AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We find evidence that storage is a significant contributor to application performance on mobile devices; our experiments provide insight into the Android storage stack and reveal its correlation with application performance

Revisiting storage for smartphones

FAST, no. 4 (2012): 17-17

Cited by: 257|Views225
EI

Abstract

Conventional wisdom holds that storage is not a big contributor to application performance on mobile devices. Flash storage (the type most commonly used today) draws little power, and its performance is thought to exceed that of the network subsystem. In this paper we present evidence that storage performance does indeed affect the perfor...More

Code:

Data:

0
Introduction
  • Tablets, and ultra-portable laptops are no longer viewed as the wimpy siblings of the personal computer.
  • For many users, they have become the dominant computing device for a wide variety of applications.
  • Research pertaining to mobile devices can be broadly split into applications and services, device architecture, and operating systems.
  • Research has tackled many important aspects: understanding and improving energy management [Flinn and Satyanarayanan 1999; Roy et al 2011; Carroll and Heiser 2010], network middleware [Meroni et al 2010], application execution models [Cuervo et al 2010; Chun et al 2011], security and privacy [Bickford et al 2011; Dietz et al 2011; Enck et al 2010; Geambasu et al 2011], and usability [Castellucci and
Highlights
  • Mobile phones, tablets, and ultra-portable laptops are no longer viewed as the wimpy siblings of the personal computer
  • We found Web browsing to be severely affected by the choice of the underlying storage; just by varying the underlying flash storage, performance of Web browsing over WiFi varied by 187% and over a faster network by 220%
  • We describe the Android apps that we use to assess the impact of storage on application performance; we automate a variety of popular and frequently used mobile apps to serve as benchmarks
  • We find evidence that storage is a significant contributor to application performance on mobile devices; our experiments provide insight into the Android storage stack and reveal its correlation with application performance
  • We find that even for an interactive application such as Web browsing, storage can affect the performance in nontrivial ways; for I/O intensive applications, the effects can get much more pronounced
  • With the advent of faster networks and I/O interconnects on the one hand, and a more diverse, powerful set of mobile apps on the other, the performance required from storage is going to increase in the future
Results
  • By 2013, more than 40% of the enhanced phone installed base will be equipped with advanced browsers [Pentin 2010].
  • Non-ioWait CPU consumption includes the contribution of the benchmark and all background activities, the authors measured CPU consumption for background activities alone
  • Note that this is unlike the set of background activities discussed in Section 3.3, as the authors turned off automatic syncing and active widgets; the authors find that the share of CPU consumption due to background tasks is less than 1% of the total.
Conclusion
  • The authors find that even for an interactive application such as Web browsing, storage can affect the performance in nontrivial ways; for I/O intensive applications, the effects can get much more pronounced.
  • With the advent of faster networks and I/O interconnects on the one hand, and a more diverse, powerful set of mobile apps on the other, the performance required from storage is going to increase in the future.
  • The authors believe the storage system on mobile devices needs a fresh look and the authors have taken the first steps in this direction
Tables
  • Table1: Data Storage Partitions for Android Partitions on internal flash and external SD card for Nexus One phone
  • Table2: I/O Activity Breakdown Aggregate seq. and random, writes and reads during benchmark; note moderate to high rand:seq write ratios for WebBench, Email, Maps, Facebook, and low for AppInstall. Zero value means no activity during run
  • Table3: Network Performance Transfer rates for WiFi and USB reverse tether link with iperf (MB/s)
  • Table4: Apps for Install and Launch from Android Market Install: top apps in August 2011, total size 55.58 MB, average size 5.56MB; Launch: 10 apps launched individually
  • Table5: App Launch Summary Total data (MB) read and written to storage and transferred over the network for the set of apps launched
  • Table6: Raw Device Performance and Cost Measurements on desktop with card reader (left) and on actual phone (right). “Sq” is sequential and “Rn” is random performance
Download tables as Excel
Related work
  • We found little published literature on storage performance for mobile devices. One of the earliest works on storage for mobile computers [Douglis et al 1994] compares the performance of hard disks and flash storage on an HP OmniBook; remarkably, many of their general observations are still valid. Datalight [2011], provider of data management technologies for mobile and embedded devices to OEMs, make an observation similar to ours with reference to their proprietary Reliance Nitro file system. According to their Web site, lack of device performance and responsiveness is one of the important shortcomings of the [Windows] Mobile platforms; OEMs using an optimized software stack can improve performance. Our results also reaffirm some of the recent findings for desktop applications on the Mac OS X [Harter et al 2011]: lack of pure sequential access for seemingly sequential application requests, heavy-handed use of synchronization primitives, and the influence of underlying libraries on application I/O.

