Jeffrey C. Mogul

Squeezing More Bits Out of HTTP Caches (2008)

(HTTP) [3], as it is currently used in the Web, incurs many more round trips than necessary (see section 2). The success of the World-Wide Web is largely due to Several researchers have proposed...

Abstract Measured Capacity of an Ethernet: Myths and Reality (2008)

HTTP accounts for most of the bytes flowing over the Internet backbone (up to 75 percent, in one study [1]). This bandwidth demand requires continued investment in link and switch capacity, and leads...

David R. Boggs, Jeffrey C. Mogul, Christopher A. Kent

cessful. There are many factors that influence a choice between different technologies, including availability, Ethernet, a 10 Mbit/sec CSMA/CD network, is acceptance as a standard, cost per station...

ABSTRACT Performance Debugging for Distributed Systems of Black Boxes (2008)

Marcos K. Aguilera, Jeffrey C. Mogul, Janet L. Wiener, Patrick Reynolds, Athicha Muthitacharoen

fMarcos.Aguilera,Jeff.Mogul,

Peer-to-peer systems (2008)

ABSTRACT SC2D: An Alternative to (2008)

new facility for resource management

Trace Anonymization, Jeffrey C. Mogul

Progress in networking research depends crucially on applying novel analysis tools to real-world traces of network activity. This often conflicts with privacy and security requirements; many raw...

The Case for Persistent-Connection HTTP Abstract (2008)

ABSTRACT Rethinking the TCP Nagle Algorithm (2008)

(HTTP) [3], as it is currently used in the Web, incurs many more round trips than necessary (see section 2). The success of the World-Wide Web is largely due to Several researchers have proposed...

The Case for Persistent-Connection (2008)

Modern TCP implementations include a mechanism, known as the Nagle algorithm, which prevents the unnecessary transmission of a large number of small packets. This algorithm has proved useful in...

Peer-to-peer systems (2008)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

ABSTRACT Performance Debugging for Distributed Systems of Black Boxes (2008)

new facility for resource management

Marcos K. Aguilera, Jeffrey C. Mogul, Janet L. Wiener, Patrick Reynolds

Many interesting large-scale systems are distributed systems of multiple communicating components. Such systems can be very hard to debug, especially when they exhibit poor performance. The problem...

Internet servers (2008)

Jeffrey C. Mogul, Fred Douglis, Anja Feldmann, Balachander Krishnamurthy

performance for

d i g i t a l (2008)

Potential benefits of delta encoding and data compression for HTTP (Corrected version)

A Recovery Protocol for (2008)

Spritely Nfs, Jeffrey C. Mogul

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

� Resource Container (2008)

Gaurav Banga, Peter Druschel, Jeffrey C. Mogul, Sebastian Biemüller

The Case for Persistent-Connection (2008)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Internet servers (2007)

ABSTRACT Clarifying the Fundamentals of HTTP (2007)

performance for

Network Appliance Inc. (2007)

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,...

A Scalable, Gaurav Banga, Gaurav Banga, Jeffrey C. Mogul, Jeffrey C. Mogul, Peter Druschel, ...

Rights to individual papers remain with the author or the author's employer. Permission is granted for noncommercial reproduction of the work for educational or research purposes. This copyright...

Abstract Exploring the Bounds of Web Latency Reduction from Caching and Prefetching (2007)

Thomas M. Kroeger, Jeffrey C. Mogul

Prefetching and caching are techniques commonly used in I/O systems to reduce latency. Many researchers have advocated the use of caching and prefetching to reduce latency in the Web. We derive...

ABSTRACT Performance Debugging for Distributed Systems of Black Boxes (2007)

Marcos K. Aguilera, Jeffrey C. Mogul, Janet L. Wiener, Patrick Reynolds, Athicha Muthitacharoen

fMarcos.Aguilera,Jeff.Mogul,

Approved for External Publication Operating Systems and Asymmetric Single-ISA CMPs: The Potential for Saving Energy (2007)

Jeffrey C. Mogul, Jayaram Mudigonda, Nathan Binkert, Partha Ranganathan, Vanish Talwar, Jeffrey C. Mogul, ...

energy savings, operating systems * Internal Accession Date Only CPUs consume too much power. Modern complex cores sometimes waste power on functions that are not useful for the code they run. In...

