A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is
Internetworks can be built from many different kinds of networks, with varying limits on maximum packet size. Throughput is usually maximized when the largest possible packet is sent; unfortunately, some routes can carry only very small packets. The IP protocol allows a gateway to fragment a packet if it is too large to be transmitted. Fragmentation is at best a necessary evil; it can lead to poor performance or complete communication failure. There are a variety of ways to reduce thedoi:10.1145/205447.205456 fatcat:7n7fmmc34fenjotszand6pu54e
more »... educe the likelihood of fragmentation; some can be incorporated into existing IP implementations without changes in protocol specifications. Others require new protocols, or modifications to existing protocols. This paper is a revised version of one published in
The simplicity of HTTP was a major factor in the success of the Web. However, as both the protocol and its uses have evolved, HTTP has grown complex. This complexity results in numerous problems, including confused implementors, interoperability failures, difficulty in extending the protocol, and a long specification without much documented rationale. Many of the problems with HTTP can be traced to unfortunate choices about fundamental definitions and models. This paper analyzes the currentdoi:10.1002/spe.573 fatcat:ofpfoqsp6baybjqrr6cxewcbw4
more »... zes the current (HTTP/1.1) protocol design, showing how it fails in certain cases, and how to improve these fundamentals. Some problems with HTTP can be fixed simply by adopting new models and terminology, allowing us to think more clearly about implementations and extensions. Other problems require explicit (but compatible) protocol changes.
through D do not include samples for which the x-axis value is zero (e.g., plot C only includes those connections that transferred at least one byte). ... The final column on the receiver's side marks compressed packets (with "C"). On lines 1 through 12, we see the series of data packets being sent, then a burst of ACKS (lines 13 through 18). ...doi:10.1145/144191.144305 fatcat:rxmchmytyjhz5j6wtlr2k4vig4
OpenFlow is a great concept, but its original design imposes excessive overheads. It can simplify network and traffic management in enterprise and data center environments, because it enables flow-level control over Ethernet switching and provides global visibility of the flows in the network. However, such fine-grained control and visibility comes with costs: the switch-implementation costs of involving the switch's control-plane too often and the distributed-system costs of involving thedoi:10.1145/2043164.2018466 fatcat:lmpbl3zo3jfb5fejs6f6gk5z2q
more »... involving the OpenFlow controller too frequently, both on flow setups and especially for statistics-gathering. In this paper, we analyze these overheads, and show that OpenFlow's current design cannot meet the needs of highperformance networks. We design and evaluate DevoFlow, a modification of the OpenFlow model which gently breaks the coupling between control and global visibility, in a way that maintains a useful amount of visibility without imposing unnecessary costs. We evaluate DevoFlow through simulations, and find that it can load-balance data center traffic as well as fine-grained solutions, without as much overhead: DevoFlow uses 10-53 times fewer flow table entries at an average switch, and uses 10-42 times fewer control messages.
