Re: Disk performance deteriated to unbearable levels

David Purton wrote:
Everything takes forever to load (including booting), but then runs ok
once loaded.

Could DMA be disabled now? Taking a long time to read initially but
running okay afterward would match that symptom. Because after the
initial read it should be in filesystem buffer cache.

My only guess is that it is filesystem related, but I am not sure how to
confirm this, nor why things would have got to the present situation.

Currently, the root/system parition is 20GB, with 50% used. /home has
only 44% used.

That seems like a good amount of free space available for the
filesystem to deal with disk fragmentation.

Any suggestions?

Since other suggested possible hard drive problems... What does
smartctl say about the health of your drive?

smartctl -H /dev/sda

Any selftest failures? Are you running smartctl selftests? If not
then please do. I always run selftests regularly to get feedback
about the drives. Let me suggest something similar to this in
/etc/smartd.conf so as to have these run automatically.

# Monitor all attributes, enable automatic online data collection,
# automatic Attribute autosave, and start a short self-test every day
# between 2-3am, and a long self test Saturdays between 3-4am.
# On failure run all installed scripts (to send notification email).
# Ignore attribute 194 temperature change.
# Ignore attribute 190 airflow temperature change.
/dev/sda -a -o on -S on -s (S/../../[1-5]/03|L/../../6/03) -I 194 -I 190 -m root -M exec /usr/share/smartmontools/smartd-runner

This will dump the selftests. Any failures?

smartctl -l selftest /dev/sda

If you need to manually run selftests:

smartctl -t short /dev/sda

If short passes pick a time and run:

smartctl -t long /dev/sda

You might try using 'hdparm' to produce some data for your disk. Read
the hdparm documentation first (lots of docs on the web such as this)

http://www.gentoo-wiki.info/Hdparm#Benchmarking_devices

and then you might try this on an otherwise idle system.

# hdparm -tT /dev/sda
Timing cached reads: 4634 MB in 2.00 seconds = 2320.31 MB/sec
Timing buffered disk reads: 378 MB in 3.01 seconds = 125.71 MB/sec

Lastly you could benchmark the filesystem (a layer on top of the disk
system) using bonnie/bonnie++.

Both are ext3

Directly on the disk partition (e.g. /dev/sda5)? Or on top of LVM?
Or on top of RAID (e.g. /dev/md1)? Or LVM on RAID?

I do not want to reinstall if at all possible.

I am always an advocate of upgrades not re-installs. :-)

Bob

Attachment: signature.asc
Description: Digital signature

Relevant Pages

  • Re: smartctl when disks are in standby (Linux)
    ... If I try a smartctl test on a standby drive, however, it fails - it will wake up the drive, but smartctl gives up waiting and returns an error message before the drive is ready. ... Anything else that I've tried that needs the disk (such as "ls" if the relevant data is not in the cache) simply blocks until the disk is up to speed, so I've assumed the issue is specific to smartctl. ... "Execute SMART Short self-test routine immediately in off-line mode". ...
    (comp.sys.ibm.pc.hardware.storage)
  • Re: Upgrading to XP Pro
    ... Knoppix comes as a bootable ISO you can burn to CD/DVD. ... Note that you can also check the Knoppix disk itself with one of the ... SmartCTL is available as a command line utility after booting either into ... If you happen to have SATA drives, 'hda' would likely be 'sda' instead. ...
    (microsoft.public.windowsxp.help_and_support)
  • Re: Lots of con-current I/O = resets SATA link? (2.6.25.10)
    ... smartctl -t short /dev/sdc ... sda-sdd are on the same power supply cable, sde, sdf are on a second one. ... I changed the disk to a new SAMSUNG disk and the first raid resync did NOT work and I had 1 reallocated sector ... ...
    (Linux-Kernel)
  • Re: smartctl when disks are in standby (Linux)
    ... drive, however, it fails - it will wake up the drive, but smartctl gives ... 1TB drives) are particularly slow to start up? ... Can you post the error message from the syslog? ... needs the disk ...
    (comp.sys.ibm.pc.hardware.storage)
  • Re: [opensuse] Computer freezes a lot
    ... I also tried smartctl --test=short /dev/sda6 but I didn't see any report afterwards. ... The test is run by the disk firmware transparently to the cpu or OS ...
    (SuSE)