documentation:examples:ipsec_performance_of_a_netgate_rcc-ve_4860
no way to compare when less than two revisions
Differences
This shows you the differences between two versions of the page.
Next revision | |||
— | documentation:examples:ipsec_performance_of_a_netgate_rcc-ve_4860 [2017/09/04 01:23] – external edit 127.0.0.1 | ||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ====== IPSec performance lab of Netgate RCC-VE 4860 ====== | ||
+ | {{description> | ||
+ | ===== Hardware detail ====== | ||
+ | |||
+ | This lab will test a [[http:// | ||
+ | * Quad cores Intel Atom C2558 (2.40GHz) | ||
+ | * AES-NI supporting AES-CBC, | ||
+ | * 2 Gigabit Intel i211 | ||
+ | * 4 Gigabit Intel i350 | ||
+ | * 8Gb of RAM | ||
+ | ===== Method used ===== | ||
+ | |||
+ | The benchmarking method used here is detailed in [[documentation: | ||
+ | |||
+ | ==== Diagram ==== | ||
+ | |||
+ | < | ||
+ | +---------------------+ | ||
+ | | R1 | ||
+ | | | ||
+ | | and receiver | ||
+ | | | ||
+ | |igb2: 198.18.0.201/ | ||
+ | | | ||
+ | | 00: | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | | | ||
+ | |igb3: 198.19.0.201/ | ||
+ | |2001: | ||
+ | | | ||
+ | +---------------------+ | ||
+ | || || | ||
+ | ==================================< | ||
+ | </ | ||
+ | ===== Devices configuration ===== | ||
+ | |||
+ | |||
+ | |||
+ | ==== Netgate (DUT) ==== | ||
+ | |||
+ | Configure IP address, routes and static IPSec: | ||
+ | |||
+ | < | ||
+ | # IPv4 router | ||
+ | gateway_enable=" | ||
+ | ifconfig_igb2=" | ||
+ | ifconfig_igb3=" | ||
+ | static_routes=" | ||
+ | route_generator=" | ||
+ | route_receiver=" | ||
+ | static_arp_pairs=" | ||
+ | static_arp_generator=" | ||
+ | static_arp_receiver=" | ||
+ | |||
+ | # IPv6 router | ||
+ | ipv6_gateway_enable=" | ||
+ | ipv6_activate_all_interfaces=" | ||
+ | ifconfig_igb2_ipv6=" | ||
+ | ifconfig_igb3_ipv6=" | ||
+ | ipv6_static_routes=" | ||
+ | ipv6_route_generator=" | ||
+ | ipv6_route_receiver=" | ||
+ | static_ndp_pairs=" | ||
+ | static_ndp_generator=" | ||
+ | static_ndp_receiver=" | ||
+ | |||
+ | # Enabling IPSec | ||
+ | ipsec_enable=" | ||
+ | |||
+ | # Enabling AES-NI | ||
+ | kld_list=" | ||
+ | </ | ||
+ | |||
+ | / | ||
+ | < | ||
+ | flush; | ||
+ | spdflush; | ||
+ | spdadd 198.18.0.0/ | ||
+ | spdadd 198.19.0.0/ | ||
+ | add 198.18.1.203 198.18.1.209 esp 0x1000 -E aes-gcm-16 " | ||
+ | add 198.18.1.209 198.18.1.203 esp 0x1001 -E aes-gcm-16 " | ||
+ | spdadd 2001:2::/49 2001: | ||
+ | spdadd 2001: | ||
+ | add 2001: | ||
+ | add 2001: | ||
+ | </ | ||
+ | |||
+ | ==== R3 (Reference device) ==== | ||
+ | |||
+ | Configure IP address, routes and static IPSec. | ||
+ | / | ||
+ | |||
+ | < | ||
+ | # IPv4 router | ||
+ | gateway_enable=" | ||
+ | ifconfig_igb2=" | ||
+ | ifconfig_igb3=" | ||
+ | |||
+ | static_routes=" | ||
+ | route_generator=" | ||
+ | route_receiver=" | ||
+ | static_arp_pairs=" | ||
+ | static_arp_generator=" | ||
+ | static_arp_receiver=" | ||
+ | |||
+ | # IPv6 router | ||
+ | ipv6_gateway_enable=" | ||
+ | ipv6_activate_all_interfaces=" | ||
