Modern high-end disk arrays often have several gigabytes of cache RAM. Unfortunately, most array caches use management policies which duplicate the same data blocks at both the client and array levels of the cache hierarchy: they are inclusive. Thus, the aggregate cache behaves as if it was only as big as the larger of the client and array caches, instead of as large as the sum of the two. Inclusiveness is wasteful: cache RAM is expensive. We explore the benefits of a simple scheme to achieve exclusive caching, in which a data block is cached at either a client or the disk array, but not both. Exclusiveness helps to create the effect of a single, large unified cache. We introduce a DEMOTE operation to transfer data ejected from the client to the array, and explore its effectiveness with simulation studies. We quantify the benefits and overheads of demotions across both synthetic and real-life workloads. The results show that we can obtain useful -- sometimes substantial -- speedups. During our investigations, we also developed some new cache-insertion algorithms that show promise for multi-client systems, and report on some of their properties.

This paper presents a novel disk storage architecture called DCD, Disk Caching Disk, for the purpose of optimizing I/O performance. The main idea of the DCD is to use a small log disk, referred to as cache-disk, as a secondary disk cache to optimize write performance. While the cache-disk and the normal data disk have the same physical properties, the access speed of the former differs dramatically from the latter because of different data units and different ways in which data are accessed. Our objective is to exploit this speed difference by using the log disk as a cache to build a reliable and smooth disk hierarchy. A small RAM buffer is used to collect small write requests to form a log which is transferred onto the cache-disk whenever the cache-disk is idle. Because of the temporal locality that exists in office/engineering work-load environments, the DCD system shows write performance close to the same size RAM (i.e. solid-state disk) for the cost of a disk. Moreover, the cache...

Modern high performance disk systems make extensive use of non-volatile RAM (NVRAM) write caches. A single-copy NVRAM cache creates a single point of failure while a dual-copy NVRAM cache is very expensive because of the high cost of NVRAM. This paper presents a new cache architecture called RAPID-Cache for Redundant, Asymmetrically Parallel, and Inexpensive Disk Cache. A typical RAPID-Cache consists of two redundant write buffers on top of a disk system. One of the buffers is a primary cache made of RAM or NVRAM and the other is a backup cache containing a two level hierarchy: a small NVRAM buffer on top of a log disk. The small NVRAM buffer combines small write data and writes them into the log disk in large sizes. By exploiting the locality property of I/O accesses and taking advantage of well-known Logstructured File Systems, the backup cache has nearly equivalent write performance as the primary RAM cache. The read performance of the backup cache is not as critical because normal read operations are performed through the primary RAM cache and reads from the backup cache happen only during error recovery periods. The RAPID-Cache presents an asymmetric architecture with a fast-write-fast-read RAM being a primary cache and a fast-write-slow-read NVRAM-disk

Abstract—Distributed sparing is a method to improve the performance of RAID5 disk arrays with respect to a dedicated sparing system with N + 2 disks (including the spare disk), since it utilizes the bandwidth of all N + 2 disks. We analyze the performance of RAID5 with distributed sparing in normal mode, degraded mode, and rebuild mode in an OLTP environment, which implies small reads and writes. The analysis in normal mode uses an M/G/1 queuing model, which takes into account the components of disk service time. In degraded mode, a low-cost approximate method is developed to estimate the mean response time of fork-join requests resulting from accesses to recreate lost data on the failed disk. Rebuild mode performance is analyzed by considering an M/G/1 vacationing server model with multiple vacations of different types to take into account differences in processing requirements for reading the first and subsequent tracks. An iterative solution method is used to estimate the mean response time of disk requests, as well as the time to read each disk, which is shown to be quite accurate through validation against simulation results. We next compare RAID5 performance in a system 1) without a cache; 2) with a cache; and 3) with a nonvolatile storage (NVS) cache. The last configuration, in addition to improved read response time due to cache hits, provides a fast-write capability, such that dirty blocks can be destaged asynchronously and at a lower priority than read requests, resulting in an improvement in read response time. The small write penalty is also reduced due to the possibility of repeated writes to dirty blocks in the cache and by taking advantage of disk geometry to efficiently destage multiple blocks at a time. Index Terms—RAID5 disk arrays, dedicated sparing, distributed sparing, disk failures, fault-tolerance, operation in degraded mode,

