TY - GEN
T1 - Distributed transactional memory for general networks
AU - Sharma, Gokarna
AU - Busch, Costas
AU - Srinivasagopalan, Srivathsan
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - We consider the problem of implementing transactional memory in large-scale distributed networked systems. We present and analyze Spiral, a novel distributed directory-based protocol for transactional memory. Spiral is designed for the data-flow distributed implementation of software transactional memory which supports three basic operations: publish, allowing a shared object to be inserted in the directory so that other nodes can find it, lookup, providing a read-only copy of the object to the requesting node, move, allowing the requesting node to write the object locally after the node gets it. The protocol runs on a hierarchical directory construction based on sparse covers, where clusters at each level are ordered to avoid race conditions while serving concurrent requests. Given a shared object the protocol maintains a directory path pointing to the object. The basic idea is to use "spiral" paths that grow outward to search for the directory path of the object in a bottom-up fashion. For general networks, this protocol guarantees an O(log 2 n · log D) approximation for move requests, where n is the number of nodes and D is the diameter of the network. It also guarantees poly-log approximation for lookup requests. To the best of our knowledge, this is the first consistency protocol for distributed transactional memory that achieves poly-log approximation in general networks.
AB - We consider the problem of implementing transactional memory in large-scale distributed networked systems. We present and analyze Spiral, a novel distributed directory-based protocol for transactional memory. Spiral is designed for the data-flow distributed implementation of software transactional memory which supports three basic operations: publish, allowing a shared object to be inserted in the directory so that other nodes can find it, lookup, providing a read-only copy of the object to the requesting node, move, allowing the requesting node to write the object locally after the node gets it. The protocol runs on a hierarchical directory construction based on sparse covers, where clusters at each level are ordered to avoid race conditions while serving concurrent requests. Given a shared object the protocol maintains a directory path pointing to the object. The basic idea is to use "spiral" paths that grow outward to search for the directory path of the object in a bottom-up fashion. For general networks, this protocol guarantees an O(log 2 n · log D) approximation for move requests, where n is the number of nodes and D is the diameter of the network. It also guarantees poly-log approximation for lookup requests. To the best of our knowledge, this is the first consistency protocol for distributed transactional memory that achieves poly-log approximation in general networks.
KW - Cache-coherence
KW - Distributed transactional memory
KW - General network
KW - Hierarchical clustering
KW - Stretch
UR - http://www.scopus.com/inward/record.url?scp=84866850997&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866850997&partnerID=8YFLogxK
U2 - 10.1109/IPDPS.2012.97
DO - 10.1109/IPDPS.2012.97
M3 - Conference contribution
AN - SCOPUS:84866850997
SN - 9780769546759
T3 - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, IPDPS 2012
SP - 1045
EP - 1056
BT - Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, IPDPS 2012
T2 - 2012 IEEE 26th International Parallel and Distributed Processing Symposium, IPDPS 2012
Y2 - 21 May 2012 through 25 May 2012
ER -