From mboxrd@z Thu Jan 1 00:00:00 1970 From: NeilBrown Subject: Re: Raid10 and page cache Date: Wed, 7 Dec 2011 15:28:53 +1100 Message-ID: <20111207152853.42594fc9@notabene.brown> References: <20111207092625.7140c5dc@notabene.brown> <20111207120133.70ca294c@notabene.brown> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/EkQMCsEdI=rSEhMrODNgYbZ"; protocol="application/pgp-signature" Return-path: In-Reply-To: Sender: linux-raid-owner@vger.kernel.org To: "Yucong Sun (=?GB2312?B?0rbT6rfJ?=)" Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids --Sig_/EkQMCsEdI=rSEhMrODNgYbZ Content-Type: text/plain; charset=GB2312 Content-Transfer-Encoding: quoted-printable On Tue, 6 Dec 2011 20:04:33 -0800 Yucong Sun (=D2=B6=D3=EA=B7=C9) wrote: > The problem with using page-flush as a write cache here is that write > to MD don't go through IO scheduler, which is a very big problem, > because when flush thread decide to write to MD, it's impossible to > control the write speed, or prioritize them with read, every requests > basically is a fifo, and when flush size is big, no read can be > served. >=20 I'm not sure I understand.... Requests don't go through an IO scheduler before they hit md, but they do after md sends them on down, so they can be re-ordered there. There was a bug where raid10 would allow an arbitrary number of writes to queue up so that flushing code didn't know when to stop. This was fixed by=20 commit 34db0cd60f8a1f4ab73d118a8be3797c20388223 nearly 2 months ago :-) NeilBrown --Sig_/EkQMCsEdI=rSEhMrODNgYbZ Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (GNU/Linux) iQIVAwUBTt7rhTnsnt1WYoG5AQKElRAAmeYvD7VJp+jiB6Qcsuri4qmGRAkOEZbR ubDMilaK0bNO7D0vwgVgz0Sr8hyn3GQphLUlUxekRuS+H36/pC1M+BhSi8TaQXsH XjLRO9KPmKgFi7iShBwK9ZzUNtahFj7v8VfaYp9W0IoDrm87WGE39LHlcoFI5l0u NWbuzbHdBnf5yiye+zBZTqDh7Mr3vW/V98EUBqzozYINomPRiP5m+3fGZgp8uCGd /8mXoeIPp0D4+VyRsU1cxLGcsRr7so3C+T4IrV0NSDb72Td6RwZqFWV1/s4bK4tK oWspjebCi7hbPxICcAWITnotAL5ZQ92G9n4vb/6R0fRXVzZT6vVtYRiIu/OQ5FeV z5f99KmnRDIWR3ixQA95WMWiTeDTnJXWG93yl2aV1NJ6sPP3nHw/qSoaS0lPAiQb bDMjl8fIb37qnkBFawVjrm8W2H76Sw9pvrhsAQh8VJs4gHm5XsRK0YEEg+JuIOs0 k+D6M//8yOoT8S8r7NYTy3aAmvnzah94RKd8VIxIbx53Mf+VPKqqN4I5/4LzRZPJ ely8divAvUgKtx9swdelBpTUyJkW3JzcSxeJQLUqKWn1daRkAUgeYdwHIOk9v+au xviEw7AuAX0T0C1dxfw1+f71Gf0NFLCPdKIgKsOx8YyMEcZtydfjuGfa7vPz3qQp N1GUq5ilwe0= =C0HJ -----END PGP SIGNATURE----- --Sig_/EkQMCsEdI=rSEhMrODNgYbZ--