Abstract | ||
---|---|---|
The metadata service of the Ursa Minor distributed storage system scales metadata throughput as metadata servers are added. While doing so, it correctly handles metadata operations that involve items served by different metadata servers, consistently and atomically updating the items. Unlike previous systems, it does so by reusing existing metadata migration functionality to avoid complex distributed transaction protocols. It also assigns item IDs to minimize the occurrence of multiserver operations. Ursa Minor's approach allows one to implement a desired feature with less complexity than alternative methods and with minimal performance penalty (under 1% in non-pathological cases). |
Year | Venue | Keywords |
---|---|---|
2010 | USENIX Annual Technical Conference | different metadata server,ursa minor storage system,existing metadata migration functionality,item ids,metadata service,alternative method,transparently-scalable metadata service,metadata server,metadata operation,ursa minor,minimal performance penalty,metadata throughput,throughput,metadata |
Field | DocType | Citations |
Metadata,Metadata repository,Meta Data Services,Computer science,Server,Distributed data store,Throughput,Distributed transaction,Database,Scalability | Conference | 14 |
PageRank | References | Authors |
0.65 | 25 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shafeeq Sinnamohideen | 1 | 301 | 29.22 |
Raja R. Sambasivan | 2 | 223 | 13.33 |
James Hendricks | 3 | 256 | 18.65 |
Likun Liu | 4 | 41 | 4.21 |
Gregory R. Ganger | 5 | 4560 | 383.16 |