No abstract

This paper presents an extensive analysis of the client workloads for educational media servers at two major U.S. universities. The goals of the analysis include providing data for generating synthetic workloads, gaining insight into the design of streaming content distribution networks, and quantifying how much server bandwidth can be saved in interactive educational environments by using recently developed multicast streaming methods for stored content.

AbstreetThispaper proposes a set of efficient primitives for process synchronization in muitiprocessors. The only assumptions made in developing the set of primitives are that hardware combining is not implemented in the hterconnect, and (in one case) that the interconnect supports broadcast.The primitives make use of synchronization bits (syncbits) to provide a simple mechanism for mutual exclusion. The proposed implementation of the primitives includes efEcient (Le. kxal) busy-waiting for syncbit& In addition, a hardware-supported mechanism for maintaining a first-come ih-st-serve queue of requests for a syncbit is proposed. This queueing mechanism aiiows for a very efEcient implementation of, as well as fair access to, binary semaphores.We also Propose t0 implement Fetch-and-Add with combining in software rather than hardware. This allows an architecture to scale to a huge number of processors while avoiding the cost of hardware combining.Scenarios for common synchronization events such as work queues and barriers are presented to demonstrate the generality and ease of use of the proposed primitives. The efficient implementation of the primitives is simpler if the multiprocessor has a hardware cache-consistency protocol. To illustrate this point, we outline how the primitives would be implemented in the Multicube multiprocessor [GoWofB].

No abstract

The performance potential of run-to-completion (RTC) parallel processor scheduling policies is investigated by examining whether ( 1) application execuhon rate characteristics such as average parallelism (avg) and processor wvrking set (pw's) andlor (2) limited preemption can be used to improve the performance of these policies. We address the first question by comparing policies (previous as well as new) that differ only In whether or not they use execution rate characteristics and by examining a wider range of the workload parameter space than previous studies. We address the second question by comparing a simple two-level queueing policy with RTC scheduling in the second level queue against RTC policies that don't allow any preemption and against dynamic equiallocation (EQ).Using simulation to estimate mean response times we find that for promising RTC policies such as adaptive static partitioning (ASP) and shortest demand first (SDF), a maximum allocation constraint that is for all practical purposes independent of avg and p ws prowdes greater and more consistent improvement in policy pert'ormance than using avg or pws. Also, under the assumption that job demand information is unavailable to the scheduler we show that the ASP-max policy outperforms all previous high performance RTC policies for workloads with coefficient of variation in processing requirement greater than one. Furthermore, a two-level queue that allows at most one preemption per job outperforms ASP-max but is not competitive with EQ.