View previous topic :: View next topic |
Author |
Message |
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Mon Sep 25, 2006 4:29 pm Post subject: |
|
|
Status Update...
In the process of all this, I ended up upgrading my gcc as well. So I am recompiling the entire system. I'm expecting it to take another couple of days, so there aren't many tweaks I can do at this point. Things already seem to be moving much faster. But I expect it to work much better once everything is recompiled with the correct march options and the freshly modified USE flags.
I'll keep you posted. I learned a LOT this thread. _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Tue Sep 26, 2006 1:40 am Post subject: |
|
|
Yes- gcc-4.1.1 definitely has made some overall improvements in compiling speed., which for us Gentoo users is great. I really see no reason to use any gcc-3.x.x version.
Don't forget about tweaking ext3, if you have any ext3 partitions, as it makes a significant performance improvement. In fact, I converted all my systems back to tuned ext3 partitions from reiserfs some time ago (once I discovered ext3 needed to be tuned), except my reiserfs /usr/portage partition, which consists mainly of very small files, at which reiserfs excels. Check out codergeek42's great "Some ext3 Filesystem Tips" thread for details, or post back if you need more comments from a long-time reiserfs devotee who's done this. https://forums.gentoo.org/viewtopic-t-305871-highlight-ext3+tweaking.html
Having a sophisticated and targeted partition scheme, where each partition is formatted with the best file system for its specific usage is a good performance tip, and well worth setting up right. For example, you might place all your huge multimedia files on an XFS partition, since it excels at handling huge files.
It's also a good idea to put your distfiles directory on a partition other than /. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Tue Sep 26, 2006 3:12 am Post subject: |
|
|
distfiles...you mean the portage tree? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
desultory Bodhisattva
Joined: 04 Nov 2005 Posts: 9410
|
Posted: Tue Sep 26, 2006 3:41 am Post subject: |
|
|
To summarize, distfiles means the files in $DISTDIR which amount to a local cache of downloaded packages.
In slightly more detail, 'distfiles' refers to the contents of the directory named in DISTDIR (in make.conf), which defaults to /usr/portage/distfiles, DISTDIR is described in man 5 portage as follows.
Quote: | DISTDIR = [path]
Defines the location of your local source file repository.
Defaults to ${PORTDIR}/distfiles. |
|
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Tue Sep 26, 2006 7:34 pm Post subject: |
|
|
Segway back to the Kernel discussion for a short time.
I wasn't 100% certain what modules I'd need for future use. So I compiled modules for a lot of features I'm not 100% sure I'll use (printing support, external device support, etc). Now...these are modules, so I assume they won't affect the filesize or the efficiency of the kernel, correct?
And what about drivers I know I'll use? IDE drivers and the like. Would it be more efficient to compile directly into the kernel or as a module? Or doesn't it matter? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Tue Sep 26, 2006 8:14 pm Post subject: |
|
|
Correct. That's the main reason for modules- to create leaner kernels. If you have Loadable module support selected in the kernel config, they should load when needed. In some cases, you might have to list certain ones in the /etc/modules.autoload.d/kernel-2.6 file. There's an ongoing debate on whether monolithic (everything compiled in) or modular kernels are better.
I think most essential drivers, or the ones you know you'll use do better compiled into the kernel. Alsa/sound seems to do better as modules on my systems. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Thu Sep 28, 2006 4:36 pm Post subject: Shiny and new |
|
|
Okay, that whole process took a bit longer than I had hoped. But it seems to be a pretty good end result, thus far. Mouse is no longer skipping across the screen constantly.
Sound is acting a bit strange. When I start the system, I can play sounds (without error) but no output is coming out. But after the machine has been on a little while, it does start playing. So I gotta figure that out. When it is playing, it still skips from time to time when I switch between applications. But with this recent trouble, I suspect it might be a sound configuration problem. I should note that the skipping is most noticable with web applications like flash. pandora.com, for example.
Hard drive tweaking...I read through that link with the e2fsck and the tune2fs tools. A lot of those were set by default. Now I'm looking into messing with the hdparm stuff. I'm sure that will help a bit as well.
Kernel - I modularized nearly everything I could with exception of my framebuffer device and my filesystem support. That does seem to be making a difference. AT least I have a lot more available memory.