Transmission systems for (2006)

Greg Minshall, Yasushi Saito, Jeffrey C. Mogul, Ben Verghese

Performance improvements to networked applications can have unintended consequences. In a study of the performance of the Network News Transport Protocol (NNTP), the initial results suggested it...

Detecting the unexpected in distributed systems (2006)

Patrick Reynolds, Charles Killian, Janet L. Wiener, Jeffrey C. Mogul, Mehul A. Shah, Amin Vahdat

Bugs in distributed systems are often hard to find. Many bugs reflect discrepancies between a system’s behavior and the programmer’s assumptions about that behavior. We present Pip 1, an...

Emergent (mis)behavior vs. complex software systems (2006)

Jeffrey C. Mogul, Jeffrey C. Mogul

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;...

Predicting short-transfer latency from TCP arcana: A trace-based validation (2005)

Martin Arlitt, Balachander Krishnamurthy, Jeffrey C. Mogul

In some contexts it may be useful to predict the latency for short TCP transfers. For example, a Web server could automatically tailor its content depending on the network path to each client, or an...

Abstract (2005)

Martin Arlitt, Er Krishnamurthy, Jeffrey C. Mogul, Martin Arlitt, Balachander Krishnamurthy, Jeffrey C. Mogul

TCP latency, network performance In some contexts it may be useful to predict the latency for short TCP transfers. For example, a Web server could automatically tailor its content depending on the...

Design, Implementation, and Evaluation of Duplicate Transfer Detection in HTTP (2004)

Yee Man Chan, Terence Kelly, Jeffrey C. Mogul, Jeffrey C. Mogul

duplicate transfer detection Organizations use Web caches to avoid transferring the same data twice over the same path. Numerous studies have shown that forward proxy caches, in practice, incur miss...

Clarifying the Fundamentals of HTTP (2002)

Server-directed transcoding (2000)

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,...

Server-directed transcoding (2000)

Transcoding, the conversion between different representations of Web content at an intermediate proxy, can ameliorate mismatches between the complex content provided by an origin server, and the...

A scalable and explicit event delivery mechanism for UNIX (1999)

Transcoding, the conversion between different representations of Web content at an intermediate proxy, can ameliorate mismatches between the complex content provided by an origin server, and the...

A scalable and explicit event delivery mechanism for UNIX (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

A scalable and explicit event delivery mechanism for UNIX (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

Trace-Based Analysis of Duplicate Suppression in HTTP (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

Jeffrey Mogul, Jeffrey C. Mogul

Many HTTP resources (pages, graphics, etc.) are exact duplicates of other resources with different URLs. If an HTTP cache contains a duplicate of a requested resource, and could detect this, it could...

Errors in timestamp-based HTTP header values (1999)

Jeffrey C. Mogul, Jeffrey C. Mogul

Many of the caching mechanism in HTTP, especially in HTTP/1.0, depend on header fields that carry absolute timestamp values. Errors in these values could lead to undetected cache incoherence, or to...

Resource Containers: A New Facility for Resource Management in Server Systems (1999)

Gaurav Banga Peter, Gaurav Banga, Peter Druschel, Jeffrey C. Mogul, Jeffrey C. Mogul

General-purpose operating systems provide inadequate support for resource management in large-scale servers. Applications lack sufficient control over scheduling and management of machine resources,...

Resource containers: A new facility for resource management in server systems (1999)

Application performance pitfalls and TCP's Nagle algorithm (1999)

General-purpose operating systems provide inadequate support for resource management in large-scale servers. Applications lack sufficient control over scheduling and management of machine resources,...

Greg Minshall, Yasushi Saito, Jeffrey C. Mogul, Ben Verghese

Performance improvements to networked applications can have unintended consequences. In a study of the performance of the Network News Transport Protocol (NNTP), the initial results suggested it...

