Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2026 Poal.co

423

Archive: https://archive.today/fdyy1

From the post:

>Kairui Song of Tencent sent out a new patch series overnight working on enhancing the Linux kernel's swap code. With the patches there are some memory savings -- and more on the way -- while also providing for slightly faster performance. The patch series removes the static "swap_map" and uses the swap table for the swap count directly. This conserves around 30% memory use for the static swap metadata, which amounts to 256MB of memory when mounting a 1TB swap device... Granted, using a 1TB swap device isn't too common outside of perhaps some very large server setups.

Archive: https://archive.today/fdyy1 From the post: >>Kairui Song of Tencent sent out a new patch series overnight working on enhancing the Linux kernel's swap code. With the patches there are some memory savings -- and more on the way -- while also providing for slightly faster performance. The patch series removes the static "swap_map" and uses the swap table for the swap count directly. This conserves around 30% memory use for the static swap metadata, which amounts to 256MB of memory when mounting a 1TB swap device... Granted, using a 1TB swap device isn't too common outside of perhaps some very large server setups.
[–] • 1 pt

Why are we concerned about swap space? This hasn't been an issue in about two decades. I usually just go ahead and allocate like 16 GB to swap in every new build. Rarely has that ever filled up.

[–] • 0 pt

It depends on your workload. I deal with legacy shit that often ends up dipping into swap due to resource contention problems. No, they won't just add more RAM for a thousand stupid reasons but you get the point.

[–] • 1 pt

Legacy shit using more resources than was originally planned for? Say it isn't so.