dc.contributor.author | Li, Xi | |
dc.date.accessioned | 2014-09-25 18:49:01 (GMT) | |
dc.date.available | 2014-09-25 18:49:01 (GMT) | |
dc.date.issued | 2014-09-25 | |
dc.date.submitted | 2014-09-23 | |
dc.identifier.uri | http://hdl.handle.net/10012/8870 | |
dc.description.abstract | Distributed filesystems are often the primary bandwidth consumers of
large-scale datacenter networks. Unsurprisingly, the datacenter network is
often the performance bottleneck for distributed filesystems. Yet even with
this close relationship, current distributed filesystems and networks are
designed independently and communicate over narrow interfaces that expose only
their basic functionalities. Even network-aware distributed
filesystems only make use of rudimentary network information, and are not
reciprocally involved in making network decisions that affect filesystem
performance.
In this thesis, we introduce Mayflower,
a new distributed filesystem co-designed
with the control plane of its underlying datacenter network. This design
approach enables Mayflower to combine both filesystem and network information
to make replica selection and dynamic flow scheduling decisions. By having more
information and controlling both the filesystem and the network, Mayflower can
perform optimizations that are unavailable to conventional distributed
filesystems and network control planes.
Our evaluation results using a real implementation
show that Mayflower reduces average
read completion time by more than 60% compared to HDFS with ECMP. | en |
dc.language.iso | en | en |
dc.publisher | University of Waterloo | en |
dc.subject | network | en |
dc.subject | distributed filesystem | en |
dc.title | Improving Distributed Filesystem Performance by Combining Replica and Network Path Selection | en |
dc.type | Master Thesis | en |
dc.pending | false | |
dc.subject.program | Computer Science | en |
uws-etd.degree.department | School of Computer Science | en |
uws-etd.degree | Master of Mathematics | en |
uws.typeOfResource | Text | en |
uws.peerReviewStatus | Unreviewed | en |
uws.scholarLevel | Graduate | en |