CS848 Paper Review Form - Fall 2006
Paper Title: Goal oriented buffer management revisited

Author(s): K. Brown, M. Carey, M. Livay

1) Is the paper technically correct?
 [ ] Yes
 [X] Mostly (minor flaws, but mostly solid)
 [ ] No

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [ ] Good
 [X] Acceptable (a little incremental but not all rehashing) 
 [ ] Marginal (very incremental)
 [ ] Poor (little or nothing that is new)

3) Technical Depth
 [ ] Very good (comparable to best conference papers)
 [X] Good (comparable to typical conference papers)
 [ ] Marginal depth
 [ ] Little or no depth

4) Impact/Significance
 [ ] Very significant
 [ ] Significant
 [X] Marginal significance.
 [ ] Little or no significance.

5) Presentation
 [ ] Very well written
 [X] Generally well written
 [ ] Readable
 [ ] Needs considerable work
 [ ] Unacceptably bad

6) Overall Rating
 [ ] Strong accept (very high quality)
 [ ] Accept (high quality - would argue for acceptance)
 [X] Weak Accept (marginal, willing to accept but wouldn't argue for it)
 [ ] Weak Reject (marginal, probably reject)
 [ ] Reject (would argue for rejection)

7) Summary of the paper's main contribution and rationale
   for your recommendation. (1-2 paragraphs)

The paper presents a control-feedback strategy for near optimial buffer
management in situations requiring explicitly stated performance isolation 
guarantees. Its main contribution is that of taking previosuly studied
strategies and combining them to make a more robust buffer allocation 
control mechanism which performs fairly well in memory restricted scenarios.

The paper offers a good summary of previous approaches and fills in the void 
with a more stable and believable (good reason to investigate further) buffer 
management strategy. The major reason for a "weak acceptance" in this case is 
that the paper is a direct evolution (a relatively straight forward modification) 
of previously published ideas. Nevertheless the value added with this paper deserves
some acknowledgment.


8) List 1-3 strengths of the paper.  (1-2 sentences each,
identified as S1, S2, S3.)

S1 - Excellent presentation of previous ideas which naturally flow into the
newly proposed control mechanism

S2 - The simplicity of the proposed technique is commendable.

S3 - An decent was done in  addressing the dangers of using of their 
control mechanism

9) List 1-3 weaknesses of the paper (1-2 sentences each,
identified as W1, W2, W3.)

W1 - Even though the concavity assumption was addressed in detail, 
the paper's arguments of (a) this is a rare phenomenon and
(b) this is 'fixable' were not 100% convincing .

W2 - One can argue that a different (better) approach to testing would have
been more convincing. The idea of mixing TPC benchmarks together to form process
'classes' is not inherintly bad, but it does not directly target the tests 
towards the newly suggested buffer management scheme.


10) Detailed comments for authors.

- Generally well written paper which deprecates the previous publishings but
as mentioned earlier re-addressing some issues and eliminating all doubt about
assumptions would make it much more valuable.