{ "mode": "man", "parameter": "IOSTAT", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/IOSTAT/1/json", "generated": "2026-07-05T23:50:15Z", "synopsis": "", "sections": { "NAME": { "content": "iostat - Report Central Processing Unit (CPU) statistics and input/output statistics for de‐\nvices and partitions.\n\n", "subsections": [] }, "SYNOPSIS": { "content": "", "subsections": [ { "name": "iostat [ -c ] [ -d ] [ -h ] [ -k | -m ] [ -N ] [ -s ] [ -t ] [ -V ] [ -x ] [ -y ] [ -z ] [", "content": "--dec={ 0 | 1 | 2 } ] [ { -f | +f } directory ] [ -j { ID | LABEL | PATH | UUID | ... } ] [" }, { "name": "-o -H -g --human --pretty -p", "content": "device [...] | ALL ] [ interval [ count ] ]\n\n", "flag": "-p", "long": "--pretty" } ] }, "DESCRIPTION": { "content": "The iostat command is used for monitoring system input/output device loading by observing the\ntime the devices are active in relation to their average transfer rates. The iostat command\ngenerates reports that can be used to change system configuration to better balance the in‐\nput/output load between physical disks.\n\nThe first report generated by the iostat command provides statistics concerning the time\nsince the system was booted, unless the -y option is used (in this case, this first report is\nomitted). Each subsequent report covers the time since the previous report. All statistics\nare reported each time the iostat command is run. The report consists of a CPU header row\nfollowed by a row of CPU statistics. On multiprocessor systems, CPU statistics are calculated\nsystem-wide as averages among all processors. A device header row is displayed followed by a\nline of statistics for each device that is configured.\n\nThe interval parameter specifies the amount of time in seconds between each report. The count\nparameter can be specified in conjunction with the interval parameter. If the count parameter\nis specified, the value of count determines the number of reports generated at interval sec‐\nonds apart. If the interval parameter is specified without the count parameter, the iostat\ncommand generates reports continuously.\n\n", "subsections": [] }, "REPORTS": { "content": "The iostat command generates two types of reports, the CPU Utilization report and the Device\nUtilization report.\n\n\nCPU Utilization Report\nThe first report generated by the iostat command is the CPU Utilization Report. For\nmultiprocessor systems, the CPU values are global averages among all processors. The\nreport has the following format:\n\n%user Show the percentage of CPU utilization that occurred while executing at the\nuser level (application).\n\n%nice Show the percentage of CPU utilization that occurred while executing at the\nuser level with nice priority.\n\n%system\nShow the percentage of CPU utilization that occurred while executing at the\nsystem level (kernel).\n\n%iowait\nShow the percentage of time that the CPU or CPUs were idle during which the\nsystem had an outstanding disk I/O request.\n\n%steal Show the percentage of time spent in involuntary wait by the virtual CPU or\nCPUs while the hypervisor was servicing another virtual processor.\n\n%idle Show the percentage of time that the CPU or CPUs were idle and the system did\nnot have an outstanding disk I/O request.\n\nDevice Utilization Report\nThe second report generated by the iostat command is the Device Utilization Report.\nThe device report provides statistics on a per physical device or partition basis.\nBlock devices and partitions for which statistics are to be displayed may be entered\non the command line. If no device nor partition is entered, then statistics are dis‐\nplayed for every device used by the system, and providing that the kernel maintains\nstatistics for it. If the ALL keyword is given on the command line, then statistics\nare displayed for every device defined by the system, including those that have never\nbeen used. Transfer rates are shown in 1K blocks by default, unless the environment\nvariable POSIXLYCORRECT is set, in which case 512-byte blocks are used. The report\nmay show the following fields, depending on the flags used (e.g. -x, -s and -k or\n-m):\n\nDevice:\nThis column gives the device (or partition) name as listed in the /dev direc‐\ntory.\n\ntps Indicate the number of transfers per second that were issued to the device. A\ntransfer is an I/O request to the device. Multiple logical requests can be com‐\nbined into a single I/O request to the device. A transfer is of indeterminate\nsize.