Hardware on Di

Inspect CPU and Memory Resources on Linux

Mon, 16 Oct 2023 14:53:28 -0500

Linux exposes CPU and memory information through /proc, /sys, firmware tables, and command-line tools. Each source answers a different question: CPU topology describes the processors visible to the operating system, free reports current memory use, and dmidecode reports the memory devices described by system firmware.

Official references:

Install the Utilities

Most distributions install lscpu, nproc, and free by default. Install the packages below if any command is missing.

On Ubuntu or Debian:

sudo apt update
sudo apt install -y util-linux coreutils procps dmidecode

On Fedora, RHEL, or Rocky Linux:

sudo dnf install -y util-linux coreutils procps-ng dmidecode

Record the System Context

Before comparing hardware reports, record the operating system, kernel, architecture, hostname, and virtualization environment.

cat /etc/os-release
uname -a
hostnamectl
systemd-detect-virt

systemd-detect-virt prints a virtualization technology such as kvm, vmware, or wsl, or returns none on supported bare-metal systems. A virtual machine normally reports the virtual CPUs and memory assigned by the hypervisor rather than the host’s complete hardware.

Understand CPU Counts

CPU terminology is easy to mix up:

A socket is a physical processor package or a virtual topology presented by a hypervisor.
A core is an independent processing core within a socket.
A thread is a hardware thread within a core when simultaneous multithreading is enabled.
A logical CPU is one processor number that the Linux scheduler can use.

For a typical two-socket system with 8 cores per socket and 2 threads per core, Linux sees 32 logical CPUs.

Display CPU Architecture and Topology

Use lscpu for a readable summary. It gathers information from sysfs, /proc/cpuinfo, and architecture-specific sources.

lscpu

The most useful fields are:

Field	Meaning
`CPU(s)`	Logical CPUs visible to the operating system
`On-line CPU(s) list`	Logical CPUs currently online
`Thread(s) per core`	Hardware threads per core
`Core(s) per socket`	Physical or virtual cores in each socket
`Socket(s)`	Processor packages visible to the system
`NUMA node(s)`	Non-uniform memory-access nodes
`Model name`	Processor model reported by the platform

Display one row per logical CPU with its core, socket, NUMA node, state, and frequency range.

lscpu --extended=CPU,CORE,SOCKET,NODE,ONLINE,MAXMHZ,MINMHZ

Use parseable output when another command or script will consume the topology. The default human-readable format can change between util-linux versions.

lscpu --parse=CPU,CORE,SOCKET,NODE,ONLINE

Produce structured JSON when the installed lscpu version supports it.

lscpu --json

Virtual machines may report a synthetic socket and core layout. Confirm the host topology in the hypervisor when licensing, NUMA placement, or performance tuning depends on physical hardware.

Count Available Processing Units

nproc reports the number of processing units available to the current process. CPU affinity, OpenMP environment variables, and cgroup v2 quotas may make this smaller than the number installed in the system.

nproc

Show the number of installed processors without applying those process-level restrictions.

nproc --all

This distinction matters for containers and restricted services. Use nproc when choosing a safe level of parallel work, such as a build job, and use lscpu when inspecting the machine’s topology.

Read Raw CPU Information

/proc/cpuinfo contains architecture-dependent information for each logical CPU.

less /proc/cpuinfo

Count the processor records exposed by architectures that provide the standard processor field.

grep -c '^processor' /proc/cpuinfo

Display unique processor model strings on x86 systems.

grep '^model name' /proc/cpuinfo | sort -u

Fields such as physical id, cpu cores, and model name are architecture-dependent and may be absent or synthetic in virtual machines. Avoid using them as the primary source for portable scripts.

Check Current Memory Usage

Use free for a snapshot of physical memory and swap usage.

free -h

The available column is usually more useful than the free column. Linux uses otherwise idle memory for caches and can reclaim much of it for applications, so a small free value alone does not indicate memory pressure.

