Talks

Log-Structured SiLo

October 21, 14:50
Room III

There is an important task of reducing the cost of storage in the cloud infrastructure. One of the most known technologies of saving space and reducing the cost of storage as a result is deduplication.

This paper presents an effective method of combining technologies of selective deduplication index and log-structured writing which allows using inline-deduplication without significant loss of performance. Aside from the overview of the SiLo-scheme, the paper includes test performance results for random write with/without log-structured writing, as well as deduplication rate tests.

The paper is addressed to the wide IT-community, particularly to data storage and cloud computing engineers, IT-service workers and developers.

Recommended for listeners with mid-level expertise.

Evgenii Anastasiev

Software Developer in R&D, RAIDIX

Linux kernel developer. Areas of interest are erasure coding, theory of reliability. At the present time he researches and develops algorithms of caching and deduplication in distributed storage systems.

Sponsors & Partners

Sponsors

Gold

JetBrainsFirst Line Software

Silver

Dell EMCDINSVeeam Software

Embedded

Auriga

Sponsors

I.T. GroupT-SystemsUnited Frontal System Program

Individual

Andrey Terekhov

Partners

Main partners

AP KITRUSSOFT

In cooperation

Association for Computing MachineryACM Special Interest Group on Software Engineering

Technical partners

CUSTISSoftInvent7pap StudioHosting-CenterGroup MPrezentPrint SalonDPI.Solutions

With support of

RAEC

Organizers

Software Russiai-Help