arXiv subjects

Alexander A. Schwarzmann

Publications and source records attributed to Alexander A. Schwarzmann.

4 recordsLinked to original sources

arXiv2020

Oh-RAM! One and a Half Round Atomic Memory

Emulating atomic read/write shared objects in a message-passing system is a fundamental problem in distributed computing. Considering that network communication is the most expensive resource, efficiency is measured first of all in terms of the communication needed to implement read and write operations. It is well known that 2 communication round-trip phases involving in total 4 message exchanges are sufficient to implemented atomic operations. It is also known that under certain constraints on the number of readers with respect to the numbers of replica servers and failures it is possible to implement single-writer atomic objects such that each operation involves one round-trip phase. We present algorithms that allow operations to complete in 3 communication exchanges without imposing any constraints on the number of readers and writers. Specifically, we present an atomic memory implementation for the SWMR setting, where reads complete in 3 communication exchanges and writes complete in 2 exchanges. We pose the question of whether it is possible to implement MWMR memory where operations complete in at most 3 communication exchanges. We answer this question in the negative by showing that an atomic memory implementation is impossible if both read and write operations take 3 communication exchanges, even when assuming two writers, two readers, and a single replica server failure. Motivated by this impossibility result, we provide a MWMR atomic memory implementation where reads involve 3 and writes 4 communication exchanges. In light of our impossibility result these algorithms are optimal in terms of the number of communication exchanges. We rigorously reason about the correctness of the algorithms.

cs.DC↗

arXiv2018

Doing-it-All with Bounded Work and Communication

We consider the Do-All problem, where $p$ cooperating processors need to complete $t$ similar and independent tasks in an adversarial setting. Here we deal with a synchronous message passing system with processors that are subject to crash failures. Efficiency of algorithms in this setting is measured in terms of work complexity (also known as total available processor steps) and communication complexity (total number of point-to-point messages). When work and communication are considered to be comparable resources, then the overall efficiency is meaningfully expressed in terms of effort defined as work + communication. We develop and analyze a constructive algorithm that has work $O( t + p \log p\, (\sqrt{p\log p}+\sqrt{t\log t}\, ) )$ and a nonconstructive algorithm that has work $O(t +p \log^2 p)$. The latter result is close to the lower bound $Ω(t + p \log p/ \log \log p)$ on work. The effort of each of these algorithms is proportional to its work when the number of crashes is bounded above by $c\,p$, for some positive constant $c < 1$. We also present a nonconstructive algorithm that has effort $O(t + p ^{1.77})$.

cs.DC↗

arXiv2018

Unleashing and Speeding Up Readers in Atomic Object Implementations

Providing efficient emulations of atomic read/write objects in asynchronous, crash-prone, message-passing systems is an important problem in distributed computing. Communication latency is a factor that typically dominates the performance of message-passing systems, consequently the efficiency of algorithms implementing atomic objects is measured in terms of the number of communication exchanges involved in each read and write operation. The seminal result of Attiya, Bar-Noy, and Dolev established that two pairs of communication exchanges, or equivalently two round-trip communications, are sufficient. Subsequent research examined the possibility of implementations that involve less than four exchanges. The work of Dutta et al. showed that for single-writer/multiple-reader (SWMR) settings two exchanges are sufficient, provided that the number of readers is severely constrained with respect to the number of object replicas in the system and the number of replica failures, and also showed that no two exchange implementations of multiple-writer/multiple-reader (MWMR) objects are possible. Later research focused on providing implementations that remove the constraint on the number of readers, while having read and write operations that use variable number of communication exchanges, specifically two, three, or four exchanges. This work presents two advances in the state-of-the-art in this area. Specifically, for SWMR and MWMR systems algorithms are given in which read operations take two or three exchanges. This improves on prior works where read operations took either (a) three exchanges, or (b) two or four exchanges. The number of readers in the new algorithms is unconstrained, and write operations take the same number of exchanges as in prior work (two for SWMR and four for MWMR settings). The correctness of algorithms is rigorously argued.

cs.DC↗

arXiv2016

Storage-Optimized Data-Atomic Algorithms for Handling Erasures and Errors in Distributed Storage Systems

Erasure codes are increasingly being studied in the context of implementing atomic memory objects in large scale asynchronous distributed storage systems. When compared with the traditional replication based schemes, erasure codes have the potential of significantly lowering storage and communication costs while simultaneously guaranteeing the desired resiliency levels. In this work, we propose the Storage-Optimized Data-Atomic (SODA) algorithm for implementing atomic memory objects in the multi-writer multi-reader setting. SODA uses Maximum Distance Separable (MDS) codes, and is specifically designed to optimize the total storage cost for a given fault-tolerance requirement. For tolerating $f$ server crashes in an $n$-server system, SODA uses an $[n, k]$ MDS code with $k=n-f$, and incurs a total storage cost of $\frac{n}{n-f}$. SODA is designed under the assumption of reliable point-to-point communication channels. The communication cost of a write and a read operation are respectively given by $O(f^2)$ and $\frac{n}{n-f}(δ_w+1)$, where $δ_w$ denotes the number of writes that are concurrent with the particular read. In comparison with the recent CASGC algorithm, which also uses MDS codes, SODA offers lower storage cost while pays more on the communication cost. We also present a modification of SODA, called SODA$_{\text{err}}$, to handle the case where some of the servers can return erroneous coded elements during a read operation. Specifically, in order to tolerate $f$ server failures and $e$ error-prone coded elements, the SODA$_{\text{err}}$ algorithm uses an $[n, k]$ MDS code such that $k=n-2e-f$. SODA$_{\text{err}}$ also guarantees liveness and atomicity, while maintaining an optimized total storage cost of $\frac{n}{n-f-2e}$.

cs.DC↗