Display separate buffers and cache columns.

free -h --wide

Display values in mebibytes, where one MiB is 1,048,576 bytes.

free -m

Display values in decimal megabytes, where one MB is 1,000,000 bytes.

free --mega

Refresh the report every two seconds and stop after five samples.

free -h --seconds 2 --count 5

For a compact view of the kernel’s raw memory counters, inspect selected fields in /proc/meminfo.

grep -E '^(MemTotal|MemAvailable|SwapTotal|SwapFree|HugePages_Total|HugePages_Free):' /proc/meminfo

Observe Memory Pressure

vmstat shows runnable processes, swapping, block I/O, interrupts, context switches, and CPU time. The first row contains averages since boot; later rows represent each sampling interval.

vmstat 1 5

Sustained nonzero values in the si and so columns indicate swap-in and swap-out activity. High swap activity together with low available memory can indicate pressure, but interpret it with application behavior and storage latency.

List processes using the most resident memory.

ps -eo pid,user,comm,%cpu,%mem,rss --sort=-rss | head -n 15

Show active swap devices and files.

swapon --show --bytes

Inspect Physical Memory Devices

dmidecode reads SMBIOS or DMI data supplied by the system firmware. Root permission is normally required.

Show only Type 17 Memory Device records, which describe installed DIMMs and empty slots.

sudo dmidecode --type 17

Show all memory-related DMI record types.

sudo dmidecode --type memory

Common Type 17 fields include:

Field	Meaning
`Locator`	Motherboard slot label
`Bank Locator`	Firmware bank name
`Size`	Installed capacity or `No Module Installed`
`Type`	DDR generation reported by firmware
`Speed`	Module-rated speed
`Configured Memory Speed`	Current configured speed
`Manufacturer`	Vendor reported in the module data
`Part Number`	Module part number
`Serial Number`	Module serial number when available

dmidecode does not probe the DIMMs directly. It reports what the firmware provides, and the upstream project warns that DMI data can be incomplete or inaccurate. Virtual machines may expose synthetic memory-device records or none at all.

Inspect NUMA Layout

lscpu summarizes NUMA nodes and the logical CPUs assigned to each node.

lscpu

If numactl is installed, show CPUs, memory size, free memory, and distance information for each NUMA node.

numactl --hardware

On a multi-socket system, NUMA-aware placement can reduce remote-memory access. Do not force NUMA policies without measuring the workload because incorrect binding can reduce performance or exhaust one node while memory remains available elsewhere.

Check Container Resource Limits

Inside a container, hardware inventory tools may describe the host or the container namespace rather than the resources the workload can actually consume. nproc may account for a cgroup v2 CPU quota, while some versions of free can still show host memory.

On a cgroup v2 system, display current memory use and the hard memory limit for the current cgroup.

cat /sys/fs/cgroup/memory.current
cat /sys/fs/cgroup/memory.max

memory.max contains max when no hard limit is set; otherwise it contains a limit in bytes.

Display the CPU quota and period.

cat /sys/fs/cgroup/cpu.max

The value max 100000 means there is no CPU bandwidth limit. A value such as 200000 100000 permits up to two CPUs worth of execution time during each period. Container runtimes can also restrict CPU affinity, so compare the result with nproc.

Troubleshoot Memory and CPU Problems

The System Is Slow but `free` Shows Little Free Memory

Check MemAvailable, swap activity, and the largest resident processes rather than judging only the free column.

free -h --wide
vmstat 1 5
ps -eo pid,user,comm,%cpu,%mem,rss --sort=-rss | head -n 15

A Process Was Killed Unexpectedly

Search the current boot’s kernel journal for out-of-memory events.

sudo journalctl -k -b --grep='Out of memory|oom-kill|Killed process'

For a container, also inspect its memory.max, memory.current, and memory.events files.

cat /sys/fs/cgroup/memory.max
cat /sys/fs/cgroup/memory.current
cat /sys/fs/cgroup/memory.events

CPU Counts Do Not Agree

Compare physical topology, installed processors, and processing units available to the current process.

lscpu
nproc --all
nproc

Differences can result from offline CPUs, CPU affinity, cgroup quotas, virtual-machine topology, or OpenMP environment variables.

