Disk I/O is very slow, system freezes for seconds

[LGB [Gábor Lénárt]]

For a while (even with previous ubuntu versions as well), speed of disk I/O is unacceptable. I thought it is a problem with my machine, but I have a quite different machine with the same problem now, and also it was quite OK a year (or years?) ago. Even installing a single deb package with dpkg lasts for minutes, other processes trying to access of disk are totally "dead", a single ls command in a terminal can wait for a minute sometimes. Also, sometimes the mouse cursor can't be moved for long seconds. There is nothing suspect in kernel log which can help. During disk I/O top reports wait state for almost all CPU time. Can it be caused by the pata->libata change for example, NCQ or something like this? I have no idea how to improve the situation. I can provide information of course if I know what I should send. Currently these are machines running up-to-date Ubuntu hardy (32 bit). I can say system is totally unusable even with smaller disk I/O load ... Thanks in advance!

[Jean-Baptiste Lallement (jibel)]

Thank you for taking the time to report this bug and helping to make Ubuntu better. Unfortunately we can't fix it without more information.

Please include the following additional information, if you have not already done so (pay attention to lspci's additional options), as required by the Ubuntu Kernel Team:
1. Please include the output of the command "uname -a" in your next response. It should be one, long line of text which includes the exact kernel version you're running, as well as the CPU architecture.
2. Please run the command "dmesg > dmesg.log" after a fresh boot and attach the resulting file "dmesg.log" to this bug report.
3. Please run the command "sudo lspci -vvnn > lspci-vvnn.log" and attach the resulting file "lspci-vvnn.log" to this bug report.

For your reference, the full description of procedures for kernel-related bug reports is available at https://wiki.ubuntu.com/KernelTeamBugPolicies

The current Alpha5 for Intrepid Ibex 8.10 contains the newer 2.6.27 Ubuntu kernel. You should be able to test via a LiveCD. Please let us know immediately if this newer 2.6.27 kernel resolves the bug reported here or if the issue remains.

Thanks in advance!

[LGB [Gábor Lénárt] (lgb)]

I can't test 2.6.27 kernels since machine locks up when starting gdm (X), so I'm using the "old" kernel (from hardy) even with intrepid, but it's another issue.

Linux vega 2.6.26-5-generic #1 SMP Fri Aug 15 13:54:58 UTC 2008 i686 GNU/Linux

I'm attaching output of lspci then dmesg. I'll try 2.6.27 later maybe without X to be able to test it.

[LGB [Gábor Lénárt] (lgb)]

And kernel messages ...

[Leann Ogasawara (leannogasawara)]

Hi LGB,

Yes, if you could try 2.6.27 without X that would be great. Thanks.

[Jean-Baptiste Lallement (jibel)]

Please can you attach the output of the following commands:
hdparm -I /dev/sda
hdparm -tT /dev/sda

Additionally, there is an interesting message in your log file :
[ 12.511114] ata1.00: ATAPI: HL-DT-STDVD-ROM GDR8164B, 0B10, max UDMA/44
[ 12.511114] ata1.00: limited to UDMA/33 due to 40-wire cable
[ 12.526835] ata1.00: configured for UDMA/33

but this should not slow down your hd because it's connected on a different channel. It doesn't hurt to unplug the dvd drive and see if it's still slow.

[LGB [Gábor Lénárt] (lgb)]

/dev/sda:
 Timing cached reads: 1084 MB in 2.00 seconds = 541.78 MB/sec
 Timing buffered disk reads: 172 MB in 3.03 seconds = 56.73 MB/sec

Output of "hdparm -I ..." is attached.

The machine can be accessed only remotely at the moment, I can't check removing the DVD, but I think it's totally another bus so it shouldn't cause problems. Also please note that eg copying file from a file through the network is quite OK. The slowness can be seen if there are concurrent I/O requests when the whole machine is painfully slow. One I/O itself (like otherwise idle machine and copying a file by sequentially reading it and eg streaming it through the network) is OK (in speed) but any other task is painfully slow, mouse cursor stops for seconds, if I try to execute even a plain 'ls' command it can wait for seconds or even more, etc. Also, I know it's hard to define as a problem, but I feel this issue is becoming more and more serious one with every newer ubuntu versions, but I know it's quite subjective thing to just say. Thanks.

[Jean-Baptiste Lallement (jibel)]

Thanks. I can't see anything obviously wrong with that drive. It's only a bit slow on cached reads. Something strange is that hdparms is unable to detect the right ide/ata standards.

You can run a test to determine if the slowness of your system is due to some hardware malfunction.
- Install the package sysstat
- copy a large amount of data in order to reproduce the issue
- run "iostat -x /dev/sda" and report the results

I've also noticed that the ide interface and the audio device are sharing the same irq. Can you please follow the steps at https://help.ubuntu.com/community/DebuggingIRQProblems and see if it helps.

[Carnalbeast (carnalbeast)]

I have the same problem.
Very very very low disk access speed, Bad performance , it can take AGES to launch an app, if i try to launch firefox i can go out and make a cigarrete.
while on windows 7 applications are started instantly.

I always wanted to move to opensource and i'm always testing linux distros but ubuntu 11.04 and after is very slow.
I don't know if my machine is incompatible but the performance is too bad to accept it.

I have better performance with pinguy os , but not like windows 7.

[Anthony Hickson (vtpvc-vsthqny-aaucu)]

I have the same problem.
Very very very slow disk access. It sounds as if the disk is doing a lot of work (as if it needed defragmenting)
Unfortunately I can't understand what to do from the instructions above.
I know a lot about some things but nothing about linux systems.

[penalvch (penalvch)]

LGB [Gábor Lénárt], this bug was reported a while ago and there hasn't been any activity in it recently. We were wondering if this is still an issue? If so, could you please test for this with the latest development release of Ubuntu? ISO images are available from http://cdimage.ubuntu.com/daily-live/current/ .

If it remains an issue, could you please run the following command in the development release from a Terminal (Applications->Accessories->Terminal), as it will automatically gather and attach updated debug information to this report:

apport-collect -p linux <replace-with-bug-number>

Also, could you please test the latest upstream kernel available (not the daily folder, but the one at the top) following https://wiki.ubuntu.com/KernelMainlineBuilds ? It will allow additional upstream developers to examine the issue. Once you've tested the upstream kernel, please comment on which kernel version specifically you tested. If this bug is fixed in the mainline kernel, please add the following tags:
kernel-fixed-upstream
kernel-fixed-upstream-VERSION-NUMBER

where VERSION-NUMBER is the version number of the kernel you tested. For example:
kernel-fixed-upstream-v3.13-rc4

This can be done by clicking on the yellow circle with a black pencil icon next to the word Tags located at the bottom of the bug description. As well, please remove the tag:
needs-upstream-testing

If the mainline kernel does not fix this bug, please add the following tags:
kernel-bug-exists-upstream
kernel-bug-exists-upstream-VERSION-NUMBER

As well, please remove the tag:
needs-upstream-testing

Once testing of the upstream kernel is complete, please mark this bug's Status as Confirmed. Please let us know your results. Thank you for your understanding.

[Launchpad Janitor (janitor)]

[Expired for linux (Ubuntu) because there has been no activity for 60 days.]