+ | ifconfig_igb2_ipv6=" | ||
+ | ifconfig_igb3_ipv6=" | ||
+ | |||
+ | ipv6_static_routes=" | ||
+ | ipv6_route_generator=" | ||
+ | ipv6_route_receiver=" | ||
+ | static_ndp_pairs=" | ||
+ | static_ndp_generator=" | ||
+ | static_ndp_receiver=" | ||
+ | |||
+ | # Enabling IPSec | ||
+ | kld_list=" | ||
+ | ipsec_enable=" | ||
+ | </ | ||
+ | |||
+ | / | ||
+ | |||
+ | < | ||
+ | flush; | ||
+ | spdflush; | ||
+ | spdadd 198.18.0.0/ | ||
+ | spdadd 198.19.0.0/ | ||
+ | add 198.18.1.203 198.18.1.209 esp 0x1000 -E aes-gcm-16 " | ||
+ | add 198.18.1.209 198.18.1.203 esp 0x1001 -E aes-gcm-16 " | ||
+ | spdadd 2001:2::/49 2001: | ||
+ | spdadd 2001: | ||
+ | add 2001: | ||
+ | add 2001: | ||
+ | </ | ||
+ | ===== Using IPSec bench " | ||
+ | |||
+ | Once done, we start using a fast method for measuring the "IPsec equilibrium throughput" | ||
+ | |||
+ | Notice that the reference device (IBM x3550-M3) used in front of the Netgate has a [[IPSec performance lab of an IBM System x3550 M3 with Intel 82580|equilibrium throughput of 843Mb/s]]. Then if the value measured during this bench is close to 843Mb/s we had to found a more powerful reference device. | ||
+ | |||
+ | From the packet generator/ | ||
+ | < | ||
+ | [root@R1]~# equilibrium -u -4 -d 00: | ||
+ | Benchmark tool using equilibrium throughput method | ||
+ | - Benchmark mode: Bandwitdh (bps) for VPN gateway | ||
+ | - UDP load = 500B, IPv4 packet size=528B, Ethernet frame size=542B | ||
+ | - Link rate = 1000 Mb/s | ||
+ | - Tolerance = 0.01 | ||
+ | Iteration 1 | ||
+ | - Offering load = 500 Mb/s | ||
+ | - Step = 250 Mb/s | ||
+ | - Measured forwarding rate = 399 Mb/s | ||
+ | Iteration 2 | ||
+ | - Offering load = 250 Mb/s | ||
+ | - Step = 250 Mb/s | ||
+ | - Trend = decreasing | ||
+ | - Measured forwarding rate = 250 Mb/s | ||
+ | Iteration 3 | ||
+ | - Offering load = 375 Mb/s | ||
+ | - Step = 125 Mb/s | ||
+ | - Trend = increasing | ||
+ | - Measured forwarding rate = 375 Mb/s | ||
+ | Iteration 4 | ||
+ | - Offering load = 437 Mb/s | ||
+ | - Step = 62 Mb/s | ||
+ | - Trend = increasing | ||
+ | - Measured forwarding rate = 399 Mb/s | ||
+ | Iteration 5 | ||
+ | - Offering load = 406 Mb/s | ||
+ | - Step = 31 Mb/s | ||
+ | - Trend = decreasing | ||
+ | - Measured forwarding rate = 399 Mb/s | ||
+ | Iteration 6 | ||
+ | - Offering load = 391 Mb/s | ||
+ | - Step = 15 Mb/s | ||
+ | - Trend = decreasing | ||
+ | - Measured forwarding rate = 391 Mb/s | ||
+ | Iteration 7 | ||
+ | - Offering load = 398 Mb/s | ||
+ | - Step = 7 Mb/s | ||
+ | - Trend = increasing | ||
+ | - Measured forwarding rate = 398 Mb/s | ||
+ | Estimated Equilibrium Ethernet throughput= 398 Mb/s (maximum value seen: 399 Mb/s) | ||
+ | </ | ||
+ | |||
+ | Using AES-GCM-128 and aesni kernel module loaded on the NetGate RCC-VE 4860, we can estimate an IPSec Equilibrium throughput of about 400Mb/s. | ||
+ | |||
+ | {{bench-ipsec-netgate-12head.png}} |
documentation/examples/ipsec_performance_of_a_netgate_rcc-ve_4860.txt · Last modified: 2020/09/22 12:08 by olivier