A DIMM Is Missing or Has the Wrong Speed

Compare the firmware table with kernel hardware messages, then verify the module in the system firmware interface.

sudo dmidecode --type 17
sudo journalctl -k -b --grep='memory|EDAC|ECC|MCE' --case-sensitive=no

Power down the machine and follow the hardware vendor’s service procedure before reseating or replacing physical memory.

Inspect Hardware Information on Linux

Wed, 21 Dec 2022 09:30:12 -0500

Linux exposes hardware information through firmware tables, sysfs, procfs, device drivers, and management controllers. No single command reports everything, so this guide groups the most useful tools by component.

Official references:

Install the Utilities

On Ubuntu or Debian, install the common inspection tools:

sudo apt update
sudo apt install -y dmidecode ethtool pciutils usbutils util-linux ipmitool lm-sensors smartmontools nvme-cli lshw

On Fedora, RHEL, or Rocky Linux:

sudo dnf install -y dmidecode ethtool pciutils usbutils util-linux kernel-tools ipmitool lm_sensors smartmontools nvme-cli lshw

Some commands are already included in a minimal installation. Package names and availability can differ between distribution releases.

Record the System Context

Start with the operating system, kernel, architecture, hostname, and virtualization environment:

cat /etc/os-release
uname -a
hostnamectl
systemd-detect-virt

A virtual machine normally reports the hardware and topology presented by its hypervisor. A container usually cannot access host firmware tables, physical storage health, sensors, or the management controller.

Display a concise hardware tree:

sudo lshw -short

Use the sanitized report when the output will be shared. It removes serial numbers, IP addresses, and other potentially sensitive identifiers:

sudo lshw -sanitize

Inspect Firmware and DMI Information

dmidecode reads the System Management BIOS tables supplied by the firmware. It reports what the firmware claims, which can be incomplete or incorrect.

Display the complete table:

sudo dmidecode

Limit the output to one DMI type:

sudo dmidecode --type bios
sudo dmidecode --type system
sudo dmidecode --type baseboard
sudo dmidecode --type chassis
sudo dmidecode --type processor
sudo dmidecode --type cache
sudo dmidecode --type memory

Read individual strings for scripts or inventory records:

sudo dmidecode --string bios-vendor
sudo dmidecode --string bios-version
sudo dmidecode --string system-manufacturer
sudo dmidecode --string system-product-name
sudo dmidecode --string system-serial-number

Extract common BIOS fields:

sudo dmidecode --type bios | grep -Ei 'Vendor:|Version:|Release Date:'

Serial numbers and asset tags can identify a specific machine. Remove them before posting diagnostic output publicly.

Inspect the CPU

Display the CPU architecture, model, sockets, cores, threads, NUMA nodes, caches, and virtualization flags:

lscpu

Display one row per logical CPU:

lscpu --extended=CPU,CORE,SOCKET,NODE,ONLINE,MAXMHZ,MINMHZ

Read the kernel’s detailed per-CPU report:

cat /proc/cpuinfo

When cpupower is installed, inspect the frequency driver, available governors, limits, and current policy:

cpupower frequency-info

The exact package depends on the distribution. Ubuntu commonly supplies cpupower through linux-tools-common and a matching linux-tools package; Debian uses linux-cpupower, while Fedora and RHEL use kernel-tools.

Changing the governor affects performance, power use, temperature, and battery life. Check the available governors before selecting one:

cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_available_governors

Temporarily request the performance governor when the active driver supports it:

sudo cpupower frequency-set --governor performance

This setting may be reset at boot or overridden by the CPU frequency driver or a power-management service.

Inspect Memory

Display current memory and swap use:

free -h

Display the physical or virtual memory devices described by the firmware:

sudo dmidecode --type memory

Useful fields include Size, Locator, Type, Speed, Configured Memory Speed, Manufacturer, Part Number, and Serial Number. Virtual machines may report only a synthetic memory device.

