-.TH MULTIPATH.CONF 5 "30 November 2006"
+.\" ----------------------------------------------------------------------------
+.\" Update the date below if you make any significant change.
+.\" Make sure there are no errors with:
+.\" groff -z -wall -b -e -t multipath/multipath.conf.5
+.\" man --warnings -E UTF-8 -l -Tutf8 -Z multipath/multipath.conf.5 >/dev/null
+.\"
+.\" TODO: Look for XXX and ???
+.\"
+.\" ----------------------------------------------------------------------------
+.
+.TH MULTIPATH.CONF 5 2017-08-18 Linux
+.
+.
+.\" ----------------------------------------------------------------------------
.SH NAME
-multipath.conf \- multipath daemon configuration file
+.\" ----------------------------------------------------------------------------
+.
+multipath.conf \- multipath daemon configuration file.
+.
+.
+.\" ----------------------------------------------------------------------------
.SH DESCRIPTION
-.B "multipath.conf"
+.\" ----------------------------------------------------------------------------
+.
+.B "/etc/multipath.conf"
is the configuration file for the multipath daemon. It is used to
overwrite the built-in configuration table of \fBmultipathd\fP.
Any line whose first non-white-space character is a '#' is considered
a comment line. Empty lines are ignored.
+.PP
+Currently used multipathd configuration can be displayed with the \fBmultipath -t\fR
+or \fBmultipathd show config\fR command.
+.
+.
+.\" ----------------------------------------------------------------------------
.SH SYNTAX
+.\" ----------------------------------------------------------------------------
+.
The configuration file contains entries of the form:
.RS
.nf
<attribute> <value>
.I "..."
.RE
+.ft B
}
.RE
+.ft B
}
.ft R
.fi
.LP
Each \fIsection\fP contains one or more attributes or subsections. The
recognized keywords for attributes or subsections depend on the
-section in which they occor.
+section in which they occur.
.LP
+.
+.
The following \fIsection\fP keywords are recognized:
.TP 17
.B defaults
.B blacklist_exceptions
This section defines which devices should be included in the
multipath topology discovery, despite being listed in the
-.I blacklist
-section.
+\fIblacklist\fR section.
.TP
.B multipaths
This section defines the multipath topologies. They are indexed by a
-\fIWorld Wide Identifier\fR(wwid), which is the result of the
-\fIgetuid_callout\fR program.
+\fIWorld Wide Identifier\fR(WWID). For details on the WWID generation
+see section \fIWWID generation\fR below.
.TP
.B devices
This section defines the device-specific settings.
+.TP
+.B overrides
+This section defines values for attributes that should override the
+device-specific settings for all devices.
.RE
.LP
+.
+.
+.\" ----------------------------------------------------------------------------
.SH "defaults section"
-The
-.B defaults
-section recognizes the following keywords:
+.\" ----------------------------------------------------------------------------
+.
+The \fIdefaults\fR section recognizes the following keywords:
+.
+.
.TP 17
+.B verbosity
+Default verbosity. Higher values increase the verbosity level. Valid
+levels are between 0 and 6.
+.RS
+.TP
+The default is: \fB2\fR
+.RE
+.
+.
+.TP
.B polling_interval
-interval between two path checks in seconds For properly functioning paths,
-the interval between checks will gradually increase to (4 * polling_interval);
-default is
-.I 5
+Interval between two path checks in seconds. For properly functioning paths,
+the interval between checks will gradually increase to \fImax_polling_interval\fR.
+This value will be overridden by the \fIWatchdogSec\fR
+setting in the multipathd.service definition if systemd is used.
+.RS
+.TP
+The default is: \fB5\fR
+.RE
+.
+.
.TP
-.B udev_dir
-directory where udev creates its device nodes; default is
-.I /dev
+.B max_polling_interval
+Maximal interval between two path checks in seconds.
+.RS
.TP
-.B verbosity
-default verbosity. Higher values increase the verbosity level. Valid
-levels are between 0 and 6; default is
-.I 2
+The default is: \fB4 * polling_interval\fR
+.RE
+.
+.
