An Innovative Approach to Achieve Compositionality Efficiently Using Multi-version Object Based Transactional Systems

Abstract

In the modern era of multi-core systems, the main aim is to utilize the cores properly.This utilization can be done by concurrent programming. But developing a flawless and well-organized concurrent program is difficult. Software Transactional Memory Systems (STMs) are a convenient programming interface which assist the programmer to access the shared memory concurrently without worrying about consistency issues such as priority-inversion, deadlock, livelock, etc. Another important feature that STMs facilitate is compositionality of concurrent programs with great ease. It composes different concurrent operations in a single atomic unit by encapsulating them in a transaction.Many STMs available in the literature execute read/write primitive operations on memory buffers. We represent them as Read-Write STMs or RWSTMs. Whereas, there exist some STMs (transactional boosting and its variants) which work on higher level operations such as insert, delete, lookup, etc. on a hash-table. We refer these STMs as Object Based STMs or OSTMs. The literature of databases and RWSTMs say that maintaining multiple versions 1 A preliminary version of this paper appeared in 20th International Symposium on Stabilization, Safety, and Security of Distributed Systems (SSS 2018) and awarded with the Best Student Paper Award. A poster version of this work received Best Poster Award in NETYS 2018. 2 Author sequence follows the lexical order of last names. All the authors can be contacted at the addresses given above. Archit Somani's phone number: +91 -7095044601. ensures greater concurrency. This motivates us to maintain multiple version at higher level with object semantics and achieves greater concurrency. So, this paper proposes the notion of Optimized Multi-version Object Based STMs or OPT-MVOSTMs which encapsulates the idea of multiple versions in OSTMs to harness the greater concurrency efficiently. For efficient memory utilization, we develop two variations of OPT-MVOSTMs. First, OPT-MVOSTM with garbage collection (or OPT-MVOSTM-GC) which uses unbounded versions but performs garbage collection scheme to delete the unwanted versions. Second, finite version OPT-MVOSTM (or OPT-KOSTM) which maintains at most K versions by replacing the oldest version when (K + 1) th version is created by the current transaction. We propose the OPT-MVOSTMs for hash-table and list objects as OPT-HT-MVOSTM and OPT-list-MVOSTM respectively. For memory utilization, we propose two variants of both the algorithms as OPT-HT-MVOSTM-GC, OPT-HT-KOSTM and OPT-list-MVOSTM-GC, OPT-list-KOSTM respectively. OPT-HT-KOSTM performs best among its variants and outperforms state-of-the-art hash-table based STMs (HT-OSTM, ESTM, RWSTM, HT-MVTO, HT-KSTM) by a factor of 3.62, 3.95, 3.44, 2.75, 1.85 for workload W1 (90% lookup, 8% insert and 2% delete), 1. 44, 2.36, 4.45, 9.84, 7.42 for workload W2 (50% lookup, 25% insert and 25% delete), and 2. 11, 4.05, 7.84, 12.94, 10.70 for workload W3 (10% lookup, 45% insert and 45% delete) respectively. Similarly, OPT-list-KOSTM performs ...

A Novel Multi Granularity Locking Scheme Based on Concurrent Multi -Version Hierarchical Structure

“…Starvation Freedom in Multi-Version OSTM (SF-MVOSTM) [24] In order to perform starvation-freedom the latest K-versions is being maintained corresponding to each key.…”

“…In case of read-write conflicts (IS-X,IX-S,S-SIX,S-X) mode unlike MGL,CGVL avoids synchronous waiting for data item reclamation by providing suitable version for each data item [31].It works on timestamp ordering principle to provide a consistent snapshot of each data item. Each requesting thread selects the suitable version of the data item by using the last committed timestamp of each version(when the version was committed).This is well known approach that exist in multi version control database scheme [14][15][16][17][18] that provide multiple version for each transactional operations to perform their work.…”

Achieving Starvation-Freedom with Greater Concurrency in Multi-Version Object-based Transactional Memory Systems

“…So, we compared our HT-SF-KOSTM with hash table based state-of-theart STMs HT-KOSTM [20], HT-SVOSTM [6], ESTM [27], RWSTM [7,Chap. 4], HT-MVTO [16] and our list-SF-KOSTM with list based state-of-the-art STMs list-KOSTM [20], list-SVOSTM [6], Trans-list [29], Boosting-list [4], NOrec-list [28], list-MVTO [16], list-KSFTM [15]. Experimental Setup: The system configuration for experiments is 2 socket Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz with 14 cores per socket and 2 hyper-threads per core, a total of 56 threads.…”

“…-Section 7 shows that SF-KOSTM is best among all propose Starvation-Free OSTMs (SF-SVOSTM, SF-MVOSTM, and SF-MVOSTM-GC) for both hash table and linked-list data structure. Proposed hash table based SF-KOSTM (HT-SF-KOSTM) performs 3.9x, 32.18x, 22.67x, 10.8x and 17.1x average speedup on max-time for a transaction to commit than state-of-the-art STMs HT-KOSTM [20], HT-SVOSTM [6], ESTM [27], RWSTM [7,Chap. 4], and HT-MVTO [16] respectively.…”

“…4], and HT-MVTO [16] respectively. Proposed list based SF-KOSTM (list-SF-KOSTM) performs 2.4x, 10.6x, 7.37x, 36.7x, 9.05x, 14.47x, and 1.43x average speedup on max-time for a transaction to commit than state-of-the-art STMs list-KOSTM [20], list-SVOSTM [6], Trans-list [29], Boostinglist [4], NOrec-list [28], list-MVTO [16], and list-KSFTM [15] respectively.…”