Get your current sysload:-
\n18:54:44 up 22 days, 22:47, 1 user, load average: 2.54, 2.69, 2.40
\nUSER TTY FROM LOGIN@ IDLE JCPU PCPU WHAT
\nkarlo pts\/0 5ed07f32.cm-7-1b 18:49 0.00s 0.09s 0.00s w
\ncat \/proc\/loadavg
\n2.49 2.68 2.39 1\/149 2085
\nThe load on server is around 2.5. This means before an interrupt (program call) is done, it has to wait for 2.5 tasks. It\u2019s like a queue. On a 20 core system, a system load of 2 would be no problem. If it is a 2 core system then we need to investigate the issue as below:-<\/p>\n
1. Check for CPU usage using top or htop.<\/p>\n
2 High IO<\/p>\n
High input\/output on your disks can lead to a high sysload. You can use iostat and iotop to investigate this. You might have to install them first. On RHEL based systems, iostat is in the package sysstat.<\/p>\n
To get the current IO, try \u201ciostat 1?:
\niostat 1:- Below is the output:-<\/p>\n
Linux 3.2.2 (srv02.leanback.eu) 06\/26\/2013 _x86_64_ (2 CPU)<\/p>\n
avg-cpu: %user %nice %system %iowait %steal %idle
\n0.53 0.14 1.19 2.73 0.25 95.16<\/p>\n
Device: tps kB_read\/s kB_wrtn\/s kB_read kB_wrtn
\nxvdap1 0.84 2.63 2.59 5222348 5128012
\nxvdap2 5.87 33.14 44.00 65726181 87260968<\/p>\n
avg-cpu: %user %nice %system %iowait %steal %idle
\n0.50 0.00 0.50 75.38 0.00 23.62<\/p>\n
Device: tps kB_read\/s kB_wrtn\/s kB_read kB_wrtn
\nxvdap1 0.00 0.00 0.00 0 0
\nxvdap2 46.00 0.00 788.00 0 788<\/p>\n
avg-cpu: %user %nice %system %iowait %steal %idle
\n0.00 0.00 0.00 49.49 0.00 50.51<\/p>\n
Device: tps kB_read\/s kB_wrtn\/s kB_read kB_wrtn
\nxvdap1 0.00 0.00 0.00 0 0
\nxvdap2 7.00 0.00 32.00 0 32<\/p>\n
If you have high read\/write numbers, this is the problem. Investigate what process is causing it with iotop.<\/p>\n
iotop<\/p>\n
<\/p>\n
The process at the top is the one which uses most IO. There might be something wrong there. Kill it.
\nStill if not fixed, then check if the system is swapping<\/p>\n
If your system is using swap, this can lead to a high system load. Check out your memory usage with \u2018free\u2019:<\/p>\n
$ free -m
\ntotal used free shared buffers cached
\nMem: 990 958 32 0 27 276
\n-\/+ buffers\/cache: 653 336
\nSwap: 1023 73 950
\nAs can be seen above, total of about 1GB RAM . There is only 32MB left. And it has used Swap (see the Swap row, and then under the \u2018free\u2019 column). This is not a good sign. Scroll back to the part about htop, and sort on memory. This will tell you what is using your precious RAM.<\/p>\n
If that is done, you can:
\n1) Clear your SWAP. Only so this if you have enough free memory. As root, do: \u201cswapoff -a; swapon -a\u201d.
\n2) Disable swap as much as possible. As root, do \u201cecho vm.swappiness=0 >> \/etc\/sysctl.conf \u201d and reboot. This will make sure your system only swapps if it is out of memory.
\nIf still you are having problems then check for hardware. For example, if a HDD is broken, or your RAID array is rebuilding, this will impact performance (and system load). You might want to check your dmesg output \u201d dmesg | less \u201d for errors. There might be something in \/var\/log\/messages .
\nIf your HDDs and bios support SMART, you might get info from there. Install smartmontools , find out what devices your file systems are on ( cat \/etc\/fstab | cut -d\u2019 \u2018 -f1 | grep -v none ) and scan them:
\n$ sudo smartctl -a \/dev\/sda<\/p>\n
by-<\/p>\n