From: Tilman Schmidt <tilman@imap.cc>
To: linux-kernel@vger.kernel.org
Subject: [2.6.18-rc7-mm1] slow boot
Date: Sun, 24 Sep 2006 18:59:18 +0200 [thread overview]
Message-ID: <4516B966.3010909@imap.cc> (raw)
[-- Attachment #1: Type: text/plain, Size: 4837 bytes --]
FYI: On my Dell OptiPlex GX110 (Intel Pentium III, 933 MHz, 512 MB
RAM, i810 chipset), kernel 2.6.18-rc7-mm1 takes drastically longer
to boot than 2.6.18 mainline release. Some data points from the
respective dmesg outputs:
<<<<<<< 2.6.18
<4>[ 26.332472] PID hash table entries: 2048 (order: 11, 8192 bytes)
<4>[ 26.334415] Console: colour VGA+ 80x25
>>>>>>> 2.6.18-rc7-mm1
<4>[ 32.102004] PID hash table entries: 2048 (order: 11, 8192 bytes)
<4>[ 32.174041] Console: colour VGA+ 80x25
Strange delay in mm wrt mainline. (There are several of these.)
<<<<<<< 2.6.18
<4>[ 26.336075] ------------------------
<4>[ 26.336130] | Locking API testsuite:
<4>[ 26.336187] ----------------------------------------------------------------------------
<4>[ 26.336270] | spin |wlock |rlock |mutex | wsem | rsem |
<4>[ 26.336352] --------------------------------------------------------------------------
<4>[ 26.336451] A-A deadlock: ok | ok | ok | ok | ok | ok |
<4>[ 26.338380] A-B-B-A deadlock: ok | ok | ok | ok | ok | ok |
<4>[ 26.340249] A-B-B-C-C-A deadlock: ok | ok | ok | ok | ok | ok |
...
<4>[ 26.408007] Good, all 218 testcases passed! |
<4>[ 26.408065] ---------------------------------
>>>>>>> 2.6.18-rc7-mm1
<4>[ 32.183079] ------------------------
<4>[ 32.183134] | Locking API testsuite:
<4>[ 32.183190] ----------------------------------------------------------------------------
<4>[ 32.183273] | spin |wlock |rlock |mutex | wsem | rsem |
<4>[ 32.183356] --------------------------------------------------------------------------
<4>[ 32.183452] A-A deadlock: ok | ok | ok | ok | ok | ok |
<4>[ 32.273613] A-B-B-A deadlock: ok | ok | ok | ok | ok | ok |
<4>[ 32.497062] A-B-B-C-C-A deadlock: ok | ok | ok | ok | ok | ok |
...
<4>[ 39.746662] Good, all 218 testcases passed! |
<4>[ 39.746720] ---------------------------------
All locking API tests are extremely slow (tenths of seconds in mm,
milliseconds in mainline.) By the end of the testsuite, the mm
kernel has already lost 13 seconds on the mainline kernel.
<<<<<<< 2.6.18
<4>[ 26.596570] evxfevnt-0089 [02] enable : Transition to ACPI mode successful
<6>[ 26.708752] NET: Registered protocol family 16
>>>>>>> 2.6.18-rc7-mm1
<4>[ 40.787142] evxfevnt-0089 [02] enable : Transition to ACPI mode successful
<6>[ 41.329553] NET: Registered protocol family 16
<<<<<<< 2.6.18
<6>[ 26.749162] ACPI: Assume root bridge [\_SB_.PCI0] bus is 0
<7>[ 26.757435] Boot video device is 0000:00:01.0
>>>>>>> 2.6.18-rc7-mm1
<6>[ 42.025638] ACPI: Assume root bridge [\_SB_.PCI0] bus is 0
<7>[ 42.435641] Boot video device is 0000:00:01.0
More inexplicable delays.