So it really comes down to hdparm and trying to figure out the funk with my sound drivers. I'll continue to post my status. I appreciate all your help thus far. The system is running 10x smoother now. _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Thu Sep 28, 2006 4:45 pm Post subject: |
|
|
desultory wrote: |
coplaniuk wrote: | Code: | 00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01) |
|
Not a disk interface, though it might look it, the module is listed as 'Intel 82801 (ICH)' under 'Device Drivers --->', 'I2C support --->', 'I2C Hardware Bus support ---> '.
|
Forgot to mention...I have this set up as a module. When I load the module, is there anything else I need to do? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Thu Sep 28, 2006 7:38 pm Post subject: |
|
|
More thoughts, Re your last post.
1. Is the sound the same or better as before all this? I assume you're using the motherboard's onboard sound? I would investigate the sound bios settings- maybe it needs it's own IRQ, or something like that. Check your motherboard manual for detailed info.
2. Did you set your ext3 partitions to use dir_index- that's the most important one. I would also try setting them to data=writeback instead of data=journal, as then the journal will then function like reiserfs (metadata only). This is the "performance" setting for ext3, according to the kernel Docs. I've also read recently that the info about jounal=data "super high performance" is now dated, and not necessarily correct with modern kernels. I'm going to change all my ext3 partitions back to writeback today.
I'd also consider changing your journal commit=n interval number from the default of every 5 seconds. For example, mine are set to 600secs and 60secs, so then there's less chance of the full journalling commit taking cpu cycles from anything else, like sound. That's also a good argument for data=writeback. I am taking an infinitesimal theoretical chance of loosing up to the last 60 or 600secs of changed data, and remember that writeback and longer commit intervals mean less intense ext3 journalling activity, but no less than reiserfs does by default. I've never lost any data on a crash, whatever mode or whatever file system I was using at the time. For me, it's a non-issue, and I'd rather have the increased performance- but that might not be your case. I guess you should decide how much current data you're willing to risk (time passed since the last journal commit). Having my cpu/system do a full journal every 5 seconds just seemed ridiculous to me, as I can't even type three new words in 5 seconds.
What's your current tune2fs -l /dev/hdXY (or dev/sdXY) output on your partitions, and your current partitioning scheme? (that's a lower case L, and you can use that command on mounted partitions).
3. Are you using a -ck kernel? This will probably help. What cpu scheduler are you using? From what you say, I think your problem seems to be that an instigated action on your part (like opening a new app, etc.) briefly takes cpu cycles away from your sound applications. I think the cpu and IO schedulers need more investigation.
Just to check, please give us the output of dmesg and lsmod.
To reduce forum clutter, maybe post your entire kernel config file on http://pastebin.com/
Here's mine (Just tried it for the first time- after hitting "send," it took about a minute to generate the url of my kernel config file, so don't think it's not working. Then I just copied the url in the address bar to this forum post)
http://pastebin.com/796330
4. On the i2c thing, I find my i2c stuff works better as modules, and I have to list them in the /etc/modules.autoload.d/kernel-2.6 file. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
desultory Bodhisattva
Joined: 04 Nov 2005 Posts: 9410
|
Posted: Fri Sep 29, 2006 3:59 am Post subject: |
|
|
coplaniuk wrote: | desultory wrote: |
coplaniuk wrote: | Code: | 00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01) |
|
Not a disk interface, though it might look it, the module is listed as 'Intel 82801 (ICH)' under 'Device Drivers --->', 'I2C support --->', 'I2C Hardware Bus support ---> '.
|
Forgot to mention...I have this set up as a module. When I load the module, is there anything else I need to do? |
Need, no. Want, maybe. To actually make use of the data made available by that device you might want to emerge sys-apps/lm_sensors. |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Fri Sep 29, 2006 4:18 am Post subject: |
|
|
I like ksensors- works great. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Fri Sep 29, 2006 4:39 am Post subject: |
|
|
Having fun with pastebin...and my lists are so long. Here gos...
