miller_lover的专栏

big data presentation of talkingdata

Facebook’s corpus of photos, videos, and other Binary Large OBjects (BLOBs) that need to be reliably stored and quickly accessible is massive and continues to grow. As the footprint of BLOBs increases, storing them in our traditional storage system, Haystack, is becoming in- creasingly inefficient. To increase our storage efficiency, measured in the effective-replication-factor of BLOBs, we examine the underlying access patterns of BLOBs and identify temperature zones that include hot BLOBs that are accessed frequently and warm BLOBs that are accessed far less often. Our overall BLOB storage sys- tem is designed to isolate warm BLOBs and enable us to use a specialized warm BLOB storage system, f4. f4 is a new system that lowers the effective-replication-factor of warm BLOBs while remaining fault tolerant and able to support the lower throughput demands. f4 currently stores over 65PBs of logical BLOBs and reduces their effective-replication-factor from 3.6 to either 2.8 or 2.1. f4 provides low latency; is resilient to disk, host, rack, and datacenter failures; and provides sufficient throughput for warm BLOBs.

This book is a broad overview of “living” on the Linux command line. Unlike some books that concentrate on just a single program, such as the shell program, bash, this book will try to convey how to get along with the command line interface in a larger sense. How does it all work? What can it do? What's the best way to use it? This is not a book about Linux system administration. While any serious discussion of the command line will invariably lead to system administration topics, this book only touches on a few administration issues. It will, however, prepare the reader for additional study by providing a solid foundation in the use of the command line, an essential tool for any serious system administration task. This book is very Linux-centric. Many other books try to broaden their appeal by in-cluding other platforms such as generic Unix and OS X. In doing so, they “water down” their content to feature only general topics. This book, on the other hand, only covers contemporary Linux distributions. Ninety-five percent of the content is useful for users of other Unix-like systems, but this book is highly targeted at the modern Linux command line user.