OffNet Newsroom

Daily topic roundup

AWS

Friday, August 28, 2026 · 8 stories, curated & summarized — click any story for the source.

AWS What's New awsdatabase

Amazon Redshift KDS streaming now supports 10MiB records

Amazon Redshift has increased its Kinesis Data Streams record size limit from 1 MiB to 10 MiB, aligning with KDS's own expanded maximum. This change allows direct ingestion of significantly larger payloads without the need for record splitting. The feature is designed to simplify ingestion pipelines and support high-volume workloads with large individual records and is now available in all commercial AWS regions.

  • Record size limit increased 10x from 1 MiB to 10 MiB for KDS streams.
  • Eliminates need to split large records before ingestion into Redshift.
  • Simplifies pipeline architecture by enabling direct large-payload streaming.
  • Available immediately in all commercial AWS regions where Redshift exists.
THE SHIFTKDS Record Size Limit Increase1 MiBPREVIOUS LIMIT10 MiBNEW LIMITEliminates need for record splitting
Hacker News (100+ points) general

Cloudflare cuts 100TB from 1.1.1.1 DNS cache via optimization

Cloudflare engineers reduced the memory footprint of their 1.1.1.1 DNS resolver by 100 terabytes through deep optimization of the DNS cache layer. The changes involved refining data structures and eviction logic to handle the massive scale of global DNS traffic more efficiently. This effort highlights the engineering rigor required to maintain performance while managing infrastructure costs at a hyperscale level.

  • DNS cache memory usage can be significantly reduced through structural optimizations.
  • Large-scale resolvers like 1.1.1.1 require constant tuning to manage TB-level memory.
  • Efficient eviction policies are critical for maintaining high hit rates with less RAM.
  • Infrastructure cost savings often come from deep algorithmic improvements, not just scaling up.
BY THE NUMBERSCloudflare Saves 100TB of Memory100TBDNS cache memory reducedOptimization of 1.1.1.1 resolver data structures
AWS What's New awsdatabase

SageMaker MLflow adds customer-managed KMS key support

AWS SageMaker MLflow now allows encryption of stored data using customer-managed keys (CMK) via AWS KMS. This GA feature enables organizations with strict compliance needs to retain full control over their encryption keys. All data access is logged to AWS CloudTrail for comprehensive auditing purposes.

  • Encrypt MLflow data with your own symmetric KMS keys for enhanced security control.
  • CMKs must reside in the same AWS account and region as the MLflow App.
  • Gain detailed audit trails for all data access via AWS CloudTrail integration.
  • Feature is generally available in all regions hosting SageMaker MLflow Apps.
CHECKLISTImplementing Customer-Managed KeysEncrypt data with your own symmetric KMS keysEnsure CMKs are in the same account and regionLeverage CloudTrail integration for detailed audit trailsDeploy in any region hosting SageMaker MLflow Apps

Amazon FSx for NetApp ONTAP now allows administrators to copy backups to different AWS Regions and trusted accounts within an organization. This capability enables storing secondary backup copies distinct from primary ones, enhancing data protection strategies. The feature supports improved business continuity and compliance by leveraging FSx's existing secure, point-in-time offline volume backups.

  • Cross-region backup copies isolate data from regional outages or disasters.
  • Cross-account copying facilitates secure data sharing with trusted organizational entities.
  • Simplifies meeting strict data retention and compliance requirements.
  • Builds on existing incremental, multi-AZ backup durability for ONTAP volumes.
CHECKLISTFSx Backup StrategyIsolate data from regional outagesShare securely with trusted accountsMeet strict compliance requirementsLeverage multi-AZ durability

OpenAI CFO Sarah Friar outlines how integrated progress in hardware, compute, models, and product layers drives scalable intelligence. The company emphasizes that these advances compound to reduce costs while increasing utility. This strategic view highlights the full stack's role in delivering abundant intelligence at scale.

  • Hardware and compute advances directly enable larger, more capable models.
  • Product layer improvements maximize the utility of underlying model gains.
  • Cost efficiency is achieved by compounding improvements across the entire stack.
  • Strategic focus is on scaling intelligence availability and reducing unit costs.

Meta has introduced MTIA 300, its first in-house AI accelerator specifically optimized for training ranking and recommendation models. This release marks a strategic expansion of the company's custom silicon efforts beyond general compute into specialized workloads. The announcement highlights Meta's ongoing effort to tailor hardware to its unique large-scale AI infrastructure needs.

  • MTIA 300 targets ranking and recommendation model training, a key Meta workload.
  • This is Meta's first in-house accelerator dedicated to these specific AI tasks.
  • Strategy shifts from general compute to specialized, workload-optimized silicon.
  • Signals continued vertical integration of Meta's AI hardware stack.

Nvidia and Cerebras are marketing batch 1 token generation speeds that serve as theoretical maximums rather than practical benchmarks. This marketing approach mirrors automotive industry tactics of highlighting top speed figures that rarely reflect real-world driving conditions. The claim suggests a disconnect between advertised hardware capabilities and the performance actually achievable in typical production workloads.

  • Batch 1 throughput is a theoretical limit, not a standard production metric
  • Marketing highlights peak specs that may not reflect real-world AI inference loads
  • Expect lower actual token rates in enterprise deployments due to overhead and batching
AWS What's New awsdatabase ↺ since 08-26

AWS RDS for Oracle adds July 2026 Release Update for 19c, 21c, 26ai

Amazon RDS for Oracle now supports the July 2026 Release Update for versions 19c, 21c, and 26ai, including critical security patches. Oracle 19c adopts a new naming convention for quarterly updates, while 21c retains its existing format. Monthly Critical Security Patch Updates for 19c and 26ai will be delivered as monthly release patches bundling security fixes with recommended updates.

  • Upgrade to July 2026 RU for 19c, 21c, and 26ai to address security vulnerabilities.
  • Oracle 19c new RU naming: 19.0.0.0.ru-YYYY-MM.mrp-YYYY-MM.rN.
  • 21c RUs keep existing naming; no format change for this version.
  • Monthly CSPUs for 19c and 26ai are available as MRPs with extra fixes.
  • Check version-specific naming changes when scripting patch management.
TRADE-OFFOracle Version Naming ShiftsOracle 19c UpdateAdopts new quarterly…Monthly patches bundle…Oracle 21c UpdateRetains existing naming formatNo changes to structurevs
↑