Inspect PCI and USB Devices

List PCI devices with numeric vendor and device IDs:

lspci -nn

Show the kernel driver assigned to each PCI device and other available modules:

lspci -nnk

Filter the report for wired and wireless network controllers:

lspci -nnk | grep -Ei -A3 'ethernet|network'

Use verbose PCI output only when more detail is needed:

sudo lspci -vv

List USB buses and devices:

lsusb

Display the USB device tree:

lsusb --tree

Inspect Network Adapters

Find the interface names and current link state first:

ip -brief link

Replace eno1 below with the actual wired interface name. Display the negotiated speed, duplex mode, port type, and link status:

sudo ethtool eno1

Display the driver, firmware version, and PCI bus address:

sudo ethtool --driver eno1

Display the permanent hardware address reported by the driver:

sudo ethtool --show-permaddr eno1

Compare it with the address currently assigned to the interface:

ip link show dev eno1

The current address can differ when NetworkManager, systemd-networkd, a virtual machine, or a privacy feature applies MAC-address randomization.

Inspect Storage Devices

Display disks, partitions, filesystems, models, serial numbers, and mount points:

lsblk --output NAME,PATH,MODEL,SERIAL,SIZE,TYPE,FSTYPE,FSAVAIL,FSUSE%,MOUNTPOINTS

Display filesystem UUIDs and labels:

lsblk --fs

Show mounted filesystems backed by real devices:

findmnt --real

Discover devices supported by smartctl:

sudo smartctl --scan-open

Replace /dev/sda with a device returned by the scan, then display its identity, capabilities, health data, error log, and self-test history:

sudo smartctl --all /dev/sda

For NVMe devices, list the controllers and namespaces:

sudo nvme list

Current nvme-cli versions use this command for the SMART and health log:

sudo nvme log smart /dev/nvme0

Older distribution packages may use the compatible legacy spelling:

sudo nvme smart-log /dev/nvme0

A passing SMART status does not replace backups. Watch media errors, critical warnings, available spare, temperature, and rapidly increasing error counts.

Inspect Temperatures, Fans, and Voltages

Display sensors already exposed by loaded kernel drivers:

sensors

On a physical machine, run hardware detection once when expected sensors are missing:

sudo sensors-detect --auto

Review the recommended kernel modules, load them as directed, and run sensors again. Do not expect useful motherboard readings inside most virtual machines or containers. Some laptops expose temperature data through ACPI instead of an lm-sensors-supported monitoring chip.

Inspect an IPMI Management Controller

IPMI is normally available only on servers with a baseboard management controller. Local access requires a compatible Linux OpenIPMI driver and sufficient privileges.

Display controller, chassis, field-replaceable unit, sensor, and event-log information:

sudo ipmitool mc info
sudo ipmitool chassis status
sudo ipmitool fru print
sudo ipmitool sensor list
sudo ipmitool sdr elist
sudo ipmitool sel list

IPMI LAN channel numbers vary by vendor and model. Inspect likely channels before using a number in another command:

sudo ipmitool channel info 1
sudo ipmitool channel info 8

After identifying the LAN channel, display its network settings and user slots. The following examples use channel 1:

sudo ipmitool lan print 1
sudo ipmitool user list 1

For a remote IPMI 2.0 controller, use lanplus and request an interactive password prompt. Replace the example address and username:

ipmitool -I lanplus -H 192.0.2.10 -U administrator -a mc info

Avoid -P password because it places the password in the command line and possibly the shell history or process list.

