burns.msst08.2

burns.msst08.2 - Remote Data Checking: Auditing the...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
Department of Computer Science, Johns Hopkins University Remote Data Checking: Auditing the Preservation Status of Massive Data Sets on Untrusted Stores Randal Burns randal@cs.jhu.edu www.cs.jhu.edu/ ~randal/
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Burns, Remote Data Checking: MSST , 24 September 2008. What ʼ s Remote Data Checking? Auditing protocols that verify the correctness of data objects on remote, untrusted stores Without transferring data to the client Constant network complexity per audit per object Constant amount of metadata per object That do not require the store to access the entire Fle Constant amount of I/O per audit per object
Background image of page 2
Burns, Remote Data Checking: MSST , 24 September 2008. Service-Oriented Architectures Outsourced storage commoditized and ubiquitous Cloud computing Amazon S3/EC SDSC Storage Resource Broker And, the associated security problems How much trust must we place in services? For data, auditing services for correctness, availability, preservation
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Burns, Remote Data Checking: MSST , 24 September 2008. Why Remote Data Checking? Verifying integrity/content on retrieval is insufFcient Too late, data are already damaged. Identifying damaged data quickly is critical to repair Data are too large to retrieve and check I/O burden on servers Lots of network trafFc Expensive! Services charge by byte of I/O and byte transferred Exposure Data are held for long periods of time Much data are accessed infrequently or never
Background image of page 4
Burns, Remote Data Checking: MSST , 24 September 2008. Don ʼ t I Trust Service Providers? Financial motivations to cheat Charge for terabytes and store gigabytes Discard unaccessed data (based on statistical analysis) Keep fewer replicas than promised Reputation Hide data loss incidents Latent errors Of which service providers are unaware There ʼ s a history of data-loss incidents
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Burns, Remote Data Checking: MSST , 24 September 2008. RDC Storage Protocol
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/27/2012 for the course CS 600 taught by Professor Smith,r during the Winter '08 term at Alabama.

Page1 / 19

burns.msst08.2 - Remote Data Checking: Auditing the...

This preview shows document pages 1 - 7. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online