CS848 Paper Review Form - Fall 2006

Paper Title: Facade: virtual storage devices with performance guarantees

Author(s):

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

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [X] Good 
 [ ] 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
 [X] Significant
 [ ] 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)
 [X] Accept (high quality - would argue for acceptance)
 [ ] 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 describes the design and evaluation of a dynamic storage controller
called facade, which sits between hosts and actual storage devices to 
provide service performance guarantees in terms of SLO. The good thing about 
facade is that it is adaptive in real-time and statistically guarantees for
any client SLO, no overprovision, no requirements of separate physical resources, 
with good experimental results concerning performance isolation. However, the 
SLO type supported by facade is restricted to a single form, failing to 
accomadate flexible needs in the real world. And its control replies on adjusting
queue length is argurably reasonable. The reason that the paper is suggested for 
acceptance is that the work is seminal in the sense of guaranteed predictable 
performance with virtualization. The paper is also well written. 

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

S1. Creative in the use of virtualization and the idea of adapting to SLO by 
adjusting queue length over shared actual resources.

S2. Well conducted evaluations by experiments.

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

W1. Not extensible for defined SLO
W2. Not enough description of using multiple VSDs and their vivid interactions.

10) Detailed comments for authors.
C1. Consider extensible SLO.
C2. Be a bit detail about using multiple VSDs