+.TP
+.B reassign_maps
+Enable reassigning of device-mapper maps. With this option multipathd
+will remap existing device-mapper maps to always point to multipath
+device, not the underlying block devices. Possible values are
+\fIyes\fR and \fIno\fR.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B multipath_dir
+Directory where the dynamic shared objects are stored. Defined at compile time,
+commonly \fI/lib64/multipath/\fR or \fI/lib/multipath/\fR.
+.RS
+.TP
+The default is: \fB<system dependent>\fR
+.RE
+.
+.
.TP
.B path_selector
The default path selector algorithm to use; they are offered by the
-kernel multipath target. There are three selector algorithms.
+kernel multipath target. There are three selector algorithms:
.RS
.TP 12
-.B "round-robin 0"
-Loop through every path in the path group, sending the same amount of IO to
-each.
+.I "round-robin 0"
+Loop through every path in the path group, sending the same amount of I/O to
+each. Some aspects of behavior can be controlled with the attributes:
+\fIrr_min_io\fR, \fIrr_min_io_rq\fR and \fIrr_weight\fR.
+.TP
+.I "queue-length 0"
+(Since 2.6.31 kernel) Choose the path for the next bunch of I/O based on the amount
+of outstanding I/O to the path.
.TP
-.B "queue-length 0"
-Send the next bunch of IO down the path with the least amount of outstanding IO.
+.I "service-time 0"
+(Since 2.6.31 kernel) Choose the path for the next bunch of I/O based on the amount
+of outstanding I/O to the path and its relative throughput.
.TP
-.B "service-time 0"
-Choose the path for the next bunch of IO based on the amount of outstanding IO
-to the path and its relative throughput.
+The default is: \fBservice-time 0\fR
.RE
+.
+.
.TP
.B path_grouping_policy
The default path grouping policy to apply to unspecified
-multipaths. Possible values are
+multipaths. Possible values are:
.RS
.TP 12
-.B failover
-1 path per priority group
+.I failover
+One path per priority group.
.TP
-.B multibus
-all paths in 1 priority group
+.I multibus
+All paths in one priority group.
.TP
-.B group_by_serial
-1 priority group per serial number
+.I group_by_serial
+One priority group per serial number.
.TP
-.B group_by_prio
-1 priority group per priority value. Priorities are determined by
+.I group_by_prio
+One priority group per priority value. Priorities are determined by
callout programs specified as a global, per-controller or
per-multipath option in the configuration file.
.TP
-.B group_by_node_name
-1 priority group per target node name. Target node names are fetched
-in /sys/class/fc_transport/target*/node_name.
+.I group_by_node_name
+One priority group per target node name. Target node names are fetched
+in \fI/sys/class/fc_transport/target*/node_name\fR.
+.TP
+The default is: \fBfailover\fR
+.RE
+.
+.
+.TP
+.B uid_attrs
+The udev attribute providing a unique path identifier for corresponding
+type of path devices. If this field is configured and matched with type
+of device, it would override any other methods providing for device
+unique identifier in config file, and it would activate merging uevents
+according to the identifier to promote effiecncy in processing uevents.
+It has no default value, if you want to identify path by udev attribute
+and to activate merging uevents for SCSI and DASD devices, you can set
+its value as: \fIuid_attrs "sd:ID_SERIAL dasd:ID_UID"\fR.
+.RS
+.TP
+The default is: \fB<unset>\fR
+.RE
+.
+.
+.TP
+.B uid_attribute
+The udev attribute providing a unique path identifier.
+.RS
+.TP
+The default is: for SCSI devices \fBID_SERIAL\fR
+.TP
+The default is: for DASD devices \fBID_UID\fR
.TP
-Default value is \fImultibus\fR.
+The default is: for NVME devices \fBID_WWN\fR
.RE
+.
+.
.TP
.B getuid_callout
-The default program and args to callout to obtain a unique path
-identifier. Should be specified with an absolute path. Default value
-is
-.I /lib/udev/scsi_id --whitelisted --device=/dev/%n
-.TP
-.B prio_callout
-The default program and args to callout to obtain a path priority
-value. The specified program will be executed and should return a
-numeric value specifying the relative priority of this path. Higher
-number have a higher priority. A '%n' in the command line will be expanded
-to the device name, a '%b' will be expanded to the device number in
-.I major:minor
-format.
