Tracing and Replaying File SystemsCapturing file system traces in a flexible and efficient manner is
difficult. This project develops a thin layer stackable tracing file
system. Tracefs can be configured dynamically to capture any number of file
system events by file system operation, file name or extension, owner,
group, process, time of day, etc. Traces can be summarized, anonymized,
compressed, encryption, or passed through any other output transform. The
traces that are captured are designed to be self-describing and efficient.
User level utilities can provide additional processing on captured traces,
including expansion or replaying the traces through the file system.
Tracefs is useful beyond traditional file system studies. For example,
Tracefs can be mounted on top of another file system in order to debug it or
educate the user about the inner operation of file systems. In addition,
hooks are available for feeding trace data into external modules such
Intrusion Detection Systems (IDSs).
Click on the list name below to access the subscription Web page. That page
will also tell you how to post to the list, access the lists' archives,
change your subscription status, etc.
||Who Can Subscribe
||Who Can Post
||For users' questions, announcements, bug reports, and general.
If you find a problem, please describe it in detail and submit a bug report via Bugzilla.
Conference and Workshop Papers:
||Name (click for home page)
||Jan 2004 - Dec 2006
||Research Staff Member, Storage and Data Services Research group, IBM T. J. Watson Research Center (Hawthorne, NY)
||Charles P. Wright
||May 2003 - May 2006
||Partner, Senior Software Architect, Illumon (New York, NY)
||May 2003 - Aug 2004
||Software Development Engineer III, AWS Elemental, Elemental Technologies (Portland, OR)
||Sep 2006 - Dec 2007
||Staff Engineer, Storage and Availability vSAN Group, VMware, Inc. (Palo Alto, CA)
||Dec 2004 - Jun 2005
||Associate, Volatility Arbitrage, Global Asset Allocation, Applied Quantitative Research (Greenwich, CT)