ﻻ يوجد ملخص باللغة العربية
Simulating a shared register can mask the intricacies of designing algorithms for asynchronous message-passing systems subject to crash failures, since it allows them to run algorithms designed for the simpler shared-memory model. Typically such simulations replicate the value of the register in multiple servers and require readers and writers to communicate with a majority of servers. The success of this approach for static systems, where the set of nodes (readers, writers, and servers) is fixed, has motivated several similar simulations for dynamic systems, where nodes may enter and leave. However, existing simulations need to assume that the system eventually stops changing for a long enough period or that the system size is bounded. This paper presents the first simulation of an atomic read/write register in a crash-prone asynchronous system that can change size and withstand nodes continually entering and leaving. The simulation allows the system to keep changing, provided that the number of nodes entering and leaving during a fixed time interval is at most a constant fraction of the current system size. The simulation also tolerates node crashes as long as the number of failed nodes in the system is at most a constant fraction of the current system size.
We investigate the minimal number of failures that can partition a system where processes communicate both through shared memory and by message passing. We prove that this number precisely captures the resilience that can be achieved by algorithms th
We consider shared-object systems that require their threads to fulfill the system jobs by first acquiring sequentially the objects needed for the jobs and then holding on to them until the job completion. Such systems are in the core of a variety of
In order to converge in the presence of concurrent updates, modern eventually consistent replication systems rely on causality information and operation semantics. It is relatively easy to use semantics of high-level operations on replicated data str
The most demanding tenants of shared clouds require complete isolation from their neighbors, in order to guarantee that their application performance is not affected by other tenants. Unfortunately, while shared clouds can offer an option whereby ten
Many cluster management systems (CMSs) have been proposed to share a single cluster with multiple distributed computing systems. However, none of the existing approaches can handle distributed machine learning (ML) workloads given the following crite