@InProceedings{soloviev:prefetching,
  author = {Valery V. Soloviev},
  title = {Prefetching in Segmented Disk Cache for Multi-Disk Systems},
  booktitle = {Proceedings of the Fourth Workshop on Input/Output in Parallel
  and Distributed Systems},
  year = {1996},
  month = {May},
  pages = {69--82},
  publisher = {ACM Press},
  address = {Philadelphia},
  keywords = {parallel I/O, prefetching, disk cache, disk array, pario-bib},
  abstract = {This paper investigates the performance of a multi-disk storage
  system equipped with a segmented disk cache processing a workload of multiple
  relational scans. Prefetching is a popular method of improving the
  performance of scans. Many modern disks have a multisegment cache which can
  be used for prefetching. We observe that, exploiting declustering as a data
  placement method, prefetching in a segmented cache causes a load imbalance
  among several disks. A single disk becomes a bottleneck, degrading
  performance of the entire system. A variation in disk queue length is a
  primary factor of the imbalance. Using a precise simulation model, we
  investigate several approaches to achieving better balancing. Our metrics are
  a scan response time for the closed-end system and an ability to sustain a
  workload without saturating for the open-end system. We arrive at two main
  conclusions: (1) Prefetching in main memory is inexpensive and effective for
  balancing and can supplement or substitute prefetching in disk cache. (2)
  Disk-level prefetching provides about the same performance as main memory
  prefetching if request queues are managed in the disk controllers rather than
  in the host. Checking the disk cache before queuing requests provides not
  only better request response time but also drastically improves balancing. A
  single cache performs better than a segmented cache for this method.},
  comment = {An interesting paper about disk-controller cache management in
  database workloads. Actually, the workloads are sequential scans of
  partitioned files, which could occur in many kinds of workloads. The
  declustering pattern (partitioning) is a little unusual for most scientific
  parallel I/O veterans, who are used to striping. And the cache-management
  algorithms seem a bit strange, particularly the fact that the cache appears
  to be used only for explicit prefetch requests. Turns out that it is best to
  put the prefetching and disk queueing in the same place, either on the
  controller or in main memory, to avoid load imbalance that arises from
  randomness in the workload, which is accentuated into a big bottleneck and a
  convoy effect.}
}