to depend on the idle-timeout parameter, for values several parameters, including the initial timeout and the above a threshold that varies somewhat with C . ... In most ''open-connection hits'' as a function of the idle-timeout times the minimum required to avoid refusing requests. parameter, for various limits on C . ...doi:10.1145/217391.217465 fatcat:kq23cv3fmnbnzbhefdw7kaxfde
X→Y , Cmin where C and C min are two constants. ... C controls the amount of cautioning, e.g., if C=0.5 then the aggressiveness is halved when the rate is twice the guarantee. ...doi:10.1145/2534169.2486027 fatcat:iearhd55rfcltpfbjeezrguvty
Jeffrey Naughton's keynote at ICDE 2010  has been widely cited as an articulation of this problem. Naughton points out: 1 we hope; see Fang et al. ... This envy may lead to the hope that perhaps, if we only insisted on more rigor, real scientists would take us seriously. • the self-reinforcing role modelling that Jeffrey Naughton pointed out: young CS ...doi:10.1145/2500098.2500112 fatcat:656r2ithzragpggkyxk44zbnnm
The HTTP protocol, as currently used in the World Wide Web, uses a separate TCP connection for each file requested. This adds significant and unnecessary overhead, especially in the number of network round trips required. We analyze the costs of this approach and propose simple modifications to HTTP that, while interoperating with unmodified implementations, avoid the unnecessary network costs. We implemented our modifications, and our measurements show that they dramatically reduce latencies.doi:10.1016/0169-7552(95)00106-1 fatcat:rk4i5w2zebhwpbj6t6azb5wjnq
A researcher in organization A might need traces that can only be made at traceowner organizations B, C, and D. ...doi:10.1145/1162678.1162686 dblp:conf/minenet/MogulA06 fatcat:4v7wbyh6y5gj3a7qfrw3epzjba
The Workshop on Organizing Workshops, Conferences, and Symposia for Computer Systems (WOWCS) was organized to "bring together conference organizers (past, present, and future) and other interested people to discuss the issues they confront." In conjunction with WOWCS, we survey some previous publications that discuss open issues related to organizing computer systems conferences, especially concerning conduct and management of the review process. We also list some topics about which we wishdoi:10.1145/1384609.1384623 fatcat:keftykbg65gnvlbxn6myrj27re
more »... t which we wish WOWCS had received submissions, but did not; these could be good topics for future articles.
Mb make #1 Compilation of portions of the C source for Magic. ... (Trial A) Figure 5 : 5 Cumulative excess CPI for all switches (Trial A) Figure 6 : 6 Cumulative excess CPI for all switches (Trial B) Figure 7 : 7 Cumulative excess CPI for all switches (Trial C) ...doi:10.1145/106973.106982 fatcat:maigjqeoyrbyxkk7zky3xxx5rq
emergent behavior, emergent misbehavior, complex systems, distributed systems Complex systems often behave in unexpected ways that are not easily predictable from the behavior of their components; this is known as emergent behavior. As software systems grow in complexity, interconnectedness, and geographic distribution, we will increasingly face unwanted emergent behavior. Unpredictable software systems are hard to debug and hard to manage. We need better tools and methods for anticipating,doi:10.1145/1218063.1217964 fatcat:zfunxe4qrbc4hdq2al3lbvostm
more »... r anticipating, detecting, diagnosing, and ameliorating emergent misbehavior. These tools and methods will require research into the causes and nature of emergent misbehavior in software systems. * Internal Accession Date Only Approved for External Publication Abstract Complex systems often behave in unexpected ways that are not easily predictable from the behavior of their components; this is known as emergent behavior. As software systems grow in complexity, interconnectedness, and geographic distribution, we will increasingly face unwanted emergent behavior. Unpredictable software systems are hard to debug and hard to manage. We need better tools and methods for anticipating, detecting, diagnosing, and ameliorating emergent misbehavior. These tools and methods will require research into the causes and nature of emergent misbehavior in software systems. Emergent (Mis)behavior vs. Complex Software Systems
Kent and Jeffrey C. Mogul. Fragmentation Considered Harmful. In Proc. SIGCOMM '87 Workshop on Frontiers in Computer Communications Technology, Pages 390-401. Stowe, VT, August, 1987. ...  C. Anthony DellaFera, Mark W. Eichin, Robert S. French, David C. Jedlinksy, John T. Kohl, William E. Sommerfield. The Zephyr Notification Service. In Proc. ...doi:10.1145/66093.66096 fatcat:hoevmbljfffgbctb3qpky5omwe
Jeff Mogul (HP Labs): If you could rely on having a trusted platform module, would that solve some of the problems? ... Answer: I don't remember.Jeff Mogul (HP Labs): I work in a company with 300K users. How would the number of groups scale with more users? ... Jeff Mogul (HP Labs): You showed the CDF of the location accuracy, but what distance was good enough? Answer: It depends on the granularity of your recovery. ...doi:10.1145/1672308.1672317 fatcat:megdusf4mnc5tixco4biis64fu
« Previous Showing results 1 — 15 out of 596 results