InfoQ Homepage Cost Optimization Content on InfoQ
-
AWS Hikes EC2 Capacity Block Rates by 15% in Uniform ML Pricing Adjustment
AWS has raised EC2 Capacity Block prices for ML by 15% across all regions, impacting GPU-based workloads. The uniform price hikes affect top-tier instances powered by NVIDIA GPUs, underscoring supply chain pressures and inflation. With limited alternatives, organizations face higher costs, emphasizing the need for effective workload optimization and cost management strategies.
-
AWS Adds Intelligent-Tiering and Replication for S3 Tables
AWS has introduced Intelligent-Tiering and cross-region replication for S3 Tables to automate cost optimization and data availability for Apache Iceberg workloads. These features allow data to transition to lower-cost storage tiers based on access patterns while maintaining consistent, read-only table replicas across regions and accounts without manual synchronization.
-
AWS Expands Well‑Architected Guidance with Data Residency and Hybrid Cloud Lens
Earlier this year, AWS launched the Well-Architected Data Residency with Hybrid Cloud Services Lens, providing guidance for hybrid cloud workloads. The lens covers data classification, operational practices, automation, and compliance, helping organizations manage data location while optimizing security, cost, and resilience.
-
Netflix Migrates to Amazon Aurora: 75% Performance Boost and 28% Cost Reduction
Netflix consolidated its relational databases onto Amazon Aurora, cutting costs by 28% and boosting performance by up to 75%. The move from self-managed PostgreSQL reduced operational toil, improving latency for critical apps. This mirrors migrations by Samsung and Panasonic, though benchmarks suggest alternatives like Timescale may suit specific workloads better.
-
AWS Introduces Flat-Rate Pricing to Eliminate Cloud Cost Overages
AWS introduces flat-rate pricing plans for website delivery and security, offering predictable monthly costs with no overages. Combining CloudFront CDN, DDoS protection, and more, tiers start from free to $1,000/month. This shift enables seamless scaling for applications and simplifies budgeting, empowering developers to innovate without fear of unexpected charges.
-
AWS Launches EC2 Capacity Manager for Centralized, Cross-Account Capacity Optimization
Introducing Amazon EC2 Capacity Manager: AWS's new centralized solution for streamlined monitoring and management of EC2 capacity across all accounts and regions. This innovative tool consolidates data into a unified dashboard, enhancing efficiency while reducing operational complexity.
-
Imagine Learning Highlights Linkerd’s Role in Cloud-Native Scale and Cost Savings
Innovative education technology provider Imagine Learning relies on Linkerd as the backbone of its cloud-native infrastructure, enabling rapid growth and ensuring reliability, scalability, and security. With over 80% reduction in compute needs and a 40% cut in networking costs, Linkerd offers a proven solution that enhances efficiency across diverse sectors.
-
AWS Budgets Improves Cross-Account Cost Visibility
AWS Budgets has enhanced its Billing View, allowing organizations to manage cross-account cloud costs more securely and efficiently. Users can create custom budgets without management account access, streamlining oversight and aligning financial planning with operational needs.
-
Microsoft Azure Storage Discovery Enters Preview with Enhanced Blob Storage Analytics
Azure Storage Discovery is a service that offers a comprehensive overview of your blob storage ecosystem. Leverage advanced insights for cost optimization and security in real-time, using natural language with Azure Copilot. Quickly analyze data trends, detect outliers, and access 18 months of historical data, all in one intuitive dashboard. Experience unparalleled visibility and efficiency.
-
When Unchecked Autoscaling Generates a $120K Cloud Spend
In the wake of a staggering $120K bill due to unchecked autoscaling during a DDoS attack, industry experts stress the necessity of robust FinOps strategies. Key recommendations include capping resource limits and utilizing real-time alerts to prevent financial disasters. Balancing cost control with system availability is crucial to safeguard modern cloud environments.
-
From Hadoop to Kubernetes: Pinterest’s Scalable Spark Architecture on AWS EKS
Pinterest revamped its data infrastructure by transitioning from a legacy Hadoop system to the Moka platform, leveraging Kubernetes and Spark on AWS EKS. This strategic shift enhances job isolation, simplifies deployment, and optimizes resource management, leading to reduced costs and improved efficiency.
-
Figma's $300,000 Daily AWS Bill Highlights Cloud Dependency Risks
Figma's IPO filing reveals a staggering $300,000 daily spend on AWS, totaling $100 million annually, or 12% of its $821 million revenue. The company's deep reliance on AWS exposes it to significant risks, including potential outages and policy changes. This highlights the critical dilemma for tech firms: balancing the benefits of cloud agility with rising costs and vendor lock-in challenges.
-
AWS Lambda Gains Native Avro and Protobuf Support for Kafka Events with Schema Registry Integration
Lambda now natively supports Apache Avro and Protobuf events, streamlining Kafka event processing - an enhancement that eliminates the need for custom deserialization, automates schema validation and filtering, and optimizes costs through efficient event handling. Integration with AWS Glue and Confluent registries simplifies development, allowing cleaner data consumption and enhanced scalability.
-
Innovation Sandbox on AWS: Provisioning and Managing Temporary Environments
AWS has recently introduced Innovation Sandbox on AWS, a new open source solution for managing AWS sandbox environments through a web user interface. This solution enables developers to provision and manage secure, cost-effective, and recyclable temporary sandbox environments.
-
Google Cloud Run Now Offers Serverless GPUs for AI and Batch Processing
Google Cloud has launched NVIDIA GPU support for Cloud Run, enhancing its serverless platform with scalable, cost-efficient GPU resources. This upgrade enables rapid AI inference and batch processing, featuring pay-per-second billing and automatic scaling to zero. Developers can access seamless GPU support easily, making advanced AI applications faster and more accessible.