This is a continuation of the earlier posts starting with this one: http://ravinote.blogspot.com/2020/09/best-practice-from-networking.html
A garbage collector will find it easier to collect aged data by levels. If there are generations in the pages to be reclaimed, it splits the work for the garbage collector so that the application operations can continue to work well.
Similarly, aggregated and large pages are easier for the garbage collector to collect rather than multiple spatially and temporally spread out pages If the pages can be bundled or allocated in clusters, it will signal the garbage collector to free them up at once when they are marked
Among the customizations for garbage collector, it is helpful to see which garbage collector is being worked the most. The garbage collector closer to the application has far more leverage in the allocations and deallocations than something downstream.
The SSD could be treated as a pool of fast storage that is common to all the processes. since it is pluggable and external from all hard drives, it can be dynamically used as long as there is any availability.
In this sense it is very similar to L3 cache, however it is not meant for dynamic partitions, balancing access speed, power consumption and storage capacity. It is not as fast as cache but it is more flexible than conventional storage and plays a vital role in managing inter-process communication. This is a simplified storage.
SSDs can make use of different storage including flash storage. The two most common are NOR and NAND. NOR was the first of the two to be developed. It is very fast for reads but not as fast for writes, so it is used most often in places where code will be written once and read a lot. NAND is faster for writes and takes up significantly less space than NOR, which also makes it less expensive. Most flash used in SSDs is the NAND variety.
No comments:
Post a Comment