WHERE DO I START?
You are here:Integrations > Linux > Linux Metrics
  • Top ↑

Linux Metrics

Relevant Topic(s)   
Note   In the following tables, the BASE column indicates whether there's a baseline band available for the metric, the CORR column indicates whether there's a contextual band available for the metric, and the UTIL column indicates whether the metric can be used as a utilization metric in the Utilization and Utilization Boxplot Reports.

Collected (Organized by Collector)

CPU

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
cpu.total.guest Percentage of CPU spent running virtual CPUs for guest operating systems. average percent 0 none none
cpu.total.guest_nice Percentage of CPU spent running low-priority virtual CPUs for guest operating systems. average percent 0 none none
cpu.total.idle Percentage of CPU not doing any work. average percent 0 none none
cpu.total.iowait Percentage of CPU time spent waiting for I/O to complete. average percent 0 none none
cpu.total.irq Percentage of CPU time spent processing hardware interrupts. average percent 0 none none
cpu.total.nice Percentage of CPU spent running user processes at low priority. average percent 0 none none
cpu.total.softirq Percentage of CPU time spent processing software interrupts. average percent 0 none none
cpu.total.steal Percentage of CPU time spent in other operating systems when running in a virtualized environment. average percent 0 none none
cpu.total.system Percentage of CPU spent running system processes. average percent 0 none none
cpu.total.user Percentage of CPU spent running user processes. average percent 0 none none

Diskspace

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
diskspace.<disk>.byte_percentfree Percentage of free bytes. average percent 0 100 none

Disk Usage

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
iostat.<disk>.average_queue_length The average length of the disk queue for the disk. average   0 none none
iostat.<disk>.await Average completion in milliseconds. average ms 0 none none
iostat.<disk>.io The total number of completed IO operations, including both reads and writes. sum   0 none none
iostat.<disk>.iops Operations per second. average iops 0 none none
iostat.<disk>.read_await Average read time completion in milliseconds. average ms 0 none none
iostat.<disk>.reads Total number of read operations. sum   0 none none
iostat.<disk>.util_percentage Percentage of CPU time spent spent servicing all IO requests, both read and write. average percent 0 100 none
iostat.<disk>.write_await Average write time completion in milliseconds. average ms 0 none none
iostat.<disk>.writes Total number of write operations. sum   0 none none

Load Average

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
loadavg.01 The is the average run queue size over the past minute. average   0 none none
loadavg.05 The is the average run queue size over the past 5 minutes. average   0 none none
loadavg.15 The is the average run queue size over the past 15 minutes. average   0 none none
loadavg.processes_running The total number of processes in a running state. average   0 none none
loadavg.processes_total The total number of processes. average   0 none none

Memory

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
memory.Active Memory currently in use. average bytes 0 none none
memory.Buffers Cache for file buffers. average bytes 0 none none
memory.Cached Cache for other things, such as disk cache. average bytes 0 none none
memory.Dirty The total amount of memory waiting to be written back to the disk. average bytes 0 none none
memory.Inactive Memory marked as not in use. average bytes 0 none none
memory.MemFree Memory not being used for anything. Note that the amount of available memory is computed by adding MemFree, Buffers, and Cache. This is because, while the memory used by Buffers and Cache is not "free", it can be freed and used by processes that need it, so it is therefore considered "available". average bytes 0 none none
memory.MemTotal The total amount of physical memory. average bytes 0 none none
memory.Shmem Shared memory that can be simultaneously accessed by multiple processes. average bytes 0 none none
memory.SwapCached Amount of swap used as cache memory. average bytes 0 none none
memory.SwapFree Amount of swap memory which is free. average bytes 0 none none
memory.SwapTotal Total amount of memory allocated for swapping. average bytes 0 none none
memory.VmallocChunk The total amount of allocated virtual address space. average bytes 0 none none
memory.VmallocTotal The total amount of used virtual address space. average bytes 0 none none
memory.VmallocUsed The largest contiguous block of available virtual address space. average bytes 0 none none

Network

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
network.<int>.rx_byte The total number of bytes of data received by the interface. sum bytes 0 none none
network.<int>.rx_errors The total number of receive errors detected by the device driver. sum   0 none none
network.<int>.rx_packets The total number of packets of data received by the interface. sum   0 none none
network.<int>.tx_byte The total number of bytes of data transmitted by the interface. sum bytes 0 none none
network.<int>.tx_errors The total number of transmit errors detected by the device driver. sum   0 none none
network.<int>.tx_packets The total number of packets of data transmitted by the interface. sum   0 none none

