Twitter Completes Data Center Migration
Twitter has completed a major data center migration and expansion, the company said today. The infrastructure expansion will help the fast-growing microblogging service manage its dynamic growth, which has seen traffic scale to more than 140 million tweets each day.
March 22, 2011
twitter-construction
Twitter has completed a major data center migration and expansion, the company said today. The infrastructure expansion will help the fast-growing microblogging service manage its dynamic growth, which has seen traffic scale to more than 140 million tweets each day.
Twitter engineer Michael Abbott provided an overview of the migration process, which involved testing and data replication between two data centers before migrating its production environment to a third, larger data center, which Abbott described as "our final nesting ground."
Abbott didn't identify the location of the data centers, but the migration presumably involves Twitter's first company-operated data center site. Twitter has been managing its infrastructure through a managed hosting agreement with NTT America, which operates several data centers in Silicon Valley, and has used Amazon’s cloud computing services to store and deploy images, including profile pictures. But Twitter said last year that it would begin operating its own facilities.
Last July Twitter said that it would open a new data center located in Salt Lake City, but industry sources say that the company instead leased data center space in Sacramento late last year. It's not clear which Twitter facility is serving as the "final nesting place," as some traceroutes show Twitter traffic routing to San Jose, Calif.
The migration involved moving 20 terabytes of Tweets between the three sites, Abbott said. "We hope (the expansion) will have a significant impact the service’s success for many years to come," he wrote. "During this time, the engineers and operations teams moved Twitter’s infrastructure to a new home while making changes to our infrastructure and our organization that will ensure that we can constantly stay abreast of our capacity needs; give users and developers greater reliability; and, allow for new product offerings."
About the Author
You May Also Like