-.I "none"
-is a valid value. Currently the following path priority programs are
-implemented:
+(Superseded by \fIuid_attribute\fR) The default program and args to callout
+to obtain a unique path identifier. Should be specified with an absolute path.
+.RS
+.TP
+The default is: \fB<unset>\fR
+.RE
+.
+.
+.TP
+.B prio
+The name of the path priority routine. The specified routine
+should return a numeric value specifying the relative priority
+of this path. Higher number have a higher priority.
+\fI"none"\fR is a valid value. Currently the following path priority routines
+are implemented:
.RS
.TP 12
-.B mpath_prio_emc /dev/%n
-Generate the path priority for EMC arrays
+.I const
+Return a constant priority of \fI1\fR.
+.TP
+.I sysfs
+Use the sysfs attributes \fIaccess_state\fR and \fIpreferred_path\fR to
+generate the path priority. This prioritizer accepts the optional prio_arg
+\fIexclusive_pref_bit\fR.
+.TP
+.I emc
+(Hardware-dependent)
+Generate the path priority for DGC class arrays as CLARiiON CX/AX and
+EMC VNX and Unity families.
+.TP
+.I alua
+(Hardware-dependent)
+Generate the path priority based on the SCSI-3 ALUA settings. This prioritizer
+accepts the optional prio_arg \fIexclusive_pref_bit\fR.
+.TP
+.I ontap
+(Hardware-dependent)
+Generate the path priority for NetApp ONTAP class and OEM arrays as IBM NSeries.
+.TP
+.I rdac
+(Hardware-dependent)
+Generate the path priority for LSI/Engenio/NetApp RDAC class as NetApp SANtricity
+E/EF Series, and OEM arrays from IBM DELL SGI STK and SUN.
+.TP
+.I hp_sw
+(Hardware-dependent)
+Generate the path priority for HP/COMPAQ/DEC HSG80 and MSA/HSV arrays with
+Active/Standby mode exclusively.
+.TP
+.I hds
+(Hardware-dependent)
+Generate the path priority for Hitachi AMS 2000 and HUS 100 families of arrays.
+.TP
+.I random
+Generate a random priority between 1 and 10.
+.TP
+.I weightedpath
+Generate the path priority based on the regular expression and the
+priority provided as argument. Requires prio_args keyword.
+.TP
+.I path_latency
+Generate the path priority based on a latency algorithm.
+Requires prio_args keyword.
+.TP
+.I datacore
+(Hardware-dependent)
+Generate the path priority for some DataCore storage arrays. Requires prio_args
+keyword.
.TP
-.B mpath_prio_alua /dev/%n
-Generate the path priority based on the SCSI-3 ALUA settings.
+.I iet
+(iSCSI only)
+Generate path priority for iSCSI targets based on IP address. Requires
+prio_args keyword.
+.PP
+The default depends on the \fBdetect_prio\fR setting: If \fBdetect_prio\fR is
+\fByes\fR (default), the default priority algorithm is \fBsysfs\fR (except for
+NetAPP E-Series, where it is \fBalua\fR). If \fBdetect_prio\fR is
+\fBno\fR, the default priority algorithm is \fBconst\fR.
+.RE
+.
+.
.TP
-.B mpath_prio_netapp /dev/%n
-Generate the path priority for NetApp arrays.
+.B prio_args
+Arguments to pass to to the prio function. This only applies to certain
+prioritizers:
+.RS
+.TP 12
+.I weighted
+Needs a value of the form
+\fI"<hbtl|devname|serial|wwn> <regex1> <prio1> <regex2> <prio2> ..."\fR
+.RS
+.TP 8
+.I hbtl
+Regex can be of SCSI H:B:T:L format. For example: 1:0:.:. , *:0:0:.
+.TP
+.I devname
+Regex can be of device name format. For example: sda , sd.e
+.TP
+.I serial
+Regex can be of serial number format. For example: .*J1FR.*324 . The serial can
+be looked up through sysfs or by running multipathd show paths format "%z". For
+example: 0395J1FR904324
+.TP
+.I wwn
+Regex can be of the form \fI"host_wwnn:host_wwpn:target_wwnn:target_wwpn"\fR
+these values can be looked up through sysfs or by running \fImultipathd show paths format
+"%N:%R:%n:%r"\fR. For example: 0x200100e08ba0aea0:0x210100e08ba0aea0:.*:.* , .*:.*:iqn.2009-10.com.redhat.msp.lab.ask-06:.*
+.RE
+.TP 12
+.I path_latency
+Needs a value of the form "io_num=\fI<20>\fR base_num=\fI<10>\fR"
+.RS
+.TP 8
+.I io_num
+The number of read IOs sent to the current path continuously, used to calculate the average path latency.
