|
From: | Michael R. Hines |
Subject: | Re: [Qemu-devel] [RFC PATCH RDMA support v1: 10/13] introduce new command migrate_check_for_zero |
Date: | Thu, 11 Apr 2013 10:35:46 -0400 |
User-agent: | Mozilla/5.0 (X11; Linux i686; rv:17.0) Gecko/20130106 Thunderbird/17.0.2 |
Can I at least get a firm yes or no whether the maintainer will accept this capability or not? What you ask would require defining what a "real world scenario" is, andI don't think that's a good discussion to have right now. Even if we did know the
definition, I do not have the infrastructure in place to do an exhaustive search of such a workload. My personal view is: new software should define APIs, not hide APIs.The capability already has a default 'true' value, which is the same behavior
that the value has always been and nobody's threatening to get rid of that. - Michael On 04/11/2013 10:17 AM, Paolo Bonzini wrote:
Ok, understood. I would be happy to add a check for the other migration URI protocols (like 'unix', 'tcp', etc) which says rejects disabling the zero page checking only if the URI is for rdma. Would that be OK? I would like to see is_dup_page() on top of a "perf" profile for a real-world scenario, and throughput numbers for the same real-world scenario with/without is_dup_page(). Once you show that, yes. Paolo
If th - Michael
[Prev in Thread] | Current Thread | [Next in Thread] |