DMCA
Multi-stage replay with crosscut (2010)
| Venue: | In Proceedings of the 6th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE ’10 |
| Citations: | 12 - 0 self |
BibTeX
@INPROCEEDINGS{Chow10multi-stagereplay,
author = {Jim Chow and Dominic Lucchetti and Tal Garfinkel and Geoffrey Lefebvre and Ryan Gardner and Joshua Mason and Sam Small and Peter M. Chen},
title = {Multi-stage replay with crosscut},
booktitle = {In Proceedings of the 6th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE ’10},
year = {2010},
pages = {13}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Deterministic record-replay has many useful applications, ranging from fault tolerance and forensics to reproducing and diagnosing bugs. When choosing a record-replay solution, the system admin-istrator must choose a priori how comprehensively to record the execution and at what abstraction level to record it. Unfortunately, these choices may not match well with how the recording is eventu-ally used. A recording may contain too little information to support the end use of replay, or it may contain more sensitive information than is allowed to be shown to the end user of replay. Similarly, fixing the abstraction level at the time of recording often leads to a semantic mismatch with the end use of replay. This paper describes how to remedy these problems by adding customizable replay stages to create special-purpose logs for the end users of replay. Our system, called Crosscut, allows replay logs to be “sliced ” along time and abstraction boundaries. Using this approach, users can create slices that include only the processes, applications, or components of interest, excluding parts that handle sensitive data. Users can also retarget the abstraction level of the replay log to higher-level platforms, such as Perl or Valgrind. Exe-cution can then be augmented with additional analysis code at re-play time, without disturbing the replayed components in the slice. Crosscut thus uses replay itself to transform logs into a more effi-cient, secure, and usable form for replay-based applications. Our current Crosscut prototype builds on VMware Worksta-tion’s record-replay capabilities, and supports a variety of differ-ent replay environments. We show how Crosscut can create slices of only the parts of the computation of interest and thereby avoid leaking sensitive information, and we show how to retarget the ab-straction level of the log to enable more convenient use during re-play debugging.
Keyphrases
multi-stage replay abstraction level end user end use sensitive information little information special-purpose log record-replay solution semantic mismatch differ-ent replay environment deterministic record-replay ab-straction level many useful application replay-based application fault tolerance re-play time usable form convenient use replayed component customizable replay stage vmware worksta-tion record-replay capability higher-level platform additional analysis code re-play debugging sensitive data abstraction boundary current crosscut prototype build replay log
