From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from meiko.romanrm.net ([195.154.92.155]:58152 "EHLO meiko.romanrm.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750833AbbK0Fkb (ORCPT ); Fri, 27 Nov 2015 00:40:31 -0500 Date: Fri, 27 Nov 2015 10:40:28 +0500 From: Roman Mamedov To: Qu Wenruo Cc: Lukas Pirl , Subject: Re: implications of mixed mode Message-ID: <20151127104028.4eb793ba@natsu> In-Reply-To: <5657BE2B.10209@cn.fujitsu.com> References: <56579BD1.4030401@lukas-pirl.de> <5657BE2B.10209@cn.fujitsu.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/PgnMZOL865.ScKPeSVDzBhZ"; protocol="application/pgp-signature" Sender: linux-btrfs-owner@vger.kernel.org List-ID: --Sig_/PgnMZOL865.ScKPeSVDzBhZ Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable On Fri, 27 Nov 2015 10:21:31 +0800 Qu Wenruo wrote: > And some extra pros and cons due to fixed(4K) small(compared to 16K=20 > default) nodesize: >=20 > + A little higher performance > node/leaf size is restricted to sectorsize, smaller node/leaf, > smaller range to lock. > In our SSD test, operations with high concurrency, the performance is > overall 10% better than 16K nodesize. > And in extreme metadata operation case, like high concurrency on > sequence write into small files, it can be 8 times the performance of > default 16K nodesize. This is surprising to read, as I thought 16K is generally faster and that's why the default value was changed to it from 4K. https://oss.oracle.com/~mason/blocksizes/ https://git.kernel.org/cgit/linux/kernel/git/mason/btrfs-progs.git/commit/?= id=3Dc652e4efb8e2dd76ef1627d8cd649c6af5905902 Seems like the 16K size prevents fragmentation, but since your SSDs do not = care much about fragmentation, that's not adding a benefit for them. --=20 With respect, Roman --Sig_/PgnMZOL865.ScKPeSVDzBhZ Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iEYEARECAAYFAlZX7MwACgkQTLKSvz+PZwg3GwCfQE0tWnolT7qAO4nB9vVgznbx x28AoI3Ivbsw+xB3ZZDkBa9nNznlhldU =fCTb -----END PGP SIGNATURE----- --Sig_/PgnMZOL865.ScKPeSVDzBhZ--