My kernel .config file:
http://pastebin.com/796579
dmesg:
http://pastebin.com/796572
As for the other things...
tune2fs -l:
Code: |
vessel etc # tune2fs -l /dev/sda6
tune2fs 1.39 (29-May-2006)
Filesystem volume name: <none>
Last mounted on: <not available>
Filesystem UUID: bce0e492-6890-46fe-a7ee-4d5765102f4e
Filesystem magic number: 0xEF53
Filesystem revision #: 1 (dynamic)
Filesystem features: has_journal dir_index filetype needs_recovery sparse_super
Default mount options: journal_data
Filesystem state: clean
Errors behavior: Continue
Filesystem OS type: Linux
Inode count: 1835008
Block count: 3664820
Reserved block count: 183241
Free blocks: 775440
Free inodes: 1456000
First block: 0
Block size: 4096
Fragment size: 4096
Blocks per group: 32768
Fragments per group: 32768
Inodes per group: 16384
Inode blocks per group: 512
Filesystem created: Wed Jul 26 20:45:31 2006
Last mount time: Thu Sep 28 18:05:07 2006
Last write time: Thu Sep 28 18:05:07 2006
Mount count: 36
Maximum mount count: -1
Last checked: Tue Sep 26 20:56:29 2006
Check interval: 0 (<none>)
Reserved blocks uid: 0 (user root)
Reserved blocks gid: 0 (group root)
First inode: 11
Inode size: 128
Journal inode: 8
First orphan inode: 278773
Default directory hash: tea
Directory Hash Seed: 388c1315-be71-46f6-a4ff-279d33bf149b
Journal backup: inode blocks
|
and finally...lsmod:
Code: |
Module Size Used by
ipw3945 96544 1
ieee80211_crypt_wep 4096 1
snd_pcm_oss 31008 0
snd_mixer_oss 13184 1 snd_pcm_oss
snd_hda_intel 12692 1
snd_hda_codec 121984 1 snd_hda_intel
snd_pcm 61704 3 snd_pcm_oss,snd_hda_intel,snd_hda_codec
snd_page_alloc 6920 2 snd_hda_intel,snd_pcm
button 4880 0
battery 7300 0
thermal 10120 0
processor 13232 1 thermal
video 12420 0
ac 3460 0
nvidia 4542164 12
ieee80211 25288 1 ipw3945
ieee80211_crypt 4736 2 ieee80211_crypt_wep,ieee80211
firmware_class 6912 1 ipw3945
i2c_i801 7052 0
|
_________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Fri Sep 29, 2006 7:44 am Post subject: |
|
|
I think you need to compile a new 2.6.18-ck1 kernel, manually, keeping your old one, and try changing CONFIG_HZ=100 to CONFIG_HZ=1000. IIRC, 100HZ is for servers.
Use could you current kernel config to load into make xconfig, and maybe tweak it a little later.
I haven't had time to really look at your files- just scanned them briefly- will try and do more later. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Fri Sep 29, 2006 7:30 pm Post subject: |
|
|
Changed to 1000hz. Performance is slightly better now.
Now that I'm getting into these minute little tweaks...performance isn't quite as noticable to me. At least it's harder for me to figure out if the machine is working better. Is there a multi-media and performance benchmark utility that you would recommend so that I can quickly figure out if a configuration has improved or hindered my performance.
data=writeback
I added that to my partition option in my fstab, and then when I rebooted, it couldn't mount the partition. I had to revert back to data=journal to get it to work. Is there an option in the kernel config that I need to tweak or a module I need to load to get this? Is this maybe a kernel command and not a mount option? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Sat Sep 30, 2006 5:23 am Post subject: |
|
|
Is the audio skipping better or solved? If you haven't done so, you really should try a 2.6.18-ck1 kernel- you won't regret it.
For a benchmark, there are several out there, but I haven't used them myself- Bonnie comes to mind. I ran Justin Piszcz's LinuxGazette script on my system. (he was kind enough to let me use it). I just googled for linux benchmarks, and got thiese Maybe I'll try some. http://lbs.sourceforge.net/
On the data writeback, the first page on the ext3 tips thread explains how. Both methods also apply to data=writeback
Quote: | There are two different ways to activate journal data mode. The first is by adding data=journal as a mount option in /etc/fstab. If you do it this way and want your root filesystem to also use it, you should also pass rootflags=data=journal as a kernel parameter in your bootloader's configuration. In the second method, you will use tune2fs to modify the default mount options in the filesystem's superblock: |
If you want to use method 1, add this line to your grub.conf kernel line at the end., in addition to the fstab entries.
rootflags=data=writeback
I use method 2- it seems easier: Boot to a knoppix cd, and at the boot prompt type:
knoppix single
and hit enter. Open a konsole, type su and hit enter, and you are root. Don't mount any partitions!!!
