Optimizing GridFTP through Dynamic Right-Sizing

نویسندگان

  • Sunil Thulasidasan
  • Wu-chun Feng
  • Mark K. Gardner
چکیده

In this paper, we describe the integration of dynamic right-sizing — an automatic and scalable buffer management technique for enhancing TCP performance — into GridFTP, a subsystem of the Globus Toolkit for managing bulk data transfers across computational grids. Such grids are often characterized by networks with large bandwidth-delay products. Unfortunately, many of today’s grid applications use only a small fraction of available bandwidth because the default buffer sizes in TCP are tuned for yesterday’s WAN speeds. Buffer sizes can be manually tuned to allow TCP flow control to adapt to high-speed WAN environments, but this is a tedious process. Although recent work has shown how to automatically tune system buffers during connection set-up, these values may not be appropriate for the connection’s lifetime due to varying network delay and throughput. We show how using the technique of dynamic rightsizing (DRS) in GridFTP helps us optimize memory usage while maintaining high throughput over the lifetime of the connection. We also show how DRS enhances important GridFTP features such as striped and third-party data transfers in a scalable way. The technique is implemented entirely in user space so that end users do not have to modify the kernel. Keywords— GridFTP, Globus, dynamic ∗This work was supported by the U.S Department of Energy through LANL contract W-7405-ENG-36. This paper is a Los Alamos Unlimited Release LA-UR-03-2486. right-sizing, DRS, drsFTP, computational grid, bandwidth-delay product, auto-tuning.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

User-space auto-tuning for TCP flow control in computational grids

With the advent of computational grids, networking performance over the wide-area network (WAN) has become a critical component in the grid infrastructure. Unfortunately, many high-performance grid applications only use a small fraction of their available bandwidth because operating systems and their associated protocol stacks are still tuned for yesterday’s network speeds. As a result, network...

متن کامل

Performance Evaluation of Data Transfer Protocol GridFTP for Grid Computing

In Grid computing, a data transfer protocol called GridFTP has been widely used for efficiently transferring a large volume of data. Currently, two versions of GridFTP protocols, GridFTP version 1 (GridFTP v1) and GridFTP version 2 (GridFTP v2), have been proposed in the GGF. GridFTP v2 supports several advanced features such as data streaming, dynamic resource allocation, and checksum transfer...

متن کامل

GridFTP-APT: Automatic Parallelism Tuning Mechanism for GridFTP in Long-Fat Networks

In this paper, we propose an extension to GridFTP that optimizes its performance by dynamically adjusting the number of parallel TCP connections. GridFTP has been used as a data transfer protocol to effectively transfer a large volume of data in Grid computing. GridFTP supports a feature called parallel data transfer that improves throughput by establishing multiple TCP connections in parallel....

متن کامل

Wiresizing with Bu er Placement and Sizing for Power-Delay Tradeo s

With the increasing in uence of the resistive e ects of interconnects on the performance of VLSI systems, a greater stress is being laid on careful interconnect design. One prominent technique is the approach of sizing wires for long interconnects to achieve the desired speed and power characteristics [1{4]. It has also been suggested that one may appropriately insert repeaters [5] for signi ca...

متن کامل

On Automatic Parameter Configuration Mechanism for Data Transfer Protocol GridFTP

In recent years, Grid computing has got a lot of attention. Grid computing is a concept of connecting geographically-distributed computational resources via networks, which is expected to realize efficient usage of computational resources and large-scale scientific and engineering computation. In Grid computing, a data transfer protocol called GridFTP has been used for large file transfer. Grid...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003