Exam DEA-1TT4 topic 1 question 15 discussion

A. Many blocks that have recently been written to storage by the compute system are retrieved and placed in cache. - NO// WRITE, MUST BE READ B. Many non-contiguous blocks that are not currently required can be retrieved from cache in advance. - NO // Must to be contiguos C. Storage system prefetches data in multiples of the original I/O request size from the compute system. - MOST ACCURATE - SO C for ME D. Storage system prefetches many non-contiguous blocks of data, with varied sizes, from cach - NO // Must to be contiguos

Correct answer is C

Prefetch: A prefetch or read-ahead algorithm is used when read requests are sequential. In a sequential read request, a contiguous set of associated blocks is retrieved. Several other blocks that have not yet been requested by the compute system can be read from the storage and placed into cache in advance. When the compute system subsequently requests these blocks, the read operations will be read hits. This process significantly improves the response time experienced by the compute system

Must be "C" "The intelligent storage system offers fixed and variable prefetch sizes. In fixed prefetch, the intelligent storage system prefetches a fixed amount of data. It is most suitable when host I/O sizes are uniform. << In variable prefetch, the storage system prefetches an amount of data in "multiples of the size of the host request". >> Maximum prefetch limits the number of data blocks that can be prefetched to prevent the disks from being rendered busy with prefetch at the expense of other I/Os. Information Storage and Management . Wiley. Kindle Edition.

From ISM v4 -> Prefetch: A prefetch or read-ahead algorithm is used when read requests are sequential. In a sequential read request, a contiguous set of associated blocks is retrieved. Several other blocks that have not yet been requested by the compute system can be read from the storage and placed into cache in advance. When the compute system subsequently requests these blocks, the read operations will be read hits. This process significantly improves the response time experienced by the compute system.

https://forum.huawei.com/enterprise/en/corpus-12891.html 1. After receiving a data read request, the storage system prefetches data to the cache based on a multiple of the read length specified in the I/O request. 2. This policy applies to sequential read applications with variable-size data or to multi-user concurrent read applications with an unknown data prefetch amount, for example, multi-user Video on Demand (VOD) initiated by users at different bit rates. C is correct.

A prefetch or read-ahead algorithm is used when read requests are sequential. In a sequential read request, a contiguous set of associated blocks is retrieved. Several other blocks that have not yet been requested by the compute system can be read from the storage and placed into cache in advance. When the compute system subsequently requests these blocks, the read operations will be read hits. This process significantly improves the response time experienced by the compute system. - Since it's a variable prefetch then D is correct.

https://www.dell.com/downloads/global/power/ps2q04-022.pdf page 97

Cache prefetching The EMC read-prediction algorithm—also known as read-ahead caching or prefetching—is adaptive in nature. The SP will prefetch data (assuming prefetching is enabled for the corresponding LUN) and fill the read cache only after two sequential reads that share spatial locality. By using this algorithm, the SP assumes that if there were two reads from the same location, there is a high probability that it will need that data from the next sequential location again. The SP will first check the read cache for the data. If the data is not present, it will then check the disk. This algorithm can help reduce SP-to-LUN latency by filling the read cache with prefetched data before it is actually needed.

D. In variable prefetch, the storage system prefetches an amount of data in multiples of the size of the host request.

It´s B - Several other blocks that have not yet been requested by the compute system can be read from the storage and placed into cache in advance

I actually think it is B, or maybe D. But maybe I am understanding this question wrong but here is what I found: Prefetch: A prefetch or read-ahead algorithm is used when read requests are sequential. In a sequential read request, a contiguous set of associated blocks is retrieved. Several other blocks that have not yet been requested by the compute system can be read from the storage and placed into cache in advance. When the compute system subsequently requests these blocks, the read operations will be read hits. This process significantly improves the response time experienced by the compute system.

should be C