Fivetran Raises $565 Million, Buys CDC Vendor HVR
Fivetran took a big step into the world of enterprise data integration today when it announced an Andreessen Horowitz-led $565 million round of financing and plans to acquire change data capture (CDC) vendor HVR for $700 million. The move positions the up-and-coming ETL company to further access exabytes of data stored in on-prem databases and ERP systems on behalf of its customers.
The Series C round and acquisition position Fivetran to be at the forefront of the next generation of data integration and extract, transform, and load (ETL) capabilities. The nine-year-old, Oakland, California company has made its mark by simplifying the process of setting up pipelines that extract data from source systems–primarily SaaS applications running on clouds–and load it into cloud-based data warehouses. Today’s news will help to expand Fivetran’s footprint with on-prem systems, including the ERP applications at the heart of established enterprises.
HVR’s software will be instrumental in getting at the on-prem data in enterprise applications, which remains woefully underutilized. According to a Gartner report references by Fivetran, 97% of companies’ data is unused, and much of that sits in on-prem databases and ERP systems from Oracle, SAP, and others.
“HVR has spent decades putting together the team and technology to solve the hardest data pipeline problem there is: replicating mission-critical database management systems for the world’s largest enterprises,” Fivetran CEO George Fraser stated in a blog post today. “These systems contain the most valuable business data, but they’re the hardest to interact with precisely because they are so mission-critical. HVR’s technology can achieve a combination of light footprint, low latency, and high throughput that can’t be found anywhere else.”
HVR’s technology complements Fivetran’s expertise, which is primarily focused around SaaS applications, Fraser said. “Fivetran has spent years learning the intricacies of hundreds of SaaS tools used by modern businesses,” he continued. “We operate a managed service that hides the complexities of these tools from the user and presents analysts with a simple, ready-to-query schema.”
HVR was listed as a Niche Player in Gartner’s 2021 Magic Quadrant for Data Integration, the same quadrant as Fivetran (see our writeup on the report here). “HVR has a singular focus on the CDC market,” Gartner analysts wrote in the report. “This enables HVR to introduce strong product capabilities in this space.”
Gartner heralded HVR’s capability to read both online and archive logs, as well as to match source and target tables for data validation. The analyst group highlighted HVR’s support for both agent-based and agentless options, which lets HVR tackle hybrid and multi-cloud deployments. It also mentioned HVR’s data compression capabilities, which is conducive to high-volume replication, as well as HVR’s support for database tables, JSON, Parquet, Avro, CSV, and XML, HVR.
Of particular note in Gartner’s report is HVR’s support for complex data transformations–including the ability to transform data at the row-level, support for “stubbing” missing values, fixing outliers, and character-set conversions. Considering that Fivetran has traditionally focused on the ELT process, whereby the transformation is handled by the database or data warehouse after the data has landed, this could be conducive to Fivetran building out its capabilities in ELT as well.
As previously mentioned, HVR was laser-focused on CDC, which enables companies to rapidly replicate changes made to production databases in real time–or as close to real-time as is feasible. Traditional relational databases typically were designed to maintain state, not to expose the event log, a fact that has made real-time streaming technologies such as Apache Kafka so popular. (On the flip side, the lack of the ability to maintain state in real-time streaming systems like Kafka has triggered the need to build something that resembles a database around Kafa. Balancing the demand of stateful data and event data is not easy, especially at scale, and compromises are the norm.)
That singular focus on CDC for HVR, which has about 400 customers, appears to make it a good fit with Fivetran for other reasons. For example, Gartner cited HVR’s lack of support for complex ETL workloads, including the capability to support data delivery styles other than data replication.
“For complex bulk/batch ETL workloads, HVR has partnerships with Talend, Matillion, and Idera,” Gartner states in its Magic Quadrant. “However, despite having the ability to enrich data, limited ability for bidirectional exchange of metadata with other tools means that customers need to stitch together HVR with other data integration tools for enabling the full breadth of data integration styles.”
Fivetran has already done much of that stitching, and armed with HVR’s support for data transformation, will be better positioned to address the full array of data transformation requirements in large enterprise accounts. The same goes for HVR’s lack of integration in the data quality, data catalog, governance, and privacy spaces, as cited by Gartner. Fivetran may not be a leader in addressing these concerns, but the company seems to have a firm grip of how these capabilities are coming together in the modern data stack.
Existing investor Andreessen Horowitz led the Series D round, which brings Fivetran’s total financing to $730 million to date. The company is said to be worth $5.6 billion, which is $4.2 billion more than it was said to be worth in June 2020, when it raised $100 million. That Series C round was co-led by a16z and General Catalyst, which also participated in this Series D. Other investors included CEAS Investments, Matrix Partners, and others, along with new investors ICONIQ Capital, D1 Capital Partners, and YC Continuity.