Linux has maintained a default 4MB minimum writeback chunk size but with the in-development Linux 6.19 kernel it will allow file-systems to override that minimum value. This in turn can help avoid fragmentation and yield a better experience for zoned rotation media and other uses.
Merged yesterday alongside other pull requests submitted by Microsoft engineer Christian Brauner was the feature of allowing file-systems to increase the minimum writeback chunk size.
WOOOOO
LET’S FUCKIN’ GOOOOO
I’m kidding but I’m assuming someone out there is this enthusiastic about this change
Anyone who has to do object storage is probably fearing the weekend of overtime while labbing out new tunings, but psyched at the potential sequential read performance gains and rebalance relief
Anyone who’s even done Ceph as a hobby knows what I’m talking about
Interesting. I’m assuming an engineer found a specific use-case for a major performance gain that makes this permanent change a benefit for all.
Guessing this is dimensional database or vector related for some “AI” applications because this is a fairly normal tweak for enterprise backend DB machines to implement.