Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 4 Mar 2021 08:44:52 +0100
From:   Florian Westphal <fw@strlen.de>
To:     Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz>
Cc:     pablo@netfilter.org, kadlec@netfilter.org, fw@strlen.de,
        netfilter-devel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/3] Revert "netfilter: x_tables: Switch synchronization
 to RCU"
Message-ID: <20210304074452.GI17911@breakpoint.cc>
References: <20210304013116.8420-1-mark.tomlinson@alliedtelesis.co.nz>
 <20210304013116.8420-3-mark.tomlinson@alliedtelesis.co.nz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20210304013116.8420-3-mark.tomlinson@alliedtelesis.co.nz>
User-Agent: Mutt/1.10.1 (2018-07-13)
Precedence: bulk

Mark Tomlinson <mark.tomlinson@alliedtelesis.co.nz> wrote:
> This reverts commit cc00bcaa589914096edef7fb87ca5cee4a166b5c.
> 
> This (and the preceding) patch basically re-implemented the RCU
> mechanisms of patch 784544739a25. That patch was replaced because of the
> performance problems that it created when replacing tables. Now, we have
> the same issue: the call to synchronize_rcu() makes replacing tables
> slower by as much as an order of magnitude.

Can you give roigh numbers?

> See https://lore.kernel.org/patchwork/patch/151796/ for why using RCU is
> not a good idea.

Please, no link.