Implementing a Loadbalancing Web Server Using Red Hat
Implementing a Load-balancing Web Server Using Red Hat Cluster Suite Ya-Lee Tsai 2/28/2021 1
Project Goals l Building a load-balancing web server l Performance evaluation 2/28/2021 2
Steps l Setting up a working environment. l Implementing load-balancing support in the system. l Performance measurement and comparison. 2/28/2021 3
Load-balancing Web Servers l Balancing the load among the servers l Providing: – High throughput – High availability 2/28/2021 4
Two Classes of Locally Distributed Architecture for Web Sites • Cluster-based web systems • Virtual IP address • Distributed web systems • IP address visible to client applications 2/28/2021 5
Architecture of A Cluster-based Web System 2/28/2021 6
Architecture of a Distributed Web System 2/28/2021 7
System Environment l Web-serving cluster: Linux cluster l DBMS: My. SQL l Benchmarks: TPC Benchmark 2/28/2021 8
Red Hat Cluster Suite l. A cluster of systems to provide highly available web services, database servers, and other types of services l Virtual web server configuration l Using Linux virtual server (LVS) technology 2/28/2021 9
A Basic LVS Configuration 2/28/2021 10
My. SQL Database Services l Serve highly available data to applications. l My. SQL server packages are installed on each cluster system that will run the service. l Database data is accessed by all cluster members. 2/28/2021 11
TPC Benchmark l TPC defines transaction performance and database benchmarks. l TPC benchmarks measure transaction processing and database performance in terms of how many transactions a given system and a database can perform per unit time. 2/28/2021 12
TPC Benchmarks l TPC-C -- OLTP l TPC-H – decision support for AD hoc queries l TPC-W – web e-commerce l TPC-R – decision support for business reporting 2/28/2021 13
References: IBM Research Report: the State of the Art in Locally Distributed Web-Server Systems, Valeria Cardellini, Emiliano Casalicchio, Michele Colajanni l Www. redhat. Com/manuals/enterprise/RHE L-3 -manual/cluster-suite l Comparing the Memory System Performance of DSS Workloads on the HP V-class and SGI Origin 2000, Rong Yu, Laxmi Bhuyan, Ravi Iyer l Building Clustered Linux Systems, 2/28/2021 14 Robert W. Lucke l
A Synthetic Streaming Workload Generator & Evaluation of Different Streaming Techniques Reference: GISMO: A Generator of Internet Streaming Media Objects and workloads Shudong Jin and Azer Bestavros Boston University A preliminary version appears in ACM SIGMETRICS Performance Evaluation Review, November, 2001 2/28/2021 15
Workload Charateristics l Session – the service initiated by a user's request for a transfer and terminated by a user's abortion of an ongoing transfer. l Workload – Session arrivals – Properties of individual sessions 2/28/2021 16
Session arrival l Object Populariy – zipf distribution – a tendency for requests to be concentrated on a few “popular” objects l Reference locality – Heavy-tailed Pareto distribution – Temporal proximity of requests to the same objects 2/28/2021 17
Individual Session l Object Size – Lognormal distribution l User interactivity – Pareto distribution l Object encoding characteristics – Model the VBR auto-correlation of a streaming object using a self-similar process – Use a heavy-tailed marginal distribution to specify the level of burstiness of the bit rate 2/28/2021 18
Streaming Architecture 2/28/2021 19
Base server bandwidth requirments 2/28/2021 20
- Slides: 20