Skip to content

Lakebase compute cache (low-latency reads of hot data)

GA
Last seen at this status: 2026-01-22·Jan 2026

Each Lakebase compute keeps hot data close to Postgres in two tiers: the Postgres shared buffers in memory and a local disk-backed compute cache sized to the compute's memory, so frequent reads avoid trips to the pageservers and object storage. The cache has been part of every Lakebase compute since the autoscaling version of Lakebase launched. This row was previously listed as Lakebase low-latency query execution.

Status history

  • GA
    2026-01-22 · Jan 2026
    Release notes

    Verified on 2026-10-15 against Databricks sources.

Sources (2)

Get Tuesday's version of this

What shipped in Databricks and why it matters, once a week. Free, one-click unsubscribe.

Read past issues first

Statuses and dates come from public Databricks sources only. We do not see the private roadmap Databricks shares with customers. If something looks wrong, report a correction.