Scaling OpenShift Container Platform HAProxy Router

The OpenShift Container Platform router is the ingress point for all external traffic destined for OpenShift Container Platform services.

On an public cloud instance of size 4 vCPU/16GB RAM, a single HAProxy router is able to handle between 7000-32000 HTTP keep-alive requests depending on encryption, page size, and the number of connections used. For example, when using TLS edge or re-encryption terminations with large page sizes and a high numbers of connections, expect to see results in the lower range. With HTTP keep-alive, a single HAProxy router is capable of saturating 1 Gbit NIC at page sizes as small as 8 kB.

The table below shows HTTP keep-alive performance on such a public cloud instance with a single HAProxy and 100 routes:

Encryption Page size HTTP(s) requests per second

none

1kB

15435

none

4kB

11947

edge

1kB

7467

edge

4kB

7678

passthrough

1kB

25789

passthrough

4kB

17876

re-encrypt

1kB

7611

re-encrypt

4kB

7395

When running on bare metal with modern processors, you can expect roughly twice the performance of the public cloud instance above. This overhead is introduced by the virtualization layer in place on public clouds and holds mostly true for private cloud-based virtualization as well. The following table is a guide on how many applications to use behind the router:

Number of applications Application type

5-10

static file/web server or caching proxy

100-1000

applications generating dynamic content

In general, HAProxy can saturate about 5-1000 applications, depending on the technology in use. The number will typically be lower for applications serving only static content.

Router sharding should be used to serve more routes towards applications and help horizontally scale the routing tier.

Optimizing Network Performance

The OpenShift SDN uses OpenvSwitch, virtual extensible LAN (VXLAN) tunnels, OpenFlow rules, and iptables. This network can be tuned by using jumbo frames, network interface cards (NIC) offloads, multi-queue, and ethtool settings.

VXLAN provides benefits over VLANs, such as an increase in networks from 4096 to over 16 million, and layer 2 connectivity across physical networks. This allows for all pods behind a service to communicate with each other, even if they are running on different systems.

VXLAN encapsulates all tunneled traffic in user datagram protocol (UDP) packets. However, this leads to increased CPU utilization. Both these outer- and inner-packets are subject to normal checksumming rules to guarantee data has not been corrupted during transit. Depending on CPU performance, this additional processing overhead can cause a reduction in throughput and increased latency when compared to traditional, non-overlay networks.

Cloud, VM, and bare metal CPU performance can be capable of handling much more than one Gbps network throughput. When using higher bandwidth links such as 10 or 40 Gbps, reduced performance can occur. This is a known issue in VXLAN-based environments and is not specific to containers or OpenShift Container Platform. Any network that relies on VXLAN tunnels will perform similarly because of the VXLAN implementation.

If you are looking to push beyond one Gbps, you can:

  • Use Native Container Routing. This option has important operational caveats that do not exist when using OpenShift SDN, such as updating routing tables on a router.

  • Evaluate network plug-ins that implement different routing techniques, such as border gateway protocol (BGP).

  • Use VXLAN-offload capable network adapters. VXLAN-offload moves the packet checksum calculation and associated CPU overhead off of the system CPU and onto dedicated hardware on the network adapter. This frees up CPU cycles for use by pods and applications, and allows users to utilize the full bandwidth of their network infrastructure.

VXLAN-offload does not reduce latency. However, CPU utilization is reduced even in latency tests.

Optimizing the MTU for Your Network

There are two MTUs (maximum transmission units) that matter: the network interface card (NIC) MTU, and the SDN overlay’s MTU.

The NIC MTU must be less than or equal to the maximum supported value of the NIC of your network. If you are optimizing for throughput, pick the largest possible value. If you are optimizing for lowest latency, pick a lower value.

The SDN overlay’s MTU must be less than the NIC MTU by 50 bytes at a minimum. This accounts for the SDN overlay header. So, on a normal ethernet network, set this to 1450. On a jumbo frame ethernet network, set this to 8950.

This 50 byte overlay header is relevant to the OpenShift SDN. Other SDN solutions might require the value to be more or less.

To configure the MTU, edit the node configuration file at /etc/origin/node/node-config.yaml, and edit the following:

networkConfig:
  mtu: 1450 (1)
  networkPluginName: "redhat/openshift-ovs-subnet" (2)
1 Maximum transmission unit (MTU) for the pod overlay network.
2 Set to redhat/openshift-ovs-subnet for the ovs-subnet plug-in, redhat/openshift-ovs-multitenant for the ovs-multitenant plug-in, or redhat/openshift-ovs-networkpolicy for the ovs-networkpolicy plug-in. This can also be set to any other CNI-compatible plug-in as well.

Configuring Network Subnets

OpenShift Container Platform provides IP address management for both pods and services. The default values allow for:

  • Maximum cluster size of 1024 nodes

  • Each of the 1024 nodes has a /23 allocated to it (510 usable IPs for pods)

  • Provides 65,536 IP addresses for services.

Under most circumstances, these networks cannot be changed after deployment. Thus it is important to plan ahead for growth.

Restrictions for resizing networks are document here: Configuring SDN documentation.

If you would like to plan for a larger environment, here are some example values to consider adding to the [OSE3:vars] section in your Ansible inventory file:

[OSE3:vars]
osm_cluster_network_cidr=10.128.0.0/10

This will allow for 8192 nodes, each with 510 usable IPs.

See the supportability limits in the OpenShift Container Platform documentation for node/pod limits for the version of software you are installing.

Optimizing IPSec

Because encrypting and decrypting node hosts uses CPU power, performance is affected both in throughput and CPU usage on the nodes when encryption is enabled, regardless of the IP security system being used.

IPSec encrypts traffic at the IP level, before it hits the NIC, protecting fields that would otherwise be used for NIC offloading. This means that some NIC acceleration features may not be usable when IPSec is enabled and will lead to increased throughput and CPU usage.