\n\nBlkread/s (kBread/s, MBread/s)\nIndicate the amount of data read from the device expressed in a number of\nblocks (kilobytes, megabytes) per second. Blocks are equivalent to sectors and\ntherefore have a size of 512 bytes.\n\nBlkwrtn/s (kBwrtn/s, MBwrtn/s)\nIndicate the amount of data written to the device expressed in a number of\nblocks (kilobytes, megabytes) per second.\n\nBlkdscd/s (kBdscd/s, MBdscd/s)\nIndicate the amount of data discarded for the device expressed in a number of\nblocks (kilobytes, megabytes) per second.\n\nBlkw+d/s (kBw+d/s, MBw+d/s)\nIndicate the amount of data written to or discarded for the device expressed in\na number of blocks (kilobytes, megabytes) per second.\n\nBlkread (kBread, MBread)\nThe total number of blocks (kilobytes, megabytes) read.\n\nBlkwrtn (kBwrtn, MBwrtn)\nThe total number of blocks (kilobytes, megabytes) written.\n\nBlkdscd (kBdscd, MBdscd)\nThe total number of blocks (kilobytes, megabytes) discarded.\n\nBlkw+d (kBw+d, MBw+d)\nThe total number of blocks (kilobytes, megabytes) written or discarded.\n\nr/s The number (after merges) of read requests completed per second for the device.\n\nw/s The number (after merges) of write requests completed per second for the de‐\nvice.\n\nd/s The number (after merges) of discard requests completed per second for the de‐\nvice.\n\nf/s The number (after merges) of flush requests completed per second for the de‐\nvice. This counts flush requests executed by disks. Flush requests are not\ntracked for partitions. Before being merged, flush operations are counted as\nwrites.\n\nsec/s (kB/s, MB/s)\nThe number of sectors (kilobytes, megabytes) read from, written to or discarded\nfor the device per second.\n\nrsec/s (rkB/s, rMB/s)\nThe number of sectors (kilobytes, megabytes) read from the device per second.\n\nwsec/s (wkB/s, wMB/s)\nThe number of sectors (kilobytes, megabytes) written to the device per second.\n\ndsec/s (dkB/s, dMB/s)\nThe number of sectors (kilobytes, megabytes) discarded for the device per sec‐\nond.\n\nrqm/s The number of I/O requests merged per second that were queued to the device.\n\nrrqm/s The number of read requests merged per second that were queued to the device.\n\nwrqm/s The number of write requests merged per second that were queued to the device.\n\ndrqm/s The number of discard requests merged per second that were queued to the de‐\nvice.\n\n%rrqm The percentage of read requests merged together before being sent to the de‐\nvice.\n\n%wrqm The percentage of write requests merged together before being sent to the de‐\nvice.\n\n%drqm The percentage of discard requests merged together before being sent to the de‐\nvice.\n\nareq-sz\nThe average size (in kilobytes) of the I/O requests that were issued to the de‐\nvice.\nNote: In previous versions, this field was known as avgrq-sz and was expressed\nin sectors.\n\nrareq-sz\nThe average size (in kilobytes) of the read requests that were issued to the\ndevice.\n\nwareq-sz\nThe average size (in kilobytes) of the write requests that were issued to the\ndevice.\n\ndareq-sz\nThe average size (in kilobytes) of the discard requests that were issued to the\ndevice.\n\nawait The average time (in milliseconds) for I/O requests issued to the device to be\nserved. This includes the time spent by the requests in queue and the time\nspent servicing them.\n\nrawait\nThe average time (in milliseconds) for read requests issued to the device to be\nserved. This includes the time spent by the requests in queue and the time\nspent servicing them.\n\nwawait\nThe average time (in milliseconds) for write requests issued to the device to\nbe served. This includes the time spent by the requests in queue and the time\nspent servicing them.\n\ndawait\nThe average time (in milliseconds) for discard requests issued to the device to\nbe served. This includes the time spent by the requests in queue and the time\nspent servicing them.\n\nfawait\nThe average time (in milliseconds) for flush requests issued to the device to\nbe served. The block layer combines flush requests and executes at most one at\na time. Thus flush operations could be twice as long: Wait for current flush\nrequest, then execute it, then wait for the next one.\n\naqu-sz The average queue length of the requests that were issued to the device.\nNote: In previous versions, this field was known as avgqu-sz.\n\n%util Percentage of elapsed time during which I/O requests were issued to the device\n(bandwidth utilization for the device). Device saturation occurs when this\nvalue is close to 100% for devices serving requests serially. But for devices\nserving requests in parallel, such as RAID arrays and modern SSDs, this number\ndoes not reflect their performance limits.