+Valid Values: Integer, [2, 200].
+.TP
+.I base_num
+The base number value of logarithmic scale, used to partition different priority ranks. Valid Values: Integer,
+[2, 10]. And Max average latency value is 100s, min average latency value is 1us.
+For example: If base_num=10, the paths will be grouped in priority groups with path latency <=1us, (1us, 10us],
+(10us, 100us], (100us, 1ms], (1ms, 10ms], (10ms, 100ms], (100ms, 1s], (1s, 10s], (10s, 100s], >100s.
+.RE
+.TP 12
+.I alua
+If \fIexclusive_pref_bit\fR is set, paths with the \fIpreferred path\fR bit
+set will always be in their own path group.
.TP
-.B mpath_prio_rdac /dev/%n
-Generate the path priority for LSI/Engenio RDAC controller.
+.I sysfs
+If \fIexclusive_pref_bit\fR is set, paths with the \fIpreferred path\fR bit
+set will always be in their own path group.
.TP
-.B mpath_prio_hp_sw /dev/%n
-Generate the path priority for Compaq/HP controller in
-active/standby mode.
+.I datacore
+.RS
+.TP 8
+.I preferredsds
+(Mandatory) The preferred "SDS name".
.TP
-.B mpath_prio_hds_modular %b
-Generate the path priority for Hitachi HDS Modular storage arrays.
+.I timeout
+(Optional) The timeout for the INQUIRY, in ms.
+.RE
+.TP 12
+.I iet
+.RS
+.TP 8
+.I preferredip=...
+(Mandatory) Th preferred IP address, in dotted decimal notation, for iSCSI targets.
+.RE
.TP
-Default value is \fBnone\fR.
+The default is: \fB<unset>\fR
.RE
+.
+.
.TP
.B features
-Specify any device-mapper features to be used. The most common of
-these features is
-.I "1 queue_if_no_path"
-Note that this can also be set via the
-.I no_path_retry
-keyword.
+Specify any device-mapper features to be used. Syntax is \fInum list\fR
+where \fInum\fR is the number, between 0 and 8, of features in \fIlist\fR.
+Possible values for the feature list are:
+.RS
+.TP 12
+.I queue_if_no_path
+(Deprecated, superseded by \fIno_path_retry\fR) Queue I/O if no path is active.
+Identical to the \fIno_path_retry\fR with \fIqueue\fR value. If both this
+feature and \fIno_path_retry\fR are set, the latter value takes
+precedence. See KNOWN ISSUES.
+.TP
+.I pg_init_retries <times>
+(Since kernel 2.6.24) Number of times to retry pg_init, it must be between 1 and 50.
+.TP
+.I pg_init_delay_msecs <msecs>
+(Since kernel 2.6.38) Number of msecs before pg_init retry, it must be between 0 and 60000.
+.TP
+.I queue_mode <mode>
+(Since kernel 4.8) Select the the queueing mode per multipath device.
+<mode> can be \fIbio\fR, \fIrq\fR or \fImq\fR, which corresponds to
+bio-based, request-based, and block-multiqueue (blk-mq) request-based,
+respectively.
+The default depends on the kernel parameter \fBdm_mod.use_blk_mq\fR. It is
+\fImq\fR if the latter is set, and \fIrq\fR otherwise.
+.TP
+The default is: \fB<unset>\fR
+.RE
+.
+.
.TP
.B path_checker
-The default method used to determine the paths' state. Possible values
-are
+The default method used to determine the paths state. Possible values
+are:
.RS
.TP 12
-.B readsector0
-Read the first sector of the device
+.I readsector0
+(Deprecated) Read the first sector of the device. This checker is being
+deprecated, please use \fItur\fR instead.
+.TP
+.I tur
+Issue a \fITEST UNIT READY\fR command to the device.
