Presentation is loading. Please wait.

Presentation is loading. Please wait.

Selected Papers from MobiSys 2007 Earl Oliver. Papers Improving Mobile Database Access Over Wide-Area Networks Without Degrading Consistency COMBINE:

Similar presentations


Presentation on theme: "Selected Papers from MobiSys 2007 Earl Oliver. Papers Improving Mobile Database Access Over Wide-Area Networks Without Degrading Consistency COMBINE:"— Presentation transcript:

1 Selected Papers from MobiSys 2007 Earl Oliver

2 Papers Improving Mobile Database Access Over Wide-Area Networks Without Degrading Consistency COMBINE: Leveraging the Power of Wireless Peers through Collaborative Downloading

3 Improving Mobile Database Access Over Wide-Area Networks Without Degrading Consistency Niraj Tolia, M. Satyanarayanan, and Adam Wolbach (Carnegie Mellon University)

4 Problem Use of mobile database applications growing (CRM, Sales, Insurance, etc.) Providing performance and consistency is hard –Limited bandwidth –Previous performance solutions: Weaken consistency Per-application consistency model

5 Existing approach SELECT query Query Query Exec. Result Time

6 Cedar overview New approach to mobile database access –Avoids compromising consistency Exploits disk storage and processing power to reduce network I/O Assumes weak WWAN connectivity Central master DB with mobile (lazily updated) replicas Implemented as JDBC stub Cedar Proxy DB Replica Application JDBC DriverCedar JDBC Driver

7 High-level overview SELECT query UPDATE queries do directly to the server Query Query Exec. Query + Recipe Result Query Exec. + Result Comparison ∆(Result)Result Time

8 Attributes of Cedar During periods of strong connectivity, Cedar directly queries master DB and synchronizes replica. DB schema transparent –So detecting differences in data is hard (explained later) Result deltas not applied to client replica IDNameAddressZipEmail 1John Doe412 Avenue15213jd2@eg.ca 2Mary Major821 Lane15232mm@eg.ca SELECT name,address,zip FROM users SELECT name,zip FROM users John Doe Mary Major 15232 15213 John Doe412 Avenue15213 Mary Major821 Lane15232

9 Commonality detection Exploit structure in results (tables) NameAddressZipEmail John Doe412 Avenue15213jd2@eg.ca Mary Major821 Lane15232mm@eg.ca John Stiles701 Street00979js@eg.ca Hash 1 Hash 2 Hash 3 Recipe SELECT name, address, zip, email FROM USERS

10 Recipes Recipes can be large, especially for results with small rows –Each hash is 20 bytes for SHA-1, 32 bytes for SHA-256 How can this ensure correctness? –Only compares results from same query: reduced key space –Therefore, a reduced probability of hash collisions –With 4 bytes and 10,000 hash values, Pr{collision} = 2.3 x 10 -6 –However, much lower than SHA-1, where Pr{collision} = 2 -160 –A hash over the entire result provides an end-to-end check 0x 2fd4e1c6 0x de9f2c7f 0x da39a3ee 7a2d28fc ed849ee1 bb76e739 1b93eb12 d25e1b3a fad3e85a 0bd17d9b 100db4b3 5e6b4b0d 3255bfef 95601890 afd80709 Solution: Only use 4 bytes as the row identifier

11 Rabin Fingerprinting vs. Structure Could Rabin fingerprinting be used? –Extensive use in storage systems –Chunks data using a stochastic process –Works well for in-place updates, deletes, insertions –Does not work well for query results Reordering of data (ORDER BY) Also hard to pick average chunk size `

12 Comparison to Rabin Fingerprinting Exploit structure is better than Rabin fingerprinting ```` Rabin Structure Based

13 Putting it all together Query Tentative Result 0x2fd4e1c6 0xda39a3ee 0x2fd4e1c6 0x8c3aea3b  0x2fd4e1c6 Authoritative Result Query 0x31b3887a30f020… ?