\n\n", "subsections": [] }, "OPTIONS": { "content": "", "subsections": [ { "name": "-c", "content": "", "flag": "-c" }, { "name": "-d", "content": "", "flag": "-d" }, { "name": "--dec={ 0 | 1 | 2 }", "content": "Specify the number of decimal places to use (0 to 2, default value is 2).\n", "long": "--dec", "arg": "{" }, { "name": "-f", "content": "+f directory\nSpecify an alternative directory for iostat to read devices statistics. Option -f\ntells iostat to use only the files located in the alternative directory, whereas op‐\ntion +f tells it to use both the standard kernel files and the files located in the\nalternative directory to read device statistics.\n\ndirectory is a directory containing files with statistics for devices managed in\nuserspace. It may contain:\n\n- a \"diskstats\" file whose format is compliant with that located in \"/proc\",\n- statistics for individual devices contained in files whose format is compliant with\nthat of files located in \"/sys\".\n\nIn particular, the following files located in directory may be used by iostat:\n\ndirectory/block/device/stat\ndirectory/block/device/partition/stat\n\npartition files must have an entry in directory/dev/block/ directory, e.g.:\n\ndirectory/dev/block/major:minor --> ../../block/device/partition\n", "flag": "-f" }, { "name": "-g", "content": "Display statistics for a group of devices. The iostat command reports statistics for\neach individual device in the list then a line of global statistics for the group dis‐\nplayed as groupname and made up of all the devices in the list. The ALL keyword means\nthat all the block devices defined by the system shall be included in the group.\n", "flag": "-g" }, { "name": "-H -g", "content": "the group are to be displayed, and not statistics for individual devices in the group.\n", "flag": "-g" }, { "name": "-h --human --pretty", "content": "", "flag": "-h", "long": "--pretty" }, { "name": "--human", "content": "Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.) The units displayed with\nthis option supersede any other default units (e.g. kilobytes, sectors...) associated\nwith the metrics.\n", "long": "--human" }, { "name": "-j", "content": "Display persistent device names. Keywords ID, LABEL, etc. specify the type of the per‐\nsistent name. These keywords are not limited, only prerequisite is that directory with\nrequired persistent names is present in /dev/disk. Optionally, multiple devices can\nbe specified in the chosen persistent name type. Because persistent device names are\nusually long, option --pretty is implicitly set with this option.\n", "flag": "-j" }, { "name": "-k", "content": "", "flag": "-k" }, { "name": "-m", "content": "", "flag": "-m" }, { "name": "-N", "content": "viewing LVM2 statistics.\n", "flag": "-N" }, { "name": "-o JSON", "content": "Display the statistics in JSON (Javascript Object Notation) format. JSON output field\norder is undefined, and new fields may be added in the future.\n", "flag": "-o", "arg": "JSON" }, { "name": "-p", "content": "Display statistics for block devices and all their partitions that are used by the\nsystem. If a device name is entered on the command line, then statistics for it and\nall its partitions are displayed. Last, the ALL keyword indicates that statistics have\nto be displayed for all the block devices and partitions defined by the system, in‐\ncluding those that have never been used. If option -j is defined before this option,\ndevices entered on the command line can be specified with the chosen persistent name\ntype.\n", "flag": "-p" }, { "name": "--pretty", "content": "Make the Device Utilization Report easier to read by a human.\n", "long": "--pretty" }, { "name": "-s", "content": "screens.\n", "flag": "-s" }, { "name": "-t", "content": "of the STIMEFORMAT environment variable (see below).\n", "flag": "-t" }, { "name": "-V", "content": "", "flag": "-V" }, { "name": "-x", "content": "", "flag": "-x" }, { "name": "-y", "content": "given interval.\n", "flag": "-y" }, { "name": "-z", "content": "sample period.\n\n", "flag": "-z" } ] }, "ENVIRONMENT": { "content": "The iostat command takes into account the following environment variables:\n\nPOSIXLYCORRECT\nWhen this variable is set, transfer rates are shown in 512-byte blocks instead of the\ndefault 1K blocks.