- How to NoSQL with Scylla: Cassandra to Scylla Migration Story in Oracle
Scylla is the real-time big data database. An open source drop-in replacement for Apache Cassandra, Scylla applies innovative systems programming techniques to a horizontally scalable NoSQL column-store design that results in extreme performance improvements: 1 million requests per second per node, with < 1msec P99 latency. 6:00 – 6:15 - Socialize over food and drinks 6:15 – 6:30 - Welcome, opening remarks and announcements 6:30 - 7:20 - Choosing the right nosql datastore: Our journey from Cassandra to Scylla - Aaron Stockton 7:30 - 8:20 - How to Ruin Performance by Choosing the Wrong Compaction Strategy for Cassandra and Scylla - Nadav Har'El In this meetup : Choosing the right NoSQL datastore: Our journey from Cassandra to Scylla - Aaron Stockton You won’t believe how one Colorado team rebuilt their batch workflow with this weird streaming trick! Aaron will share the process of migrating from batch workflow to a streaming one, and how moving from Cassandra to Scylla enable this transition, simplify the process and reduce costs. How to Ruin Performance by Choosing the Wrong Compaction Strategy for Cassandra and Scylla - Nadav Har'El Scylla, Apache Cassandra, and many other modern databases are using Log Structured Merge (LSM) design for efficient writes that are immediately available for reads (for example Lucene search engine, 1999). When using LSM, one need to choose the right Compaction Strategy, but it's not always clear what is the best option for each workload. In his talk, Nadav will go over the trade-off of each strategy and present a novel strategy which will combine the benefits of two existing strategies. Drink and food will be served, as well as limited number of Scylla swag (shirts and plush mascots :) See you all there! About the speakers Aaron Stockton is a Principal Software Engineers on the Fulfillment team within Oracle Data Cloud, managing delivery to hundreds of partners for advertising. Having grown in scale for years with the business, some of the team’s legacy batch jobs were becoming a huge operational burden as a result of their increasing runtime, cost, and instability. They’ll talk through their use-case for a redesigned streaming system, challenges encountered while prototyping various data stores to meet its needs, and client-side changes that ultimately made the project a success. Nadav Har'El Nadav Har’El has had a diverse 20-year career in computer programming and computer science. In the past he worked on scientific computing, networking software, and information retrieval, but in recent years his focus has been on virtualization and operating systems, and among other things he has worked on nested virtualization and exit-less I/O in KVM, and today he maintains the OSv kernel and also works on Seastar and ScyllaDB. Address: Menachem Begin Rd. 132, Tel Aviv. Azrieli, Round Building, 21st floor, Oracle.
- What could you do with Cassandra at 1.8 million requests per node?
This talk will immediately follow http://www.meetup.com/Tel-Aviv-Cassandra-Users/events/226230820/ 11:30-12:00 “ScyllaDB: What could you do with Cassandra compatibility at 1.8 million requests per node?” Scylla is a new, open-source NoSQL data store with a novel design optimized for modern hardware, capable of 1.8 million requests per second per node, while providing Apache Cassandra compatibility and scaling properties. While conventional NoSQL databases suffer from latency hiccups, expensive locking, and low throughput due to low processor utilization, the Scylla design is based on a modern shared-nothing approach. Scylla runs multiple engines, one per core, each with its own memory, CPU and multi-queue NIC. The result is a NoSQL database that delivers an order of magnitude more performance, with less performance tuning needed from the administrator. With extra performance to work with, NoSQL projects can have more flexibility to focus on other concerns, such as functionality and time to market. Come for the tech details on what Scylla does under the hood, and leave with some ideas on how to do more with NoSQL, faster. Seastar uses shared-nothing data structures that eliminate costly locking between CPUs, and a dedicated user-space TCP implementation that runs on DPDK. These radical changes in the server design translate into 5X-10x performance gain while preserving all of the Cassandra goodies. Bio: Dor Laor is the CEO of ScyllaDB. Previously, Dor was part of the founding team of the KVM hypervisor under Qumranet that was acquired by Red Hat. At Red Hat Dor was managing the KVM and Xen development for several years. Dor holds an MSc from the Technion and a Phd in snowboarding.