News for hackers. Stuff that matters.

A comment on Disk write buffering and its interactions with write flushes.

Re:Disk write buffering and its interactions with write flushes by randkyp on Thursday March 21, 2024 @08:28PM (#39786146)
I found this recent thread interesting, specifically about really considering whether you're going to read the data you just wrote in the near future or not (in which case, use direct IO) and a set of (abandoned?) patches for write-behind caching for sequential writes in Linux (https://lore.kernel.org/lkml/156896493723.4334.1334048120714...).

https://lore.kernel.org/linux-mm/45odvhgymm7fxsgwpewoiiggaok...

[ Parent | on HN ]
Re:Disk write buffering and its interactions with write flushes by rwmj on Friday March 22, 2024 @04:34AM (#39788533)
Direct IO is very inflexible. A better way is this recommended by Linus in an old post:

https://lkml.iu.edu/hypermail/linux/kernel/1005.2/01845.html

I implemented something along the same lines but a bit less spicy here:

https://gitlab.com/nbdkit/nbdkit/-/commit/aa5a2183a6d16afd91...

[ Parent | on HN ]
Re:Disk write buffering and its interactions with write flushes by rwmj on Friday March 22, 2024 @08:25AM (#39789969)
That second link is wrong, should be: https://gitlab.com/nbdkit/nbdkit/-/commit/a956e2e75d6c88eeef...
[ Parent | on HN ]