if the abovementioned KPI (especially inspected throughput) reaches the maximum value. (For example, if the test iteration with 64 KB of HTTP response object size reached the maximum inspected throughput limitation of the DUT/SUT, the test iterationMAY be interrupted and the result for 64 KB must not be reported.)¶
The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective ("Target connections per second") in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable TCP connections per second within the test results validation criteria.¶
Determine the sustainable inspected throughput of the DUT/SUT for HTTP transactions varying the HTTP response object size.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial throughput: 10% of "Target inspected throughput"¶
Note: Initial throughput is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.3.4.¶
| Object size (KB) | Number of requests / Weight |
|---|---|
| 0.2 | 1 |
| 6 | 1 |
| 8 | 1 |
| 9 | 1 |
| 10 | 1 |
| 25 | 1 |
| 26 | 1 |
| 35 | 1 |
| 59 | 1 |
| 347 | 1 |
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
Inspected throughput and HTTP transactions per secondMUST be reported for each object size.¶
The test procedure is designed to measure HTTP throughput of the DUT/ SUT. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (initial throughput) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions and HTTP response object sizes.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish "initial throughput", as defined inSection 7.3.3.2.¶
The traffic load profileMUST be defined as described inSection 4.3.4. The DUT/SUTMUST reach the "initial throughput" during the sustain phase. Measure all KPIs, as defined inSection 7.3.3.4.¶
The measured KPIs during the sustain phaseMUST meet the test results validation criteria "a" defined inSection 7.3.3.3. The test results validation criteria "b" and "c" areOPTIONAL for Step 1.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objective ("Target inspected throughput") defined inSection 7.3.3.2. The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable inspected throughput within the test results validation criteria and measure the KPI metric transactions per second. The final test iterationMUST be performed for the test duration defined inSection 4.3.4.¶
Using HTTP traffic, determine the HTTP transaction latency when the DUT is running with sustainable HTTP transactions per second supported by the DUT/SUT under different HTTP response object sizes.¶
Test iterationsMUST be performed with different HTTP response object sizes in two different scenarios: one with a single transaction and the other with multiple transactions within a single TCP connection. For consistency, both the single and multiple transaction testsMUST be configured with the same HTTP version.¶
Scenario 1: The clientMUST negotiate HTTP and close the connection with FIN immediately after the completion of a single transaction (GET and RESPONSE).¶
Scenario 2: The clientMUST negotiate HTTP and close the connection with FIN immediately after the completion of 10 transactions (GET and RESPONSE) within a single TCP connection.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial objective for scenario 2: 10% of "Target objective for scenario 2"¶
Note: The initial objectives are not KPIs to report. These values are configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.4.4.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
The TTFB (minimum, average, and maximum) and TTLB (minimum, average, and maximum)MUST be reported for each object size.¶
The test procedure is designed to measure the TTFB or TTLB when the DUT/SUT is operating close to 50% of its maximum achievable connections per second or inspected throughput. The test procedure consists of two major steps. Step 1 ensures the DUT/SUT is able to reach the initial performance values and meets the test results validation criteria when it was very minimally utilized. Step 2 measures the latency values within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IP types (IPv4 only, IPv6 only, and IPv4 and IPv6 mixed traffic distribution), HTTP response object sizes, and single and multiple transactions per connection scenarios.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish the initial objectives, as defined inSection 7.4.3.2. The traffic load profileMUST be defined as described inSection 4.3.4.¶
The DUT/SUTMUST reach the initial objectives before the sustain phase. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.4.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objectives defined inSection 7.4.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4.¶
The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUTMUST reach the desired value of the target objective in the sustain phase.¶
Measure the minimum, average, and maximum values of the TTFB and TTLB.¶
Determine the number of concurrent TCP connections that the DUT/SUT sustains when using HTTP traffic.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be noted for this benchmarking test:¶
Initial concurrent connection: 10% of "Target concurrent connection"¶
Note: Initial concurrent connection is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.5.4.¶
The clientMUST negotiate HTTP, and each clientMAY open multiple concurrent TCP connections per server endpoint IP.¶
Each client sends 10 GET requests requesting 1 KB HTTP response object in the same TCP connection (10 transactions / TCP connections), and the delay (think time) between each transactionMUST be X seconds, where X is as follows.¶
X = ("Ramp up time" + "steady state time") / 10¶
The established connectionsMUST remain open until the ramp down phase of the test. During the ramp down phase, all connectionsMUST be successfully closed with FIN.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
Average concurrent TCP connectionsMUST be reported for this benchmarking test.¶
