So, this is what we started to build, operating under the code name Cookie Monster. Customers told us they wanted to run data warehousing at scale in the cloud, that they didn’t want to compromise on performance or functionality, and that it had to be cost-effective enough for them to analyze all of their data. They were expensive, had punitive licensing, were hard to scale, and customers couldn’t analyze all of their data. In many cases, it was the last thing they were running on premises, and they were still dealing with all of the challenges of on-premises data warehouses. Rahul: We had been meeting with customers who in the years leading up to the launch of Amazon Redshift had moved just about every workload they had to the cloud except for their data warehouse. In June a subset of the team will present the paper “ Amazon Redshift re-invented ” at a leading international forum for database researchers, practitioners, and developers, the ACM SIGMOD/PODS Conference in Philadelphia.
Today, the service is used by tens of thousands of customers to process exabytes of data daily.
The Redshift team has been sprinting to keep apace of customer demand ever since. If we hadn’t done that preview, we would have been caught short.” So we scrambled right after re:Invent to accelerate our hardware orders to ensure we had enough capacity on the ground for when the product became generally available in early 2013. “Within about three days we realized that we had ten times more demand for Redshift than we had planned for the entire first year of the service. “At preview we asked customers to sign up and give us some indication of their data volume and workloads,” Pathak, now vice president of Relational Engines at AWS, said. “But we didn’t really understand how popular,” he recalls. That’s why, on the day of the announcement, Rahul Pathak, then a senior product manager, and the entire Amazon Redshift team were confident the product would be popular. They saw speedups ranging from 10x – 150x!” ’s data warehouse team has been piloting Amazon Redshift and comparing it to their on-premise data warehouse for a range of representative queries against a two billion row data set. In a blog post on November 28, 2012, Werner Vogels, Amazon chief technical officer, highlighted the news: “Today, we are excited to announce the limited preview of Amazon Redshift, a fast and powerful, fully managed, petabyte-scale data warehouse service in the cloud.”įurther in the post, Vogels added, “The result of our focus on performance has been dramatic.