Ofer Biran

A Stable Network-Aware VM Placement for Cloud Systems

Virtual Machine (VM) placement has to carefully consider the aggregated resource consumption of co-located VMs in order to obey service level agreements at lower possible cost. In this paper, we focus on satisfying the traffic demands of the VMs in addition to CPU and memory requirements. This is a much more complex problem both due to its quadratic nature (being the communication between a pair of VMs) and since it involves many factors beyond the physical host, like the network topologies and the routing scheme. Moreover, traffic patterns may vary over time and predicting the resulting effect on the actual available bandwidth between hosts within the data center is extremely difficult. We address this problem by trying to allocate a placement that not only satisfies the predicted communication demand but is also resilient to demand time-variations. This gives rise to a new optimization problem that we call the Min Cut Ratio-aware VM Placement (MCRVMP). The general MCRVMP problem is NP-Hard, hence, we introduce several heuristics to solve it in reasonable time. We present extensive experimental results, associated with both placement computation and run-time performance under time-varying traffic demands, to show that our heuristics provide good results (compared to the optimal solution) for medium size data centers.

Guaranteeing High Availability Goals for Virtual Machine Placement

The placement of virtual machines (VMs) on a cluster of hosts under multiple constraints, including administrative (security, regulations) resource-oriented (capacity, energy), and QoS-oriented (performance) is a highly complex task. We define a new high-availability property for a VM, when a VM is marked as k-resilient, as long as there are up to k host failures, it should be guaranteed that it can be relocated to a non-failed host without relocating other VMs. Together with Hardware Predictive Failure Analysis and live migration, which enable VMs to be evacuated from a host before it fails, this property allows the continuous running of VMs on the cluster despite host failures. The complexity of the constraints associated with k-resiliency, which are naturally expressed by Second Order logic statements, prevented their integration into the placement computation until now. We present a novel algorithm which enables this integration by transforming the k-resiliency constraints to rules consumable by a generic Constraint Programming engine, prove that it guarantees the required resiliency and describe the implementation. We provide some preliminary results and compare our high availability support with naive solutions.

VM Placement Strategies for Cloud Scenarios

The problem of Virtual Machine (VM) placement in a compute cloud infrastructure is well-studied in the literature. However, the majority of the existing works ignore the dynamic nature of the incoming stream of VM deployment requests that continuously arrive to the cloud provider infrastructure. In this paper we provide a practical model of cloud placement management under a stream of requests and present a novel technique called Backward Speculative Placement (BSP) that projects the past demand behavior of a VM to a candidate target host. We exploit the BSP technique in two algorithms, first for handling the stream of deployment requests, second in a periodic optimization, to handle the dynamic aspects of the demands. We show the benefits of our BSP technique by comparing the results on a simulation period with a strategy of choosing an optimal placement at each time instant, produced by a generic MIP solver.

Internet Protocol storage area networks

The sheer scale of the storage needs of most organizations makes block storage management an important system administration problem. Application servers, databases, and file systems rely on an efficient underlying block storage system. The storage area network paradigm is fast emerging as a desirable block storage solution, due to its performance, resource-sharing, and capacity-scaling benefits. This paper shows that the ubiquitous Internet Protocol (IP) network is technically well-suited to host a storage area network. The paper presents the storage protocol, management, and security building blocks that are necessary for making IP storage a reality. The paper then discusses performance issues that must be addressed in order to make IP storage area networks competitive with other storage area network technologies.

Tight bounds on the round complexity of distributed 1-solvable tasks

Abstract A distributed task T is 1-solvable if there exists a protocol that solves it in the presence of (at most) one crash failure. A precise characterization of the 1-solvable tasks was given by Biran et al. (1990). In this paper we determine the number of rounds of communication that are required, in the worst case, by a protocol which 1-solves a given 1-solvable task T for n processors. We define the radius R ( T ) of T , and show that if R ( T ) is finite, then the number of rounds is Θ ( log n R ( T )); more precisely, we give a lower bound of log ( n − 1) R ( T ), and an upper bound of 2 + ⌈ log ( n − 1) R ( T )⌉. The upper bound implies, for example, that each of the following tasks: renaming, order preserving renaming (Attiya et al, 1990) and binary monotone consensus (Biran et al., 1990) can be solved in the presence of one fault in 3 rounds of communications. All previous protocols that 1-solved these tasks required Ω(n) rounds. The result is also generalized to tasks whose radii are not bounded, e.g., the approximate consensus and its variants (Dolev et al., 1986; Biran et al., 1990).

Technical forum—Management of application complexes in multitier clustered systems

In this Technical Forum article, we describe a generalized management framework for application complexes in multitiered cluster environments. The application complexes can be viewed as distinct autonomic computing entities that live together in thecluster. The management framework was implemented on a rack-mounted cluster of servers using the IBM Director management tool.

A virtual resource placement service

Server, storage, and network virtualization and the growing adoption of cloud computing has expanded both the complexity and the value of intelligent allocation and management of data center resources. Resource allocation in a cloud environment is of fundamental importance. There are many competing goals, with differing priorities, that contribute to optimizing virtual resource allocation and placement including performance, reliability, security, energy, etc. We have developed an open extensible architecture to provide placement recommendations which allows for different independently developed Domain Managers to provide input/advice on placement. We have further developed the means to orchestrate the placement, ensuring that the required configuration actions be enacted both before and after the migration of the virtual machine. This paper explores the topic of providing a core placement calculation and orchestration architecture to facilitate management of workload demands in a cloud environment. We describe this architecture for placement services and orchestration, and present some results from a prototype implementation.

Composite-Path Switching

Hybrid switching combines a high-bandwidth optical circuit switch in parallel with a low-bandwidth electronic packet switch. It presents an appealing solution for scaling datacenter architectures. Unfortunately, it does not fit many traffic patterns produced by typical datacenter applications, and in particular the skewed traffic patterns that involve highly intensive one-to-many and many-to-one communications. In this paper, we introduce composite-path switching by allowing for composite circuit/packet paths between the two switches. We show how this enables the datacenter network to deal with skewed traffic patterns, and offer a practical scheduling algorithm that can directly extend any hybrid-switching scheduling algorithm. Through extensive evaluations using modern datacenter workloads, we show how our solution outperforms two recently proposed state-of-the-art scheduling techniques, both in completion time and in circuit utilization.

Cloud services brokering for elastic workloads

With the growing trend of using public clouds for significant portion of enterprise workloads and the multitude of available cloud providers, arises a real need for brokerage of cloud services. The IBM Cloud Service Broker adds value to cloud services on behalf of cloud consumers by providing the means to handle relationships with multiple cloud providers. It allows the consumer to compare and select the best matching cloud offerings for each workload, taking into account various aspects such as QoS, policies, regulations, and cost. Furthermore, it supports orchestrated workload provisioning and resource allocation over different clouds.