The test procedure is designed to measure the concurrent TCP connection capacity of the DUT/SUT at the sustaining period of the traffic load profile. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (Initial concurrent connection) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure test equipment to establish "Initial concurrent connections" defined inSection 7.5.3.2. Except ramp up time, the traffic load profileMUST be defined as described inSection 4.3.4.¶
During the sustain phase, the DUT/SUTMUST reach the "Initial concurrent connections". The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.5.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objective ("Target concurrent TCP connections"). The test equipmentMUST follow the traffic load profile definition (except ramp up time) as described inSection 4.3.4.¶
During the ramp up and sustain phases, the other KPIs, such as inspected throughput, TCP connections per second, and application transactions per second,MUST NOT reach the maximum value the DUT/SUT can support.¶
The test equipmentMUST start to measure and record KPIs defined inSection 7.5.3.4. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable concurrent TCP connections capacity within the test results validation criteria.¶
Using HTTPS traffic, determine the sustainable TLS session establishment rate supported by the DUT/SUT under different throughput load conditions.¶
Test iterationsMUST include common cipher suites and key strengths, as well as forward-looking stronger keys. Specific test iterationsMUST include ciphers and keys defined inSection 7.6.3.2.¶
For each cipher suite and key strength, test iterationsMUST use a single HTTPS response object size defined inSection 7.6.3.2 to measure connections per second performance under a variety of DUT/SUT security inspection load conditions.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial connections per second: 10% of "Target connections per second"¶
Note: Initial connections per second is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.6.4.)¶
The clientMUST negotiate HTTPS and close the connection without error immediately after the completion of one transaction. In each test iteration, the clientMUST send a GET request requesting a fixed HTTPS response object size.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole test duration.¶
If HTTP 1.1 or HTTP/2 is used, TCP connections per secondMUST be reported for each test iteration (for each object size).¶
If HTTP/3 is used, QUIC connections per secondMUST be measured and reported for each test iteration (for each object size).¶
The KPI metric TLS handshake rate can be measured in the test using 1 KB object size.¶
The test procedure is designed to measure the DUT/SUT's rate of TCP or QUIC connections per second during the sustaining period of the traffic load profile. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (Initial connections per second) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish "Initial connections per second", as defined inSection 7.6.3.2. The traffic load profileMUST be defined as described inSection 4.3.4.¶
The DUT/SUTMUST reach the "Initial connections per second" before the sustain phase. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.6.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish "Target connections per second", as defined inSection 7.6.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4.¶
During the ramp up and sustain phases, other KPIs, such as inspected throughput, concurrent TCP or QUIC connections, and application transactions per second,MUST NOT reach the maximum value the DUT/SUT can support. The test results for the specific test iterationMUST NOT be reported as valid results if the abovementioned KPI (especially inspected throughput) reaches the maximum value. (For example, if the test iteration with 64 KB of HTTPS response object size reached the maximum inspected throughput limitation of the DUT, the test iterationMAY be interrupted, and the result for 64 KB should not be reported).¶
The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective ("Target connections per second") in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable connections per second within the test results validation criteria.¶
Determine the sustainable inspected throughput of the DUT/SUT for HTTPS transactions by varying the HTTPS response object size.¶
Test iterationsMUST include common cipher suites and key strengths, as well as forward-looking stronger keys. Specific test iterationsMUST include the ciphers and keys defined inSection 7.7.3.2.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial throughput: 10% of "Target inspected throughput"¶
Note: Initial throughput is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.7.4.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
Inspected throughput and HTTPS transactions per secondMUST be reported for each object size.¶
The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (initial throughput) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions and HTTPS response object sizes.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish "initial throughput", as defined inSection 7.7.3.2.¶
The traffic load profileMUST be defined as described inSection 4.3.4. The DUT/SUTMUST reach the "initial throughput" during the sustain phase. Measure all KPIs, as defined inSection 7.7.3.4.¶
The measured KPIs during the sustain phaseMUST meet the test results validation criteria "a" defined inSection 7.7.3.3. The test results validation criteria "b" and "c" areOPTIONAL for Step 1.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objective ("Target inspected throughput") defined inSection 7.7.3.2. The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable average inspected throughput within the test results validation criteria. The final test iterationMUST be performed for the test duration defined inSection 4.3.4.¶
Using HTTPS traffic, determine the HTTPS transaction latency when the DUT/SUT is running with sustainable HTTPS transactions per second supported by the DUT/SUT under different HTTPS response object sizes.¶