A scalable and explicit event delivery mechanism for UNIX (1999)

A scalable and explicit event delivery mechanism for UNIX (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

A scalable and explicit event delivery mechanism for UNIX (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

Resource containers: A new facility for resource management in server systems (1999)

UNIX applications not wishing to block when doing I/O often use the select() system call, to wait for events on multiple file descriptors. The select() mechanism works well for small-scale...

Key Differences between HTTP/1.0 and HTTP/1.1 (1999)

General-purpose operating systems provide inadequate support for resource management in large-scale servers. Applications lack sufficient control over scheduling and management of machine resources,...

Balachander Krishnamurthy, Jeffrey C. Mogul, David M. Kristol

The HTTP/1.1 protocol is the result of four years of discussion and debate among a broad group of Web researchers and developers. It improves upon its phenomenally successful predecessor, HTTP/1.0,...

Resource containers: A new facility for resource management in server systems (1999)

Resource containers: A new facility for resource management in server systems (1999)

General-purpose operating systems provide inade-quate support for resource management in large-scale servers. Applications lack sufficient control over scheduling and management of machine resources,...

A Usenet Performance Study (1998)

General-purpose operating systems provide inadequate support for resource management in large-scale servers. Applications lack sufficient control over scheduling and management of machine resources,...

Yasushi Saito, Jeffrey C. Mogul, Ben Verghese

This report is an attempt to address these problems. First, we introduce Usenet and describe the structure of servers that manage Usenet. Next, we show the result of a trace study conducted on a...

Scalable kernel performance for Internet servers under realistic loads (1998)

Better Operating System Features for Faster Network Servers (1998)

UNIX Internet servers with an event-driven architecture often perform poorly under real workloads, even if they perform well under laboratory benchmarking conditions. We investigated the poor...

Scalable kernel performance for Internet servers under realistic loads (1998)

Widely-used operating systems provide inadequate support for large-scale Internet server applications. Their algorithms and interfaces fail to efficiently support either event-driven or...

Gaurav Banga Rice, Gaurav Banga, Jeffrey C. Mogul, Jeffrey C. Mogul

UNIX Internet servers with an event-driven architecture often perform poorly under real workloads, even if they perform well under laboratory benchmarking conditions. We investigated the poor...

Key Differences between HTTP/1.0 and HTTP/1.1 - Work Project No. 3116-17-1001 (1998)

Balachander Krishnamurthy, From Balachander, Jeffrey C. Mogul, David M. Kristol

this paper we describe the major changes between the HTTP/1.0 and HTTP/1.1 protocols. While some attempts have been made to document the differences between these protocols (

Scalable kernel performance for Internet servers under realistic loads (1998)

Scalable kernel performance for Internet servers under realistic loads (1998)

UNIX Internet servers with an event-driven architecture often perform poorly under real workloads, even if they perform well under laboratory benchmarking conditions. We investigated the poor...

Better Operating System Features for Faster Network Servers (1998)

UNIX Internet servers with an event-driven architecture often perform poorly under real workloads, even if they perform well under laboratory benchmarking conditions. We investigated the poor...

Better Operating System Features for Faster Network Servers (1998)

Widely-used operating systems provide inadequate support for large-scale Internet server applications. Their algorithms and interfaces fail to efficiently support either event-driven or...

Eliminating receive livelock in an interrupt-driven kernel (1997)

Widely-used operating systems provide inadequate support for large-scale Internet server applications. Their algorithms and interfaces fail to efficiently support either event-driven or...

Jeffrey Mogul, Dec Western, Jeffrey C. Mogul, K. K. Ramakrishnan

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low of-fered load, but degrade significantly at higher...

Eliminating receive livelock in an interrupt-driven kernel (1997)

Jeffrey Mogul, Dec Western, Jeffrey C. Mogul, K. K. Ramakrishnan

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low of-fered load, but degrade significantly at higher...

Eliminating receive livelock in an interrupt-driven kernel (1997)

Jeffrey C. Mogul, K. K. Ramakrishnan

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low offered load, but degrade significantly at higher...

Potential benefits of delta encoding and data compression for HTTP (1997)

Exploring the Bounds of Web Latency Reduction from Caching and Prefetching (1997)

ing with credit is permitted. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Abstract Caching in the World Wide Web...

