[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Yj2hMRrY7i7OSGqH@yuki>
Date: Fri, 25 Mar 2022 12:02:09 +0100
From: Cyril Hrubis <chrubis@...e.cz>
To: Miklos Szeredi <miklos@...redi.hu>
Cc: Theodore Ts'o <tytso@....edu>,
Christian Brauner <brauner@...nel.org>,
Miklos Szeredi <mszeredi@...hat.com>,
linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
Linux API <linux-api@...r.kernel.org>,
linux-man <linux-man@...r.kernel.org>,
LSM <linux-security-module@...r.kernel.org>,
Karel Zak <kzak@...hat.com>, Ian Kent <raven@...maw.net>,
David Howells <dhowells@...hat.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Al Viro <viro@...iv.linux.org.uk>,
Christian Brauner <christian@...uner.io>,
Amir Goldstein <amir73il@...il.com>,
James Bottomley <James.Bottomley@...senpartnership.com>
Subject: Re: [RFC PATCH] getvalues(2) prototype
Hi!
> > If so, have you benchmarked lsof using this new interface?
>
> Not yet. Looked yesterday at both lsof and procps source code, and
> both are pretty complex and not easy to plug in a new interface. But
> I've not yet given up...
Looking at lsof it seems to use fopen() and fgets() to parse various
proc files. I doubt that we can make the parsing singificantly faster
without completely rewriting the internals.
As for procps the readproc.c has file2str() function that does copy
whole proc files into a buffer with open() - read() - close(). It may be
reasonably easy to hook the new systall there and it will probably make
ps and top slightly faster.
--
Cyril Hrubis
chrubis@...e.cz
Powered by blists - more mailing lists