when does hotspot forms in google file system-:
I am seeing lots of stuffs in this and it is just confusing me.
(I can’t share the link due t o being new user)this slide says-: Hotspots means many clients accessing 1 chunk file.
Q1) How hotspot occurs only when client accessing 1 chunk file?? Why not for multi chunk files? Can’t hotspot be there if file is not replicated enough?
This slide says-: Hotspot means some files may be accessed too much so fix is to use higher replication factor.
The second one makes sense to me rather than the first one.
But what is written in original google research paper
original research paper is different thing, So I got ■■■■ confused.
On the other hand, a large chunksize, even with lazy space allocation, has its disadvantages
A small file consists of a small number of chunks, perhaps just one
The chunkservers storing those chunks may become hot spots if many clients are accessing the same file
In practice, hot spots have not been a major issue because our applications mostly read large multi-chunk files sequentially.
this slide says different thing-:
small files consist of few chunks which then get lots of traffic from concurrent clients. this can be mitigated by increasing the replication factor.
Q2) Why do small files that have few chunks get lots of traffic from concurrent clients? Is there any reason behind that?