Sinfonia: a new paradigm for building scalable distributed systems

By Marcos Kawazoe Aguilera, A. Merchant, Mehul A. Shah, Alistair C. Veitch, C. Karamanolis. Symposium on Operating Systems Principles, 2007

329 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/fcc5e3ea26ead374905ce9c88cea48f0a7c9b600

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

Citations in the corpus

Fast crash recovery in RAMCloud (2011, methodology): “In the future we plan to experiment with more powerful features suc h as indexes, mini-transactions [4], and support for large grap hs.”
Fast in-memory transaction processing using RDMA and HTM (2015, methodology): “First, similar to some prior work [2, 52], DrTM requires advance knowledge of read/write sets of transactions for proper locking to implement the 2PL-like protocol.”
PNUTS: Yahoo!'s hosted data serving platform (2008, background): “Examples include Ceph [27], Boxwood [20], and Sinfonia [3].”
Stronger Semantics for Low-Latency Geo-Replicated Storage (2013, neutral): “The implementers of Sinfonia [1], TxCache [46], HBase [32], and Spanner [22], also recognized the importance of limited transactions.”
Large-scale Incremental Processing Using Distributed Transactions and Notifications (2010, background): “Sinfonia [3] provides a transactional interface to a distributed repository.”
Don't settle for eventual: scalable causal consistency for wide-area storage with COPS (2011, background): “Sinfonia [1] provides “mini” transactions to distributed shared memory via a lightweight two-phase commit protocol, but only considers operations within a single datacenter.”
OLTP through the looking glass, and what we found there (2008, background): “Twenty years ago, various researchers [KR81, ACL87 ] performed exhaustive simulations that clearly showed the superiority of dynamic locking relative to other concurrency control techniques.”
Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases (2017, methodology): “Systems like Sinfonia [39] avoid recovery by using techniques like process pairs and state machine replication.”
No compromises: distributed transactions with consistency, availability, and performance (2015, background): “The limited resolution of the system timer explains why the interrupt-driven lease manager has more false positives than the polling-based one with 1ms leases.”
Trinity: a distributed graph engine on a memory cloud (2013, methodology): “For applications that need transaction support, we can implement light-weight atomic operation primitives that span multiple cells, such as MultiOp primitives [13] and Mini-transaction primitives [7], on top of the atomic cell operation primitives.”
ZooKeeper: Wait-free Coordination for Internet-scale Systems (2010, background): “Sinfonia [2] introduces mini-transactions , a new paradigm for building scalable distributed systems.”
Finding a Needle in Haystack: Facebook's Photo Storage (2010, background): “Similarly, Sinfonia’s [1] mini-transactions and PNUTS’s [5] database functionality provide more features and stronger guarantees than Haystack needs.”
Transactional storage for geo-replicated systems (2011, methodology): “Sinfonia uses transactions for infrastructure services [3, 4], while Percolator [38] uses them for search indexing.”