With the rapid increase in the size and volume of cloud services and data centers, architectures with multiple job dispatchers are quickly becoming the norm. Load balancing is a key element of such systems. Nevertheless, current solutions to load balancing in such systems admit a paradoxical behavior in which more accurate information regarding server queue lengths degrades performance due to herding and detrimental incast effects. Indeed, both in theory and in practice, there is a common doubt regarding the value of information in the context of multi-dispatcher load balancing. As a result, both researchers and system designers resort to more straightforward solutions, such as the power-of-two-choices to avoid worst-case scenarios, potentially sacrificing overall resource utilization and system performance. A principal focus of our investigation concerns the value of information about queue lengths in the multi-dispatcher setting. We argue that, at its core, load balancing with multiple dispatchers is a distributed computing task. In that light, we propose a new job dispatching approach, called Tidal Water Filling, which addresses the distributed nature of the system. Specifically, by incorporating the existence of other dispatchers into the decision-making process, our protocols outperform previous solutions in many scenarios. In particular, when the dispatchers have complete and accurate information regarding the server queues, our policies significantly outperform all existing solutions.

This paper provides a formal framework for reasoning about randomized distributed algorithms. We generalize the notion of indistinguishability, the most useful tool in deterministic lower bounds, to apply to a probabilistic setting. We use the new notion to prove a lower bound on the probability at which it can be guaranteed that honest parties will not decide on a possibly bogus value. Moreover, we show that the bound is tight by providing a protocol that matches the bound. This completely characterizes the quality of decisions that protocols for a randomized multi-valued Consensus problem can guarantee in an asynchronous environment with Byzantine faults.

This paper investigates how null messages can transfer information in fault-prone synchronous systems. The notion of an f-resilient message block is defined and is shown to capture the fundamental communication pattern for knowledge transfer. In general, this pattern combines both null messages and explicit messages. It thus provides a fault-tolerant extension of the classic notion of a message-chain. Based on the above, we provide tight necessary and sufficient characterizations of the generalized communication patterns that can serve to solve the distributed tasks of (nice-run) Signalling and Ordered Response.

Current-day data centers and high-volume cloud services employ a broad set of heterogeneous servers. In such settings, client requests typically arrive at multiple entry points, and dispatching them to servers is an urgent distributed systems problem. This paper presents an efficient solution to the load balancing problem in such systems that improves on and overcomes problems of previous solutions. The load balancing problem is formulated as a stochastic optimization problem, and an efficient algorithmic solution is obtained based on a subtle mathematical analysis of the problem. Finally, extensive evaluation of the solution on simulated data shows that it outperforms previous solutions. Moreover, the resulting dispatching policy can be computed very efficiently, making the solution practically viable.

Lower bounds and impossibility results in distributed computing are both intellectually challenging and practically important. Hundreds if not thousands of proofs appear in the literature, but surprisingly, the vast majority of them apply to deterministic algorithms only. Probabilistic protocols have been around for at least four decades and are receiving a lot of attention with the emergence of blockchain systems. Nonetheless, we are aware of only a handful of randomized lower bounds. In this work we provide a formal framework for reasoning about randomized distributed algorithms. We generalize the notion of indistinguishability, the most useful tool in deterministic lower bounds, to apply to a probabilistic setting. We apply this framework to prove a result of independent interest. Namely, we completely characterize the quality of decisions that protocols for a randomized multi-valued Consensus problem can guarantee in an asynchronous environment with Byzantine faults. We use the new notion to prove a lower bound on the guaranteed probability that honest parties will not decide on a possibly bogus value proposed by a malicious party. Finally, we show that the bound is tight by providing a protocol that matches it. This brief announcement consists of an introduction to the full paper [Guy Goren et al., 2020] by the same title. The interested reader is advised to consult the full paper for a detailed exposition.

In reliable settings, null messages allow the transfer of information without explicit communication in cases of interest. We investigate the use of null messages in the much more challenging Byzantine model (without signatures). Different ways of using null messages are discussed. One of them, called a silent validation round, can provide processes with global information about all correct sites of the system, without any message exchange. As a case study, we consider optimizing the behavior in failure-free runs of protocols for the classic Byzantine Consensus problem.

With the rapid increase in the size and volume of cloud services and data centers, architectures with multiple job dispatchers are quickly becoming the norm. Load balancing is a key element of such systems. Nevertheless, current solutions to load balancing in such systems admit a paradoxical behavior in which more accurate information regarding server queue lengths degrades performance due to herding and detrimental incast effects. Indeed, both in theory and in practice, there is a common doubt regarding the value of information in the context of multi-dispatcher load balancing. As a result, both researchers and system designers resort to more straightforward solutions, such as the power-of-two-choices to avoid worst-case scenarios, potentially sacrificing overall resource utilization and system performance. A principal focus of our investigation concerns the value of information about queue lengths in the multi-dispatcher setting. We argue that, at its core, load balancing with multiple dispatchers is a distributed computing task. In that light, we propose a new job dispatching approach, called Tidal Water Filling, which addresses the distributed nature of the system. Specifically, by incorporating the existence of other dispatchers into the decision-making process, our protocols outperform previous solutions in many scenarios. In particular, when the dispatchers have complete and accurate information regarding the server queue lengths, our policies significantly outperform all existing solutions.

The cost of communication is a substantial factor affecting the scalability of many distributed applications. Every message sent can incur a cost in storage, computation, energy, and bandwidth. Consequently, reducing the communication costs of distributed applications is highly desirable. The best way to reduce message costs is by communicating without sending any messages whatsoever. This article initiates a rigorous investigation into the use of silence in synchronous settings, in which processes can fail. We formalize sufficient conditions for information transfer using silence, as well as necessary conditions for particular cases of interest. This allows us to identify message patterns that enable communication through silence. In particular, a pattern called a silent choir is identified, and shown to be central to information transfer via silence in failure-prone systems. The power of the new framework is demonstrated on the atomic commitment problem (AC). A complete characterization of the tradeoff between message complexity and round complexity in the synchronous model with crash failures is provided, in terms of lower bounds and matching protocols. In particular, a new message-optimal AC protocol is designed using silence, in which processes decide in three rounds in the common case. This significantly improves on the best previously known message-optimal AC protocol, in which decisions were performed in Θ( n ) rounds. And in the naked light I saw Ten thousand people, maybe more People talking without speaking … People writing songs that voices never share And no one dared Disturb the sound of silence Paul Simon, 1964