To change a partition to writeback mode, do this:
Code: | # tune2fs -o journal_data_writeback /dev/sdXY |
If you want to experiment with the commit interval, here's how I set that up fstab:
Code: | /dev/sda1 /boot ext2 noatime, 1 2
/dev/sda2 none swap sw 0 0
/dev/sda3 / ext3 noatime,nodiratime,commit=60 0 1
/dev/sda5 /mnt/portage ext3 noatime,nodiratime,commit=600 0 1
/dev/sda6 /var ext3 noatime,nodiratime,commit=600 0 1
/dev/sda7 /tmp ext3 noatime,nodiratime,commit=600 0 1
/dev/sda8 /home ext3 noatime,nodiratime,commit=60 0 1
/dev/sda9 /mnt/data ext3 noatime,nodiratime,commit=1800,users 0 1
/dev/sda10 /mnt/data2 ext3 noatime,nodiratime,commit=1800,users 0 1
/dev/sdb6 /mnt/sdb6 vfat defaults 0 0
/dev/sdb7 /mnt/sdb7 vfat defaults 0 0
| Oh yeah- noatime and nodiratime are pretty important performance tweaks too. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Tue Oct 03, 2006 4:22 pm Post subject: |
|
|
Ok, thought I had things going very smoothly, but I'm still having problems. Things are definately better...but not performing the way it should.
Mouse still hangs and skips from time to time, usually when the machine is trying to load multiple web pages or compile something. Music is a little better, but still skips from time to time when I'm task switching. mpg321 (in a terminal window) plays a song flawlessly. But x11amp and streamed audio (via pandora.com) will skip when I taskswitch.
I had pretty much done everything we've discussed in this thread so far -- tweaks to the kernel, tweaks to the hard drive, upgraded to gcc 4, march options, etc -- except for two things. I hadn't yet tried to ck-sources and I havn't tried to set up the data=writeahead kernel/fstab option.
Last night, I downloaded and compiled a kernel with the ck-sources. As a test, I emerged (from file) xfce while I played around in KDE after booting from the ck-sources. x11amp still skipped. Mouse still lagged from time to time. I couldn't test pandora.com because I didn't yet compile my ipw3945 and ieee80211 modules to work with the new kernel. But I think those two things alone were enough to show me that there wasn't much of an improvement.
Once xfce4 compiled, I switched to that instead of KDE. x11amp didn't skip as much...but it still skipped when I taskswitched. Mouse acted pretty much the same. So XFCE was a bit of an improvement, but not much.
I know it's not RAM (I have 1gig RAM), Processor should be good enough (1.86ghz). Linux partition is only 40% full. My swap drive is barely used. I can't think of anything else that might help improve performance.
Any ideas? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
desultory Bodhisattva
Joined: 04 Nov 2005 Posts: 9410
|
Posted: Wed Oct 04, 2006 3:47 am Post subject: |
|
|
Try the anticipatory IO scheduler. |
|
Back to top |
|
|
drescherjm Advocate
Joined: 05 Jun 2004 Posts: 2790 Location: Pittsburgh, PA, USA
|
Posted: Wed Oct 04, 2006 8:35 am Post subject: |
|
|
Quote: | #hdparm -tT /dev/sda6
/dev/sda6:
Timing cached reads: 3628 MB in 2.00 seconds = 1815.13 MB/sec
Timing buffered disk reads: 94 MB in 3.06 seconds = 30.67 MB/sec |
BTW, Is this a laptop? If not there is a real problem here as the 30.67MB/s is very slow for a desktop computer with a sata drive unless the drive is 5 years old or more.
Here is a recent sata (330GB Seagate 7200.10) drive on my main rig:
Code: | /dev/sda:
Timing cached reads: 3312 MB in 2.00 seconds = 1656.51 MB/sec
Timing buffered disk reads: 232 MB in 3.01 seconds = 77.03 MB/sec
|
_________________ John
My gentoo overlay
Instructons for overlay |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Wed Oct 04, 2006 1:29 pm Post subject: |
|
|
One thing-I notice under general setup in your kernel config you have:
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
make xconfig help says:
Quote: | Optimize for size (Look out for broken compilers!) (CC_OPTIMIZE_FOR_SIZE)
Enabling this option will pass "-Os" instead of "-O2" to gcc
resulting in a smaller kernel.
WARNING: some versions of gcc may generate incorrect code with this
option. If problems are observed, a gcc upgrade may be needed.
