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 da...@us.ibm.com
With this and my pipe refcount fix, all my pipe tests pass, including
the ones that were stuck before because
OL Original patch posted by Dan Smith.
Tested-by: Dan Smith da...@us.ibm.com
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 or...@cs.columbia.edu
Date: Mon, 31 Jan 2011 19:01:49 -0500
Subject: [PATCH] c/r: clear the objhash before completing restart, but delay
free (v3)
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
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 complexity
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 the tasks ?
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 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 again.