Urgent.News

What's breaking now, across thousands of outlets.

Tech

If hardware price squeezes make you sad, VMware says it will all end in tiers

Virtzilla finding more ways to pull data out of DRAM to enable ‘densification’ and dodge the RAMpocalypse

If hardware price squeezes make you sad, VMware says it will all end in tiers

VMware is exploring new uses for its memory tiering technology amid persistently high memory and hardware prices. The technique moves data out of DRAM and onto fast NVMe drives, allowing CPUs to access information without slowing application performance. Introduced last year in version 9 of Cloud Foundation, VMware's memory tiering now includes performance enhancements for databases and added management tools.

The technology supports approximately 75% of workloads and aims to increase this percentage by accommodating Microsoft's Radius cloud-native application platform and monster VMs with up to 960 vCPUs and 16TB of memory. VMware engineers are working on improving memory tiering's performance for vMotion, the method of moving VMs with minimal downtime, and plan to roll out further enhancements in the VCF 9.2 release around May 2027.

By using memory tiering, organizations can lower CPU cycles by up to 30% and cut the cost of ownership by 40%, as servers can be densified into fewer units.

Written by urgent.news from The Register's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at theregister.com →

More in Tech

I'm Building an Open-Source MMORPG with Rust & Python — Join the Project

I'm Building an Open-Source MMORPG in Rust and Python — Looking for Contributors Hi everyone! 👋 I'm currently working on The Last Signal , an open-source post-apocalyptic MMORPG project.

  • The Last Signal is an open-source post-apocalyptic MMORPG being developed
  • Project utilizes Rust and Python programming languages
  • Focus on client-server communication and cryptographic integration

A scraper isn’t a monitor: detecting new Telegram posts with Apify and n8n

My Actor run succeeded. It returned five recent Telegram posts, each with an ID, timestamp, and permalink. Then I asked the question the automation actually needed to answer: Which posts are new?

  • Actor retrieves five recent Telegram posts with ID, timestamp, and permalink
  • Introduces state layer for stable record identity and partitioning by channel
  • n8n workflow compares messages with durable state to identify new items

More from Tuesday 1 September →