1. Before We Start How to read a research paper?
How to write a paper review?

2. Reading A Research Paper
Differs from reading a text book
May not always provide all background details
Iteratively activity
Often requires obtaining additional background or skipping details

3. Active Reading Use a highlighter Write questions down Underline
Go back and forth between sections

4. Organization Abstract Introduction Background/Related work
Proposed Technique
Evaluation
Conclusion

5. Abstract
Usually less than 300 words. Summarizes the paper including brief motivation, high level description of contribution and results/ conclusions
Stands on its own. The abstract of a paper can be removed and the rest of the paper is still complete
Don’t need to define all terms in an abstract
If you do define them you need to re-define in proper part of paper

6. Introduction
This provides the high level motivation for the work. If the introduction is not compelling the paper will not be read
Should also state what problem is being solved, what other work has been done that is similar, and why this work is unique
Often ends with a list of the contributions

7. Introduction App oversubscription Under client web service controlVM
Guest OS
App
Under client web service control
oversubscription

8. Motivation
The principle bottleneck in large-scale clusters is often inter-node communication bandwidth
Two solutions:
Specialized hardware and communication protocols
e.g. Infiband, Myrinet(supercomputer environment)
Cons: No commodity parts (expensive)
The protocols are not compatible with TCP/IP
Commodity Ethernet Switches
Cons: Scale poorly
non-linear cost increases with cluster Size.
high-end core switch, oversubscription(tradeoff)

9. Oversubscription Ratio
……………
Server 2
Server n B
Upper Link Bandwidth(UB) B
Server 1
Oversubscription Ratio= B*n/UB

10. Current Data Center Topology
Edge hosts connect to 1G Top of Rack (ToR) switch
ToR switches connect to 10G
End of Row (EoR) switches
Large clusters: EoR switches
to 10G core switches
Oversubscription of 2.5:1
to 8:1 typical in guidelines
Key challenges: performance, cost, routing, energy, cabling

11. Data Center Cost

12. Design Goals Scalable interconnection bandwidth
Arbitrary host communication at full bandwidth
Economies of scale
Commodity Switch
Backward compatibility
Compatible with hosts running Ethernet and IP

13. Related Work Sometimes combined with background
Briefly describes other similar research papers and tells how the work presented in the current paper differs
Not meant to be a complete summary of each paper
Usually categorizes other work into like groups. Often found right before conclusions

14. Background
Any technical background that is required to understand the techniques that are presented should appear here.
Often has a motivating example that can be used to explain the ideas.

15. Proposed Technique
This is where you provide detail of the new material in your paper. You can present algorithms/methods/processes, etc.
If you have a running example from the intro or background you can use this to illustrate your ideas.

16. Fat-Tree Topology k/2 Aggregation Switch in each pod
K Pods
k/2 Aggregation Switch in each pod
k/2 Edge Switches in each pod
k/2 servers in each Rack

17. Fat-tree Topology Equivalent

18. Routing (k/2)*(k/2) shortest path! IP needs extension here!
Single-Path Routing VS Multi-Path Routing
Static VS Dynamic

19. ECMP（Equal-Cost Multiple-Path Routing)
Static Follow scheduling
limited multiplicity of path to 8-16
Increase routing table multiplicatively, hence latency time
Advantage: Don’t need reordering! Modern Switch support!
Extract Source and Destination Address
Hash Function(CRC16)
Determine which region fall in 1 2 3 4
Hash-Threshold

20. Two-level Routing Table
Routing Aggregation
/24
/24
/24
/24 1
/24
/24
/24 1
/24
/24

21. Two-level Routing Table
Addressing
Using /8 private IP address
Pod Switch: 10. pod. Switch.1.
pod range is [0, k-1](left to right)
switch range is [0, k-1] (left to right, bottom to top)
Core Switch: 10. k. i . j
(i,j) is the point in (k/2)*(k/2) grid
Host: 10.pod. Switch.ID
ID range is [2, k/2+1] (left to right)

22. Two-level Routing Table

23. Two-level Routing Table
Two-level Routing Table Structure
Two-level Routing Table implementation
TCAM=Ternary Content-Addressable Memory
Parallel searching
Priority encoding

