CPU Information

How many cores? What speed? Is the CPU maxed out? Let's find out.

lscpu - CPU Overview

Terminal

$lscpu

Architecture: x86_64 CPU(s): 4 Thread(s) per core: 2 Core(s) per socket: 2 Socket(s): 1 Model name: Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz CPU MHz: 1992.000 CPU max MHz: 4000.0000

Key fields:

CPU(s): Total logical CPUs (cores × threads)
Core(s) per socket: Physical cores
Thread(s) per core: Hyperthreading (usually 2)
Socket(s): Physical CPU chips

Cores vs Threads

A 4-core CPU with hyperthreading shows as 8 CPUs. Physical cores matter most for CPU-bound work.

/proc/cpuinfo

Detailed info for each CPU:

Terminal

$cat /proc/cpuinfo | grep -E 'model name|cpu cores|processor' | head -8

processor : 0 model name : Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz cpu cores : 2 processor : 1 model name : Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz cpu cores : 2

Quick Core Count

Terminal

$nproc

nproc gives total available CPUs - useful in scripts.

CPU Usage

Instant Check

Terminal

$uptime

10:30:45 up 5 days, load average: 0.52, 0.48, 0.45

Load average: 1, 5, 15 minute averages.

Real-time with top

Terminal

$top -bn1 | head -5

top - 10:30:45 up 5 days, 2 users, load average: 0.52, 0.48, 0.45 Tasks: 142 total, 1 running, 141 sleeping, 0 stopped %Cpu(s): 5.2 us, 2.1 sy, 0.0 ni, 92.5 id, 0.2 wa, 0.0 hi, 0.0 si

CPU breakdown:

Code	Meaning
us	User processes
sy	System (kernel)
ni	Nice (low priority)
id	Idle
wa	I/O wait
hi	Hardware interrupts
si	Software interrupts

High wa means CPU is waiting for slow disk.

Per-Process

Terminal

$ps aux --sort=-%cpu | head -5

USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND user 1234 45.2 5.1 65432 41234 ? R 10:30 2:30 python heavy.py

mpstat - Per-Core Stats

Terminal

$mpstat -P ALL 1 1

CPU %usr %nice %sys %iowait %idle all 5.12 0.00 2.13 0.25 92.50 0 8.00 0.00 3.00 0.50 88.50 1 3.00 0.00 1.50 0.00 95.50 2 4.50 0.00 2.00 0.25 93.25 3 5.00 0.00 2.00 0.25 92.75

This shows if one core is maxed while others are idle (single-threaded bottleneck).

Knowledge Check

A server shows 4 CPUs with lscpu. The load average is 2.0. Is this concerning?

Quick Reference

Command	Shows
`lscpu`	CPU specifications
`nproc`	Number of CPUs
`/proc/cpuinfo`	Detailed CPU info
`uptime`	Load averages
`top` then `1`	Per-core usage
`mpstat -P ALL`	Per-core statistics

Key Takeaways

lscpu shows CPU specifications
nproc gives CPU count for scripts
Load average should be compared to core count
High wa (I/O wait) indicates disk bottleneck
Use top with 1 key to see per-core usage

Next: reading system logs.

CPU Information

How many cores? What speed? Is the CPU maxed out? Let's find out.

lscpu - CPU Overview

Terminal

$lscpu

Architecture: x86_64 CPU(s): 4 Thread(s) per core: 2 Core(s) per socket: 2 Socket(s): 1 Model name: Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz CPU MHz: 1992.000 CPU max MHz: 4000.0000

Key fields:

CPU(s): Total logical CPUs (cores × threads)
Core(s) per socket: Physical cores
Thread(s) per core: Hyperthreading (usually 2)
Socket(s): Physical CPU chips

Cores vs Threads

A 4-core CPU with hyperthreading shows as 8 CPUs. Physical cores matter most for CPU-bound work.

/proc/cpuinfo

Detailed info for each CPU:

Terminal

$cat /proc/cpuinfo | grep -E 'model name|cpu cores|processor' | head -8

processor : 0 model name : Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz cpu cores : 2 processor : 1 model name : Intel(R) Core(TM) i7-8550U CPU @ 1.80GHz cpu cores : 2

Quick Core Count

Terminal

$nproc

nproc gives total available CPUs - useful in scripts.

CPU Usage

Instant Check

Terminal

$uptime

10:30:45 up 5 days, load average: 0.52, 0.48, 0.45

Load average: 1, 5, 15 minute averages.

Real-time with top

Terminal

$top -bn1 | head -5

top - 10:30:45 up 5 days, 2 users, load average: 0.52, 0.48, 0.45 Tasks: 142 total, 1 running, 141 sleeping, 0 stopped %Cpu(s): 5.2 us, 2.1 sy, 0.0 ni, 92.5 id, 0.2 wa, 0.0 hi, 0.0 si

CPU breakdown:

Code	Meaning
us	User processes
sy	System (kernel)
ni	Nice (low priority)
id	Idle
wa	I/O wait
hi	Hardware interrupts
si	Software interrupts

High wa means CPU is waiting for slow disk.

Per-Process

Terminal

$ps aux --sort=-%cpu | head -5

USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND user 1234 45.2 5.1 65432 41234 ? R 10:30 2:30 python heavy.py

mpstat - Per-Core Stats

Terminal

$mpstat -P ALL 1 1

CPU %usr %nice %sys %iowait %idle all 5.12 0.00 2.13 0.25 92.50 0 8.00 0.00 3.00 0.50 88.50 1 3.00 0.00 1.50 0.00 95.50 2 4.50 0.00 2.00 0.25 93.25 3 5.00 0.00 2.00 0.25 92.75

This shows if one core is maxed while others are idle (single-threaded bottleneck).

Knowledge Check

A server shows 4 CPUs with lscpu. The load average is 2.0. Is this concerning?

Quick Reference

Command	Shows
`lscpu`	CPU specifications
`nproc`	Number of CPUs
`/proc/cpuinfo`	Detailed CPU info
`uptime`	Load averages
`top` then `1`	Per-core usage
`mpstat -P ALL`	Per-core statistics

Key Takeaways

lscpu shows CPU specifications
nproc gives CPU count for scripts
Load average should be compared to core count
High wa (I/O wait) indicates disk bottleneck
Use top with 1 key to see per-core usage

Next: reading system logs.