[Colloquium] [Syspeople] Systems Seminar update

[Haryadi Gunawi]

Hi all,

Just a reminder, tomorrow *11:30am in Ryerson 255*, we'll have an EMC
sponsored lunch (a nice lunch from The Nile).
If you can come 5 minutes early that'd be great so the line is not long and
slow.

Fred will talk about EMC internship opportunities as well as their recent
FAST paper (RAIDShield).

Hope to see many of you tomorrow!
-- Har


On Wed, Apr 8, 2015 at 1:55 PM, Sandra Quarles <squarles at cs.uchicago.edu>
wrote:

> *REMINDER NEW TIME AND LUNCH DETAILS*
>
> The University of Chicago
> Computer Science
> Systems Seminar Presents:
>
> Tuesday, April 14, 2015
> Ryerson 255 @11:30 am
>
> Fred Douglis
> Advanced Development Group EMC Core Technologies Division
>
> Title: " RAIDShield: Characterizing, Monitoring, and Proactively
> Protecting Against Disk Failures"
>
> Abstract:  Modern storage systems orchestrate a group of disks to achieve
> their performance and reliability goals. Even though such systems are
> designed to withstand the failure of individual disks, failure of multiple
> disks poses a unique set of challenges. We empirically investigate disk
> failure data from a large number of production systems, specifically
> focusing on the impact of disk failures on RAID storage systems. Our data
> covers about one million SATA disks from 6 disk models for periods up to 5
> years. We show how observed disk failures weaken the protection provided by
> RAID. The count of reallocated sectors correlates strongly with impending
> failures. With these findings we designed RAIDSHIELD, which consists of two
> components. First, we have built and evaluated an active defense mechanism
> that monitors the health of each disk and replaces those that are predicted
> to fail imminently. This proactive protection has been incorporated into
> our product and is observed to eliminate 88% of triple disk errors, which
> are 80% of all RAID failures. Second, we have designed and simulated a
> method of using the joint failure probability to quantify and predict how
> likely a RAID group is to face multiple simultaneous disk failures, which
> can identify disks that collectively represent a risk of failure even when
> no individual disk is flagged in isolation. We find in simulation that
> RAID-level analysis can effectively identify most vulnerable RAID-6
> systems, improving the coverage to 98% of triple errors.
>
> *Joint work with Ao Ma, Guanlin Lu, Darren Sawyer (EMC Corporation),
> Surendar Chandra and Windsor Hsu (Datrium, Inc).*
> Host:  Haryadi Gunawi
>
> (Lunch provided from The Nile restaurant sponsored by EMC at 11:30 am)
>
> Sandy Quarles
> Project Assistant
> Computer Science Department
> 1100 E. 58th Street
> Chicago, IL 60637
> 773.702.3508
> 773.702.8487 Fax
>
>
>
>
>
>
>
>
>
> _______________________________________________
> Syspeople mailing list
> Syspeople at mailman.cs.uchicago.edu
> https://mailman.cs.uchicago.edu/mailman/listinfo/syspeople
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20150413/45aaaf9a/attachment.htm