24. Two-level Routing Table---example
Prefix
Outgoing Port
/24
/24 1 /0
Suffix
Outgoing Port /8 3 /8 2
Two-level Routing Table---example
Prefix
Outgoing Port
/16
/16 1
/16 2
/16 3
example
Prefix
Outgoing Port
/24
/24 1 /0
Prefix
Outgoing Port
/32
/32 1 /0
Suffix
Outgoing Port /8 2 /8 3
Suffix
Outgoing Port /8 2 /8 3
Prefix
Outgoing Port
/32
/32 1 /0
Suffix
Outgoing Port /8 2 /8 3

25. Two-Level Routing Table
Avoid Packet Reordering
traffic diffusion occurs in the first half of a packet journey
Centralized Protocol to Initialize the Routing Table

26. Flow Classification(Dynamic)
Soft State(Compatible with Two-Level Routing Table)
A flow=packet with the same source and destination IP address
Avoid Reordering of Flow
Balancing
Assignment and Updating

27. Flow Classification—Flow Assignment
Hash(Src,Des)
Have seen this hash value?
Lookup previously assign port x
Send packet on port x Y
Record new flow record f
Assign f to least-loaded port x N

28. Flow Classification—Update

29. Flow Scheduling
distribution of transfer times and burst lengths of Internet traffic is long-tailed
Large flow dominating
Large flow should be specially handled

30. Flow Scheduling Notify the central controller
Eliminates global congestion
Prevent long lived flows from sharing the same links
Assign long lived flows to different links
Edge Switch Detecting Flow size above a threshold
Notify the central controller
Assign this flow to non-conflicting path

31. Fault-Tolerance Bidirectional Forwarding Detection session (BFD)
Lower- to Upper-layer Switches
Upper-layer to Core Switches
For flow scheduling, it is much more easier to handle.

32. Failure b/w upper layer and core switches
Outgoing inter-pod traffic:
local routing table marks the affected link as unavailable and chooses another core switch
Incoming inter-pod traffic:
core switch broadcasts a tag to upper switches directly connected signifying its inability to carry traffic to that entire pod, then upper switches avoid that core switch when assigning flows destined to that pod

33. Failure b/w lower and upper layer switches
Outgoing inter- and intra pod traffic from lower-layer:
the local flow classifier sets the cost to infinity and does not assign it any new flows, chooses another upper layer switch
Intra-pod traffic using upper layer switch as intermediary:
Switch broadcasts a tag notifying all lower level switches, these would check when assigning new flows and avoid it
Inter-pod traffic coming into upper layer switch:
Tag to all its core switches signifying its ability to carry traffic, core switches mirror this tag to all upper layer switches, then upper switches avoid affected core switch when assigning new flaws

34. Evaluation
A strong paper has very extensive evaluation, including testbed implementation based and simulation based evaluation.
Parts of this section include: methdology, metrics used, results, comparison, etc

35. Experiment Description—Fat-tree, Click
4-port fat-tree, there are 16 hosts, four pods (each with four switches), and four core switches.
We multiplex these 36 elements onto ten physical machines, interconnected by a 48-port ProCurve switch with 1 Gigabit Ethernet links.
Each pod of switches is hosted on one machine; each pod’s hosts are hosted on one machine; and the two remaining machines run two core switches each.
bandwidth-limited to 96Mbit/s to ensure that the configuration is not CPU limited.
Each host generates a constant 96Mbit/s of outgoing traffic

36. Experiment Description—hierarchical tree,click
four machines running four hosts each, and four machines each running four pod switches with one additional uplink
The four pod switches are connected to a 4- port core switch running on a dedicated machine.
3.6:1 oversubscription on the uplinks from the pod switches to the core switch
Each host generates a constant 96Mbit/s of outgoing traffic

37. Result

38. Power and Heat

39. End of the Paper Conclusions and Future Work:
Summarize your results and any conclusions drawn
Describe briefly the main areas you plan to pursue as future work

40. Conclusion
Bandwidth is the scalability bottleneck in large scale clusters
Existing solutions are expensive and limit cluster size
Fat-tree topology with scalable routing and backward compatibility with TCP/IP and Ethernet

41. What Makes A Good Research Paper
Good methodology/technique
Novel: new and not resembling something formerly known or used
Good writing
Publish in good journals/conferences

42. Paper Reviews We will write a series of paper review in this class
First review due on next Tuesday in class for this paper
Hand in a hard copy

43. Paper Review Form Paper (author, title, complete reference)
Short 100 word overview description
Questions:
What problem is the paper addressing?
What is the contribution?
Did you find any drawbacks?
What is your assessment of the overall presentation style of the paper (consistency, clarity, ease of reading)?
Any possible future work or improvements?