On Non-Preemptive VM Scheduling in the Cloud

Abstract

We study the problem of scheduling VMs (Virtual Machines) in a distributed server platform, motivated by cloud computing applications. The VMs arrive dynamically over time to the system, and require a certain amount of resources (e.g. memory, CPU, etc) for the duration of their service. To avoid costly preemptions, we consider non-preemptive scheduling: Each VM has to be assigned to a server which has enough residual capacity to accommodate it, and once a VM is assigned to a server, its service cannot be disrupted (preempted). Prior approaches to this problem either have high complexity, require synchronization among the servers, or yield queue sizes/delays which are excessively large. We propose a non-preemptive scheduling algorithm that resolves these issues. In general, given an approximation algorithm to Knapsack with approximation ratio r , our scheduling algorithm can provide r β fraction of the throughput region for β < r . In the special case of a greedy approximation algorithm to Knapsack, we further show that this condition can be relaxed to β < 1. The parameters β and r can be tuned to provide a tradeoff between achievable throughput, delay, and computational complexity of the scheduling algorithm. Finally extensive simulation results using both synthetic and real traffic traces are presented to verify the performance of our algorithm.

Scheduling Jobs with Random Resource Requirements in Computing Clusters

“…Since this may not happen under general service time distributions (e.g. one may construct adversarial service durations that prevent server from becoming empty), in all our algorithms we can incorporate a stalling technique proposed in [11] that actively forces a server to become empty by preventing it from scheduling new jobs. The decision to stall a server is made whenever server operates in an "inefficient" configuration.…”

“…In the second category, we have schedulers with throughput guarantees, e.g., [6], [8], [9], [10], [11]. They work under the assumption that there is a finite number of discrete job types.…”

“…In this case, it is well known that the supportable workload region is the sum of convex hull of feasible configurations of servers, e.g. [6], [8], [9], [10], [11], which are defined as follows.…”

“…The optimal or near-optimal scheduling policies then basically follow the well-known MaxWeight algorithm [21]. Let Q j (t) be the number of type-j jobs waiting in queue at time t. At any time t for each server , the algorithm maintains a feasible configuration k(t) that has the "maximum weight" [8], [9] (or a fraction of the maximum weight [11]), among all the feasible configurations K. The weight of a configuration is formally defined below.…”

“…The majority of the past work relies on a crucial assumption that there is a predefined finite set of discrete types, e.g. [6], [7], [8], [9], [10], [11]. Although we can consider every possible resource profile as a type, the number of such types could be formidably large.…”