Kalman Z. Meth

Object storage: the future building block for storage systems

The concept of object storage was introduced in the early 1990s by the research community. Since then it has greatly matured and is now in its early stages of adoption by the industry. Yet, object storage is still not widely accepted. Viewing object store technology as the future building block particularly for large storage systems, our team in IBM Haifa Research Lab has invested substantial efforts in this area. In this position paper we survey the latest developments in the area of object store technology, focusing on standardization, research prototypes, and technology adoption and deployment. A major step has been the approval of the TIO OSD protocol (version I) as an OSD standard in late 2004. We also report on prototyping efforts that are carried out in IBM Haifa Research Lab in building an object store. Our latest prototype is compliant with a large subset of the TIO standard. To facilitate deployment of the new technology and protocol in the community at large, our team also implemented a TIO-compliant OSD (iSCSI) initiator for Linux. The initiator is interoperable with object disks of other vendors. The initiator is available as an open source driver for Linux.

Design of the iSCSI protocol

The iSCSI protocol enables accessing SCSI I/O devices over an IP network. TCP is used as a transport for SCSI I/O commands. We describe the design considerations and decisions in defining the iSCSI protocol: why we use TCP how multiple TCP connections can be used to increase performance and reliability, why we require allegiance of a command to a particular TCP connection, the importance of Direct Data Placement, various levels and complexity of error recovery, security and naming issues.

Storage modeling for power estimation

Power consumption is a major issue in todays datacenters. Storage typically comprises a significant percentage of datacenter power. Thus, understanding, managing, and reducing storage power consumption is an essential aspect of any efforts that address the total power consumption of datacenters. We developed a scalable power modeling method that estimates the power consumption of storage workloads. The modeling concept is based on identifying the major workload contributors to the power consumed by the disk arrays. To estimate the power consumed by a given host workload, our method translates the workload to the primitive activities induced on the disks. In addition, we identified that I/O queues have a fundamental influence on the power consumption. Our power estimation results are highly accurate, with only 2% deviation for typical random workloads with small transfer sizes (up to 8K), and a deviation of up to 8% for workloads with large transfer sizes. We successfully integrated our modeling into a power-aware capacity planning tool to predict system power requirements and integrated it into an online storage system to provide online estimation for the power consumed.

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.

Leveraging disk drive acoustic modes for power management

Reduction of disk drive power consumption is a challenging task, particularly since the most prevalent way of achieving it, powering down idle disks, has many undesirable side-effects. Some hard disk drives support acoustic modes, meaning they can be configured to reduce the acceleration and velocity of the disk head. This reduces instantaneous power consumption but sacrifices performance. As a result, input/output (I/O) operations run longer at reduced power. This is useful for power capping since it causes significant reduction in peak power consumption of the disks. We conducted experiments on several disk drives that support acoustic management. Most of these disk drives support only two modes — quiet and normal. We ran different I/O workloads, including SPC-1 to simulate a real-world online transaction processing workload. We found that the reduction in peak power can reach up to 23% when using quiet mode. We show that for some workloads this translates into a reduction of 12.5% in overall energy consumption. In other workloads we encountered the opposite phenomenon-an increase of more than 6% in the overall energy consumption.

Zero-Copy Receive for Virtualized Network Devices

When receiving network traffic on guest VMs (virtual machines) running on the KVM hypervisor, data is copied from hypervisor buffers to guest buffers. This copy incurs CPU and latency overhead. It seems desirable to avoid this copy, if possible, and to use guest buffers directly to receive network data. A number of challenges must be overcome in order to accomplish this zero-copy receive, and some additional overhead is incurred in setting it up. We present the technical details on a zero-copy receive design and implementation and discuss the resulting performance degradation. In our implementation, the savings in CPU from avoiding the copy is overshadowed by the extra handling required for the smaller and often underutilized buffers .

MIKELANGELO: MIcro KErneL virtualizAtioN for hiGh pErfOrmance cLOud and HPC Systems

MIKELANGELO is a project, targeted to disrupt the core underlying technologies of Cloud computing, enabling even bigger uptake of Cloud computing, HPC in the Cloud and Big Data technologies under one umbrella. The vision of it is to improve responsiveness, agility and security of the virtual infrastructure through packaged applications, using lean guest operating system OSv and superfast hypervisor SuperKVM. In short, the work will concentrate on improvement of virtual I/O in KVM, using additional virtio expertise, integrated with the light-weight operating system OSv and with enhanced Security. The HPC in the Cloud focus will be provided through involvement of a large HPC centre, with the ability and business need to cloudify their HPC business. The Consortium consists of hand-picked experts (e.g., the original creator of KVM - Avi Kivity) who participate in the overall effort to reduce one of the last performance hurdles in the virtualisation (I/O). Other layers of inefficiency are addressed through OSv (thin operating system). Such approach will allow for use of MIKELANGELO stack on heterogeneous infrastructures, with high responsiveness, agility and improved security. The targeted audience are primarily SMEs (e.g. simulation dependent SMEs) and data center operators who either benefit from higher performance or flexibility, introduced by the software stack. Four real world use-cases with clear owners, serve as validators and also directly contribute to the exploitation of project results.

Zero-copy receive path in virtio

In the KVM hypervisor, incoming packets from the network must pass through several objects in the Linux kernel before being delivered to the guest VM. Currently, both the hypervisor and the guest keep their own sets of buffers on the receive path. For large packets, the overall processing time is dominated by the copying of data from hypervisor buffers to guest buffers.