North-South Load Balancing of Kubernetes Services with eBPF/XDP Martynas Pumputis (Isovalent) October 28, 2020 10.0.0.1 10.0.0.2 10.0.0.3 httpd httpd “httpd” service 10.0.0.1:30000 10.0.0.2:30000

<_ZN4CPin5resetEv>: ... 080001b0 <_ZN4CPin3setEv>: ...Dynamic Polymorphism without de-virtualization Load the vtable address in r3. 43

: push {r0, r1, r2, lr} ldr r3, [pc, #28] ; (80001e4 : 0x080001b1 0x0800025c : 0x08000199 CPin vtableDynamic Polymorphism without de-virtualization Load the address of the set method from the vtable into r3. 44

: push {r0, r1, r2, lr} ldr

Processing and Analytics Vasiliki (Vasia) Kalavri
 vkalavri@bu.edu Spring 2020 4/09: Flow control and load shedding ??? Vasiliki Kalavri | Boston University 2020 Keeping up with the producers • Producers (back-pressure, flow control) 2 ??? Vasiliki Kalavri | Boston University 2020 Load management approaches 3 ! Load shedder (a) Load shedding (b) Back-pressure (c) Elasticity Selectively drop records: Suitable for transient load increase. Scale resource allocation: • Addresses the case of increased load and additionally ensures no resources are left idle when the input load decreases. ??? Vasiliki

Discovery ................................................................................ 6 1.3.7 Load Balancing............................................................................................. an Application .....................................................26 3.3 Load Balancing using Rancher Load Balancing services ............................................27 3.4 Service Discovery needs robust cluster management capabilities that can handle scheduling, service discovery, load balancing, resource monitoring and isolation, and more. For years, Google has used a cluster manager

individual containers getting started or destroyed as the application scales out / in to adapt to load changes and during rolling updates that are deployed as part of continuous delivery. This shift toward containers causes these approaches to struggle to scale side by side with the application as load balancing tables and access control lists carrying hundreds of thousands of rules that need to be updated with cloud network routers If you are already running routing daemons Load Balancing Cilium implements distributed load balancing for traffic between application containers and to external services and

individual containers getting started or destroyed as the application scales out / in to adapt to load changes and during rolling updates that are deployed as part of continuous delivery. This shift toward containers causes these approaches to struggle to scale side by side with the application as load balancing tables and access control lists carrying hundreds of thousands of rules that need to be updated conjunction with cloud network routers If you are already running routing daemons Load balancing Distributed load balancing for traffic between application containers and to external services. The loadbalancing

individual containers getting started or destroyed as the application scales out / in to adapt to load changes and during rolling updates that are deployed as part of continuous delivery. This shift toward containers causes these approaches to struggle to scale side by side with the application as load balancing tables and access control lists carrying hundreds of thousands of rules that need to be updated with cloud network routers If you are already running routing daemons Load Balancing Cilium implements distributed load balancing for traffic between application containers and to external services and

event of server failure. Hugely flexible clustering. Create clusters of servers that know how to load balance messages. Link geographically distributed clusters over unreliable connections to form a messaging systems allow you to create groups of messaging servers called clusters. Clusters allow the load of sending and consuming messages to be spread over many servers. This allows your system to scale provides very configurable state-of-the-art clustering model where messages can be intelligently load balanced between the servers in the cluster, according to the number of consumers on each node, and

event of server failure. Hugely flexible clustering. Create clusters of servers that know how to load balance messages. Link geographically distributed clusters over unreliable connections to form a messaging systems allow you to create groups of messaging servers called clusters. Clusters allow the load of sending and consuming messages to be spread over many servers. This allows your system to scale provides very configurable state-of-the-art clustering model where messages can be intelligently load balanced between the servers in the cluster, according to the number of consumers on each node, and

event of server failure. Hugely flexible clustering. Create clusters of servers that know how to load balance messages. Link geographically distributed clusters over unreliable connections to form a messaging systems allow you to create groups of messaging servers called clusters. Clusters allow the load of sending and consuming messages to be spread over many servers. This allows your system to scale provides very configurable state-of-the-art clustering model where messages can be intelligently load balanced between the servers in the cluster, according to the number of consumers on each node, and