fbpx
See all blog posts

NoSQL Insights & Innovations at ScyllaDB Summit Day 1

Distributed ledger technology that simplifies collaboration and instills trust across a global supply chain. Cybersecurity applications that perform near-real-time correlation of millions of unassociated network events per second. Social platforms that connect people who cross paths on the street… or that open up new worlds of possibilities in the metaverse.

Today’s data-intensive applications are creating new types of data challenges. And ScyllaDB Summit 2022 is the place for exploring the strategies and technical advancements that gamechangers are using to overcome these challenges.

ScyllaDB Summit is a 2-day highly interactive virtual conference where thousands of engineers, architects, and developers around the world are:

  • Discovering innovations in distributed databases & the infrastructure they run on.
  • Hearing how experts at top companies are solving their most complex data challenges.
  • Learning what’s new with ScyllaDB, our monstrously fast and scalable NoSQL database.
  • Exploring the latest trends across event streaming, wide column and graph databases, and the broader data ecosystem.

Update:  ScyllaDB Sumit 2022 is now complete. All the on-demand recordings and speaker slide decks are available now. 

WATCH VIDEOS ON DEMAND

READ DAY 2 RECAP

We’re In a New Tech Cycle

ScyllaDB co-founder and CEO, Dor Laor, kicked off the conference sharing his insights on what’s distinctive about this next tech cycle:

  • Infrastructure has advanced substantially, offering tremendous power and performance to applications that can take advantage of it.
  • Applications need to work at previously-unimaginable scale — fast — and available all the time. They need to work flawlessly across a dizzying array of environments and conditions. And the teams building them need the ability to move seamlessly from MVP to global scale – and to rapidly evolve business-critical applications in production.
  • Data-intensive applications – from food delivery, to fitness tracking apps, to communication platforms – are now woven into the fabric of our lives. Data is involved in virtually everything that we do.
  • The rise of NFTs, cryptocurrency, distributed ledger technology, and the metaverse are taking distributed applications to a new level.

Is your Database Prepared?

This not only means more data, but also new pressures on the database. Ultra high performance and low latency are expected. But as our lives grow increasingly digital, it’s becoming harder and harder to accept any tradeoff on the consistency side of the CAP theorem.

Adding to the complexity, Dor finds that organizations are now performing up to 100x more queries than before, on data sets that are often 10x larger than before. Data is being enriched, cleaned, streamed, fed into AI/ML pipelines, replicated, and cached from multiple sources. “The more data you have, the more you use that data…and that means more opportunity to gain advantages via data in this new world of ours.”

What does this mean for your database latency? According to Dor’s calculations, if you have 100x the queries, P99 becomes P36. Things break at scale. And costs skyrocket.

That’s why it’s more important than ever to have a database that’s up to the task. How can you tell if you’re ready? Dor offered a set of attributes to consider – efficiency, overprovisioning, scale, maintenance, freedom – as well as equations for assessing your standing on each vector. For example:

The Next Wave of ScyllaDB Innovation

The focus then shifted to changing those equations in your favor. Enter ScyllaDB 5, the next generation of ScyllaDB.

Dor presented the vision of ScyllaDB 5 with a focus on the value provided to the end users and their teams. For example, he introduced new Raft-based consensus algorithms that set ScyllaDB on the path to immediate consistency with zero overhead. There’s also a variety of optimizations that make an already (monstrously) fast database even faster. The many improvements roll out first in ScyllaDB open source NoSQL, and ultimately will provide ScyllaDB Cloud (NoSQL DBaaS) users:

  • Extreme elasticity
  • Excellent isolation and control between workloads
  • The ability to manage thousands of clusters
  • The ability to use mega nodes or tiny pods
  • The ability to do further cluster consolidation and table consolidation within a cluster

Co-founder and CTO Avi Kivity took the stage next, providing insight into the specific features that make the vision of ScyllaDB 5 a reality. There are a lot of new features — too many to cover here, actually. A new shard-aware Rust driver. Caching changes that eliminate performance penalties typically associated with large partitions. IO scheduler optimizations. User-defined functions with Wasm. New compaction strategies that simplify data modeling for time series data. And that’s just the start.

There are so many new features that it’s taking 2 keynotes, 2 blocks of lightning talks, and 7 deep dives by ScyllaDB engineers to cover it all. .

WATCH VIDEOS ON DEMAND

There are also some very exciting developments with respect to two new Amazon EC2 instance types – the Intel-based I4i and the Graviton2-based Is4gen and Im4gn series – that are perfect for data-intensive storage and IO-heavy workloads like ScyllaDB. This was covered in a joint presentation by Head of Specialized Solution Architects, Compute at AWS, Ken Krupa, and ScyllaDB VP of Product, Tzach Livyatan. We can’t cover the news here, but you can watch the session on-demand.

“Dare Mighty Things” … with Databases

Hearing about database innovations is great; seeing how they’re put into practice is even better. We’re honored to have ScyllaDB users sharing how the first three generations of ScyllaDB have enabled them to “dare mighty things.” For example, today we learned:

  • How Rakuten migrated the product catalog’s live data processing pipeline from Cassandra without disrupting their 1.5B worldwide members.
  • How Palo Alto Networks is correlating millions of records per second from different sensors, in different forms and formats, to determine what entries actually describe the same network session – all in near in real time.
  • How IOTA Foundation addressed supply chain digitization challenges across the trade corridors in East Africa, including the role of data serialization formats, distributed ledgers, and scalable, resilient databases.
  • Numberly’s lessons learned transitioning a business-critical data-intensive application from Python to Rust – why they made the move, lessons learned along the journey, and their assessment on whether it was worth it.
  • How Happn, a leading European dating app, achieved a 75% TCO reduction by migrating a Cassandra cluster containing more than 68B records – in 5 days.

 

What to Expect in Day 2: K8s, Raft, PB-Scale Benchmarks, Event Streaming, and More

Day 2 features even more great tech talks. You can look forward to:

  • A live demo of a hybrid and multi-cloud ScyllaDB-powered application on top of Google Anthos (via SADA).
  • A close look at the latest performance features in ScyllaDB Operator for Kubernetes, as well as new security, stability, and user experience updates.
  • Bryan Cantrill, co-founder and CTO of Oxide Computer, looking back at past predictions of the future and analyzing what it all means for the present.
  • Insight on how the new Raft consensus infrastructure enables radical new capabilities in ScyllaDB 5.0 and beyond – including immediate consistency with zero overhead.
  • A deep dive into how ScyllaDB is optimizing our IO scheduler to get even better latencies from SSDs.
  • An overview of how ScyllaDB Cloud supports a seamless application development lifecycle, from MVP to global scale.
  • A look at how we benchmark ScyllaDB at the petabyte level – and tips on how you can achieve smooth and predictable performance at such monstrous scale.
  • Use cases from A(mdocs) to Z(eotap), including how Amdocs optimizes complex data and AI pipelines for the modern telecom, including diagnostics and predictive analytics, and how Zeotap satisfies technical requirements for supporting a mix of OLTP, OLAP, and real-time data ingestion with their Customer Data Platform.
  • Different takes of how to integrate ScyllaDB into event streaming architectures, including Confluent Kafka, Streamnative Pulsar, and Redpanda.

Also, we’ll be unveiling the 2022 ScyllaDB Innovation award winners, hosting a lively Speakers Lounge, and offering some fun ways to connect with your peers (and win some swag and prizes in the process).

Update: It’s a wrap! Read about Day 2 below.

Read Day 2 Recap

About Cynthia Dunlop

Cynthia is Senior Director of Content Strategy at ScyllaDB. She has been writing about software development and testing for 20+ years.