    A recent study of Web browsers on smartphones [Wang et al 2011] examined the reasons behind slow Web browsing performance and found that optimizations centering around compute-intensive operations provide only marginal improvements; instead, “resource loading” (e.g., files of various types being fetched from the Web server) contributes most to browser delay. While this work focuses more specifically on the browser and the network, it reaffirms the observation that improvements in the OS and hardware are needed to improve application performance.
Reference
  • ALPHONSO LABS. Pulse News Reader. https://market.android.com/details?id=com.alphonso.pulse&hl=en. ANDROID DEBUG BRIDGE (ADB).201Homepage.http://developer.android.com/guide/developing/tools/
    Findings
  • CHEN, S., GIBBONS, P. B., AND NATH, S. 2011. Rethinking database algorithms for phase change memory. In Proceedings of the 5th Biennial Conference on Innovative Data Sysytems Research (CIDR’11), 21–31.
    Google ScholarLocate open access versionFindings
  • ENCK, W., GILBERT, P., CHUN, B.-G., COX, L. P., JUNG, J., MCDANIEL, P., AND SHETH, A. N. 2010. Taintdroid: an information-flow tracking system for realtime privacy monitoring on smartphones. In Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation (OSDI’10). USENIX, Berkeley, CA, 1–6.
    Google ScholarLocate open access versionFindings
  • FALAKI, H., MAHAJAN, R., KANDULA, S., LYMBEROPOULOS, D., GOVINDAN, R., AND ESTRIN, D. 2010. Diversity in smartphone usage. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services (MobiSys ’10). ACM, New York, 179–194.
    Google ScholarLocate open access versionFindings
  • FLINN, J. AND SATYANARAYANAN, M. 1999. Energy-aware adaptation for mobile applications. In Proceedings of the 17th ACM Symposium on Operating Systems Principles (SOSP ’99). ACM, New York, 48–63.
    Google ScholarLocate open access versionFindings
  • FLINN, J., SINNAMOHIDEEN, S., TOLIA, N., AND SATYANARAYANAN, M. 2003. Data staging on untrusted surrogates. In Proceedings of the 2nd USENIX Symposium on File and Storage Technologies (FAST ’03).
    Google ScholarLocate open access versionFindings
  • GARTNER. 2011. Gartner highlights key predictions for it organizations and users in 2010 and beyond. http://www.gartner.com/it/page.jsp?id=1278413.
    Findings
  • GEAMBASU, R., JOHN, J. P., GRIBBLE, S. D., KOHNO, T., AND LEVY, H. M. 2011. Keypad: an auditing file system for theft-prone devices. In Proceedings of the 6th Conference on Computer Systems (EuroSys ’11). ACM, New York, 1–16.
    Google ScholarLocate open access versionFindings
  • GUNDOTRA, V. AND BARRA, H. 2011. Android: momentum, mobile and more at Google I/O. http://googleblog.blogspot.com/2011/05/android-momentum-mobile-and-more-at.html.
    Locate open access versionFindings
  • HACKBORN, D. 20Multitasking the Android way. http://android-developers.blogspot.com/2010/04/multitasking-android-way.html.
    Findings
  • HALPERIN, D., KANDULA, S., PADHYE, J., BAHL, P., AND WETHERALL, D. 20Augmenting data center networks with multi-gigabit wireless links. In Proceedings of the ACM SIGCOMM 2011 Conference (SIGCOMM ’11). ACM, New York, 38–49.
    Google ScholarLocate open access versionFindings
  • HARTER, T., DRAGGA, C., VAUGHN, M., ARPACI-DUSSEAU, A. C., AND ARPACI-DUSSEAU, R. H. 2011. A file is not a file: understanding the I/O behavior of Apple desktop applications. In Proceedings of the 23rd ACM Symposium on Operating Systems Principles (SOSP’11).
    Google ScholarLocate open access versionFindings
  • HTC. 2011a. HTC Desire. http://www.htc.com/www/product/desire/specification.html.
    Findings
