Messages in this thread | | | Date | Thu, 3 Aug 2006 17:15:47 -0700 | From | "Nate Diller" <> | Subject | Re: [PATCH -mm] [1/2] Remove Deadline I/O scheduler |
| |
On 8/3/06, Adrian Bunk <bunk@stusta.de> wrote: > On Thu, Aug 03, 2006 at 03:57:32PM -0700, Nate Diller wrote: > > > This patch removes the Deadline I/O scheduler. Performance-wise, it > > should be superceeded by the Elevator I/O scheduler in the following > > patch. I would be very ineterested in hearing about any workloads or > > benchmarks where Deadline is a substantial improvement over Elevator, > > in throughput, fairness, latency, anything. > >... > > You are starting with the last step.
You're right, I should have made myself clear. My goal is not to get deadline removed, but a discussion with Andrew some months ago showed he was averse to creating more options than we already have. So since I expect elevator can surpass deadline, I wanted to show that I think deadline is the one that it should replace. Certainly, CFQ and as can both beat elevator for a good number of workloads. > > First, get your Elevator I/O scheduler reviewed [1] and show some data > that backs your "it should be superceeded by the Elevator I/O scheduler" > claim. > > Then get your Elevator I/O scheduler included in Linus' tree.
My first priority is to get that patch in order.
> > Then you might perhaps schedule the Deadline I/O scheduler for removal.
what are people's thoughts on this? since schedulers are modular, do we need a scheduled removal, or can this just sit in -mm for a while? if people are concerned about scripts which ask for 'deadline', we could add another exception (like the as->anticipatory one).
NATE - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |