Thanks for testing - pushed both patches to v23-rc1.
Oren.
On 02/01/2011 02:38 PM, Dan Smith wrote:
> OL> Original patch posted by Dan Smith.
>
> Tested-by: Dan Smith
>
> With this and my pipe refcount fix, all my pipe tests pass, including
> the ones that were stuck before because the hash w
OL> Original patch posted by Dan Smith.
Tested-by: Dan Smith
With this and my pipe refcount fix, all my pipe tests pass, including
the ones that were stuck before because the hash was getting free'd
late.
Thanks!
--
Dan Smith
IBM Linux Technology Center
email: da...@us.ibm.com
___
I modifed the patch a bit according to our IRC chat today:
>From 9c74f82411d77cf0194a17ba99af0dd31070e88a Mon Sep 17 00:00:00 2001
From: Oren Laadan
Date: Mon, 31 Jan 2011 19:01:49 -0500
Subject: [PATCH] c/r: clear the objhash before completing restart, but delay
free (v3)
This patch causes t
OL> So to be clear: is there a performance issue due to moving the
OL> cleanup - some or all - to before allowing tasks to resume ?
OL> (This is what I understood over IRC).
Not that I have been able to measure, no.
--
Dan Smith
IBM Linux Technology Center
email: da...@us.ibm.com
___
On 11/01/2010 01:01 PM, Dan Smith wrote:
> OL> Does this patch solve the performance problem in freeing all
> OL> the objhash entries upfront (e.g. before letting userspace
> OL> resume) ?
>
> OL> If so, is there still a performance hit for doing the 'clear'
> OL> portion early before resuming t
OL> Does this patch solve the performance problem in freeing all
OL> the objhash entries upfront (e.g. before letting userspace
OL> resume) ?
OL> If so, is there still a performance hit for doing the 'clear'
OL> portion early before resuming the tasks ? How much does it
OL> depend on the complex
Dan,
Does this patch solve the performance problem in freeing all
the objhash entries upfront (e.g. before letting userspace
resume) ?
If so, is there still a performance hit for doing the 'clear'
portion early before resuming the tasks ? How much does it
depend on the complexity of the hierarc
On Tue, Oct 19, 2010 at 07:03:11AM -0700, Dan Smith wrote:
> This patch causes the restart coordinator to clear the object hash
> before releasing the restarted tasks. It does this to make sure
> that any objects being held exclusively by the hash are released
> before the tasks start running agai