Filters








21 Hits in 2.4 sec

Fbufs: a high-bandwidth cross-domain transfer facility

Peter Druschel, Larry L. Peterson
1993 ACM SIGOPS Operating Systems Review  
This paper introduces a high-bandwidth cross-domain transfer and buffer management facility, called fast buffers (fbufs), and shows how it can be optimized to support data that originates and/or terminates  ...  This paper outlines the requirements for a cross-domain transfer facility, describes the design of the fbuf mechanism that meets these requirements, and experimentally quantifies the impact of fbufs on  ...  Section 3 gives the design of a cross-domain transfer facility that supports (exploits) these requirements (restrictions).  ... 
doi:10.1145/173668.168634 fatcat:yeq6wimk5bcz5ngzmvgcz637li

Fbufs: a high-bandwidth cross-domain transfer facility

Peter Druschel, Larry L. Peterson
1993 Proceedings of the fourteenth ACM symposium on Operating systems principles - SOSP '93  
This paper introduces a high-bandwidth cross-domain transfer and buffer management facility, called fast buffers (fbufs), and shows how it can be optimized to support data that originates and/or terminates  ...  This paper outlines the requirements for a cross-domain transfer facility, describes the design of the fbuf mechanism that meets these requirements, and experimentally quantifies the impact of fbufs on  ...  Section 3 gives the design of a cross-domain transfer facility that supports (exploits) these requirements (restrictions).  ... 
doi:10.1145/168619.168634 dblp:conf/sosp/DruschelP93 fatcat:2kgrasnxrfexncb5clwghx4nky

Operating system support for high-speed communication

Peter Druschel
1996 Communications of the ACM  
The optimization integrates buffer management and cross-domain data transfer facility by placing the entire buffer aggregate into fbufs.  ...  Achieving a high-performance I/O system requires an integrated design of application programming interface, cross-domain data transfer, buffer management, and network interface.  ...  To copy otherwise, to republish, to post on servers, or to redistribute to lists requires prior specific permission and/or a fee.  ... 
doi:10.1145/234215.234470 fatcat:2vtjmwg3sbakxbmq3vvtlhb3zu

Experiences with a high-speed network adaptor

Peter Druschel, Larry L. Peterson, Bruce S. Davie
1994 Proceedings of the conference on Communications architectures, protocols and applications - SIGCOMM '94  
This paper describes our experiences, from a software perspective, with the OSIRIS network adaptor.  ...  Intel is a trademark of the Intel Corporation. UNIX is a trademark of the X/Open Company. RISC System/6000 is a trademark of International Business Machines.  ...  The fbuf mechanism is designed to address this problem-it is a high-bandwidth cross-domain buffer transfer and management facility. The fbuf mechanism itself is simple to understand.  ... 
doi:10.1145/190314.190315 dblp:conf/sigcomm/DruschelPD94 fatcat:mt6zke5bx5bbxcpyvjkrpm3xkm

Experiences with a high-speed network adaptor

Peter Druschel, Larry L. Peterson, Bruce S. Davie
1994 Computer communication review  
This paper describes our experiences, from a software perspective, with the OSIRIS network adaptor.  ...  Intel is a trademark of the Intel Corporation. UNIX is a trademark of the X/Open Company. RISC System/6000 is a trademark of International Business Machines.  ...  The fbuf mechanism is designed to address this problem-it is a high-bandwidth cross-domain buffer transfer and management facility. The fbuf mechanism itself is simple to understand.  ... 
doi:10.1145/190809.190315 fatcat:y5vwsm5lmfgpdesiqamoxbzym4

High-speed I/O

Matthew Burnside, Angelos D. Keromytis
2003 Proceedings of the ACM SIGCOMM workshop on Network-I/O convergence experience, lessons, implications - NICELI '03  
We propose a new operating system architecture that removes the memory and CPU from the data path.  ...  With the increasing disparity between I/O bandwidth and CPU performance, this architecture exposes the processor and memory subsystems as the bottlenecks to system performance.  ...  [21] describes a mechanism for optimizing high-bandwidth I/O called fbufs.  ... 
doi:10.1145/944747.944756 fatcat:ob4ykky45nd7lc5z3nobszkvk4

IO-Lite: a unified I/O buffering and caching system

Vivek S. Pai, Peter Druschel, Willy Zwaenepoel
2000 ACM Transactions on Computer Systems  
IO-Lite eliminates all copying and multiple bu ering of I O data, and enables various cross-subsystem optimizations.  ...  Protection and security are maintained through a combination of access control and read-only sharing.  ...  Fbufs: Fbufs is a copy-free cross-domain transfer and bu ering mechanism for I O data, based on immutable bu ers that can be concurrently shared.  ... 
doi:10.1145/332799.332895 fatcat:mxhmhzjapjh4leyp6y65phrgde

Container shipping: operating system support for I/O-intensive applications

J. Pasquale, E. Anderson, P.K. Muller
1994 Computer  
For example, an uncompressed high-definition television frame requires 6 Mbytes, and a high-quality computer-generated video frame from a motion picture such as Jurussic Park requires 36 Mbytes.  ...  In this article, we focus on an important aspect of operating system support for these applications: efficient transfer of large data objects between the protection domains in which processes and devices  ...  Peterson, "Fbufs: A High-Bandwidth Cross-Domain Transfer Facility," Operating System Princp/es, ACM Press, New York, 1993, pp. F Figure 4 . 4 Physical versus virtual moving.  ... 
doi:10.1109/2.268890 fatcat:qnnofyvlzjffxfozeltpml2jv4