<<<<<<< 2.6.18
<6>[ 30.233858] PNP: PS/2 Controller [PNP0303:KBD,PNP0f13:MOU] at 0x60,0x64 irq 1,12
<6>[ 30.242857] serio: i8042 AUX port at 0x60,0x64 irq 12
<6>[ 30.249613] serio: i8042 KBD port at 0x60,0x64 irq 1
<6>[ 30.257604] mice: PS/2 mouse device common for all mice
<6>[ 30.265941] input: PC Speaker as /class/input/input0
<6>[ 30.304365] input: AT Translated Set 2 keyboard as /class/input/input1
>>>>>>> 2.6.18-rc7-mm1
<6>[ 56.409925] PNP: PS/2 Controller [PNP0303:KBD,PNP0f13:MOU] at 0x60,0x64 irq 1,12
<6>[ 56.660486] serio: i8042 AUX port at 0x60,0x64 irq 12
<6>[ 57.028188] serio: i8042 KBD port at 0x60,0x64 irq 1
<6>[ 57.036853] mice: PS/2 mouse device common for all mice
<6>[ 58.532944] input: PC Speaker as /devices/platform/pcspkr/input0
<6>[ 59.224917] input: AT Translated Set 2 keyboard as /devices/platform/i8042/serio1/input1
<6>[ 61.408168] input: ImPS/2 Generic Wheel Mouse as /devices/platform/i8042/serio0/input2
Keyboard and mouse detection take 100x as long as normal.
<<<<<<< 2.6.18
<6>[ 37.446763] md: ... autorun DONE.
<6>[ 38.578832] NTFS driver 2.1.27 [Flags: R/W MODULE].
<6>[ 38.771306] NTFS volume version 3.1.
>>>>>>> 2.6.18-rc7-mm1
<6>[ 73.384371] md: ... autorun DONE.
<6>[ 73.565190] warning: process `showconsole' used the removed sysctl system call
<6>[ 75.436369] NTFS driver 2.1.27 [Flags: R/W MODULE].
<6>[ 75.637003] NTFS volume version 3.1.
In the end, the mm kernel has taken twice as much time to get up
and running as the mainline kernel.
Please let me know if you need more information.
--
Tilman Schmidt E-Mail: tilman@imap.cc
Bonn, Germany
Diese Nachricht besteht zu 100% aus wiederverwerteten Bits.
Ungeoeffnet mindestens haltbar bis: (siehe Rueckseite)
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 253 bytes --]
next reply other threads:[~2006-09-24 16:57 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-24 16:59 Tilman Schmidt [this message]
2006-09-24 19:22 ` [2.6.18-rc7-mm1] slow boot Valdis.Kletnieks
2006-09-24 22:02 ` Tilman Schmidt
2006-09-24 21:53 ` Andrew Morton
2006-09-24 22:15 ` Tilman Schmidt
2006-09-24 22:36 ` Alan Cox
2006-09-24 22:41 ` Andrew Morton
2006-09-26 23:48 ` Tilman Schmidt
2006-09-27 0:21 ` Andrew Morton
2006-09-28 17:00 ` Tilman Schmidt
2006-09-28 17:12 ` Andi Kleen
2006-09-28 23:20 ` Tilman Schmidt
2006-09-28 23:30 ` Randy Dunlap
2006-09-29 0:15 ` Tilman Schmidt
2006-09-29 7:10 ` Jan Beulich
2006-09-29 16:12 ` Andi Kleen
2006-09-29 18:39 ` Ingo Molnar
2006-10-04 7:05 ` Jan Beulich
2006-09-29 8:49 ` Andi Kleen
2006-09-24 21:58 ` [2.6.18-mm1] slow boot (was: [2.6.18-rc7-mm1] slow boot) Tilman Schmidt
2006-09-25 12:09 ` [2.6.18-rc7-mm1] slow boot Alexander Gran
2006-10-25 18:14 ` Tilman Schmidt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4516B966.3010909@imap.cc \
--to=tilman@imap.cc \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox