So taking a shot at this: what makes a good SOSP/OSDI submission?
Caveats: purely my opinion, and likely others in the community will disagree.
A thread. (1/n)
Caveats: purely my opinion, and likely others in the community will disagree.
A thread. (1/n)
1) The most important aspect is problem selection. The problem has to be timely and significant. By reading a lot of SOSP/OSDI papers, you develop a sense of whether a given problem is significant enough. If you tackle the "wrong" problem, paper won't get accepted no matter what.
2) The second important aspect is building a real system (to the point it can run actual user workloads). It is rare to have SOSP or OSDI papers based on simulation. Measurement papers don't build a real system, but then have the burden of interesting, surprising insights.
3) Most SOSP/OSDI papers have a strong evaluation. Here's an old thread where I talk about what a good evaluation should accomplish:
4) SOSP and OSDI aren't super concerned with novelty. They understand that there is novelty in synthesis, so as long as you are tackling an important problem, it isn't crucial that you have "novel" techniques in your solution.
5) This isn't to say you can repeat what prior work has done and expect to get accepted. But there is value in combining known techniques (in perhaps a new way) to solve a novel problem, and I believe this is recognized at these conferences.
6) SOSP and OSDI papers usually have impressive results (though not always). If the focus is perf, perf is improved by a lot. If the focus is finding bugs, a lot of new bugs are discovered. If the focus is measurement, the paper usually contains multiple interesting insights.
7) Finally, and this is true at all confs, writing is super super important. It doesn't matter how good your results are if nobody can understand them. The problem must be clear and well-motivated, the insights behind the solution described, and results must be explained.
8) Writing is the most common failure mode. Rejected papers at SOSP and OSDI usually contain amazing results which are not explained well.
10x, but from where?
Why does your system perform well? Why is this problem important?
Please explain how your complex system works.
10x, but from where?
Why does your system perform well? Why is this problem important?
Please explain how your complex system works.
9) A good SOSP/OSDI weaves a tightly-knot, engrossing story:
Here's this important problem.
But look, current solutions are bad!
Insight: we can solve it by doing X!
Here's how we built a system around this insight.
Since we do X, perf is up Y%!
We can do new thing Z!
Here's this important problem.
But look, current solutions are bad!
Insight: we can solve it by doing X!
Here's how we built a system around this insight.
Since we do X, perf is up Y%!
We can do new thing Z!
The "story" aspect is the toughest to obtain, because a bunch of incoherent techniques won't cut it. It has to make sense to the reviewer intuitively. The story aspect improves (for me) as we rewrite the paper -- the story in the first draft is rarely what gets submitted.
