Messages in this thread | | | Subject | Re: [PATCH 2/2] futex: lockless wakeups | From | Davidlohr Bueso <> | Date | Mon, 20 Apr 2015 10:31:05 -0700 |
| |
On Mon, 2015-04-20 at 16:57 +0200, Peter Zijlstra wrote: > Haha, you dug that out did you ;-) > > Does this patch on its own actually help anything? Back when I wrote > that there was the vague hope it would actually help some of the > client-server ping-pong workloads, where the client does sync requests > to the server. > > In that case, if the server can handle the req. while the client yields > we've saved on an expensive wakeup. > > Reality never really worked out for that -- even after we fixed a few > boot and runtime issues with it.
I had boot problems about 2 years ago (even with qemu) with it. Nowadays, I cannot trigger any issues with it. And on a large machine I've been using it just fine, throwing a lot of workloads at it. All in all my schedule auditing has only been by searching the code, not from this patch.
Thanks, Davidlohr
| |