Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userZeus: Locality-aware Distributed Transactions
99
0
0.0
(
0
)
Added by
Antonios Katsarakis
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Authors
Antonios Katsarakis
Ask ChatGPT about the research
No Arabic abstract
State-of-the-art distributed in-memory datastores (FaRM, FaSST, DrTM) provide strongly-consistent distributed transactions with high performance and availability. Transactions in those systems are fully general; they can atomically manipulate any set of objects in the store, regardless of their location. To achieve this, these systems use complex distributed transactional protocols. Meanwhile, many workloads have a high degree of locality. For such workloads, distributed transactions are an overkill as most operations only access objects located on the same server -- if sharded appropriately. In this paper, we show that for these workloads, a single-node transactional protocol combined with dynamic object re-sharding and asynchronously pipelined replication can provide the same level of generality with better performance, simpler protocols, and lower developer effort. We present Zeus, an in-memory distributed datastore that provides general transactions by acquiring all objects involved in the transaction to the same server and executing a single-node transaction on them. Zeus is fault-tolerant and strongly-consistent. At the heart of Zeus is a reliable dynamic object sharding protocol that can move 250K objects per second per server, allowing Zeus to process millions of transactions per second and outperform more traditional distributed transactions on a wide range of workloads that exhibit locality.
rate research
Read More
Many distributed storage systems are transactional and a lot of work has been devoted to optimizing their performance, especially the performance of read-only transactions that are considered the most frequent in practice. Yet, the results obtained so far are rather disappointing, and some of the design decisions seem contrived. This paper contributes to explaining this state of affairs by proving intrinsic limitations of transactional storage systems, even those that need not ensure strong consistency but only causality. We first consider general storage systems where some transactions are read-only and some also involve write operations. We show that even read-only transactions cannot be fast: their operations cannot be executed within one round-trip message exchange between a client seeking an object and the server storing it. We then consider systems (as sometimes implemented today) where all transactions are read-only, i.e., updates are performed as individual operations outside transactions. In this case, read-only transactions can indeed be fast, but we prove that they need to be visible. They induce inherent updates on the servers, which in turn impact their overall performance.
Distributed systems achieve scalability by distributing load across many machines, but wide-area deployments can introduce worst-case response latencies proportional to the networks diameter. Crux is a general framework to build locality-preserving distributed systems, by transforming an existing scalable distributed algorithm A into a new locality-preserving algorithm ALP, which guarantees for any two clients u and v interacting via ALP that their interactions exhibit worst-case response latencies proportional to the network latency between u and v. Crux builds on compact-routing theory, but generalizes these techniques beyond routing applications. Crux provides weak and strong consistency flavors, and shows latency improvements for localized interactions in both cases, specifically up to several orders of magnitude for weakly-consistent Crux (from roughly 900ms to 1ms). We deployed on PlanetLab locality-preservi
Context: Concurrent objects with asynchronous messaging are an increasingly popular way to structure highly available, high performance, large-scale software systems. To ensure data-consistency and support synchronization between objects such systems often use distributed transactions with Two-Phase Locking (2PL) for concurrency control and Two-Phase commit (2PC) as atomic commitment protocol. Inquiry In highly available, high-throughput systems, such as large banking infrastructure, however, 2PL becomes a bottleneck when objects are highly contended, when an object is queuing a lot of messages because of locking. Approach: In this paper we introduce Path-Sensitive Atomic Commit (PSAC) to address this situation. We start from message handlers (or methods), which are decorated with pre- and post-conditions, describing their guards and effect. Knowledge: This allows the PSAC lock mechanism to check whether the effect of two incoming messages at the same time are independent, and to avoid locking if this is the case. As a result, more messages are directly accepted or rejected, and higher overall throughput is obtained. Grounding: We have implemented PSAC for a state machine-based DSL called Rebel, on top of a runtime based on the Akka actor framework. Our performance evaluation shows that PSAC exhibits the same scalability and latency characteristics as standard 2PL/2PC, and obtains up to 1.8 times median higher throughput in congested scenarios. Importance: We believe PSAC is a step towards enabling organizations to build scalable distributed applications, even if their consistency requirements are not embarrassingly parallel.
As ISPs begin to cooperate to expose their network locality information as services, e.g., P4P, solutions based on locality information provision for P2P traffic localization will soon approach their capability limits. A natural question is: can we do any better provided that no further locality information improvement can be made? This paper shows how the utility of locality information could be limited by conventional P2P data scheduling algorithms, even as sophisticated as the local rarest first policy. Network codings simplified data scheduling makes it competent for improving P2P applications throughput. Instead of only using locality information in the topology construction, this paper proposes the locality-aware network coding (LANC) that uses locality information in both the topology construction and downloading decision, and demonstrates its exceptional ability for P2P traffic localization. The randomization introduced by network coding enhances the chance for a peer to find innovative blocks in its neighborhood. Aided by proper locality-awareness, the probability for a peer to get innovative blocks from its proximity will increase as well, resulting in more efficient use of network resources. Extensive simulation results show that LANC can significantly reduce P2P traffic redundancy without sacrificing application-level performance. Aided by the same locality knowledge, the traffic redundancies of LANC in most cases are less than 50% of the current best approach that does not use network coding.
While many researchers adopt a sharding approach to design scaling blockchains, few works have studied the transaction placement problem incurred by sharding protocols. The widely-used hashing placement algorithm renders an overwhelming portion of transactions as cross-shard. In this paper, we analyze the high cost of cross-shard transactions and reveal that most Bitcoin transactions have simple dependencies and can become single-shard under a placement algorithm taking transaction dependencies into account. In addition, we perform a case study of OptChain, which is the state-of-the-art transaction placement algorithm for sharded blockchains, and find a defect of it. A fix is proposed, and our evaluation results demonstrate that the fix helps OptChain improve the system throughput by 4x.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
