Enabling On-demand Query Result Caching in DotSlash for Handling Web Hotspots Effectively

Zhao, Weibin; Schulzrinne, Henning

doi:10.1109/hotweb.2006.355257

Cited by 6 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SIP overload falls into the broader category of application server overload where, in particular, web server overload control [7,12,48] has been studied extensively. Although most of the work on web server overload control uses a request-based workload model, Cherkasova and Phaal [6] presented a study using session-based workload, which is closer to our SIP overload study.…”

Section: Related Workmentioning

confidence: 99%

On TCP-based SIP server overload control

Shen

Schulzrinne

2010

Principles, Systems and Applications of IP Telecommunications

Self Cite

View full text Add to dashboard Cite

The Session Initiation Protocol (SIP) server overload management has attracted interest since SIP is being widely deployed in the Next Generation Networks (NGN) as a core signaling protocol. Yet all existing SIP overload control work is focused on SIP-over-UDP, despite the fact that TCP is increasingly seen as the more viable choice of SIP transport. This paper answers the following questions: is the existing TCP flow control capable of handling the SIP overload problem? If not, why and how can we make it work? We provide a comprehensive explanation of the default SIP-over-TCP overload behavior through server instrumentation. We also propose and implement novel but simple overload control algorithms without any kernel or protocol level modification. Experimental evaluation shows that with our mechanism the overload performance improves from its original zero throughput to nearly full capacity. Our work leads to the important general insight that the traditional notion of TCP flow control alone is incapable of managing overload for time-critical session-based applications, which would be applicable not only to SIP, but also to a wide range of other common applications such as database servers.

show abstract

Section: Related Workmentioning

confidence: 99%

On TCP-based SIP server overload control

Shen

Schulzrinne

2010

Principles, Systems and Applications of IP Telecommunications

Self Cite

View full text Add to dashboard Cite

show abstract

“…These systems typically cache (fragments of) the generated pages [7], distribute the computation across multiple application servers [1,23] or cache the results of database queries [2,4,19,27,30]. However, although these techniques can be very effective depending on the application, in many cases their ultimate scalability bottleneck resides in the throughput of the origin database where the authoritative version of the application state is stored.…”

Section: Www 2007mentioning

confidence: 99%

“…To remove this bottleneck, various techniques have been proposed to cache the results of database queries at the edge servers [2,4,19,27,30]. Consistency of cached results must also be maintained when the underlying database is updated.…”

Section: Background and Related Workmentioning

confidence: 99%

Globetp

Groothuyse

Sivasubramanian

Pierre

2007

Proceedings of the 16th International Conference on World Wide Web

View full text Add to dashboard Cite

Generic database replication algorithms do not scale linearly in throughput as all update, deletion and insertion (UDI) queries must be applied to every database replica. The throughput is therefore limited to the point where the number of UDI queries alone is sufficient to overload one server. In such scenarios, partial replication of a database can help, as UDI queries are executed only by a subset of all servers. In this paper we propose GlobeTP, a system that employs partial replication to improve database throughput. Glo-beTP exploits the fact that a Web application's query workload is composed of a small set of read and write templates. Using knowledge of these templates and their respective execution costs, GlobeTP provides database table placements that produce significant improvements in database throughput. We demonstrate the efficiency of this technique using two different industry standard benchmarks. In our experiments, GlobeTP increases the throughput by 57% to 150% compared to full replication, while using identical hardware configuration. Furthermore, adding a single query cache improves the throughput by another 30% to 60%.

show abstract

“…The DotSlash framework by Zhao and Schulzrinne [52,53] is another academic project that adopts a dynamic script replication technique to manage dynamic content. DotSlash was not designed for large-scale CDNs, but it rather provides a system to handle sudden load spikes that affect the performance of Web sites through the dynamic provisioning of rescue servers which act as caching proxies.…”

Section: Application Layer Replicationmentioning

confidence: 99%

“…Recently, the idea of dynamically replicating the back-end tier using a query cache to improve scalability has been proposed. For example, the QCache module of the DotSlash framework [53] proposes an agreement of cooperating Web sites that can temporarily enable a distributed query cache facility to alleviate the overload conditions in case of unexpected traffic surges.…”

Section: Content Blind Cachingmentioning

confidence: 99%