Optional: Configure the IPMI Network

IPMI network changes are persistent and can disconnect the management controller. Perform them from the server console or another recovery path, confirm the correct channel and user IDs, and record the existing configuration first:

sudo ipmitool lan print 1
sudo ipmitool user list 1

Replace the documentation addresses below with the reserved management address, subnet mask, and gateway for the server. Apply the commands only after checking for an address conflict:

sudo ipmitool lan set 1 ipsrc static
sudo ipmitool lan set 1 ipaddr 192.0.2.10
sudo ipmitool lan set 1 netmask 255.255.255.0
sudo ipmitool lan set 1 defgw ipaddr 192.0.2.1
sudo ipmitool lan set 1 access on
sudo ipmitool lan print 1

To change a known user slot’s password without putting the password in the command line, provide only the verified user ID and respond to the prompts. This example uses user ID 2:

sudo ipmitool user set password 2

Never assume that user ID 2 is the intended administrator. Confirm it with ipmitool user list and verify remote access before ending the console session.

Troubleshooting

DMI Information Is Unavailable

dmidecode requires root privileges and readable firmware tables. Containers, some virtual machines, ARM systems, and systems with restricted firmware access may return incomplete data or no supported entry point.

ethtool Reports Unsupported Operations

Not every driver implements every ethtool query. Confirm the interface and driver, then use the driver’s kernel documentation or vendor utility for unsupported fields:

ip -brief link
sudo ethtool --driver eno1

CPU Frequency Information Is Missing

The guest hypervisor or active CPU driver may not expose cpufreq data. Identify the environment and driver before changing packages or policies:

systemd-detect-virt
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_driver

Sensors Are Missing

Check which hardware-monitoring modules are loaded and whether sysfs contains sensor devices:

lsmod | grep -E 'coretemp|k10temp|nct|it87'
find /sys/class/hwmon -maxdepth 2 -type f -name name -print

Sensor labels and scaling depend on the motherboard and driver. Do not treat an unexplained voltage or temperature reading as authoritative until it is matched with the board documentation.

Local IPMI Access Fails

Check for an IPMI device and load the common local-interface modules when appropriate for the server:

ls -l /dev/ipmi* /dev/ipmi/* 2>/dev/null
sudo modprobe ipmi_devintf
sudo modprobe ipmi_si
sudo ipmitool mc info

If the server uses an OEM-specific transport or does not expose a local IPMI interface, use the vendor documentation or a secured remote lanplus connection.

Save a Diagnostic Snapshot

Create a directory with sanitized, read-only reports before a hardware change or support case:

mkdir -p hardware-report
sudo lshw -sanitize > hardware-report/lshw.txt
lscpu > hardware-report/lscpu.txt
lspci -nnk > hardware-report/lspci.txt
lsusb --tree > hardware-report/lsusb.txt
lsblk --output NAME,PATH,MODEL,SIZE,TYPE,FSTYPE,MOUNTPOINTS > hardware-report/lsblk.txt
sensors > hardware-report/sensors.txt 2>&1

Review every file before sharing it. PCI and USB identifiers are usually harmless, but storage serial numbers, MAC addresses, firmware serial numbers, IPMI addresses, hostnames, and asset tags can identify the system or reveal management-network details.

Hardware on Di

Inspect CPU and Memory Resources on Linux

Install the Utilities

Record the System Context

Understand CPU Counts

Display CPU Architecture and Topology

Count Available Processing Units

Read Raw CPU Information

Check Current Memory Usage

Observe Memory Pressure

Inspect Physical Memory Devices

Inspect NUMA Layout

Check Container Resource Limits

Troubleshoot Memory and CPU Problems

The System Is Slow but free Shows Little Free Memory

A Process Was Killed Unexpectedly

CPU Counts Do Not Agree

A DIMM Is Missing or Has the Wrong Speed

Inspect Hardware Information on Linux

Install the Utilities

Record the System Context

Inspect Firmware and DMI Information

Inspect the CPU

Inspect Memory

Inspect PCI and USB Devices

Inspect Network Adapters

Inspect Storage Devices

Inspect Temperatures, Fans, and Voltages

Inspect an IPMI Management Controller

Optional: Configure the IPMI Network

Troubleshooting

DMI Information Is Unavailable

ethtool Reports Unsupported Operations

CPU Frequency Information Is Missing

Sensors Are Missing

Local IPMI Access Fails

Save a Diagnostic Snapshot

The System Is Slow but `free` Shows Little Free Memory