Most high-performance software transactional memories (STM) use optimistic invisible reads. Consequently, a transaction might have an inconsistent view of the objects it accesses unless the consistency of the view is validated whenever the view changes. Although all STMs usually detect inconsistencies at commit time, a transaction might never reach this point because an inconsistent view can provoke arbitrary behavior in the application (e.g., enter an infinite loop). In this paper, we formally introduce a lazy snapshot algorithm that verifies at each object access that the view observed by a transaction is consistent. Validating previously accessed objects is not necessary for that, however, it can be used on-demand to prolong the view's validity. We demonstrate both formally and by measurements that the performance of our approach is quite competitive by comparing other STMs with an STM that uses our algorithm.

https://doc.rero.ch/record/18139/files/Riegel_Torvald_-_A_Lazy_Snapshot_Algorithm_with_Eager_Validation_20100430.pdf

A Lazy Snapshot Algorithm with Eager Validation

An effective way to reduce the number of aborts in software transactional memory (STM) is to keep multiple versions of transactional objects. In this paper, we study inherent properties of STMs that use multiple versions to guarantee successful commits of all read-only transactions. We first show that these STMs cannot be disjoint-access parallel. We then consider the problem of garbage collecting old object versions, and show that no STM can be optimal in the number of previous versions kept. Moreover, we show that garbage collecting useless versions is impossible in STMs that implement invisible reads. Finally, we present an STM algorithm using visible reads that efficiently garbage collects useless object versions.

https://webee.technion.ac.il/people/idish/ftp/podcfp169-perelman.pdf

On maintaining multiple versions in STM

We introduce transactions into libraries of concurrent data structures; such transactions can be used to ensure atomicity of sequences of data structure operations. By focusing on transactional access to a well-defined set of data structure operations, we strike a balance between the ease-of-programming of transactions and the efficiency of custom-tailored data structures. We exemplify this concept by designing and implementing a library supporting transactions on any number of maps, sets (implemented as skiplists), and queues. Our library offers efficient and scalable transactions, which are an order of magnitude faster than state-of-the-art transactional memory toolkits. Moreover, our approach treats stand-alone data structure operations (like put and enqueue) as first class citizens, and allows them to execute with virtually no overhead, at the speed of the original data structure library.

https://dl.acm.org/doi/pdf/10.1145/2980983.2908112

Transactional data structure libraries

Modern big data processing platforms employ huge in-memory key-value (KV) maps. Their applications simultaneously drive high-rate data ingestion and large-scale analytics. These two scenarios expect KV-map implementations that scale well with both real-time updates and large atomic scans triggered by range queries. We present KiWi, the first atomic KV-map to efficiently support simultaneous large scans and real-time access. The key to achieving this is treating scans as first class citizens,and organizing the data structure around them. KiWi provides wait-free scans, whereas its put operations are lightweight and lock-free. It optimizes memory management jointly with data structure access.We implement KiWi and compare it to state-of-the-art solutions. Compared to other KV-maps providing atomic scans, KiWi performs either long scans or concurrent puts an order of magnitude faster. Its scans are twice as fast as non-atomic ones implemented via iterators in the Java skiplist.

KiWi: A Key-Value Map for Scalable Real-Time Analytics

Software Transactional Memory Systems STM are a promising alternative for concurrency control in shared memory systems. Multiversion STM systems maintain multiple versions for each t-object. The advantage of storing multiple versions is that it facilitates successful execution of higher number of read operations than otherwise. Multi-Version permissiveness mv-permissiveness is a progress condition for multi-version STMs that states that a read-only transaction never aborts. Recently a STM system was proposed that maintains only a single version but is mv-permissive. This raises a natural question: how much concurrency can be achieved by multi-version STM. We show that fewer transactions are aborted in multi-version STMs than single-version systems. We also show that any STM system that is permissive w.r.t opacity must maintain at least as many versions as the number of live transactions. A direct implication of this result is that no single-version STM can be permissive w.r.t opacity.

In this paper we present a time-stamp based multiversion STM system that satisfies opacity and is easy to implement. We formally prove the correctness of the proposed STM system. Although many multi-version STM systems have been proposed in literature that satisfy opacity, to the best of our knowledge none of them has been formally proved to be opaque. We also present garbage collection procedure which deletes unwanted versions of the transaction objects. We show that with garbage collection the number of versions maintained is bounded by number of live transactions.

/pdf/a-timestamp-based-multi-version-stm-algorithm-uucyoejs0o.pdf

A TimeStamp Based Multi-version STM Algorithm

We present Selective Multi-Versioning (SMV), a new STM that reduces the number of aborts, especially those of long read-only transactions. SMV keeps old object versions as long as they might be useful for some transaction to read. It is able to do so while still allowing reading transactions to be invisible by relying on automatic garbage collection to dispose of obsolete versions.

SMV is most suitable for read-dominated workloads, for which it performs better than previous solutions. It has an up to ×7 throughput improvement over a single-version STMand more than a two-fold improvement over an STMkeeping a constant number of versions per object. We show that the memory consumption of algorithms keeping a constant number of versions per object might grow exponentially with the number of objects, while SMV operates successfully even in systems with stringent memory constraints.

/pdf/smv-selective-multi-versioning-stm-2s6gb5368e.pdf

Oleg Litmanovich

Papers

SMV: selective multi-versioning STM