VMStat

Fully Qualified Name (FQN) Description Statistic Units Min Max Sparse Data Strategy (SDS) BASE CORR UTIL
vmstat.pgpgin Number of pageins. average   0 none none
vmstat.pgpgout Number of pageouts. average   0 none none
vmstat.pswpin Number of swapins. average   0 none none
vmstat.pswpout Number of swapouts. average   0 none none

Computed (Organized by Collector)

CPU (Computed)

Fully Qualified Name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.cpu.total.utilization.percent

The overall average CPU Utilization across all CPUs. This is a normalized metric.

Computation:
(data['cpu.total.idle'] != null && data['cpu.total.idle'].actual != null) ? ((data.sum('cpu.total.*') - data['cpu.total.idle'].actual) / data.sum('cpu.total.*')) * 100 : data['cpu.cpu0.idle'] != null ? ((data.sum('cpu[.].*') - data.sum('cpu[.].*.idle')) / data.sum('cpu[.].*')) * 100 : null

percent 0 100 Linux - CPU Threshold Exceeded, Linux - Heavy CPU Load
netuitive.linux.cpu.total.normalized.user

Percentage of CPU spent running user processes. This is a normalized metric.

Computation:
attribute['cpus'] == null ? null : data['cpu.total.user'] / attribute['cpus'].value

percent 0 100  
netuitive.linux.cpu.total.normalized.system

Percentage of CPU spent running system processes. This is a normalized metric.

Computation:
attribute['cpus'] == null ? null : data['cpu.total.system'] / attribute['cpus'].value

percent 0 100  

Diskspace (Computed)

Fully Qualified Name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.diskspace.*.byte_percentused

Percentage of disk space used.

Computation:
100 - diskspace.*.byte_percentfree

percent 0 100 Linux - Disk Utilization Threshold Exceeded
netuitive.linux.diskspace.avg_byte_percentused

Average disk space utilization across all disks.

Computation:
100 0 data.avg('diskspace.*.byte_percentfree')

percent 0 100  

Disk Usage (Computed)

Fully Qualified Name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.iostat.totalreads

Total reads across all disks.

Computation:
data.sum('iostat\\..*\\.reads)

  0 none  
netuitive.linux.iostat.totalwrites

Total writes across all disks.

Computation:
data.sum('iostat\\..*\\.writes)

  0 none  
netuitive.linux.iostat.max_util_percentage

Maximum disk utilization across all disks.

Computation:
data.max('iostat\\..*\\.util_percentage)

percent 0 100  

Load Average (Computed)

Fully Qualified Name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.loadavg.01.normalized

The is the average run queue size over the past minute, normalized across CPUs.

Computation:
attribute['cpus'] == null ? null : (data['loadavg.01'].actual / attribute['cpus'].value)

  0 none  
netuitive.linux.loadavg.05.normalized

The is the average run queue size over the past 5 minutes, normalized across CPUs.

Computation:
attribute['cpus'] == null ? null : (data['loadavg.05'].actual / attribute['cpus'].value)

  0 none  
netuitive.linux.loadavg.15.normalized

The is the average run queue size over the past 15 minutes, normalized across CPUs.

Computation:
attribute['cpus'] == null ? null : (data['loadavg.15'].actual / attribute['cpus'].value)

  0 none  

Memory (Computed)

Fully Qualified Name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.memory.utilizationpercent

Under Linux, memory buffered and cached are part of memory which can be considered available. See the following explanation.

Computation:
100 - (memory.Buffers + memory.Cached + memory.MemFree) / memory.MemTotal * 100

percent 0 100 Linux - Memory Utilization Threshold Exceeded, Linux - Elevated Memory Usage

Network (Computed)

Fully Qualified name (FQN) Description Units Min Max BASE CORR UTIL Related Default policies
netuitive.linux.network.*.errors

The total number of errors, both transmit and receive.

Computation:
network.*.rx_errors + network.*.tx_errors

errors 0 none  
netuitive.linux.network.*.packets

The total number of packets, both transmitted and received.

Computation:
network.*.rx_packets + network.*.tx_packets

packets 0 none  
netuitive.linux.network.*.errors.percent

The percentage of errors, both transmit and receive.

Computation:
(netuitive.diamond.network.*.errors / netuitive.diamond.network.*.packets) * 100

percent 0 100