scispace - formally typeset
Journal ArticleDOI

Soft timers: efficient microsecond software timer support for network processing

Mohit Aron, +1 more
- 01 Aug 2000 - 
- Vol. 18, Iss: 3, pp 197-228
Reads0
Chats0
TLDR
This paper proposes and evaluates soft timers, a new operating system facility that allows the efficient scheduling of software events at agranularity down to tens of microseconds, and shows that this technique can improve the throughput of a Web server by up to 25%.
Abstract: 
This paper proposes and evaluates soft timers, a new operating system facility that allows the efficient scheduling of software events at agranularity down to tens of microseconds. Soft timers can be used to avoid interrupts and reduce context switches associated with network processing, without sacrificing low communication delays. More specifically, soft timers enable transport protocols like TCP to efficiently perform rate-based clocking of packet transmissions. Experiments indicate that soft timers allow a server to employ rate-based clocking with little CPU overhead (2-6%) at high aggregate bandwidths. Soft timers can also be used to perform network polling, which eliminates network interrupts and increases the memory access locality of the network subsystem without sacrificing delay. Experiments show that this technique can improve the throughput of a Web server by up to 25%.

read more

Citations
More filters
Proceedings ArticleDOI

Safe and effective fine-grained TCP retransmissions for datacenter communication

TL;DR: This paper uses high-resolution timers to enable microsecond-granularity TCP timeouts and shows that eliminating the minimum retransmission timeout bound is safe for all environments, including the wide-area.
Proceedings ArticleDOI

Improving dynamic voltage scaling algorithms with PACE

TL;DR: This paper addresses algorithms for dynamically varying CPU speed and voltage in order to save energy, and refers to the approach as PACE (Processor Acceleration to Conserve Energy) since the resulting schedule increases speed as the task progresses.
Proceedings Article

Measurement and analysis of TCP throughput collapse in cluster-based storage systems

TL;DR: This paper analyzes this Incast problem, explores its sensitivity to various system parameters, and examines the effectiveness of alternative TCP- and Ethernet-level strategies in mitigating the TCP throughput collapse.
Proceedings ArticleDOI

FlexSC: flexible system call scheduling with exception-less system calls

TL;DR: FlexSC, an implementation of exceptionless system calls in the Linux kernel, and an accompanying user-mode thread package (Flex SC-Threads), binary compatible with POSIX threads, that translates legacy synchronous system calls into exception-less ones transparently to applications are presented.
Proceedings ArticleDOI

System noise, OS clock ticks, and fine-grained parallel applications

TL;DR: This work identifies a major source of noise to be indirect overhead of periodic OS clock interrupts ("ticks"), that are used by all general-purpose OSs as a means of maintaining control, and suggests replacing ticks with an alternative mechanism the authors call "smart timers".
References
More filters
Journal ArticleDOI

TCP Vegas: end to end congestion avoidance on a global Internet

TL;DR: The three key techniques employed by Vegas are described, and the results of a comprehensive experimental performance study, using both simulations and measurements on the Internet, of the Vegas and Reno implementations of TCP are presented.
Proceedings ArticleDOI

End-to-end Internet packet dynamics

TL;DR: The prevalence of unusual network events such as out-of-order delivery and packet corruption are characterized and a robust receiver-based algorithm for estimating "bottleneck bandwidth" is discussed that addresses deficiencies discovered in techniques based on "packet pair".
Journal ArticleDOI

Simulation-based comparisons of Tahoe, Reno and SACK TCP

TL;DR: The congestion control algorithms in the simulated implementation of SACK TCP are described and it is shown that while selective acknowledgments are not required to solve Reno TCP's performance problems when multiple packets are dropped, the absence of selective acknowledgements does impose limits to TCP's ultimate performance.
Journal ArticleDOI

Web server workload characterization: the search for invariants

TL;DR: This paper concludes with a discussion of caching and performance issues, using the invariants to suggest performance enhancements that seem most promising for Internet Web servers.

Specification of the Controlled-Load Network Element Service

TL;DR: This memo specifies the network element behavior required to deliver Controlled-Load service in the Internet, which provides the client data flow with a quality of service closely approximating the QoS that same flow would receive from an unloaded network element, but uses capacity control to assure that this service is received even when thenetwork element is overloaded.
Related Papers (5)