14 Evaluation/Results Cedar evaluated using MobileSales benchmark –Based on TCP-App –Using EVDO with various data rates Cedar improves average throughput of read-write workloads by 39% - 224% Reduces average response time by 28% to 79%

15 COMBINE: Leveraging the Power of Wireless Peers through Collaborative Downloading Ganesh Ananthanarayanan, Venkat Padmanabhan, Lenin Ravidranath, Chandu Thekkath (Microsoft Research India)

16 Problem Multi-homed mobile devices (laptops and phones) are increasingly common How do we bridge the gap between the range- speed dichotomy of these networks? SpeedCoverage WLAN (Wi-Fi, Bluetooth)1 – 54 MbpsWi-Fi Hotspots WWAN (3G, GPRS)50 – 200 kbpsCellular Network

17 Solution Pool WWAN bandwidths Using the WLAN to coordinate between mobile devices How? WiFi

18 Internet GPRS HTTP Server COMBINE Approach Initiator

19 Internet GPRS HTTP Server Search for collaborators Wi-Fi or Bluetooth COMBINE Approach Initiator

20 Internet GPRS Wi-Fi HTTP Server Connect to collaborators over Wi-Fi Wi-Fi Initiator Collaborator Collaborator COMBINE Approach

21 Internet GPRS Wi-Fi HTTP Server Dynamically distribute the work Wi-Fi Collaborator Collaborator Initiator COMBINE Approach

22 Existing Work Collaboration via WLAN to increase the coverage of the WWAN – UCAN Bandwidth Aggregation across WWAN links: –Attached to same device – Horde, MAR, pTCP –Across multiple devices – PRISM-IMUX, MOPED, Handheld Routers

23 What’s new in COMBINE? 1.Incentives –Promise of higher throughput may not be enough –Energy is a critical resource 2.Accounting –Ephemeral association – Tit-for-tat does not work 3.Node Discovery –Collaboration happens at unpredictable times –Idle power consumption is high 4.Work Distribution –Centralized proxies hurt deployability (PRISM-IMUX)

24 1. Incentives

25 Participation costs: Monetary Cost –Service provider fee –Size of data transfer Energy Cost –Battery energy depletion “Dynamic Market” for selling and buying unused bandwidth Unify the monetary and energy costs Cost (TC) = (Service Provider fee)/(Battery Remaining)

26 Estimating Battery Depletion Battery remaining likely to change during long transfers Energy models for network interfaces exist… –Require special hardware (compromise deployability) –Battery characteristics could change over time Battery Depletion = (time_elapsed * BD t ) + (bytes WLAN * BD d_WLAN ) + (bytes WWAN * BD d_WWAN )

27 2. Accounting

28 How does money change hands? Central authority issues key-pair (key pub, key priv ) to users Initiator signs IOU’s to the collaborator IOU = {key pub, amount, nonce, seq, exp} sign(key_priv) –key pub and key priv identify the initiator (payer) –exp is expiration time –nonce and seq maintain authenticity of IOU

29 Internet GPRS HTTP Server Issue IOU, redeem with central authority Central Authority IO U Collaborators are credited their price! Collaborator Collaborator Initiator

30 Central Authority Collaborators need not be online with accounting authority (unlike electronic funds transfers) –Redemption can be periodic and offline Validity and freshness of IOU verified (unlike digital cash schemes)

31 3. Node Discovery

32 Hello, anybody out there? Idle power consumption of Wi-Fi cards is high –Battery life reduces by a third Nodes cannot keep their Wi-Fi NICs on in anticipation of neighbours

33 Energy-efficient discovery Waiting Mode –Periodic beaconing of I-am-Alive (Price, Supported bandwidth) –Similar to Power Saving Mode Multiple radios –Bluetooth for node discovery (future work) Keeping Bluetooth interface on is inexpensive –Wi-Fi cards are switched on only for data transfer

34 4. Work Distribution

35 Protocol Design Striping –Application-level: HTTP byte-range requests Initiator willing to pay C units for a file of size F bytes Dynamic environment –Collaborator’s link characteristics vary –Collaborator’s advertised price might exceed the threshold (C/F) –Personal activity to be given higher priority

36 Conservative Approach Group Selection –Threshold-Price = (C/F) –Initiator accumulates I-am-Alive messages (bids) –Selects nodes with price ≤ Threshold-Price Work Distribution –Work-queue with equal-sized work items –Collaborators service work-queue by picking up one work-item at a time faster nodes automatically service more work items –Chunk size needs to be optimum (experiments found 200 KB chunks for HTTP)

37 Analysis (brief) Group formation takes less than 8 seconds Near-linear speed-up for both laptops and PPCs – download an 8 MB file across the Internet

38 Collaborative downloading –Software-only solution for bandwidth boost Practical cost and accounting scheme Easy-to-deploy striping mechanism Energy cognizance COMBINE Summary

39 Questions?


Download ppt "Selected Papers from MobiSys 2007 Earl Oliver. Papers Improving Mobile Database Access Over Wide-Area Networks Without Degrading Consistency COMBINE:"

Similar presentations


Ads by Google