\n\nSCOLORS\nBy default statistics are displayed in color when the output is connected to a termi‐\nnal. Use this variable to change the settings. Possible values for this variable are\nnever, always or auto (the latter is equivalent to the default settings).\nPlease note that the color (being red, yellow, or some other color) used to display a\nvalue is not indicative of any kind of issue simply because of the color. It only in‐\ndicates different ranges of values.\n\nSCOLORSSGR\nSpecify the colors and other attributes used to display statistics on the terminal.\nIts value is a colon-separated list of capabilities that defaults to\nH=31;1:I=32;22:M=35;1:N=34;1:Z=34;22. Supported capabilities are:\n\nH= SGR (Select Graphic Rendition) substring for percentage values greater than or\nequal to 75%.\n\nI= SGR substring for device names.\n\nM= SGR substring for percentage values in the range from 50% to 75%.\n\nN= SGR substring for non-zero statistics values.\n\nZ= SGR substring for zero values.\n\nSTIMEFORMAT\nIf this variable exists and its value is ISO then the current locale will be ignored\nwhen printing the date in the report header. The iostat command will use the ISO 8601\nformat (YYYY-MM-DD) instead. The timestamp displayed with option -t will also be com‐\npliant with ISO 8601 format.\n\n", "subsections": [] }, "EXAMPLES": { "content": "iostat Display a single history since boot report for all CPU and Devices.\n", "subsections": [ { "name": "iostat -d 2", "content": "Display a continuous device report at two second intervals.\n" }, { "name": "iostat -d 2 6", "content": "Display six reports at two second intervals for all devices.\n" }, { "name": "iostat -x sda sdb 2 6", "content": "Display six reports of extended statistics at two second intervals for devices sda and\nsdb.\n" }, { "name": "iostat -p sda 2 6", "content": "Display six reports at two second intervals for device sda and all its partitions\n(sda1, etc.)\n\n" } ] }, "BUGS": { "content": "/proc filesystem must be mounted for iostat to work.\n\nKernels older than 2.6.x are no longer supported.\n\nAlthough iostat speaks of kilobytes (kB), megabytes (MB)..., it actually uses kibibytes\n(kiB), mebibytes (MiB)... A kibibyte is equal to 1024 bytes, and a mebibyte is equal to 1024\nkibibytes.\n\n", "subsections": [] }, "FILES": { "content": "/proc/stat contains system statistics.\n/proc/uptime contains system uptime.\n/proc/diskstats contains disks statistics.\n/sys contains statistics for block devices.\n/proc/self/mountstats contains statistics for network filesystems.\n/dev/disk contains persistent device names.\n\n", "subsections": [] }, "AUTHOR": { "content": "Sebastien Godard (sysstat orange.fr)\n\n", "subsections": [] }, "SEE ALSO": { "content": "sar(1), pidstat(1), mpstat(1), vmstat(8), tapestat(1), nfsiostat(1), cifsiostat(1)\n\nhttps://github.com/sysstat/sysstat\nhttp://pagesperso-orange.fr/sebastien.godard/\n\n\n\nLinux OCTOBER 2020 IOSTAT(1)", "subsections": [] } }, "summary": "iostat - Report Central Processing Unit (CPU) statistics and input/output statistics for de‐ vices and partitions.", "flags": [ { "flag": "-c", "long": null, "arg": null, "description": "" }, { "flag": "-d", "long": null, "arg": null, "description": "" }, { "flag": "", "long": "--dec", "arg": "{", "description": "Specify the number of decimal places to use (0 to 2, default value is 2)." }, { "flag": "-f", "long": null, "arg": null, "description": "+f directory Specify an alternative directory for iostat to read devices statistics. Option -f tells iostat to use only the files located in the alternative directory, whereas op‐ tion +f tells it to use both the standard kernel files and the files located in the alternative directory to read device statistics. directory is a directory containing files with statistics for devices managed in userspace. It may contain: - a \"diskstats\" file whose format is compliant with that located in \"/proc\", - statistics for individual devices contained in files whose format is compliant with that of files located in \"/sys\". In particular, the following files located in directory may be used by iostat: directory/block/device/stat directory/block/device/partition/stat partition files must have an entry in directory/dev/block/ directory, e.g.: directory/dev/block/major:minor --> ../../block/device/partition" }, { "flag": "-g", "long": null, "arg": null, "description": "Display statistics for a group of devices. The iostat command reports statistics for each individual device in the list then a line of global statistics for the group dis‐ played as groupname and made up of all the devices in