🥳🎉 Meta's backtracking on #jemalloc is hailed as a #groundbreaking move! Because clearly, the world needed another deep dive into memory allocation strategies over their morning coffee. 🙄🔍 Who knew infrastructure updates could be so riveting?
https://engineering.fb.com/2026/03/02/data-infrastructure/investing-in-infrastructure-metas-renewed-commitment-to-jemalloc/ #Meta #memoryallocation #infrastructureupdates #technews #HackerNews #ngated
Investing in Infrastructure: Meta’s Renewed Commitment to jemalloc

Meta recognizes the long-term benefits of jemalloc, a high-performance memory allocator, in its software infrastructure. We are renewing focus on jemalloc, aiming to reduce maintenance needs and mo…

Engineering at Meta
FOSDEM 2025 - A memory allocator with only 0,006% fixed overhead written from scratch

It’s a new day, a new video from #eurorust24! Whether you’re tuning in fresh or rewatching, dive into memory allocation with Arthur Pastel from Codspeed. Learn why stack, heap, and static memory aren’t all created equal, and how the right choices can boost your Rust app’s performance. 🦀

Watch it here 📹👉 https://youtu.be/pJ-FRRB5E84

#rustlang #performance #memoryallocation

The Impact of Memory Allocators on Performance: A Deep Dive - Arthur Pastel | EuroRust 2024

YouTube
Memory Allocation

A visual introduction to memory allocation.

Love this content about memory allocation, so useful!
https://samwho.dev/memory-allocation/
#memoryallocation
Memory Allocation

A visual introduction to memory allocation.

#Development #Guides
Memory allocation · An interactive introduction to memory allocation with visuals and a playground https://ilo.im/12v1zc

_____
#MemoryManagement #MemoryAllocation #Fragmentation #WebDevelopment #WebDev #Server #Visualization #Playground

Memory Allocation

A visual introduction to memory allocation.

This blog entry by Raymond Chen, "Why doesn’t Windows use the 64-bit virtual address space below 0x00000000`7ffe0000?"¹ is absolutely brilliant.

What I thought was a trivial design decision of some kind turns out to have deep roots in 32-bit Windows (the separation between user and kernel) and, this is where it becomes surreal, the DEC Alpha processor ​!

I quote Raymond Chen directly:

"On the Alpha AXP, most 32-bit constants can be generated in at most two instructions. But there’s a range of values that requires three instructions: 0x7fff8000 to 0x7fffffff. "

As the person who ran the first three DEC Alpha systems in the UK outside DEC "REO" (Reading Office) I have a bit of history with these processors and yet I had never ever heard of this.

Don't ignore the links embedded in the page because they are worth reading too.

(also, if you do not follow Raymond Chen's blog via RSS you should - his series on processors and the history of Windows design decisions is fabulous).

#Windows #MemoryAllocation #DECAlpha #WindowsOnAlpha
__
¹ https://devblogs.microsoft.com/oldnewthing/20221216-00/?p=107598

Why doesn't Windows use the 64-bit virtual address space below 0x00000000`7ffe0000?

It does use it, although it doesn't look like it.

The Old New Thing
Untangling Lifetimes: The Arena Allocator

Making performant dynamic manual memory management in C feel almost like garbage collection.

Digital Grove

🤔:

“Don’t Use ProtoBuf For Telemetry”, Richard Startin (https://richardstartin.github.io/posts/dont-use-protobuf-for-telemetry).

The HN-thread has comments from previous & current maintainers of #ProtoBuf on the design trade-offs: https://news.ycombinator.com/item?id=25582962

#ProtocolBuffers #Tracing #Telemetry #Performance #MemoryAllocation

Don’t use Protobuf for Telemetry

Protobuf needs no introduction, but this post argues that you shouldn’t use it for telemetry. The basic premise of this post is that a good telemetry library needs to be lightweight to avoid perturbing the application; inefficient diagnostic tools are self-defeating. Unlike other formats, nested Protobuf messages cannot be written contiguously into a stream without significant buffering. The post doesn’t argue to never use Protobuf, but that the trade-off made by the wire-format itself, as opposed to any existing implementation, is unlikely to work for lightweight message senders.

Richard Startin’s Blog