NASA’s new dark energy space telescope can also detect killer asteroids
technologyreview.com·3h ago
Cloud & Infrastructure
Google Cloud Blog·27d ago·5 min read
C4N, now GA: Delivering cloud’s highest per vCPU network and block storage I/O for x86 workloads
TL;DR
C4N is Google Cloud's new Compute Engine instance optimized for network and block storage, addressing performance bottlenecks in high-demand workloads. It delivers the highest per vCPU network and block storage I/O for x86 applications.
✦ Why It Matters
Engineers can adopt C4N instances to enhance the performance of their data-intensive applications immediately.
Key Takeaways
- Evaluate C4N for network-intensive applications like firewalls and load balancers.
- Consider Hyperdisk Extreme for high-performance block storage needs.
- Utilize C4N's predictable I/O performance to avoid over-provisioning resources.
- Explore cost-saving options like Committed Use Discounts for C4N instances.
Full Summary
As organizations increasingly rely on data-intensive applications, traditional virtual machines often struggle with I/O performance. Google Cloud's C4N instances, now generally available, are designed to address these challenges by utilizing a custom Titanium offload architecture that enhances network and block storage performance.
C4N instances provide up to 400 Gbps of network bandwidth and 25 GiB/s of block storage throughput, outperforming comparable Intel-based offerings. This architecture allows for efficient scaling of network, storage, and compute resources, which can lead to significant cost savings.
Additionally, C4N supports Hyperdisk Extreme, enabling high IOPS and low-latency access for modern workloads. Customers like Ericsson and Teradata are already leveraging C4N to achieve unprecedented performance in their applications.