  • HTC. 2011b. HTC EVO 4G. http://www.htc.com/us/products/evo-sprint#tech-specs.
    Findings
  • HUAI, Y. 2008. Spin-transfer torque MRAM (STT-MRAM): challenges and prospects. AAPPS Bull. 18, 6 (Dec.), 33–40.
    Google ScholarLocate open access versionFindings
  • HUANG, J., XU, Q., TIWANA, B., MAO, Z. M., ZHANG, M., AND BAHL, P. 2010. Anatomizing application performance differences on smartphones. In Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services (MobiSys’10). ACM, New York, 165–178.
    Google ScholarLocate open access versionFindings
  • IEEE WG802.11. IEEE STANDARD 802.11n-2009 Wireless LAN Working Group. http://standards.ieee.org/findstds/standard/802.11n-2009.html.
    Findings
  • ITRS. 2009. ITRS 2009 Edition. Tech. rep., International Technology Roadmap for Semiconductors.
    Google ScholarFindings
  • JOO, Y., RYU, J., PARK, S., AND SHIN, K. G. 2011. Fast: quick application launch on solid-state drives. In Proceedings of the 9th USENIX Conference on File and Storage Technologies (FAST’11).
    Google ScholarLocate open access versionFindings
  • KIM, H., AGRAWAL, N., AND UNGUREANU, C. 2012. Revisiting storage for smartphones. In Proceedings of the 10th USENIX Conference on File and Storage Technologies (FAST’12).
    Google ScholarLocate open access versionFindings
  • KIM, J., KIM, J. M., NOH, S., MIN, S. L., AND CHO, Y. 2002. A space-efficient flash translation layer for CompactFlash systems. IEEE Trans. Consum. Electron. 48, 2, 366–375.
    Google ScholarLocate open access versionFindings
  • KISTLER, J. AND SATYANARAYANAN, M. 1992. Disconnected operation in the Coda file system. ACM Trans. Comput. Syst. 10, 1, 3–25.
    Google ScholarLocate open access versionFindings
  • KONISHI, R., AMAGAI, Y., SATO, K., HIFUMI, H., KIHARA, S., AND MORIAI, S. 2006. The Linux implementation of a log-structured file system. SIGOPS Oper. Syst. Rev. 40, 3, 102–107.
    Google ScholarLocate open access versionFindings
  • KOUKOUMIDIS, E., LYMBEROPOULOS, D., STRAUSS, K., LIU, J., AND BURGER, D. 2011. Pocket cloudlets. In Proceedings of the 16th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’11). ACM, New York, 171–184.
    Google ScholarLocate open access versionFindings
  • LG. 2011. LG G2X datasheet. http://www.lg.com/us/products/documents/LG-G2x-Datasheet.pdf.
    Findings
  • MANNING, C. 2004. YAFFS: Yet another flash file system. http://www.aleph1.co.uk/yaffs.
    Findings
  • MERONI, P., PAGANI, E., ROSSI, G. P., AND VALERIO, L. 2010. An opportunistic platform for android-based mobile devices. In Proceedings of the 2nd International Workshop on Mobile Opportunistic Networking (MobiOpp’10). ACM, New York, 191–193.
    Google ScholarLocate open access versionFindings
  • MONKEYRUNNER. 2012. MonkeyRunner for Android developers. http://developer.android.com/guide/developing/tools/monkeyrunner concepts.html.
    Findings
  • MOTOROLA. 2011. Motorola Webtop: release your smartphone’s true potential. http://www.motorola.com/Consumers/US-EN/Consumer-Product-and-Services/WEBTOP/Meet-WEBTOP.
    Findings
  • NEXUS ONE. 2011. Google Nexus One. http://en.wikipedia.org/wiki/Nexus One.
    Locate open access versionFindings
  • NOBLE, B. D., SATYANARAYANAN, M., NARAYANAN, D., TILTON, J. E., FLINN, J., AND WALKER, K. R. 1997. Agile application-aware adaptation for mobility. In Proceedings of the 16th ACM Symposium on Operating Systems Principles (SOSP’97). ACM, New York, 276–287.
    Google ScholarLocate open access versionFindings
  • PENTIN. 2010. Gartner’s mobile predictions. http://ifonlyblog.wordpress.com/2010/01/14/gartners-mobilepredictions/.
    Findings
  • REDLICENSE LABS. 2012. RL benchmark: SQLite. https://market.android.com/details?id=com.redlicense.benchmark.sqlite.