If unsure, say N | IMO, compiling desktop OS kernels with -Os instead of the default -O2 is not a good idea, performance wise. If you want a larger kernel
optimized for speed, do not enable it. I've also read that this can cause various problems with a variety of things.
You also have a lot of modules in your config that you are definitely NOT using. For example, like under "IDE chipset support/bugfixes" and "SCSI low-level drivers" you need to only enable stuff related to the hardware you actually have, or expect to have in the future. Setting all the extra modules won't make the actual kernel larger, but will save lots of kernel compiling time. In other words, there's no reason to build kernel modules for hardware you don't have or use.
Oh yeah- that should be "data=writeback" instead of "data=writeahead." It's easier to boot to knoppix and use tune2fs to change the superblock on unmounted partitions than the fstab /grub method. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Wed Oct 04, 2006 4:17 pm Post subject: |
|
|
drescherjm wrote: | Quote: | #hdparm -tT /dev/sda6
/dev/sda6:
Timing cached reads: 3628 MB in 2.00 seconds = 1815.13 MB/sec
Timing buffered disk reads: 94 MB in 3.06 seconds = 30.67 MB/sec |
BTW, Is this a laptop? If not there is a real problem here as the 30.67MB/s is very slow for a desktop computer with a sata drive unless the drive is 5 years old or more.
|
Machine is a laptop, and that's a laptop SATA drive. _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Wed Oct 04, 2006 4:21 pm Post subject: |
|
|
I recompiled to kernel removing the option for size optimization. Don't know how that got in there...but it's gone now.
wrc1944 wrote: |
Oh yeah- that should be "data=writeback" instead of "data=writeahead." It's easier to boot to knoppix and use tune2fs to change the superblock on unmounted partitions than the fstab /grub method. |
For now, I got it working with the grub/fstab method 'cause I'm at work and don't have a liveCD handy. I will set it up via tune3fs if that's what you recommend. _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Wed Oct 04, 2006 10:08 pm Post subject: |
|
|
coplaniuk wrote: Quote: | For now, I got it working with the grub/fstab method 'cause I'm at work and don't have a liveCD handy. I will set it up via tune3fs if that's what you recommend. |
Doesn't really matter, as long as it's done, and verified by tune2fs -l /dev/hdXY .
And yes, I agree with drescherj, Quote: | Timing buffered disk reads: 94 MB in 3.06 seconds = 30.67 MB/sec | and something is definitely not right. I think we need to look at this section of your config file. For example: if this is an Intel chipset board, why is CONFIG_SCSI_SATA_NV=y? (nvidia support). It's a longshot, but maybe somebody who has your exact same laptop, and normal hdparm speed (60+MB/sec) can post their kernel config file for comparison.
# SCSI low-level drivers
#
# CONFIG_ISCSI_TCP is not set
CONFIG_BLK_DEV_3W_XXXX_RAID=m
CONFIG_SCSI_3W_9XXX=m
CONFIG_SCSI_ACARD=m
CONFIG_SCSI_AACRAID=m
CONFIG_SCSI_AIC7XXX=m
CONFIG_AIC7XXX_CMDS_PER_DEVICE=32
CONFIG_AIC7XXX_RESET_DELAY_MS=5000
CONFIG_AIC7XXX_DEBUG_ENABLE=y
CONFIG_AIC7XXX_DEBUG_MASK=0
CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
# CONFIG_SCSI_AIC7XXX_OLD is not set
CONFIG_SCSI_AIC79XX=m
CONFIG_AIC79XX_CMDS_PER_DEVICE=32
CONFIG_AIC79XX_RESET_DELAY_MS=5000
# CONFIG_AIC79XX_ENABLE_RD_STRM is not set
CONFIG_AIC79XX_DEBUG_ENABLE=y
CONFIG_AIC79XX_DEBUG_MASK=0
CONFIG_AIC79XX_REG_PRETTY_PRINT=y
CONFIG_SCSI_DPT_I2O=m
CONFIG_SCSI_ADVANSYS=m
