Web Server Load Balancing/Scheduling

1. Web Server Load Balancing/Scheduling Asima Silva Tim Sutherland

2. Outline • Web Server Introduction • Information Management Basics • Load Sharing Policies • FLEX • WARD • EquiLoad • AdaptLoad • Summary • Conclusions • Future Work

3. Request enters a router Load balancing server determines which web server should serve the request Sends the request to the appropriate web server Request Response Web Servers Introduction to Web Server Load Balancing Internet Router Load-Balancing Server Traditional Web Cluster

4. Content Server Farm How do we split up information? ?

5. Replication Information Strategies Partition

6. Load Balancing Approaches

7. Issues • Efficiently processing requests with optimizations for load balancing • Send and process requests to a web server that has files in cache • Send and process requests to a web server with the least amount of requests • Send and process requests to a web server determined by the size of the request

8. FLEX • Locality aware load-balancing strategy based on two factors: • Accessed files, memory requirements • Access rates (working set), load requirements • Partitions all servers into equally balanced groups • Each server transfers the response to the browser to reduce bottleneck through the router (TCP Handoff)

9. Flex Diagram S1 S2 Requests Forwards Request S3 S4 To Client Browser S5 S6 W(S1) ≈ W(S2) ≈ W(S3) ≈ … ≈ W(S6) Ar(S1) ≈ Ar(S2) ≈ Ar(S3) ≈ … ≈ Ar(S6)

10. FLEX Cont. • Advantages: • Highly scalable • Reduces bottleneck by the load balancer • No software is required • Reduces number of cache misses

11. FLEX Cont. II • Disadvantages: • Not dynamic, routing tale must be recreated • Only compared to RR • Number of access logs required on each server could be tremendous • Responsibility of load-balancing and transferring response is given to web servers – unorganized responsibility • How often to update access rates and working sets? Monitor?

12. WARD • Workload-Aware Request Distribution Strategy • Server core are essential files that represent majority of expected requests • Server core is replicated at every server • Ward-analysis computes the nearly optimal core size determined by workload access patterns • Number of nodes • Node RAM • TCP handoff overhead • Disk access overhead

13. Distributor Server Server Dispatcher Switch Distributor Server Dispatcher Front End Front End Distributor Server Server LAN LAN WARD Cont. • Three components: dispatcher (load balancer), distributor (router), web server • Three progressive architectures: WARD CARD LARD Dispatcher Distributor Server Switch Front End Dispatcher Distributor Server LAN Single front-end distributor, centralized dispatcher Co-located distributor and server Co-located distributor, server, and dispatcher

14. WARD Diagram S1 S2 S3 Queue: Queue: Requests Queue: S4 Queue: S5 S6 • Each computer is a distributor • and a dispatcher Queue: Queue:

15. WARD Cont. II • Similar to FLEX, sends response directly to client • Minimizes forwarding overhead from handoffs for the most frequent files • Optimizes the overall cluster RAM usage • “by mapping a small set of most frequent files to be served by multiple number of nodes, we can improve both locality of accesses and the cluster performance significantly”

16. WARD Cont. III • Advantages: • No decision making, core files are replicated on every server • Minimizes transfer of requests and disk reads, both are “equally bad” • Outperforms Round Robin • Efficient use of RAM • Performance gain with increased number of nodes

17. WARD Cont. IV • Disadvantages: • Core files are created on past day’s data, could decrease performance up to 15% • Distributed dispatcher increases the number of TCP requests transfers • If core files not selected correctly, higher cache miss rate and increased disk accesses

18. WARD Results

19. EquiLoad • Determines which server will process a request determined by the size of the requested file • Splits the content on each server by file size, forcing the queues sizes to be consistent.

20. EquiLoad Solves Queue Length Problems • This is bad Queue Queue • This is better Queue Queue

21. EquiLoad Diagram S1 S2 1k-2k Requests 2k-3k Forwards Request S3 S4 3k-10k 10k-20k To Client Browser S5 S6 20k-100k >100k

22. EquiLoad • Advantages • Dynamic repartitioning • Can be implemented at various levels • DNS • Dispatcher • Server • Minimum queue buildup • Performs well under variable workload and high system load

23. EquiLoad • Disadvantages • Cache affinity is neglected • Requires a front end dispatcher • Distributor must communicate with servers • Thresholds of parameter adjustment

24. EquiLoad  AdaptLoad • AdaptLoad improves upon EquiLoad using “fuzzy boundaries” • Allows for multiple servers to process a request • Behaves better in situations where server partitions are very close in size

25. AdaptLoad Diagram S1 S2 1k-3k Requests 2k-4k Forwards Request S3 S4 3k-10k 8k-20k To Client Browser S5 S6 15k-100k >80k

26. AdaptLoad Results

27. Summary FLEX EquiLoad, AdaptLoad WARD

28. Conclusions • There is no “best” way to distribute content among servers. • There is no optimal policy for all website applications. • Certain strategies are geared towards a particular website application.

29. Future Work • Compare and contrast the three policies • Figure out how often nodes should be repartitioned • Compare each policy to a standard benchmark • Figure out which policy works in a particular environment

30. Questions? • Anyone have one?