+.TP
+.I emc_clariion
+(Hardware-dependent)
+Query the DGC/EMC specific EVPD page 0xC0 to determine the path state
+for CLARiiON CX/AX and EMC VNX and Unity arrays families.
+.TP
+.I hp_sw
+(Hardware-dependent)
+Check the path state for HP/COMPAQ/DEC HSG80 and MSA/HSV arrays with
+Active/Standby mode exclusively.
.TP
-.B tur
-Issue a
-.I TEST UNIT READY
-command to the device.
+.I rdac
+(Hardware-dependent)
+Check the path state for LSI/Engenio/NetApp RDAC class as NetApp SANtricity E/EF
+Series, and OEM arrays from IBM DELL SGI STK and SUN.
.TP
-.B emc_clariion
-Query the EMC Clariion specific EVPD page 0xC0 to determine the path
-state.
+.I directio
+(Deprecated) Read the first sector with direct I/O. This checker is being
+deprecated, it could cause spurious path failures under high load.
+Please use \fItur\fR instead.
.TP
-.B hp_sw
-Check the path state for HP storage arrays with Active/Standby firmware.
+.I cciss_tur
+(Hardware-dependent)
+Check the path state for HP/COMPAQ Smart Array(CCISS) controllers.
.TP
-.B rdac
-Check the path state for LSI/Engenio RDAC storage controller.
+.I none
+Do not check the device, fallback to use the values retrieved from sysfs
.TP
-.B directio
-Read the first sector with direct I/O.
+.I rbd
+Check if the path is in the Ceph blacklist and remap the path if it is.
.TP
-Default value is \fIreadsector0\fR.
+The default is: \fBtur\fR
.RE
+.
+.
+.TP
+.B alias_prefix
+The \fIuser_friendly_names\fR prefix.
+.RS
+.TP
+The default is: \fBmpath\fR
+.RE
+.
+.
.TP
.B failback
-Tell the daemon to manage path group failback, or not to. 0 or
+Tell multipathd how to manage path group failback.
+To select \fIimmediate\fR or a \fIvalue\fR, it's mandatory that the device
+has support for a working prioritizer.
+.RS
+.TP 12
.I immediate
-means immediate failback, values >0 means deferred failback (in
-seconds).
-.I manual
-means no failback. Default value is
+Immediately failback to the highest priority pathgroup that contains
+active paths.
+.TP
.I manual
+Do not perform automatic failback.
+.TP
+.I followover
+Used to deal with multiple computers accessing the same Active/Passive storage
+devices. Only perform automatic failback when the first path of a pathgroup
+becomes active. This keeps a cluster node from automatically failing back when
+another node requested the failover.
+.TP
+.I values > 0
+Deferred failback (time to defer in seconds).
+.TP
+The default is: \fBmanual\fR
+.RE
+.
+.
.TP
.B rr_min_io
-The number of IO to route to a path before switching to the next in
-the same path group. Default is
-.I 1000
+Number of I/O requests to route to a path before switching to the next in the
+same path group. This is only for \fIBlock I/O\fR(BIO) based multipath and
+only apply to \fIround-robin\fR path_selector.
+.RS
.TP
-.B rr_weight
-If set to \fIpriorities\fR the multipath configurator will assign
-path weights as "path prio * rr_min_io". Possible values are
-.I priorities
-or
-.IR uniform .
-Default is
-.IR uniform .
+The default is: \fB1000\fR
+.RE
+.
+.
.TP
-.B no_path_retry
-Specify the number of retries until disable queueing, or
-.I fail
-for immediate failure (no queueing),
-.I queue
-for never stop queueing. Default is 0.
+.B rr_min_io_rq
+Number of I/O requests to route to a path before switching to the next in the
+same path group. This is only for \fIRequest\fR based multipath and
+only apply to \fIround-robin\fR path_selector.
+.RS
.TP
-.B user_friendly_names
-If set to
-.I yes
-, using the bindings file
-.I /etc/multipath/bindings
-to assign a persistent and unique alias to the multipath, in the form of mpath<n>.
-If set to
-.I no
-use the WWID as the alias. In either case this be will
-be overriden by any specific aliases in the \fImultipaths\fR section.
-Default is
-.I no
+The default is: \fB1\fR
+.RE
+.
