From: Artem Bityutskiy Subject: Re: [PATCHv6 3/5] ext4: remove unnecessary superblock dirtying Date: Wed, 11 Jul 2012 16:36:16 +0300 Message-ID: <1342013776.18274.52.camel@sauron.fi.intel.com> References: <1342000698-13556-1-git-send-email-dedekind1@gmail.com> <1342000698-13556-4-git-send-email-dedekind1@gmail.com> <20120711100726.GE1316@quack.suse.cz> <20120711101150.GH1316@quack.suse.cz> Reply-To: dedekind1@gmail.com Mime-Version: 1.0 Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature"; boundary="=-M09F2wkXjz6TraIu71G9" Cc: Theodore Tso , Linux FS Maling List , Linux Kernel Maling List , Ext4 Mailing List To: Jan Kara Return-path: Received: from mga01.intel.com ([192.55.52.88]:62981 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754932Ab2GKNcA (ORCPT ); Wed, 11 Jul 2012 09:32:00 -0400 In-Reply-To: <20120711101150.GH1316@quack.suse.cz> Sender: linux-ext4-owner@vger.kernel.org List-ID: --=-M09F2wkXjz6TraIu71G9 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Wed, 2012-07-11 at 12:11 +0200, Jan Kara wrote: > > > So case 2.b is a bit controversial, but I think it is acceptable. Aft= er all, by > > > enabling checksumming we already sign up for paying the price of calc= ulating > > > it. The way to improve checksumming performance globally would be to = calculate > > > it just before sending buffers to the I/O queue. We'd need some kind = of > > > call-back which could be registered by file-systems. > Actually, the most common case of adding orphan inode used > ext4_handle_dirty_super_now() so for that case there is no difference. An= d > other cases are so rare it really does not matter... So there shouldn't b= e > any measurable difference. Actually, the entire "orphan" case uses 'ext4_handle_dirty_super_now()', so this code-path is actually unaffected by my patch-set, so I do not have to even worry about it. My changes affect only the 'ext4_handle_dirty_super()' users, and there are only 3 of them, and they are extremely rare one-time events. --=20 Best Regards, Artem Bityutskiy --=-M09F2wkXjz6TraIu71G9 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAABAgAGBQJP/YFQAAoJECmIfjd9wqK0ux4QAL3OCUVT3fbTMwzacISAGrMW c0Ak/XyQy8ecXA6nAsiZPvTpuUg8LuVkvsq5v1YcOooL4TVJHxTvxHwo72sPSNEo RdVf5XxnEUJasKecAz7aBB7U5DIrVQPi3UrWW3aEWwARiXzE7X3Wix68cq5hykm5 XCVgGBcREqj3P57hInyMWQF9ev/aR/OtOehNNA086XOd75RXfd8T6HgbGJ7G83nM ItZcRHxDWjwtZ5/+5olh7ayouxA3tPfg45hudY9i9dUeEwqH4XYsxEHGfDCL6qT3 8PXmF5dnWnz/13EXQajs27sUpdFqMtQqeqFjpcWQc2/qwwPAjF+7OxsHoxICZZZA T8pUez+ER/WKzgKdMCKN5aequM0VeSciXdum9ylBPK7+kozrd2TONBxyk53/dOBJ RLC7vTFIfYIWQ7KbqR4OTVhYACJos/Rl5/IscsABRYFoIDhfXfxXly1oW0RSGhD4 z6MDKRWvH6i+UCKlM4+cZSUSfUR7xanU/DETp2AQYoyZoPQ3apuBvlyIbE1+D9Rq hBMESsIJ2N6cZrBJjyKxO9njglU4z1JN4QPf7hWwc3PYrIHx2NaU9bMohvR9vQc+ fFgphFnyw/KbveF1Ahku3lfryZbsgvzTZoBUPxPqEpR0Yz1/oxFUyWKJuy64vgOD 75zgfpqE7EQTpJ1Oup2L =vHqr -----END PGP SIGNATURE----- --=-M09F2wkXjz6TraIu71G9--