How to Diagnose High Load with Low CPU on Linux: Tools & Tips

Common Load Analysis Methods

High CPU & High Load

Use top to find the PID of the process consuming the most CPU.

Run top -Hp PID to locate the thread (TID) with the highest CPU usage within that process.

For Java applications, execute jstack to print thread stack information.

Use printf %x tid to display the hexadecimal ID of the most CPU‑intensive thread.

Low CPU & High Load

The root cause is typically many processes waiting for disk I/O, which inflates the load average while CPU remains idle.

Check CPU I/O wait time with top (field %wa ).

Inspect disk I/O statistics using iostat -d -x -m 1 10 (install with yum install -y sysstat if needed).

View network I/O via sar -n DEV 1 10 .

Identify I/O‑heavy processes with: <code>ps -e -L h o state,cmd | awk '{if($1=="R"||$1=="D"){print $0}}' | sort | uniq -c | sort -k 1nr</code>

High CPU & High Load Analysis

Use vmstat to view system‑level CPU load.

Use top to view process‑level CPU load.

2.1 Using vmstat to View System‑Level CPU Load

vmstat -n 1

refreshes the statistics every second.

<code>[root@VM-1-14-centos ~]# vmstat -n 1
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
 1  0      0 250304 163472 2154300    0    0     1    16    0    4  1  0 98  0  0
 ... (output truncated) ...</code>

Key columns:

r : Number of processes waiting for CPU; a high value indicates a long run queue.

b : Number of blocked processes.

us : Time spent in user space.

sy : Time spent in kernel space; high values suggest heavy system calls or I/O.

wa : Percentage of CPU time spent waiting for I/O; high values point to I/O bottlenecks.

id : Percentage of idle CPU time; consistently low while

sy

is double

us

may indicate CPU shortage.

Common issues and solutions:

If

r

frequently exceeds 4 and

id

stays below 40, the CPU is heavily loaded.

If

pi

and

po

are non‑zero for long periods, memory is insufficient.

If disk I/O counters are non‑zero and the

b

queue exceeds 3, I/O performance is poor.

2.2 Using top to View Process‑Level CPU Load

top

shows per‑process CPU and memory usage.

<code>top - 19:49:59 up 36 days, 23:15,  3 users,  load average: 0.11, 0.04, 0.05
Tasks: 133 total,   1 running, 131 sleeping,   0 stopped,   1 zombie
%Cpu(s):  3.1 us,  3.1 sy,  0.0 ni, 93.8 id,  0.0 wa,  0.0 hi,  0.0 si,  0.0 st
... (output truncated) ...</code>

Press

P

in the interface to sort processes by CPU usage descending, then investigate the top consumers using logs.

Low CPU & High Load

Problem Description

Linux shows an idle CPU but a very high load average.

Analysis

Many processes are blocked waiting for disk I/O, inflating the load average while CPU remains idle. Typical scenarios include:

1. Excessive disk read/write requests causing I/O wait.

2. MySQL queries without indexes or deadlocks leading to I/O blockage.

3. External storage failures (e.g., NFS server down) causing prolonged I/O waits.

Remediation

Load average reflects the length of the task queue; a high value signals many waiting tasks.

Check for uninterruptible (D) state processes with

ps -axjf

.

D‑state processes cannot be killed; resolve by restoring dependent resources or rebooting.

<code>ps -e -L h o state,cmd | awk '{if($1=="R"||$1=="D"){print $0}}' | sort | uniq -c | sort -k 1nr</code>