From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from lists.gentoo.org ([140.105.134.102] helo=robin.gentoo.org) by nuthatch.gentoo.org with esmtp (Exim 4.62) (envelope-from ) id 1I8j5r-0005iU-Nf for garchives@archives.gentoo.org; Wed, 11 Jul 2007 20:47:28 +0000 Received: from robin.gentoo.org (localhost [127.0.0.1]) by robin.gentoo.org (8.14.0/8.14.0) with SMTP id l6BKkD5r028919; Wed, 11 Jul 2007 20:46:13 GMT Received: from smtp11.unit.tiscali.de (smtp11.unit.tiscali.de [213.205.33.47]) by robin.gentoo.org (8.14.0/8.14.0) with ESMTP id l6BKfWkH023997 for ; Wed, 11 Jul 2007 20:41:32 GMT Received: from homer_gentoo64.phheimnetz (89.57.44.92) by smtp11.unit.tiscali.de (7.3.121) (authenticated as florian.philipp@tiscali.de) id 4674D1B10036D17D for gentoo-user@lists.gentoo.org; Wed, 11 Jul 2007 14:30:18 +0200 From: Florian Philipp To: gentoo-user@lists.gentoo.org Subject: Re: [gentoo-user] Absymal IDE performance with gentoo-sources-2.6.22 and why hda instead of sda? Date: Wed, 11 Jul 2007 14:30:13 +0200 User-Agent: KMail/1.9.5 References: <2262129.MyGpgaN8yZ@kn.gn.rtr.message-center.info> In-Reply-To: <2262129.MyGpgaN8yZ@kn.gn.rtr.message-center.info> Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: List-Id: Gentoo Linux mail X-BeenThere: gentoo-user@gentoo.org Reply-to: gentoo-user@lists.gentoo.org MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1675714.OTEQThLnxN"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <200707111430.16675.f.philipp@addcom.de> X-Archives-Salt: 26cfc110-1e71-47b2-a098-ff2572bafd80 X-Archives-Hash: ec7498a54f6641cd2cdafa32dce9507c --nextPart1675714.OTEQThLnxN Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Am Mittwoch 11 Juli 2007 10:01 schrieb Alexander Skwar: > Hello. > > Yesterday, I installed gentoo-sources-2.6.22. When I now boot this new > kernel, I notice that all of a sudden my SATA disk is addressed with > /dev/hda, whereas it used to be addressed with /dev/sda in 2.6.21. Why's > that? > > But much more important: The IDE performance is now extremely bad. > > ,----[ hdparm -tT /dev/hda, kernel 2.6.22 ] > > | /dev/hda: > | Timing cached reads: 2414 MB in 2.00 seconds =3D 1208.28 MB/sec > | Timing buffered disk reads: 8 MB in 3.99 seconds =3D 2.00 MB/sec > > `---- > > With 2.6.21, it's A LOT faster: > > ,----[ hdparm -tT /dev/sda, kernel 2.6.21 ] > > | /dev/sda: > | Timing cached reads: 2414 MB in 2.00 seconds =3D 1207.80 MB/sec > | Timing buffered disk reads: 150 MB in 3.01 seconds =3D 49.76 MB/sec > > `---- > > The drive is (is?) running with udma5 in both cases, according to > hdparm: > > ,----[ hdparm -Him /dev/sda, kernel 2.6.21 ] > > | /dev/sda: > | drive temperature (celsius) is: 42 > | drive temperature in range: yes > | HDIO_GET_MULTCOUNT failed: Inappropriate ioctl for device > | > | Model=3DHitachi HTS721010G9SA00 , FwRev=3DMCZOC10H, > | SerialNo=3D MPCZN7Y0H7E5VL Config=3D{ HardSect NotMFM HdSw>15uSec = =46ixed > | DTR>10Mbs } > | RawCHS=3D16383/16/63, TrkSize=3D0, SectSize=3D0, ECCbytes=3D4 > | BuffType=3DDualPortCache, BuffSize=3D7538kB, MaxMultSect=3D16, MultSec= t=3D?8? > | CurCHS=3D16383/16/63, CurSects=3D16514064, LBA=3Dyes, LBAsects=3D19537= 1568 > | IORDY=3Don/off, tPIO=3D{min:240,w/IORDY:120}, tDMA=3D{min:120,rec:120} > | PIO modes: pio0 pio1 pio2 pio3 pio4 > | DMA modes: mdma0 mdma1 mdma2 > | UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 > | AdvancedPM=3Dyes: mode=3D0x80 (128) WriteCache=3Denabled > | Drive conforms to: ATA/ATAPI-7 T13 1532D revision 1:=20 > | ATA/ATAPI-2,3,4,5,6,7 > | > | * signifies the current active mode > > `---- > > ,----[ hdparm -Him /dev/hda, kernel 2.6.22 ] > > | /dev/hda: > | drive temperature (celsius) is: 41 > | drive temperature in range: yes > | multcount =3D 16 (on) > | > | Model=3DHitachi HTS721010G9SA00, FwRev=3DMCZOC10H, SerialNo=3DMPCZN7Y0= H7E5VL > | Config=3D{ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs } > | RawCHS=3D16383/16/63, TrkSize=3D0, SectSize=3D0, ECCbytes=3D4 > | BuffType=3DDualPortCache, BuffSize=3D7538kB, MaxMultSect=3D16, MultSec= t=3D16 > | CurCHS=3D16383/16/63, CurSects=3D16514064, LBA=3Dyes, LBAsects=3D19537= 1568 > | IORDY=3Don/off, tPIO=3D{min:240,w/IORDY:120}, tDMA=3D{min:120,rec:120} > | PIO modes: pio0 pio1 pio2 pio3 pio4 > | DMA modes: mdma0 mdma1 mdma2 > | UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 > | AdvancedPM=3Dyes: mode=3D0x80 (128) WriteCache=3Denabled > | Drive conforms to: ATA/ATAPI-7 T13 1532D revision 1:=20 > | ATA/ATAPI-2,3,4,5,6,7 > | > | * signifies the current active mode > > `---- > > What do I have to do, so that the drive is fast in kernel 2.6.22 as > well? > > I'm booting the 2.6.22 kernel with this entry in grub menu.lst: > > ,----[ kernel 2.6.22 ] > > | title Gentoo GNU/Linux (zuletzt gebauter Kernel mit hda) > | root (hd0,2) > | kernel /vmlinuz root=3D/dev/hda6 lapic libata.atapi_enabled=3D1 > | combined_mode=3Dlibata > > `---- > > Kernel 2.6.21 is started with the following entry in grub: > > ,----[ kernel 2.6.21 ] > > | title Gentoo GNU/Linux (vorletzter gebauter Kernel) > | root (hd0,2) > | kernel /vmlinuz.old root=3D/dev/sda6 lapic libata.atapi_enabled= =3D1 > | combined_mode=3Dlibata > > `---- I had the same problem on my laptop. You have to deactivate generic drivers= in=20 your kernel. (Stuff like Generic ATA Support) --nextPart1675714.OTEQThLnxN Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQBGlM1VCBEaaFO6I+ARAi4pAJ0cTkyS9Hbrj+Y24H11Vs3G2Vhs3gCaA3qC n9+V9MACYrDENjKUbujNeuI= =S9qh -----END PGP SIGNATURE----- --nextPart1675714.OTEQThLnxN-- -- gentoo-user@gentoo.org mailing list