Imagine a CDN configured as a caching hierarchy, with end users accessing content from edge caches, which fetch the content for a parent cache upon a cache miss, and so on up to a root cache, which ultimately fetches content from an origin server. What metrics would guide provisioning decisions to (a) add more storage capacity to a given cache versus (b) adding an additional level to the caching hierarchy.

Imagine a CDN configured as a caching hierarchy, with end users accessing content from edge caches, which fetch the content for a parent cache upon a cache miss, and so on up to a root cache, which ultimately fetches content from an origin server. What metrics would guide provisioning decisions to (a) add more storage capacity to a given cache versus (b) adding an additional level to the caching hierarchy.

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

In a split L1 cache organization the I-cache size is 16-KB and the D-cache is 32-KB; the access time for both caches is 1 cycle. The miss rates are given in the table below. There is a 256KB second level cache (L2) that is a unified cache and has a miss rate given in the table. Please assume that miss penalty is 20 cycles to get data from L2 cache. There is a 4MB third level cache (L3) that has a latency of 42 cycles; its miss rate is 1.28%. 124 cycles are required to get data from main memory. A program executes 8.6×10° instructions; 32.8% of the executed instructions are data references (i.e. loads or stores). AMAT = Hit Time + Miss Rate x Miss Penalty Cache miss rates a) Please determine the AMAT for this memory system. [7 points] Cache Size L1 I-Cache L1 D-Cache L2 Unified Cache 8 KB 0.82% 12.21% 8.63% 16 KB 0.38% 11.36% 6.75% L1: I D 32 KB 0.14% 10.67% 5.18% 64 KB 0.06% 10.15% 4.89% L2: U_cache 128 KB 0.03% 9.81% 3.66% 256 KB 0.002% 9.06% 2.76% L3: U_cache M: Main
Consider a 2-way set associative cache (S,E,B,m) = (8,2,4,13) Excluding the overhead of the tags and valid bits, what is the capacity of this cache? Draw a figure of this cache. Draw a diagram that shows the parts of the address that are used to determine the cache tag, cache set index, and cache block offset.
help
Define Direct cache mapping, Associative mapping, Set associative mapping. Compare their advantages and disadvantages.
Separate a direct mapped cache from a completely associative cache.
Compare directly mapped and completely associative caches.
A performance boost may be achieved by taking use of a system's inherent qualities of "spatial locality" and "temporal locality." Consider the numerous ways in which caches make advantage of these two events.
Discuss the challenges of creating an optimal cache replacement approach for all addresses.
Give two reasons why caches are useful. What problems do they solve? What problems do they cause? If a cache can be made as large as the device for which it is caching (for instance, a cache as large as a disk), why not make it that large and eliminate the device?
In a log entry, which fields are available to the log processing function? Assuming 64-byte cache blocks and no prefetching, how many cache misses does the following code cause on average for each entry?
Give two reasons why caches are useful. What problems do they solve? What problems do they cause? If a cache can be made as large as the device for which it is caching (for instance, a cache as large as a disk), why not make it that large and eliminate the device?
What are the miss rates for 64 KiB data caches with varied set associativity, broken down by miss type (cold, capacity, and conflict misses) for each benchmark?