Jeffrey Hutzelman wrote: > In addition, AFS does not do any sort of > automatic read-ahead, so cold-cache reads will be rather bursty, > requiring more pre-buffering and/or extra effort to achieve a continuous > transfer.
The Windows client implements a pre-fetch algorithm that is hinted based upon the Windows CreateFile() flags indicating whether the usage model is sequential or random access usage. If no hint is provided, the client will always queue a pre-fetch of the next chunk beyond the one that was requested if it is not already present in the cache. Jeffrey Altman _______________________________________________ OpenAFS-info mailing list [email protected] https://lists.openafs.org/mailman/listinfo/openafs-info
