[arch-general] Suspicious activity and slowness ...
Hello, since some days, I'm noticing HD is too busy, and my laptop is very slow in some cases. Are there any invisible background threads running? How can I find out about those? Running top, cpu use should be only about 30%, so it should wait for tasks to be executed, instead. Kind regards Peter
On Mon, 17 Dec 2018 at 16:04, Peter Nabbefeld
since some days, I'm noticing HD is too busy, and my laptop is very slow in some cases.
Are there any invisible background threads running? How can I find out about those? Running top, cpu use should be only about 30%, so it should wait for tasks to be executed, instead.
According to these two I suggest you take a look at the load, as it measures responsiveness more correctly than cpu time, as data transfer usually clogs up the machine the same as computing does. Use htop and turn on the IO_RATE column to find out which process uses your disks. Also, you might need to run as root to see the details of all processes. -- Oliver
since some days, I'm noticing HD is too busy, and my laptop is very slow in some cases.
Are there any invisible background threads running? How can I find out about those? Running top, cpu use should be only about 30%, so it should wait for tasks to be executed, instead. iotop should show which processes cause I/O.
Op ma 17 dec. 2018 16:33 schreef mpan since some days, I'm noticing HD is too busy, and my laptop is very slow
in some cases. Are there any invisible background threads running? How can I find out
about those? Running top, cpu use should be only about 30%, so it should
wait for tasks to be executed, instead.
iotop should show which processes cause I/O. 30% (as average?) appears a little steep, depending on what normal
processes are running. Don't forget to check your memory usage...
Mvg, Guus Snijders
On Mon, 17 Dec 2018 at 15:04, Peter Nabbefeld
since some days, I'm noticing HD is too busy, and my laptop is very slow in some cases.
It might also be worth checking the health of your hard disk with "smartctl -A /dev/sd<x>". Look out for "Reallocated Event Count", "Current Pending Sector", and "Offline Uncorrectable". These should be zero. If they're not zero, the hard disk may be slowing down due to the firmware trying to correct disk read errors transparently, causing processes to spend an excessive time in IO-wait. I've found that these days, failing hard disks tend to cause slow-downs rather than outright crashes. Paul
participants (5)
-
Guus Snijders
-
mpan
-
Paul Gideon Dann
-
Peter Nabbefeld
-
Temlin Olivér