[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <a62606ed-df12-4406-3e22-5387809734b4@virtuozzo.com>
Date: Tue, 23 Jan 2018 20:09:04 +0300
From: Kirill Tkhai <ktkhai@...tuozzo.com>
To: Eric Dumazet <edumazet@...gle.com>
Cc: Eric Dumazet <eric.dumazet@...il.com>,
netdev <netdev@...r.kernel.org>,
David Miller <davem@...emloft.net>,
David Ahern <dsahern@...il.com>,
Florian Westphal <fw@...len.de>,
Xin Long <lucien.xin@...il.com>,
Daniel Borkmann <daniel@...earbox.net>,
mschiffer@...verse-factory.net, jakub.kicinski@...ronome.com,
Vladislav Yasevich <vyasevich@...il.com>,
Jiri Benc <jbenc@...hat.com>
Subject: Re: [PATCH] net: Make synchronize_net() be expedited only when it's
really need
On 23.01.2018 19:58, Eric Dumazet wrote:
>>
>> Your original patch did not provide any test results. Only the fact synchronize_rcu_expedited()
>> completes faster than plain synchronize_rcu(). But this is an obvious fact
>> just because of the design, and this is described even in the documentation.
>> Beleive me, I don't want to offend you this words, but it's strange you hadn't
>> gone the way you suggest me.
>
> Well, I guess you missed the fine changelog.
>
> Please carefully read it :
>
> https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/commit/?id=be3fc413da9eb17cce0991f214ab019d16c88c41
This is just what I said.
> And you' ll noticed I had an Ack from Paul E. McKenney, the RCU maintainer.
I won't ask you either you had the ACK before you sent the patch, because
the answer is obvious.
Anyway, this doesn't matter. I don't insist on the fix for this place.
If you're so negative on this question, we may leave everything as is,
and live with this ambiguous place several years more.
Kirill
Powered by blists - more mailing lists