+.
.TP
.B max_fds
Specify the maximum number of file descriptors that can be opened by multipath
-and multipathd. This is equivalent to ulimit -n. A value of \fImax\fR will set
-this to the system limit from /proc/sys/fs/nr_open. If this is not set, the
+and multipathd. This is equivalent to ulimit \-n. A value of \fImax\fR will set
+this to the system limit from \fI/proc/sys/fs/nr_open\fR. If this is not set, the
maximum number of open fds is taken from the calling process. It is usually
1024. To be safe, this should be set to the maximum number of paths plus 32,
if that number is greated than 1024.
+.RS
.TP
-.B checker_timeout
-Specify the timeout to user for path checkers that issue scsi commands with an
-explict timeout, in seconds; default taken from
-.I /sys/block/sd<x>/device/timeout
+The default is: \fBmax\fR
+.RE
+.
+.
.TP
-.B fast_io_fail_tmo
-Specify the number of seconds the scsi layer will wait after a problem has been
-detected on a FC remote port before failing IO to devices on that remote port.
-This should be smaller than dev_loss_tmo. Setting this to
-.I off
-will disable the timeout.
+.B rr_weight
+If set to \fIpriorities\fR the multipath configurator will assign path weights
+as "path prio * rr_min_io". Possible values are
+.I priorities
+or
+.I uniform .
+Only apply to \fIround-robin\fR path_selector.
+.RS
.TP
-.B dev_loss_tmo
-Specify the number of seconds the scsi layer will wait after a problem has
-been detected on a FC remote port before removing it from the system.
+The default is: \fBuniform\fR
+.RE
+.
+.
+.TP
+.B no_path_retry
+Specify what to do when all paths are down. Possible values are:
+.RS
+.TP 12
+.I value > 0
+Number of retries until disable I/O queueing.
+.TP
+.I fail
+For immediate failure (no I/O queueing).
+.TP
+.I queue
+For never stop I/O queueing, similar to \fIqueue_if_no_path\fR. See KNOWN ISSUES.
+.TP
+The default is: \fBfail\fR
+.RE
+.
+.
.TP
.B queue_without_daemon
If set to
.I no
, when multipathd stops, queueing will be turned off for all devices.
-This is useful for devices that set no_path_retry. If a machine is
+This is useful for devices that set no_path_retry. If a machine is
shut down while all paths to a device are down, it is possible to hang waiting
-for IO to return from the device after multipathd has been stopped. Without
+for I/O to return from the device after multipathd has been stopped. Without
multipathd running, access to the paths cannot be restored, and the kernel
-cannot be told to stop queueing IO. Setting queue_without_daemon to
+cannot be told to stop queueing I/O. Setting queue_without_daemon to
.I no
-, avoids this problem. Default is
-.I yes
+, avoids this problem.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
.
-.SH "blacklist section"
-The
-.I blacklist
-section is used to exclude specific device from inclusion in the
-multipath topology. It is most commonly used to exclude local disks or
-LUNs for the array controller.
-.LP
-The following keywords are recognized:
-.TP 17
-.B wwid
-The \fIWorld Wide Identification\fR of a device.
.TP
-.B devnode
-Regular expression of the device nodes to be excluded.
+.B checker_timeout
+Specify the timeout to use for path checkers and prioritizers that issue SCSI
+commands with an explicit timeout, in seconds.
+.RS
.TP
-.B device
-Subsection for the device description. This subsection recognizes the
-.I vendor
-and
-.I product
-keywords. For a full description of these keywords please see the
-.I devices
-section description.
-.SH "blacklist_exceptions section"
-The
-.I blacklist_exceptions
-section is used to revert the actions of the
-.I blacklist
-section, ie to include specific device in the
-multipath topology. This allows to selectively include devices which
-would normally be excluded via the
-.I blacklist
-section.
-.LP
-The following keywords are recognized:
-.TP 17
-.B wwid
-The \fIWorld Wide Identification\fR of a device.
+The default is: in \fB/sys/block/sd<x>/device/timeout\fR
+.RE
+.
+.
.TP
-.B devnode
-Regular expression of the device nodes to be excluded.
+.B flush_on_last_del
+If set to
+.I yes
+, multipathd will disable queueing when the last path to a device has been
+deleted.