Scenario 1: The clientMUST negotiate HTTPS and close the connection immediately after the completion of a single transaction (GET and RESPONSE).¶
Scenario 2: The clientMUST negotiate HTTPS and close the connection immediately after the completion of 10 transactions (GET and RESPONSE) within a single TCP or QUIC connection.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial objective for scenario 2: 10% of "Target objective for scenario 2"¶
Note: The initial objectives are not KPIs to report. These values are configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.8.4.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
The TTFB (minimum, average, and maximum) and TTLB (minimum, average, and maximum)MUST be reported for each object size.¶
The test procedure is designed to measure the TTFB or TTLB when the DUT/SUT is operating close to 50% of its maximum achievable connections per second or inspected throughput. The test procedure consists of two major steps. Step 1 ensures the DUT/SUT is able to reach the initial performance values and meets the test results validation criteria when it is very minimally utilized. Step 2 measures the latency values within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IP types (IPv4 only, IPv6 only, and IPv4 and IPv6 mixed traffic distribution), HTTPS response object sizes, and single and multiple transactions per connection scenarios.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure the traffic load profile of the test equipment to establish the initial objectives, as defined inSection 7.8.3.2. The traffic load profileMUST be defined as described inSection 4.3.4.¶
The DUT/SUTMUST reach the initial objectives before the sustain phase. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inSection 7.8.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objectives defined inSection 7.8.3.2. The test equipmentMUST follow the traffic load profile definition described inSection 4.3.4.¶
The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUTMUST reach the desired value of the target objective in the sustain phase.¶
Measure the minimum, average, and maximum values of the TTFB and TTLB.¶
Determine the number of concurrent TCP or QUIC connections the DUT/SUT sustains when using HTTPS traffic.¶
The testbed setupMUST be configured as defined inSection 4. Any specific testbed configuration changes (number of interfaces, interface type, etc.)MUST be documented.¶
In this section, benchmarking-test-specific parameters are defined.¶
DUT/SUT parametersMUST conform to the requirements defined inSection 4.2. Any configuration changes for this specific benchmarking testMUST be documented.¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The following parametersMUST be documented for this benchmarking test:¶
Initial concurrent connections: 10% of "Target concurrent connections"¶
Note: Initial concurrent connections is not a KPI to report. This value is configured on the traffic generator and used to perform Step 1 (Test Initialization and Qualification) described inSection 7.9.4.¶
The clientMUST perform HTTPS transactions with persistence, and each client can open multiple concurrent connections per server endpoint IP.¶
Each client sends 10 GET requests requesting 1 KB HTTPS response objects in the same TCP or QUIC connections (10 transactions/connections), and the delay (think time) between each transactionMUST be X seconds, where X is as follows.¶
X = ("Ramp up time" + "steady state time") / 10¶
The established connectionsMUST remain open until the ramp down phase of the test. During the ramp down phase, all connectionsMUST be successfully closed with FIN.¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole sustain phase of the traffic load profile.¶
Average concurrent TCP or QUIC connectionsMUST be reported for this benchmarking test.¶
The test procedure is designed to measure the concurrent TCP connection capacity of the DUT/SUT at the sustaining period of the traffic load profile. The test procedure consists of three major steps. Step 1 ensures the DUT/SUT is able to reach the performance value (Initial concurrent connection) and meets the test results validation criteria when it was very minimally utilized. Step 2 determines whether the DUT/SUT is able to reach the target performance value within the test results validation criteria. Step 3 determines the maximum achievable performance value within the test results validation criteria.¶
This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions.¶
Verify the link status of all connected physical interfaces. All interfaces are expected to be in "UP" status.¶
Configure test equipment to establish "Initial concurrent connections" defined inSection 7.9.3.2. Except ramp up time, the traffic load profileMUST be defined as described inSection 4.3.4.¶
During the sustain phase, the DUT/SUTMUST reach the "Initial concurrent connections". The measured KPIs during the sustain phaseMUST meet the test results validation criteria "a" and "b" defined inSection 7.9.3.3.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
Configure test equipment to establish the target objective ("Target concurrent connections"). The test equipmentMUST follow the traffic load profile definition (except ramp up time) described inSection 4.3.4.¶
During the ramp up and sustain phases, the other KPIs, such as inspected throughput, TCP or QUIC connections per second, and application transactions per second,MUST NOT reach the maximum value that the DUT/SUT can support.¶
The test equipmentMUST start to measure and record KPIs defined inSection 7.9.3.4. Continue the test until all traffic profile phases are completed.¶
Within the test results validation criteria, the DUT/SUT is expected to reach the desired value of the target objective in the sustain phase. Follow Step 3 if the measured value does not meet the target value or does not fulfill the test results validation criteria.¶
Determine the achievable concurrent TCP or QUIC connections within the test results validation criteria.¶
This document makes no specific request of IANA.¶
