Latest iteration includes logical database configurations, robust resharding, and compute minimizing hash fields
SAN FRANCISCO – October 21, 2025 – Valkey, an open source key-value database under the Linux Foundation, today announced the general availability of Valkey 9.0. The latest version introduces expiration dates for hash fields, atomic slot migration, and multiple databases in cluster mode, which fortify Valkey’s use at scale. A Valkey 9.0 cluster can support over 1 billion requests per second, delivering on new capabilities for scalability, reliability, and efficiency in distributed data environments, all while reducing cost and overhead for engineering teams.
Valkey 9.0 continues the project’s mission to provide a fully open, community-driven in-memory data store that evolves with modern application needs. When compared with version 8.1, users of Valkey 9.0 experience up to 40% more throughput in their applications of the project. This version represents significant progress in horizontal scalability and compute efficiency – areas that have traditionally challenged distributed systems.
“Valkey 9.0 is a game changer for us,” said Khawaja Shams, co-founder and CEO of Momento. “It allows us to support larger working sets and higher throughput with the same hardware, translating into massive efficiency gains at our scale. Valkey's inclusive community has also consistently fueled our team's ambition. The project keeps outpacing itself, and we're thrilled to be part of that journey.”
Users of Valkey 9.0 will gain three banner features in this latest release: hash field expiration, atomic slot migration, and multiple databases in cluster mode. Additional upgrades in Valkey 9.0 include:
“One of our goals is to make Valkey as resilient as possible, so that our users can depend on it for serving their application traffic.” said Madelyn Olson, maintainer of Valkey and Principal Software Engineer at AWS. “Valkey 9.0 is a major step forward in that direction with larger and more stable clusters that can more easily scale to meet user demands.”
Hash Field Expiration
Valkey 9.0 delivers on another long-anticipated community request: hash field expiration. This feature allows developers to set time-to-live (TTL) values on individual fields within a hash, automatically removing expired data and freeing memory. This feature simplifies feature development while also reducing compute overhead and memory usage.
When Valkey 9.0’s hash field expiration is implemented, developers have seen increased predictability in memory usage, making the feature critical for modern key-value databases.
Atomic Slot Migration
Valkey reshards data during horizontal scaling operations using slot migration. In the past, this process led to errors, processing overhead, and data loss for operators and clients during large key movements. Atomic slot migration, included in Valkey 9.0, is a major breakthrough in reliability and performance, ensuring horizontal scaling operations are seamless and error-free.
Valkey’s atomic slot migration solves this by introducing a snapshot-based migration process that is triggered by a single command. A child process first forks and streams data incrementally from the source to the target node, allowing both nodes to remain active throughout migration. Once all data is migrated, Valkey performs an atomic handoff and clients are redirected instantly to the target node, all without downtime or errors previously encountered in traditional slot migration.
By batching and utilizing this snapshot-based approach, Valkey 9.0 improves reliability and reduces latency during resharding, greatly simplifying automated scale out and rebalancing. As a result, users can lower operating costs through more efficient scaling, ensuring Valkey 9.0 remains fast and resilient as data volumes and demands increase.
Multiple Databases in Cluster Mode
Valkey 9.0 introduces multiple databases in cluster mode. The main benefit of this feature is the ability to run multiple distinct namespaces on the same cluster, avoiding the limitations and wasted memory of legacy database configurations. Users can now logically separate datasets with numbered databases, making for neater keyspaces and more intelligent database configurations.
In practice, clustered databases might be different caches that are part of the same application, or even a staging environment running alongside an active environment. For large-scale operations, this unhampers operations and decreases overall cost.
Valkey 9.0’s numbered databases are highly scalable and can be spread over a breadth of clusters, all with zero overhead when unused. This feature improves clarity, reduces memory usage, and enables more efficient data organization at scale.
To upgrade to Valkey 9.0 and explore its scalability enhancements, visit valkey.io.
###
About Valkey
Valkey is an open source key-value database under the Linux Foundation, designed for high performance, horizontal scalability, and deep observability. The project supports a wide variety of data structures and workloads, from caching and messaging to primary in-memory storage, all under a permissive BSD license. Valkey is backed by a rich ecosystem of contributors and industry partners, including Aiven, Alibaba Cloud, AWS, Bytedance, Ericsson, Google Cloud, k0rdent, NetApp Instaclustr, Oracle, Percona and UpCloud.
###
Media Contact
Grace Lucier
The Linux Foundation
pr@linuxfoundation.org