# CONFIG_MEGARAID_NEWGEN is not set
CONFIG_MEGARAID_LEGACY=m
CONFIG_MEGARAID_SAS=m
CONFIG_SCSI_SATA=y
CONFIG_SCSI_SATA_AHCI=y
# CONFIG_SCSI_SATA_SVW is not set
CONFIG_SCSI_ATA_PIIX=y
# CONFIG_SCSI_SATA_MV is not set
CONFIG_SCSI_SATA_NV=y
# CONFIG_SCSI_PDC_ADMA is not set
# CONFIG_SCSI_SATA_QSTOR is not set
CONFIG_SCSI_SATA_PROMISE=m
CONFIG_SCSI_SATA_SX4=m
CONFIG_SCSI_SATA_SIL=m
CONFIG_SCSI_SATA_SIL24=m
CONFIG_SCSI_SATA_SIS=m
CONFIG_SCSI_SATA_ULI=m
CONFIG_SCSI_SATA_VIA=m
CONFIG_SCSI_SATA_VITESSE=m
CONFIG_SCSI_SATA_INTEL_COMBINED=y
CONFIG_SCSI_BUSLOGIC=m
# CONFIG_SCSI_OMIT_FLASHPOINT is not set
# CONFIG_SCSI_DMX3191D is not set
CONFIG_SCSI_EATA=m
# CONFIG_SCSI_EATA_TAGGED_QUEUE is not set
# CONFIG_SCSI_EATA_LINKED_COMMANDS is not set
CONFIG_SCSI_EATA_MAX_TAGS=16
# CONFIG_SCSI_FUTURE_DOMAIN is not set
CONFIG_SCSI_GDTH=m
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_PPA is not set
# CONFIG_SCSI_IMM is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
# CONFIG_SCSI_QLA_FC is not set
# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
# CONFIG_SCSI_NSP32 is not set
# CONFIG_SCSI_DEBUG is not set
------------------------------------------------------------------------------------------------------------------------------
I'll look at your dmesg and kernel config more when I have time, but I'm wondering about these things right off the bat. Maybe somebody else knows more about what they actually mean (if anything) in relation to your problems. Is there something about:
PCI: Bridge: 0000:00:1c.0
IO window: disabled.
MEM window: disabled.
PREFETCH window: disabled.
in your bios settings?
PCI: Using ACPI for IRQ routing
PCI: If a device doesn't work, try "pci=routeirq". If it helps, post a report
PCI: Cannot allocate resource region 7 of bridge 0000:00:1c.0
PCI: Cannot allocate resource region 8 of bridge 0000:00:1c.0
PCI: Cannot allocate resource region 7 of bridge 0000:00:1c.1
PCI: Cannot allocate resource region 8 of bridge 0000:00:1c.1
PCI: Cannot allocate resource region 7 of bridge 0000:00:1c.2
PCI: Cannot allocate resource region 8 of bridge 0000:00:1c.2
PCI: Cannot allocate resource region 0 of device 0000:06:00.0
PCI: Failed to allocate mem resource #6:20000@d0000000 for 0000:01:00.0
PCI: Bridge: 0000:00:01.0
IO window: disabled.
MEM window: d0000000-d1ffffff
PREFETCH window: c0000000-cfffffff
PCI: Bridge: 0000:00:1c.0
IO window: disabled.
MEM window: disabled.
PREFETCH window: disabled.
PCI: Bridge: 0000:00:1c.1
IO window: disabled.
MEM window: disabled.
PREFETCH window: disabled.
PCI: Bridge: 0000:00:1c.2
IO window: disabled.
MEM window: 52000000-520fffff
PREFETCH window: disabled.
PCI: Bus 9, cardbus bridge: 0000:08:06.0
IO window: 00002400-000024ff
IO window: 00002800-000028ff
PREFETCH window: 50000000-51ffffff
MEM window: 54000000-55ffffff
PCI: Bridge: 0000:00:1e.0
IO window: 2000-2fff
MEM window: d2000000-d20fffff
PREFETCH window: 50000000-51ffffff
AND:
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: Failed to reset mouse on isa0060/serio1
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: issuing reconnect request
input: PS/2 Generic Mouse as /class/input/input2
psmouse.c: Failed to enable mouse on isa0060/serio1
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 4
psmouse.c: TouchPad at isa0060/serio4/input0 lost sync at byte 1
psmouse.c: TouchPad at isa0060/serio4/input0 - driver resynched. _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Thu Oct 05, 2006 3:34 am Post subject: |
|
|
FYI...My laptop:
HP Pavillion, dv5000t with the nvidia geforce GO 7400.
What other info could I paste to help troubleshoot?
