Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 23 Mar 2022 08:14:05 +0100
From:   Greg KH <gregkh@linuxfoundation.org>
To:     Casey Schaufler <casey@schaufler-ca.com>
Cc:     Miklos Szeredi <mszeredi@redhat.com>,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-api@vger.kernel.org, linux-man@vger.kernel.org,
        linux-security-module@vger.kernel.org, Karel Zak <kzak@redhat.com>,
        Ian Kent <raven@themaw.net>,
        David Howells <dhowells@redhat.com>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Christian Brauner <christian@brauner.io>,
        Amir Goldstein <amir73il@gmail.com>,
        James Bottomley <James.Bottomley@hansenpartnership.com>
Subject: Re: [RFC PATCH] getvalues(2) prototype
Message-ID: <YjrIvRCg2iUeMN2V@kroah.com>
References: <20220322192712.709170-1-mszeredi@redhat.com>
 <f80f372b-4249-eb25-ed95-9f8615877745@schaufler-ca.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <f80f372b-4249-eb25-ed95-9f8615877745@schaufler-ca.com>
Precedence: bulk

On Tue, Mar 22, 2022 at 01:36:26PM -0700, Casey Schaufler wrote:
> On 3/22/2022 12:27 PM, Miklos Szeredi wrote:
> > Add a new userspace API that allows getting multiple short values in a
> > single syscall.
> > 
> > This would be useful for the following reasons:
> > 
> > - Calling open/read/close for many small files is inefficient.  E.g. on my
> >    desktop invoking lsof(1) results in ~60k open + read + close calls under
> >    /proc and 90% of those are 128 bytes or less.
> 
> You don't need the generality below to address this issue.
> 
> int openandread(const char *path, char *buffer, size_t size);
> 
> would address this case swimmingly.

Or you can use my readfile(2) proposal:
	https://lore.kernel.org/r/20200704140250.423345-1-gregkh@linuxfoundation.org

But you had better actually benchmark the thing.  Turns out that I could
not find a real-world use that shows improvements in anything.

Miklos, what userspace tool will use this new syscall and how will it be
faster than readfile() was?

I should rebase that against 5.17 again and see if anything is different
due to the new spectre-bhb slowdowns.

thanks,

greg k-h