Now that io_uring will be in the upcoming 5.1 kernel, I spent some time writing up how it came to be and how it works. More formats likely coming, and I expect a few revisions too. For now, consider this v1.0 of the doc: http://kernel.dk/io_uring.pdf
I don't think that part is very interesting, since CFQ is gone and only BFQ supports priorities. They do map all the way down to the driver though, so hardware support is trivial.
-
-
Does that mean priority support is feasible, eventually? For example some of us want high-pri for log writes, lower pri for background LSM compaction writes and b-tree page write-back.
-
Right, we have priority plumbed through the stack, but not really utilized. At least it means that when we do define proper semantics for this, everything is ready to go.
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.