Thomas M. Kroeger, Jeffrey C. Mogul

Prefetching and caching are techniques commonly used in I/O systems to reduce latency. Many researchers have advocated the use of caching and prefetching to reduce latency in the Web. We derive...

Potential Benefits Of Delta Encoding and Data Compression for HTTP (Corrected Version) (1997)

Jeffrey C. Mogul, Fred Douglis, Anja Feldmann, Balachander Krishnamurthy

Caching in the World Wide Web currently follows a naive model, which assumes that resources are referenced many times between changes. The model also provides no way to update a cache entry if a...

Eliminating receive livelock in an interrupt-driven kernel (1997)

Jeffrey Mogul, Dec Western, Jeffrey C. Mogul, K. K. Ramakrishnan

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low of-fered load, but degrade significantly at higher...

Eliminating receive livelock in an interrupt-driven kernel (1997)

Jeffrey C. Mogul, K. K. Ramakrishnan

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Using Predictive Prefetching to Improve World Wide Web Latency (1996)

Venkata N. Padmanabhan, Jeffrey C. Mogul

The long-term success of the World Wide Web depends on fast response time. People use the Web to access information from remote sites, but do not like to wait long for their results. The latency of...

Using Predictive Prefetching to Improve World Wide Web Latency (1996)

Venkata Padmanabhan, Jeffrey C. Mogul

The long-term success of the World Wide Web depends on fast response time. People use the Web to access information from remote sites, but do not like to wait long for their results. The latency of...

Hypertext Transfer Protocol - HTTP/1.1 (1996)

R. Fielding, H. Frystyk, T. Berners-Lee, J. Gettys, Jeffrey C. Mogul

The Hypertext Transfer Protocol (HTTP) is an application-level protocol for distributed, collaborative, hypermedia information systems. It is a generic, stateless, object-oriented protocol which can...

Operating system support for busy internet servers (1995)

Eliminating Receive Livelock in an Interrupt-driven Kernel (1995)

mogul @ wrl.dec.com The Internet has experienced exponential growth in the use of the World-Wide Web, and rapid growth in the use of other Internet services such as VSENET news and electronic mail....

Jeffrey C. Mogul, K. K. Ramakrishnan

Most operating systems use interface interrupts to schedule network tasks. Interrupt-driven systems can provide low overhead and good latency at low offered load, but degrade significantly at higher...

Operating Systems Support for Busy Internet Servers (1995)

Operating system support for busy internet servers (1995)

The Internet has experienced exponential growth in the use of the World-Wide Web, and rapid growth in the use of other Internet services such as USENET news and electronic mail. These applications...

Performance Implications of Multiple Pointer Sizes (1995)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Jeffrey C. Mogul, Joel F. Bartlett, Robert N. Mayo, Amitabh Srivastava

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Some file systems can delay writing modified data to disk, in order to reduce disk traffic and overhead. Prudence dictates that such delays be bounded, in case the system crashes. We refer to an...

Jeffrey Mogul Digital, Jeffrey C. Mogul

while a modification that fills a block results in an immediate, although asynchronous, write. The Some file systems can delay writing modified ULTRIX operating system can be configured to be data to...

Some file systems can delay writing modified partially-filled data block results in a delayed write, while a modification that fills a block results in an immediate, although asynchronous, write. The...

Recovery in Spritely NFS (1994)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Recovery in Spritely NFS (1993)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Spritely Nfs, Jeffrey C. Mogul

NFS suffers from its lack of an explicit cache-consistency protocol. The Spritely NFS experiment, which grafted Sprite's cache-consistency protocol onto NFS, showed that this could improve NFS...

Observing TCP Dynamics in Real Networks (1992)

Recovery Protocol or Spritely NFS (1992)

The behavior of the TCP protocol in simple situations is well-understood, but when multiple connections share a set of network resources the protocol can exhibit surprising phenomena. Earlier studies...

Spritely Nfs, Jeffrey C. Mogul

NFS suffers from its lack of an explicit cache-consistency protocol. The Spritely NFS experiment, which grafted Sprite's cache-consistency protocol onto NFS, showed that this could improve NFS...

