---
title: "ClickHouse Cloud on Google Cloud Now Powered by Google Axion Processors: 30–55% Faster Queries, ~15% Fewer Compute Credits"
description: "ClickHouse Cloud transitioned its Google Cloud infrastructure from x86 N2D instances to Arm-based Google Axion C4A instances to resolve CPU throttling and performance ceilings under peak query loads. The migration leverages Axion's dedicated physical cores per vCPU, higher memory bandwidth, local SSDs, and improved thermal and clock frequency stability. In automated ClickBench testing across 100 million rows, every query in the 43-query benchmark improved by 30% to 55%, while data load times decreased by approximately half. A production analysis of 38 migrated customer services demonstrated an average 15% reduction in compute credits consumed per query across diverse production workloads. ClickHouse Cloud executed this rollout using automated validation checks, scheduled maintenance windows, and capacity coordination with Google Cloud."
---

# ClickHouse Cloud on Google Cloud Now Powered by Google Axion Processors: 30–55% Faster Queries, ~15% Fewer Compute Credits

[Clickhouse](https://yomu.fyi/company/clickhouse) · ClickHouse · Apr 22, 2026

**Type:** Announcement

## Summary

ClickHouse Cloud transitioned its Google Cloud infrastructure from x86 N2D instances to Arm-based Google Axion C4A instances to resolve CPU throttling and performance ceilings under peak query loads. The migration leverages Axion's dedicated physical cores per vCPU, higher memory bandwidth, local SSDs, and improved thermal and clock frequency stability. In automated ClickBench testing across 100 million rows, every query in the 43-query benchmark improved by 30% to 55%, while data load times decreased by approximately half. A production analysis of 38 migrated customer services demonstrated an average 15% reduction in compute credits consumed per query across diverse production workloads. ClickHouse Cloud executed this rollout using automated validation checks, scheduled maintenance windows, and capacity coordination with Google Cloud.

## Context

Several large ClickHouse Cloud customers on Google Cloud encountered performance ceilings on x86-based N2D nodes, including persistent CPU throttling and insufficient compute capacity during peak query loads. Workloads were also subject to clock frequency variation under sustained multi-tenant load.

## Approach / What changed

ClickHouse Cloud initiated a phased migration to Google Axion C4A instances offering single-vCPU-per-physical-core Arm architecture, higher memory bandwidth, and local SSDs. Rollouts were automated through staging, validation checks, regional capacity coordination, and scheduled low-traffic maintenance windows, prioritizing SharedCatalog services.

## Takeaways

- In standard ClickBench benchmarks, migrating from N2D to Axion C4A instances yielded a 30% to 55% query latency improvement across all 43 queries and cut data load times roughly in half.
- A study of 38 production services migrating to Axion showed an average 15% reduction in compute credits per query across varied real-world workloads.
- Unlike x86 instances with two logical vCPUs per physical core and clock frequency variance under load, Axion provides one vCPU per core and improved thermal and frequency stability.

**Tags:** [Google Cloud](https://yomu.fyi/topic/gcp), [Migrations](https://yomu.fyi/topic/migration), [Performance](https://yomu.fyi/topic/performance), [Scalability](https://yomu.fyi/topic/scalability)

- Source: [Clickhouse](https://clickhouse.com/blog/google-axion)
- Source URL: https://clickhouse.com/blog/google-axion
- Ingested by Yomu: 2026-08-28T01:24:49.280Z

[Read original post](https://clickhouse.com/blog/google-axion)