Chapter 5: Copying data
Copy from one, it's plagiarism; copy from two, it's research.
—Wilson Mizner
Abstract
Most Web servers, and computers in general, routinely make a number of extra copies of received and sent messages. Ultimately, if there are k copies involved in processing a message in a Web server, the throughput of the Web server can be k times slower. This chapter focusses on removing the obvious waste involved in such unnecessary copies. Eliminating redundant copies allows the software to come closer to realizing the potential of the hardware, one of the goals of network algorithmics. This chapter surveys techniques for reducing the costs of data manipulation without sacrificing modularity and without major changes to operating system ...
Get Network Algorithmics, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