Should I try a genkernel? _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
wrc1944 Advocate
Joined: 15 Aug 2002 Posts: 3435 Location: Gainesville, Florida
|
Posted: Thu Oct 05, 2006 5:06 am Post subject: |
|
|
I would stay away from genkernel myself, but on the other hand, who knows?
http://www.techarp.com/showarticle.aspx?artno=98&pgno=1
https://laptopmag.com/Review/HP-Pavilion-dv5000t.htm
I just read these pages- so I'd know what we're talking about. Sounds like this laptop has plenty of power/ram and should not be giving you these problems. It has to be a tuning/config issue (or two). I'll give it some more thought.
Did we look at your emerge --info? _________________ Main box- AsRock x370 Gaming K4
Ryzen 7 3700x, 3.6GHz, 16GB GSkill Flare DDR4 3200mhz
Samsung SATA 1000GB, Radeon HD R7 350 2GB DDR5
OpenRC Gentoo ~amd64 plasma, glibc-2.36-r7, gcc-13.2.1_p20230304
kernel-6.8.4 USE=experimental python3_11 |
|
Back to top |
|
|
coplaniuk Guru
Joined: 14 Apr 2004 Posts: 461 Location: Philadelphia, USA
|
Posted: Thu Oct 05, 2006 5:45 am Post subject: |
|
|
Not a current one. I'll post that again:
emerge --info:
Code: |
Portage 2.1.1 (default-linux/x86/2006.1, gcc-4.1.1, glibc-2.4-r3, 2.6.17-gentoo-r8 i686)
=================================================================
System uname: 2.6.17-gentoo-r8 i686 Genuine Intel(R) CPU T1350 @ 1.86GHz
Gentoo Base System version 1.12.5
Last Sync: Wed, 04 Oct 2006 01:20:01 +0000
app-admin/eselect-compiler: [Not Present]
dev-java/java-config: 1.3.7, 2.0.30
dev-lang/python: 2.4.3-r4
dev-python/pycrypto: 2.0.1-r5
dev-util/ccache: [Not Present]
dev-util/confcache: [Not Present]
sys-apps/sandbox: 1.2.17
sys-devel/autoconf: 2.13, 2.59-r7
sys-devel/automake: 1.4_p6, 1.5, 1.6.3, 1.7.9-r1, 1.8.5-r3, 1.9.6-r2
sys-devel/binutils: 2.16.1-r3
sys-devel/gcc-config: 1.3.13-r4
sys-devel/libtool: 1.5.22
virtual/os-headers: 2.6.17-r1
ACCEPT_KEYWORDS="x86"
AUTOCLEAN="yes"
CBUILD="i686-pc-linux-gnu"
CFLAGS="-O2 -march=prescott -pipe -fomit-frame-pointer"
CHOST="i686-pc-linux-gnu"
CONFIG_PROTECT="/etc /usr/kde/3.5/env /usr/kde/3.5/share/config /usr/kde/3.5/shutdown /usr/share/X11/xkb /usr/share/config"
CONFIG_PROTECT_MASK="/etc/env.d /etc/env.d/java/ /etc/gconf /etc/java-config/vms/ /etc/revdep-rebuild /etc/terminfo"
CXXFLAGS="-O2 -march=prescott -pipe -fomit-frame-pointer"
DISTDIR="/usr/portage/distfiles"
FEATURES="autoconfig distlocks metadata-transfer sandbox sfperms strict"
GENTOO_MIRRORS="http://gentoo.osuosl.org/ ftp://distro.ibiblio.org/pub/linux/distributions/gentoo/ http://distro.ibiblio.org/pub/linux/distributions/gentoo/ ftp://ftp.gtlib.gatech.edu/pub/gentoo http://www.gtlib.gatech.edu/pub/gentoo http://gentoo.mirrors.pair.com/ ftp://gentoo.mirrors.pair.com/ http://mirrors.acm.cs.rpi.edu/gentoo/ http://mirror.datapipe.net/gentoo ftp://mirror.datapipe.net/gentoo "
LINGUAS=""
MAKEOPTS="-j2"
PKGDIR="/usr/portage/packages"
PORTAGE_RSYNC_OPTS="--recursive --links --safe-links --perms --times --compress --force --whole-file --delete --delete-after --stats --timeout=180 --exclude='/distfiles' --exclude='/local' --exclude='/packages'"
PORTAGE_TMPDIR="/var/tmp"
PORTDIR="/usr/portage"
SYNC="rsync://rsync.namerica.gentoo.org/gentoo-portage"
USE="x86 X acpi alsa apache apache2 arts berkdb bitmap-fonts bluetooth cli cups dlloader dri dvd dvdr dvdread elibc_glibc fortran gd gdbm gnome gpm gtk input_devices_evdev input_devices_keyboard input_devices_mouse kde kerberos kernel_linux libg++ mmx mp3 mpeg mysql ncurses nls nptl nptlonly nvidia opengl pam pcre pdf perl png pppd python qt qt3 quicktime readline reflection session spl sse sse2 sse3 ssl tcpd truetype-fonts type1-fonts udev unicode userland_GNU video_cards_nvidia video_cards_vesa video_cards_vga widescreen wifi win32codecs xine xml xorg xscreensaver xvid zlib"
Unset: CTARGET, EMERGE_DEFAULT_OPTS, INSTALL_MASK, LANG, LC_ALL, LDFLAGS, PORTAGE_RSYNC_EXTRA_OPTS, PORTDIR_OVERLAY
|
While I'm at it...I'll post some more info...
