On Mon, 9 Nov 2020 13:17:08 +0100 Peter Zijlstra <[email protected]> wrote:
> This patch is misleading, it doesn't optimize it nearly as much as is > possible and actually fixes the softirq case, which isn't at all > mentioned. This is actually an old patch I had for some time (it's been in the ring buffer code for a while). I honestly didn't even realize that it fixed softirq, which is why it isn't mentioned ;-) I only said "optimize" I didn't say "optimal", thus it can be improved more. When I first wrote this, I saw non noise improvements with it, so it does indeed optimize it. > > Let me go do that other patch. I'll keep this patch, and replace the code when your version is available. Thanks! -- Steve
