Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 24 Apr 2018 09:17:00 +0300
From:   Alexey Dobriyan <adobriyan@gmail.com>
To:     jeffm@suse.com
Cc:     linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        Al Viro <viro@zeniv.linux.org.uk>,
        "Eric W . Biederman" <ebiederm@xmission.com>,
        Oleg Nesterov <oleg@redhat.com>
Subject: Re: [RFC] [PATCH 0/5] procfs: reduce duplication by using symlinks
Message-ID: <20180424061700.GA3689@avx2>
References: <20180424022106.16952-1-jeffm@suse.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20180424022106.16952-1-jeffm@suse.com>
User-Agent: Mutt/1.9.4 (2018-02-28)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Apr 23, 2018 at 10:21:01PM -0400, jeffm@suse.com wrote:
> Memory pressure isn't really an issue on this machine, so we
> end up using well over 100GB for proc files.

Text files at scale!

> With these patches applied, running the same testcase, the proc_inode
> cache only gets to about 600k objects, which is about 99.7% fewer.  I
> get that procfs isn't supposed to be scalable, but this is kind of
> extreme. :)

Easy stuff:
* all ->get_link hooks are broken in RCU lookup (use GFP_KERNEL),
* "%.*s" for dentry names is probably unnecessary,
  they're always NUL terminated
* kasprintf() does printing twice, since we're kind of care about /proc
  performance, allocate for the worst case.

* "int nlinks = nlink_tgid;"
  Unsigned police.

* (inode->i_mode & S_IFLNK)
	this is sketchy, S_ISLNK exists.