IANA has assigned IPv4 and IPv6 address blocks in[RFC6890] that have been registered for special purposes. The IPv6 address block 2001:2::/48 has been allocated for the purpose of IPv6 benchmarking[RFC5180], and the IPv4 address block 198.18.0.0/15 has been allocated for the purpose of IPv4 benchmarking[RFC2544]. This assignment was made to minimize the chance of conflict in case a testing device were to be accidentally connected to the part of the Internet.¶
The primary goal of this document is to provide benchmarking terminology and methodology for next-generation network security devices for use in a laboratory-isolated test environment. However, readers should be aware that there is some overlap between performance and security issues. Specifically, the optimal configuration for network security device performance may not be the most secure, and vice versa. Testing security platforms with working exploits and malware carries risks. Ensure proper access controls are implemented to prevent unintended exposure to vulnerable networks or systems. The cipher suites recommended in this document are for test purposes only. The cipher suite recommendation for a real deployment is outside the scope of this document.¶
Security assessment of an NGFW/NGIPS product could also include an analysis whether any type of uncommon traffic characteristics would have a significant impact on performance. Such performance impacts would allow an attacker to use such specifically crafted traffic as a DoS attack to reduce the remaining performance available to other traffic through the NGFW/NGIPS. Such uncommon traffic characteristics might include, for example, IP-fragmented traffic, a specific type of application traffic, or uncommonly high HTTP transaction rate traffic.¶
This test methodology verifies the DUT/SUT is able to detect, prevent, and report the vulnerabilities.¶
In this test, background test traffic will be generated to utilize the DUT/SUT. In parallel, some malicious traffic will be sent to the DUT/SUT as encrypted and cleartext payload formats using a traffic generator.Section 4.2.1 defines the selection of the malicious traffic from the Common Vulnerabilities and Exposures (CVEs) list for testing.¶
The following KPIs are measured in this test:¶
The same testbedMUST be used for security effectiveness tests and for benchmarking test cases defined inSection 7.¶
In this section, the benchmarking-test-specific parameters are defined.¶
DUT/SUT configuration parametersMUST conform to the requirements defined inSection 4.2. The same DUT configurationMUST be used for the security effectiveness test and for benchmarking test cases defined inSection 7. The DUT/SUTMUST be configured in "Inline" mode, all detected attack trafficMUST be dropped, and the sessionMUST be reset¶
Test equipment configuration parametersMUST conform to the requirements defined inSection 4.3. The same client and server IP rangesMUST be configured as used in the benchmarking test cases. In addition, the following parametersMUST be documented for this benchmarking test:¶
The following criteria are the test results validation criteria. The test results validation criteriaMUST be monitored during the whole test duration.¶
The following KPI metricsMUST be reported for this test scenario:¶
Mandatory KPIs:¶
Blocked CVEs: TheyMUST be represented in the following ways:¶
Unblocked CVEs: TheyMUST be represented in the following ways:¶
Background traffic behavior: ItMUST be represented in one of the followings ways:¶
Optional KPIs:¶
The test procedure is designed to measure the security effectiveness of the DUT/SUT at the sustaining period of the traffic load profile. The test procedure consists of two major steps. This test procedureMAY be repeated multiple times with different IPv4 and IPv6 traffic distributions.¶
Generate background traffic at the transmission rate defined inAppendix A.3.2.¶
The DUT/SUTMUST reach the target objective (HTTP(S) throughput) in the sustain phase. The measured KPIs during the sustain phaseMUST meet all the test results validation criteria defined inAppendix A.4.¶
If the KPI metrics do not meet the test results validation criteria, the test procedureMUST NOT be continued to Step 2.¶
While generating background traffic (in the sustain phase), send the CVE traffic, as defined in the parameter section (Appendix A.3.2).¶
The test equipmentMUST start to measure and record all specified KPIs. Continue the test until all CVEs are sent.¶
The measured KPIsMUST meet all the test results validation criteria defined inAppendix A.4.¶
In addition, the DUT/SUT should report the detected vulnerabilities in the log correctly, or thereMUST be reference material available that will allow for verification that the correct vulnerability was detected if, for example, a different naming convention is used. This reference materialMUST be cited in the report.¶
This document aims to classify the DUT/SUT into four different categories based on its maximum-supported firewall throughput performance number defined in the vendor datasheet. This classificationMAY help users to determine specific configuration scales (e.g., number of ACL entries), traffic profiles, and attack traffic profiles, scaling those proportionally to the DUT/SUT sizing category.¶
The four different categories are Extra Small (XS), Small (S), Medium (M), and Large (L). TheRECOMMENDED throughput values for the following categories are:¶
The authors wish to acknowledge the members of NetSecOPEN for their participation in the creation of this document. Additionally, the following members need to be acknowledged:¶
Anand Vijayan,Chris Marshall,Jay Lindenauer,Michael Shannon,Mike Deichman,Ryan Riese, andToulnay Orkun.¶
The following individuals contributed significantly to the creation of this document:¶
Alex Samonte,Amritam Putatunda,Aria Eslambolchizadeh,Chao Guo,Chris Brown,Cory Ford,David DeSanto,Jurrie Van Den Breekel,Michelle Rhines,Mike Jack,Ryan Liles,Samaresh Nair,Stephen Goudreault,Tim Carlin, andTim Otto.¶