Re: [rfc] direct IO submission and completion scalability issues

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Nick Piggin <npiggin@...>
Cc: Siddha, Suresh B <suresh.b.siddha@...>, Christoph Lameter <clameter@...>, <linux-kernel@...>, <arjan@...>, <mingo@...>, <ak@...>, <jens.axboe@...>, <James.Bottomley@...>, <andrea@...>, <akpm@...>, <andrew.vasquez@...>
Date: Tuesday, July 31, 2007 - 8:55 pm

On Wed, Aug 01, 2007 at 02:41:18AM +0200, Nick Piggin wrote:

Yes.

Ingo, in general with CFS micro accounting, we should be able to avoid
penalizing the running task by tracking irq/softirq time. Isn't it?


I am not recommending SCHED_FIFO. I will take a look at softirq
infrastructure for this.


Nick remember that there are hundreds of disks in this setup and at
an instance, there will be max 1 or 2 requests per disk.


Ok. Currently the patch handles both direct and buffered IO. While making
improvements to this patch I will make sure that both the paths take
advantage of this.

thanks,
suresh
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[rfc] direct IO submission and completion scalability issues, Siddha, Suresh B, (Fri Jul 27, 9:21 pm)
Re: [rfc] direct IO submission and completion scalability is..., Christoph Lameter, (Mon Jul 30, 2:20 pm)
Re: [rfc] direct IO submission and completion scalability is..., Siddha, Suresh B, (Tue Jul 31, 8:55 pm)