Bo Hong

Managing flash crowds on the Internet

A flash crowd is a surge in traffic to a particular Web site that causes the site to be virtually unreachable. We present a model of flash crowd events and evaluate the performance of various multilevel caching techniques suitable for managing these events. By using well-dispersed caches and with judicious choice of replacement algorithms we show reductions in client response times by as much as a factor of 25. We also show that these caches eliminate the server and network hot spots by distributing the load over the entire network.

The relevance of long-range dependence in disk traffic and implications for trace synthesis

Accurate disk workloads are crucial for storage systems design, but I/O traces are difficult to obtain, unwieldy to work with, and unparameterizable. I/O traces are often bursty and difficult to characterize. Although good models of I/O workloads would be extremely useful, such bursty traces cannot accurately be modeled using exponential or Poisson arrival times. Much experimental evidence suggests that I/O traces are self-similar, which researchers have hoped might help to model bursty traces. In this paper, we show that self-similarity at large time scales does not significantly affect disk behavior with respect to response times. This allows us to generate synthetic arrival patterns at relatively small time scales, improving the accuracy of trace generation. The relative error of our method, with input parameters suitable for the workload, ranges from approximately 8% to 12%.

Zone-based shortest positioning time first scheduling for MEMS-based storage devices

Access latency to secondary storage devices is frequently a limiting factor in computer system performance. New storage technologies promise to provide greater storage densities at lower latencies than is currently obtainable with hard disk drives. MEMS-based storage devices use orthogonal magnetic or physical recording techniques and thousands of simultaneously active MEMS-based read-write tips to provide high-density low-latency nonvolatile storage. These devices promise seek times 10-20 times faster than hard drives, storage densities 10 times greater, and power consumption an order of magnitude lower. Previous research has examined data layout and request ordering algorithms that are analogs of those developed for hard drives. We present an analytical model of MEMS device performance that motivates a computationally simple MEMS-based request scheduling algorithm called ZSPTF, which has average response times comparable to shortest positioning time first (SPTF) but with response time variability comparable to circular scan (C-SCAN).

Using MEMS-based storage in computer systems---device modeling and management

MEMS-based storage is an emerging nonvolatile secondary storage technology. It promises high performance, high storage density, and low power consumption. With fundamentally different architectural designs from magnetic disk, MEMS-based storage exhibits unique two-dimensional positioning behaviors and efficient power state transitions. We model these low-level, device-specific properties of MEMS-based storage and present request scheduling algorithms and power management strategies that exploit the full potential of these devices. Our simulations show that MEMS-specific device management policies can significantly improve system performance and reduce power consumption.

Using MEMS-based storage in computer systems---MEMS storage architectures

As an emerging nonvolatile secondary storage technology, MEMS-based storage exhibits several desirable properties including high performance, high storage volumic density, low power consumption, low entry cost, and small form factor. However, MEMS-based storage provides a limited amount of storage per device and is likely to be more expensive than magnetic disk. Systems designers will therefore need to make trade-offs to achieve well-balanced designs. We present an architecture in which MEMS devices are organized into MEMS storage enclosures with online spares. Such enclosures are proven to be highly reliable storage building bricks with no maintenance during their economic lifetimes. We also demonstrate the effectiveness of using MEMS as another layer in the storage hierarchy, bridging the cost and performance gap between MEMS storage and disk. We show that using MEMS as a disk cache can significantly improve system performance and cost-performance ratio.

Using MEMS-based storage to boost disk performance

Non-volatile storage technologies such as flash memory, magnetic RAM (MRAM), and MEMS-based storage are emerging as serious alternatives to disk drives. Among these, MEMS storage is predicted to be the least expensive and highest density, and at about 1 ms access times still considerably faster than hard disk drives. Like the other emerging non-volatile storage technologies, it is highly suitable for small mobile devices but it is expensive to replace hard drives entirely. Its non-volatility, dense storage, and high performance still make it an ideal candidate for the secondary storage subsystem. We examine the use of MEMS storage in the storage hierarchy and show that using a technique called MEMS caching disk, we can achieve 30-49% of the pure MEMS storage performance by using only a small amount (3% of the disk capacity) of MEMS storage in conjunction with a standard hard drive. The resulting system is ideally suited for commercial packaging with a small MEMS device included as part of a standard disk controller or paired with a disk.

Cluster-based input/output trace synthesis

I/O traces are crucial for understanding the performance of new storage architectures. Unfortunately, traces are extremely bursty and difficult to characterize. They are large, difficult to obtain, and unwieldy. In this paper, we examine a trace synthesis method based on cluster analysis of time-varying characteristics of I/O traces. Representative trace segments are selected, and synthetic traces are reconstructed from these segments. We show that we can achieve a 5-10% demerit factor for I/O response times with a reduction of trace data volume of 75-90%.

Ensuring Performance in Activity-Based File Relocation

Dynamic storage tiering (DST) is the concept of grouping storage devices into tiers based on their characteristics, and relocating files dynamically to leverage on the heterogeneity of the underlying devices. An important usage of DST is activity-based file relocation, where less active files can be stored on less expensive devices without affecting the overall perceived quality of the storage system. In activity-based file relocation, improper choices on how much activity a file should have before it is relocated introduce the potential for overcommitting the performance capability of the preferred tier. We present an approach to prevent performance degradation caused by excessive skewing of loads. Our approach enables the delineation of periods when performance requirements are different. We consider the load pattern of files and limit the total amount of loads to be placed on the preferred tier during the periods when fast response time is desirable, and increase the load limit in other periods when throughput is more important. Considering the variation of performance requirements in time enables the finer attainment of QoS goals.

Reliability of MEMS-based storage enclosures

MEMS-based storage is a new, non-volatile storage technology currently under development. It promises fast data access, high throughput, high storage density, small physical size, low power consumption, and low entry costs. These properties make MEMS-based storage into a serious alternative to disk drives, in particular for mobile applications. The first generation of MEMS will only offer a fraction of the storage capacity of disks; therefore, we propose to integrate multiple MEMS devices into a MEMS storage enclosure, organizing them as a RAID Level 5 with multiple spares, to be used as the basic storage building block. The paper investigates the reliability of such an enclosure. We find that mean-time-to-failure is an inappropriate reliability metric for MEMS enclosures. We show that the reliability of the enclosures is appropriate for their economic lifetime if users choose not to replace failed MEMS storage components. In addition, we investigate the benefits of occasional, preventive maintenance of enclosures.