AWS

Amazon ElastiCache has added support for Valkey 9.1, enabling customers to run latency-sensitive and high-throughput in-memory workloads with improved efficiency. This update introduces stronger isolation mechanisms for multi-tenant environments and new commands designed to streamline operational workflows. Additionally, enhanced observability features provide operators with deeper visibility into engine behavior.

• Valkey 9.1 improves memory efficiency and throughput for demanding workloads.
• Stronger isolation supports safer multi-tenant and shared-cluster deployments.
• New commands simplify common application and operational management tasks.
• Enhanced observability tools offer better visibility into engine performance.
• Fully managed service delivers latest Valkey innovations without self-operation.

The AWS Database Blog outlines how to build a user authentication service with session management on Amazon Aurora DSQL. The post walks through the complete request flow and highlights design considerations specific to the DSQL architecture. It also shares practical lessons learned from testing against a live cluster.

• Aurora DSQL requires specific design considerations for stateful session management compared to traditional databases.
• Implementation guidance covers the full request lifecycle from client to the DSQL cluster and back.
• Real-world testing insights are provided to help practitioners avoid common pitfalls during development.
• Focus is on building secure authentication services directly leveraging DSQL capabilities.

Securonix migrated hundreds of Amazon ElastiCache clusters from Redis OSS to Valkey, achieving a 20% reduction in caching costs and over $100,000 in annualized savings. The migration also improved CPU utilization and overall throughput across their global SIEM platform. This platform processes hundreds of terabytes of data daily for enterprise security teams worldwide.

• Migrating from Redis OSS to Valkey on ElastiCache can yield significant cost reductions.
• Securonix realized over $100k in annualized savings through this specific migration.
• The move improved CPU utilization and throughput for high-volume SIEM workloads.
• Valkey offers a compatible alternative for existing Redis-based ElastiCache deployments.

Apple has expanded its Private Cloud Compute offering to Google Cloud, marking its first collaboration outside its own data centers. The infrastructure leverages NVIDIA Blackwell GPUs, Intel Trust Domain Extensions (TDX), and Google's Titan security chip. Apple enforces security through an independent append-only hardware ledger and dual-vendor attestation roots, explicitly excluding AWS and Azure from this initiative.

• Apple's PCC now runs on Google Cloud, expanding beyond its proprietary data centers.
• Security relies on NVIDIA Blackwell GPUs, Intel TDX, and Google Titan chip.
• Apple uses an append-only hardware ledger and dual-vendor attestation for verification.
• This collaboration excludes AWS and Azure, focusing solely on Google Cloud infrastructure.

SoftBank is launching a GPU rental service to monetize a massive 10 GW data center facility under construction in the United States. The move positions the Japanese conglomerate as a direct competitor in the rapidly expanding cloud GPU market. This strategy aims to address excess capacity while meeting growing demand for AI training infrastructure from American clients.

• SoftBank targets US AI training demand with its new GPU rental offering.
• The 10 GW facility provides significant scale for high-density compute workloads.
• Entry adds competitive pressure to existing cloud GPU providers in the US.
• Monetizing large-scale infrastructure becomes a priority for telecom giants.