    Findings
  • ROSENBLUM, M. AND OUSTERHOUT, J. 1992. The design and implementation of a log-structured file system. ACM Trans. Comput. Syst. 10, 1 (Feb.), 26–52.
    Google ScholarLocate open access versionFindings
  • ROY, A., RUMBLE, S. M., STUTSMAN, R., LEVIS, P., MAZIERES, D., AND ZELDOVICH, N. 2011. Energy management in mobile devices with the cinder operating system. In Proceedings of the 6th Conference on Computer Systems (EuroSys ’11). ACM, New York, 139–152.
    Google ScholarLocate open access versionFindings
  • SAMSUNG CORP. 2011. Samsung ships industrys first multi-chip package with a PRAM chip for handsets. http://tinyurl.com/4y9bsds.
    Findings
  • SATYANARAYANAN, M. 2010. Mobile computing: the next decade. In Proceedings of the 1st ACM Workshop on Mobile Cloud Computing and Services: Social Networks and Beyond (MCS ’10). ACM, New York, 5:1–5:6.
    Google ScholarLocate open access versionFindings
  • SATYANARAYANAN, M., BAHL, P., CACERES, R., AND DAVIES, N. 2009. The case for VM based cloudlets in mobile computing. IEEE Pervasive Comput. 8, 14–23.
    Google ScholarLocate open access versionFindings
  • SCHLOSSER, S. W. AND GANGER, G. R. 2004. MEMS-based storage devices and standard disk interfaces: a square peg in a round hole? In Proceedings of the 3rd USENIX Symposium on File and Storage Technologies (FAST ’04). 87–100.
    Google ScholarLocate open access versionFindings
  • SD ASSOCIATION. 2012. SD speed class/UHS speed class. https://www.sdcard.org/consumers/speed class/.
    Findings
  • SIVATHANU, M., PRABHAKARAN, V., POPOVICI, F. I., DENEHY, T. E., ARPACI-DUSSEAU, A. C., AND ARPACI-DUSSEAU, R. H. 2003. Semantically-smart disk systems. In Proceedings of the 2nd USENIX Symposium on File and Storage Technologies (FAST ’03). 73–88.
    Google ScholarLocate open access versionFindings
  • SOURCEFORGE. 2012. Iperf. iperf network performance tool. http://sourceforge.net/projects/iperf.
    Findings
  • SQLITE. 2012. Using databases. http://developer.android.com/guide/topics/data/data-storage.html#db.
    Findings
  • SQLITE. 2011. SQLite backend with write-ahead logging. http://www.sqlite.org/draft/releaselog/3 7 0.html.
    Findings
  • STARBURST. 2012. Starburst data2sd. http://starburst.droidzone.in/.
    Findings
  • TOLIA, N., HARKES, J., KOZUCH, M., AND SATYANARAYANAN, M. 2004. Integrating portable and distributed storage. In Proceedings of the 3rd USENIX Symposium on File and Storage Technologies (FAST ’04). 227–238.
    Google ScholarLocate open access versionFindings
  • TSO, T. 2010. Android will be using ext4 starting with Gingerbread. http://www.linuxfoundation.org/newsmedia/blogs/browse/2010/12/android-will-be-using-ext4-starting-gingerbread.
    Findings
  • UNREVOKED. 2012. Unrevoked 3: Set your phone free. http://unrevoked.com/recovery/.
    Findings
  • VEERARAGHAVAN, K., FLINN, J., NIGHTINGALE, E. B., AND NOBLE, B. 2010. quFiles the right file at the right time. In Proceedings of the 8th USENIX Conference on File and Storage Technologies (FAST’10). USENIX Association, Berkeley, CA.
    Google ScholarLocate open access versionFindings
  • WANG, Z., LIN, F. X., AND ZHONG, L. 2011. Why are Web browsers slow on smartphones? In Proceedings of the ACM International Workshop on Mobile Computing Systems and Applications (HotMobile ’11).
    Google ScholarLocate open access versionFindings
  • WEBKIT. 2012. Android WebKit package. http://developer.android.com/reference/android/webkit/packagesummary.html.
    Findings
  • Received April 2012; accepted April 2012
    Google ScholarFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科