Is the paper online? If someone can produce a standard URL for it, we'll change the link in this post.
Twitter Heron: Stream Processing at Scale
11–15 of 15 posts
Re: Twitter Heron: Stream Processing at Scale
#12Earlier quoted context omitted.
Every stream manager is connected to every other stream manager. k managers = k^2 connections.
Yea I must be missing something here. If you have k=2 stream managers you have 1 connection, not 4 . Even if the connections weren't bidirectional you'd have 2 connections.
it's (k-1)^2 actually - each to each except self.
Re: Twitter Heron: Stream Processing at Scale
#13Earlier quoted context omitted.
Every stream manager is connected to every other stream manager. k managers = k^2 connections.
Yea I must be missing something here. If you have k=2 stream managers you have 1 connection, not 4 . Even if the connections weren't bidirectional you'd have 2 connections.
Parent is talking big-O and so is ignoring that it isn't exactly k^2. Depending on how you count (do 2 nodes require 2 connections or 1 bi-directional connection) it's k(k-1).
Re: Twitter Heron: Stream Processing at Scale
#14Is the paper online? If someone can produce a standard URL for it, we'll change the link in this post.
http://dl.acm.org/citation.cfm?id=2742788
Sorry, I meant the pdf. Is there a url for it that will work for everybody? The one I get when I click "pdf" on that ACM page seems unlikely.
Re: Twitter Heron: Stream Processing at Scale
#15Earlier quoted context omitted.
http://dl.acm.org/citation.cfm?id=2742788
Sorry, I meant the pdf. Is there a url for it that will work for everybody? The one I get when I click "pdf" on that ACM page seems unlikely.
SIGMOD 2015 proceedings are open access, meaning the conference has arranged with ACM to provide the content to pretty much everyone.
That being said, the submission is to someone's (Adrian's) interpretation of the work, and is arguably more useful than just linking at the pdf itself.