Citation Context

...ds (a few hundred queries/sec). Ganesh et al. proposed using a logstructured filesystem so that a striping system could perfectly predict which disks must be awake for writing [13]. Finally, Pergamum =-=[49]-=- used nodes much like our wimpy nodes to attach to spun-down disks for archival storage purposes, noting that the wimpy nodes consume much less power when asleep. The system achieved low power, though...

Citation Context

...[36], Network Appliance [22] and Panasas [32] are all delivering products that use erasure codes beyond RAID-5 for data availability. Academic projects such as LoCI [3], Oceanstore [29], and Pergamum =-=[31]-=- are doing the same. And of equal importance, major technology corporations such as Hewlett Packard [34], IBM [12, 13] and Microsoft [15, 16] are performing active research on erasure codes for storag...

Citation Context

...ted across tiers as the workload changes. Pergamum is an archival storage system designed to be energy-efficient with techniques for reducing inter-disk dependencies and staggering rebuild operations =-=[23]-=-. Gurumurthi et al. propose intra-disk parallelism on high capacity drives to improve disk bandWorkload Size Reads [GB] Writes [GB] Volume Volume [GB] Total Uniq Total Uniq accessed mail 500 62.00 29....

Citation Context

...al size 166.6 GB File insertion, global storage utilization in a P2P system Pastiche [9] File system with 1641 files, 109 dirs, 13.4 MB total size Performance of backup and restore utilities Pergamum =-=[47]-=- Randomly generated files of “several” megabytes Data transfer performance Samsara [10] File system with 1676 files and 13 MB total size Data transfer and querying performance, load during querying Se...

Citation Context

...r future availability. However, a large fraction of this data will never be read. The workload for these systems consists of introspection, checking that data are intact, and error recovery. Pergamum =-=[20]-=- defined archival systems of this type based on massive arrays of idle disks (MAID). They demonstrate that 95% of disks may be powered off at all times. We extend Pergamum’s vision of infrequent error...

Citation Context

...s (a few hundred queries/sec). Ganesh et al. proposed using a log-structured filesystem so that a striping system could perfectly predict which disks must be awake for writing [11]. Finally, Pergamum =-=[25]-=- used nodes much like our wimpy nodes to attach to spun-down disks for archival storage purposes, noting that the wimpy nodes consume much less power when asleep. The system achieved low power, though...

Citation Context

... which improves reliability in the face of failures. There have been many dispersed storage systems developed in the past ten years. Examples include storage systems such as Oceanstore [23], Pergamum =-=[29]-=-, POTSHARDS [30], PASIS [9], Gridsharing [31], Glacier [11], Cleversafe [4] and TahoeLAFS [32] among others. Related to dispersed storage systems are distributed or peer-to-peer storage systems which ...

Citation Context

...torage system. Second, the metric does not reflect the real world, but is often interpreted as a real world estimate. For example, the Pergamum archival storage system estimates a MTTDL of 1400 years =-=[13]-=-. These estimates are based on the assumptions of the underlying Markov models and are typically well beyond the life of any storage system. Finally, MTTDL values tend to be incomparable because each ...

Citation Context

... performance and density of NAND flash memory devices offer the promise of great performance and low energy consumption. NAND flash is being used to replace DRAM-based disk caches [7], store metadata =-=[5]-=-, replace disks in laptops, and even replace high-performance disk arrays [8]. Unfortunately, NAND flash memory has limitations. First, write performance depends on the underlying architecture and doe...