uname -a:
Code: |
Linux vessel 2.6.17-gentoo-r8 #19 PREEMPT Wed Oct 4 11:58:48 EDT 2006 i686 Genuine Intel(R) CPU T1350 @ 1.86GHz GNU/Linux
|
lspci:
Code: |
00:00.0 Host bridge: Intel Corporation Mobile Memory Controller Hub (rev 03)
00:01.0 PCI bridge: Intel Corporation Mobile PCI Express Graphics Port (rev 03)
00:1b.0 Class 0403: Intel Corporation 82801G (ICH7 Family) High Definition Audio Controller (rev 01)
00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 1 (rev 01)
00:1c.1 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 2 (rev 01)
00:1c.2 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 3 (rev 01)
00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #1 (rev 01)
00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #2 (rev 01)
00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #3 (rev 01)
00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #4 (rev 01)
00:1d.7 USB Controller: Intel Corporation 82801G (ICH7 Family) USB2 EHCI Controller (rev 01)
00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev e1)
00:1f.0 ISA bridge: Intel Corporation 82801GBM (ICH7-M) LPC Interface Bridge (rev 01)
00:1f.1 IDE interface: Intel Corporation 82801G (ICH7 Family) IDE Controller (rev 01)
00:1f.2 Class 0106: Intel Corporation 82801GBM/GHM (ICH7 Family) Serial ATA Storage Controllers cc=AHCI (rev 01)
00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01)
01:00.0 VGA compatible controller: nVidia Corporation Unknown device 01d8 (rev a1)
06:00.0 Network controller: Intel Corporation Unknown device 4222 (rev 02)
08:06.0 CardBus bridge: Texas Instruments Unknown device 8039
08:06.1 FireWire (IEEE 1394): Texas Instruments Unknown device 803a
08:06.2 Mass storage controller: Texas Instruments Unknown device 803b
08:06.3 Class 0805: Texas Instruments Unknown device 803c
08:08.0 Ethernet controller: Intel Corporation Unknown device 1092 (rev 01)
|
lsmod:
Code: |
Module Size Used by
ieee80211_crypt_wep 4096 1
ipw3945 96544 1
ieee80211 25288 1 ipw3945
ieee80211_crypt 4736 2 ieee80211_crypt_wep,ieee80211
snd_pcm_oss 35616 0
snd_mixer_oss 14976 1 snd_pcm_oss
snd_hda_intel 13716 0
snd_hda_codec 133504 1 snd_hda_intel
snd_pcm 72584 3 snd_pcm_oss,snd_hda_intel,snd_hda_codec
snd_page_alloc 7560 2 snd_hda_intel,snd_pcm
button 4880 0
battery 7300 0
thermal 10120 0
processor 13232 1 thermal
video 12420 0
ac 3460 0
nvidia 4542164 12
firmware_class 7552 1 ipw3945
i2c_i801 7564 0
|
And you already have my dmesg and kernel config. Of course I disabled the "compile for size" option since then and I'm using the anticipatory scheduler now. _________________ -- Coplan
~/ Outland - Art, Music, PHP and Hidden Corners of the Web
-{ Embrace Life. Evolve your computer. Emerge Gentoo. }- |
|
Back to top |
|
|
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|
|