the list. The ALL keyword means that all the block devices defined by the system shall be included in the group." }, { "flag": "-g", "long": null, "arg": null, "description": "the group are to be displayed, and not statistics for individual devices in the group." }, { "flag": "-h", "long": "--pretty", "arg": null, "description": "" }, { "flag": "", "long": "--human", "arg": null, "description": "Print sizes in human readable format (e.g. 1.0k, 1.2M, etc.) The units displayed with this option supersede any other default units (e.g. kilobytes, sectors...) associated with the metrics." }, { "flag": "-j", "long": null, "arg": null, "description": "Display persistent device names. Keywords ID, LABEL, etc. specify the type of the per‐ sistent name. These keywords are not limited, only prerequisite is that directory with required persistent names is present in /dev/disk. Optionally, multiple devices can be specified in the chosen persistent name type. Because persistent device names are usually long, option --pretty is implicitly set with this option." }, { "flag": "-k", "long": null, "arg": null, "description": "" }, { "flag": "-m", "long": null, "arg": null, "description": "" }, { "flag": "-N", "long": null, "arg": null, "description": "viewing LVM2 statistics." }, { "flag": "-o", "long": null, "arg": "JSON", "description": "Display the statistics in JSON (Javascript Object Notation) format. JSON output field order is undefined, and new fields may be added in the future." }, { "flag": "-p", "long": null, "arg": null, "description": "Display statistics for block devices and all their partitions that are used by the system. If a device name is entered on the command line, then statistics for it and all its partitions are displayed. Last, the ALL keyword indicates that statistics have to be displayed for all the block devices and partitions defined by the system, in‐ cluding those that have never been used. If option -j is defined before this option, devices entered on the command line can be specified with the chosen persistent name type." }, { "flag": "", "long": "--pretty", "arg": null, "description": "Make the Device Utilization Report easier to read by a human." }, { "flag": "-s", "long": null, "arg": null, "description": "screens." }, { "flag": "-t", "long": null, "arg": null, "description": "of the STIMEFORMAT environment variable (see below)." }, { "flag": "-V", "long": null, "arg": null, "description": "" }, { "flag": "-x", "long": null, "arg": null, "description": "" }, { "flag": "-y", "long": null, "arg": null, "description": "given interval." }, { "flag": "-z", "long": null, "arg": null, "description": "sample period." } ], "examples": [ "iostat Display a single history since boot report for all CPU and Devices.", "Display a continuous device report at two second intervals.", "Display six reports at two second intervals for all devices.", "Display six reports of extended statistics at two second intervals for devices sda and", "sdb.", "Display six reports at two second intervals for device sda and all its partitions", "(sda1, etc.)" ], "see_also": [ { "name": "sar", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/sar/1/json" }, { "name": "pidstat", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/pidstat/1/json" }, { "name": "mpstat", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/mpstat/1/json" }, { "name": "vmstat", "section": "8", "url": "https://www.chedong.com/phpMan.php/man/vmstat/8/json" }, { "name": "tapestat", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/tapestat/1/json" }, { "name": "nfsiostat", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/nfsiostat/1/json" }, { "name": "cifsiostat", "section": "1", "url": "https://www.chedong.com/phpMan.php/man/cifsiostat/1/json" } ], "tldr": { "source": "official", "description": "Report statistics for devices and partitions.", "examples": [ { "description": "Display a report of CPU and disk statistics since system startup", "command": "iostat" }, { "description": "Display a report of CPU and disk statistics with units converted to megabytes", "command": "iostat -m" }, { "description": "Display CPU statistics", "command": "iostat {{-c|--compact}}" }, { "description": "Display disk statistics with disk names (including LVM)", "command": "iostat -N" }, { "description": "Display extended disk statistics with disk names for device \"sda\"", "command": "iostat -xN {{sda}}" }, { "description": "Display incremental reports of CPU and disk statistics every 2 seconds", "command": "iostat {{2}}" } ] } }