Large RAM caches are generally used to speed up disk accesses. Such caches more effectively improve read performance than write performance, since write requests must be frequently written into disks to protect them from data loss or damage due to system failures. While Non-volatile RAM (NVRAM) caches can be used to improve write performance, large NVRAM caches are too expensive for many applications. This paper presents a new disk cache architecture called DCD, Disk Caching Disks. DCD takes the advantage of large data transfer sizes and uses inexpensive disk space to provide a high-performance, low-cost and reliable caching solution.

Present day applications that require reliable data storage use one of five commonly available RAID levels to protect against data loss due to media or disk failures. With a marked rise in the quantity of stored data and no commensurate improvement in disk reliability, a greater variety is becoming necessary to contain costs. Adding new RAID codes to an implementation becomes cost prohibitive since they require significant development, testing and tuning efforts. We suggest a novel solution to this problem: a generic RAID Engine and Optimizer (REO). It is generic in that it works for any XOR-based erasure (RAID) code and under any combination of sector or disk failures. REO can systematically deduce a least cost reconstruction strategy for a read to lost pages or for an update strategy for a flush of dirty pages. Using trace driven simulations we show that REO can automatically tune I/O performance to be competitive with existing RAID implementations. 1

Disk array architectures such as RAID-5 have become an acceptable way for designing highly reliable and high-performance storage systems. However, one major drawback of a RAID-5 disk array system is that an update to a data block may involve four disk accesses. Such a high overhead is especially undesirable for workloads with high update rate as in transaction processing. In this paper, we present a new scheme for improving the write performance of disk arrays using controller cache to store data as well as parity information. We have developed a trace-driven model to simulate cached disk arrays for transaction processing environment. We have studied the effect of caching parity information at the controller level along with caching data. The simulation results show a considerable improvement in response time of data and parity cached disk array over disk arrays with only data caching. The improvement in response time for disk array employing parity cache is about 10%-20% for the param...

Multi-level buffer cache architecture has been widely deployed in today's multiple-tier computing environments. However, caches in different levels are inclusive. To make better use of these caches and to achieve the expected performance commensurate to the aggregate cache size, exclusive caching has been proposed. Demotion-based exclusive caching [1] introduces a DEMOTE operation to transfer blocks discarded by a upper level cache to a lower level cache. In this paper, we propose a DEMOTE buffering mechanism over storage networks to reduce the visible costs of DEMOTE operations and provide more flexibility for optimizations. We evaluate the performance of DEMOTE buffering using simulations across both synthetic and real-life workloads on three different networks and protocol layers (TCP/IP on Fast Ethernet, IBNice on InfiniBand, and VAPI on InfiniBand). Our results show that DEMOTE buffering can effectively hide demotion costs. A maximum speedup of 1.4x over the original DEMOTE approach is achieved for some workloads. Speedups in the range of 1.08-1.15x are achieved for two real-life workloads. The vast performance gains results from overlapping demotions and other activities, reduced communication operations and high utilization of the network bandwidth.

We present the results of a variety of trace-driven simulations of disk cache design. Our traces come from a variety of mainframe timesharing and database systems in production use. We compute miss ratios, run lengths, traffic ratios, cache residency times, degree of memory pollution and other statistics for a variety of designs, varying block size, prefetching algorithm and write algorithm. We find that for this workload, sequential prefetching produces a significant (about 20%) but still limited improvement in the miss ratio, even using a powerful technique for detecting sequentiality. Copy-back writing decreased write traffic relative to write-through; periodic flushing of the dirty blocks increased write traffic only slightly compared to pure write-back, and then only for large cache sizes. Write-allocate had little effect compared to no-write-allocate. Block sizes of over a track don't appear to be useful. Limiting cache occupancy by a single processor transaction appears to have little effect. This study is unique in the variety and quality of the data used in the studies.

Abstract not found