Observing TCP Dynamics in Real Networks (1992)

Network locality at the scale of processes (1991)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Network locality at the scale of processes (1991)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

The effect of context switches on cache performance (1991)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Jeffrey C. Mogul, Anita Borg

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Efficient use of workstations for passive monitoring of local area networks (1990)

WRL Research Report 89/4 (1989)

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Simple And Flexible, Jeffrey C. Mogul

Internetworks that connect multiple organizations create potential security problems that cannot be solved simply by internal administrative procedures. Organizations would like to restrict...

Performance Implications of Multiple Pointer Sizes (1989)

Jeffrey C. Mogul, Joel F. Bartlett, Robert N. Mayo, Amitabh Srivastava

Many users need 64-bit architectures: 32-bit systems cannot support the largest applications, and 64-bit systems perform better for some applications. However, performance on some other applications...

Simple and Flexible Datagram Access Controls for Unix-based Gateways (1989)

Visa Protocols for Controlling Inter-Organizational Datagram Flow (1989)

Internetworks that connect multiple organizations create potential security problems that cannot be solved simply by internal administrative procedures. Organizations would like to restrict...

Deborah Estrin, Jeffrey C. Mogul, Gene Tsudik, Kamaljit Anand

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

WRL Research Report 88/4 (1988)

Measured Capacity, David R. Boggs, Jeffrey C. Mogul, Christopher A. Kent

Ethernet, a 10 Mbit/sec CSMA/CD network, is one of the most successful LAN technologies. Considerable confusion exists as to the actual capacity of an Ethernet, especially since some theoretical...

The Experimental Literature of the Internet: An Annotated Bibliography (1988)

Measured capacity of an ethernet: Myths and reality (1988)

The DARPA Internet is the most successful experiment in heterogeneous internetworking. It connects computer systems from almost every major vendor, using a wide variety of wide-area and local-area...

David R. Boggs, Jeffrey C. Mogul, Christopher A. Kent

research relevant to the design and application of high performance scientific computers. We test our ideas by designing, building, and using real systems. The systems we build are research...

Errata for ‘‘Measured Capacity of an Ethernet: Myths and Reality’’ (1987)

David R. Boggs, Jeffrey C. Mogul, Christopher A. Kent

We wish to correct several errors in our paper on the performance of Ethernet [1]. 1. In section 2.1, it is incorrectly stated that hosts may transmit a minimal length packet every 51.2 microseconds....

(Originally published in Proc. SIGCOMM ‘87, vol. 17, No. 5, October 1987) Internetworks can be built from many different kinds of networks, with varying limits on maximum packet size. Throughput is...

The Packet Filter: An Efficient Mechanism for User-level Network Code (1987)

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,...

Jeffrey Mogul Digital, Jeffrey C. Mogul, Richard F. Rashid, Michael J. Accetta

Code to implement network protocols can be either inside the kernel of an operating system or in user-level processes. Kernel-resident code is hard to develop, debug, and maintain, but user-level...

The Packet Filter: An Efficient Mechanism for User-level Network Code (1987)

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,...

Jeffrey C. Mogul, Richard F. Rashid, Michael J. Accetta

Code to implement network protocols can be either inside the kernel of an operating system or in user-level processes. Kernel-resident code is hard to develop, debug, and maintain, but user-level...

The Packet Filter: An Efficient Mechanism for User-level Network Code (1987)

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,...

Jeffrey C. Mogul, Richard F. Rashid, Michael J. Accetta

Code to implement network protocols can be either inside the kernel of an operating system or in user-level processes. Kernel-resident code is hard to develop, debug, and maintain, but user-level...

Representing information about files / (1986)

Representing information about files / (1986)

Thesis (Ph. D.)--Stanford University, 1986.

Attaching the VAX-11/780 to the local network /--by Jeffrey C. Mogul. (1979)

Thesis (Ph. D.)--Stanford University, 1986.

Squeezing more bits out of HTTP caches (0000)

Supervised by Stephen A. Ward.

Squeezing more bits out of HTTP caches

Computer system designers often use caches to solve performance problems Computer system designers often use caches to solve performance problems. Caching in the World Wide Web has...