Operating system support for multimedia systems

T. Plagemann, V. Goebel, P. Halvorsen, O. Anshus
2000 Computer Communications  
Partitioned file systems consist of multiple subfile systems, each tailored to handle data of a specific data type.  ...  ], Shark [Haskin 93], Tiger Shark [Haskin et al. 96], and the combination of UFS and CMFS in [Ramakrishnan et al. 93]. © Integrated file systems multiplex all available resources (storage space, disk bandwidth  ...  Furthermore, fast buffers (fbufs) [Druschel 96 ], [Druschel et al. 93a ] is a facility for I/O buffer management and data transfers across protection domain boundaries primarily designed for handling  ... 
doi:10.1016/s0140-3664(99)00180-2 fatcat:wmr4vqndazezjlocfa5kvtggxe

Efficient Packet Processing in User-Level OSes: A Study of UML

Younggyun Koh, Calton Pu, Sapan Bhatia, Charles Consel
2006 Local Computer Networks (LCN), Proceedings of the IEEE Conference on  
(ULOSes) However, the isolation and security they bring comes at the price of performance, as virtualization introduces a number of overheads into the system.  ...  Our studies of the TCP/IP stack in User-mode Linux (UML), an implementation of a ULOS, attribute the resulting slow-downs to three main sources: the execution of privileged code, memory management across  ...  Fbufs [12] uses shared memory space to move data between different address space domains. Our shared socket buffers use the same idea of fbuf.  ... 
doi:10.1109/lcn.2006.322071 dblp:conf/lcn/KohPBC06 fatcat:k4gcnerp6jfkhnnfq7l4pxp53m

Evaluation of a zero-copy protocol implementation

K.-A. Skevik, T. Plagemann, V. Goebel, P. Halvorsen
Proceedings 27th EUROMICRO Conference. 2001: A Net Odyssey  
Since a high and rapidly increasing number of users retrieve multimedia data with high data rates, the data servers can represent a severe bottleneck.  ...  high-speed network communication, based on UVM [6] .  ...  Furthermore, fast buffers (fbufs) [8] is a facility for I/O buffer management and data transfers across protection domain boundaries, primarily designed for handling network streams using shared virtual  ... 
doi:10.1109/eurmic.2001.952471 dblp:conf/euromicro/SkevikPGH01 fatcat:fbbs64o2obdjbk76qodnnsn2iu

Universal Continuous Media I/O: Design and Implementation

Charles Cranor
1994
To address these I/O subsystem issues, our high level objective is to modify the traditional Unix operating system's I/O subsystem to support new high-speed networks and high-bandwidth multimedia applications  ...  The problem this paper addresses is how to modify an existing operating system's I/O subsystem to support new high-speed networks and high-bandwidth multimedia applications that will play an important  ...  Some of these streams (typically video streams) have high bandwidth and stringent real-time QOS requirements.  ... 
doi:10.7936/k7zc813h fatcat:4vhxxashnzcvne6iwzg74u7clu

Position summary: a streaming interface for real-time interprocess communication

J. Loser, H. Hartig, L. Reuther
Proceedings Eighth Workshop on Hot Topics in Operating Systems  
Timely transfer of long, continuous data streams and handling data omission are stringent requirements of multimedia applications.  ...  Therefore, we add a time track to data streams and add mechanisms to limit the validity of data. For cases of overload we add notification and revocation techniques.  ...  Druschel and Peterson introduced Fbufs [DP93], an efficient I/O buffer management facility to transfer data across protection-domain boundaries.  ... 
doi:10.1109/hotos.2001.990090 dblp:conf/hotos/LoserHR01 fatcat:vfry6u6vbzcvzfnsr4xw5zlvuq

A comparative study of some network subsystem organizations

D.V. Ponomarev, K. Ghose
Proceedings. Fifth International Conference on High Performance Computing (Cat. No. 98EX238)  
The impact of alternative network subsystem design for realizing low end-to-end latencies and high network throughput in a switched LAN are studied in detail through simulation.  ...  In a conventional setup, with the NIC placed on the I/O bus, we show that changing traffic priorities on the memory bus to speed up the transfers between the NIC and the DRAM has little impact on overall  ...  These cross domain transfers have to be co-ordinated by the operating system (OS) after performing the required authentication checks.  ... 
doi:10.1109/hipc.1998.738019 dblp:conf/hipc/PonomarevG98 fatcat:3jbc6nttajfx5iyxaskh4jk3hm

Unifier: Unifying cache management and communication buffer management for PVFS over intiniband

Jiesheng Wu, P. Wyckoff, D. Pandal, R. Ross
IEEE International Symposium on Cluster Computing and the Grid, 2004. CCGrid 2004.  
The advent of networking technologies and high performance transport protocols facilitates the service of storage over networks.  ...  It offers a single copy data sharing among all components in a server application safely and concurrently. (2) It reduces memory registration and deregistration costs to enable applications to take full  ...  Introduction Network storage systems are increasingly becoming a mainstream solution for I/O intensive applications in various domains, such as data-centers, high performance computing systems, and the  ... 
doi:10.1109/ccgrid.2004.1336646 dblp:conf/ccgrid/WuWPR04 fatcat:nf3oyqlimjhonclepadrvn25oy
« Previous Showing results 1 — 15 out of 21 results