+.RS
.TP
-.B device
-Subsection for the device description. This subsection recognizes the
-.I vendor
-and
-.I product
-keywords. For a full description of these keywords please see the
-.I devices
-section description.
-.SH "multipaths section"
-The only recognized attribute for the
-.B multipaths
-section is the
-.I multipath
-subsection.
-.LP
-The
-.B multipath
-subsection recognizes the following attributes:
-.TP 17
-.B wwid
-Index of the container. Mandatory for this subsection.
+The default is: \fBno\fR
+.RE
+.
+.
.TP
-.B alias
-(Optional) symbolic name for the multipath map.
-.LP
-The following attributes are optional; if not set the default values
-are taken from the
-.I defaults
-section:
-.sp 1
-.PD .1v
+.B user_friendly_names
+If set to
+.I yes
+, using the bindings file \fI/etc/multipath/bindings\fR to assign a persistent
+and unique alias to the multipath, in the form of mpath<n>. If set to
+.I no
+use the WWID as the alias. In either case this be will
+be overridden by any specific aliases in the \fImultipaths\fR section.
.RS
-.TP 18
-.B path_grouping_policy
-.TP
-.B path_selector
.TP
-.B failback
+The default is: \fBno\fR
+.RE
+.
+.
.TP
-.B no_path_retry
+.B fast_io_fail_tmo
+Specify the number of seconds the SCSI layer will wait after a problem has been
+detected on a FC remote port before failing I/O to devices on that remote port.
+This should be smaller than dev_loss_tmo. Setting this to
+.I off
+will disable the timeout.
+.RS
.TP
-.B rr_min_io
+The default is: in \fB5\fR
.RE
-.PD
-.LP
-.SH "devices section"
-The only recognized attribute for the
-.B devices
-section is the
-.I device
-subsection.
-.LP
-The
-.I device
-subsection recognizes the following attributes:
-.TP 17
-.B vendor
-(Mandatory) Vendor identifier
-.TP
-.B product
-(Mandatory) Product identifier
+.
+.
+.TP
+.B dev_loss_tmo
+Specify the number of seconds the SCSI layer will wait after a problem has
+been detected on a FC remote port before removing it from the system. This
+can be set to "infinity" which sets it to the max value of 2147483647
+seconds, or 68 years. It will be automatically adjusted to the overall
+retry interval \fIno_path_retry\fR * \fIpolling_interval\fR
+if a number of retries is given with \fIno_path_retry\fR and the
+overall retry interval is longer than the specified \fIdev_loss_tmo\fR value.
+The Linux kernel will cap this value to \fI600\fR if \fIfast_io_fail_tmo\fR
+is not set. See KNOWN ISSUES.
+.RS
+.TP
+The default is: \fB600\fR
+.RE
+.
+.
+.TP
+.B bindings_file
+The full pathname of the binding file to be used when the user_friendly_names
+option is set.
+.RS
+.TP
+The default is: \fB/etc/multipath/bindings\fR
+.RE
+.
+.
+.TP
+.B wwids_file
+The full pathname of the WWIDs file, which is used by multipath to keep track
+of the WWIDs for LUNs it has created multipath devices on in the past.
+.RS
+.TP
+The default is: \fB/etc/multipath/wwids\fR
+.RE
+.
+.
+.TP
+.B prkeys_file
+The full pathname of the prkeys file, which is used by multipathd to keep
+track of the persistent reservation key used for a specific WWID, when
+\fIreservation_key\fR is set to \fBfile\fR.
+.RS
+.TP
+The default is \fB/etc/multipath/prkeys\fR
+.RE
+.
+.
+.TP
+.B log_checker_err
+If set to
+.I once
+, multipathd logs the first path checker error at logging level 2. Any later
+errors are logged at level 3 until the device is restored. If set to
+.I always
+, multipathd always logs the path checker error at logging level 2.
+.RS
+.TP
+The default is: \fBalways\fR
+.RE
+.
+.
+.TP
+.B reservation_key
+This is the service action reservation key used by mpathpersist. It must be
+set for all multipath devices using persistent reservations, and it must be
+the same as the RESERVATION KEY field of the PERSISTENT RESERVE OUT parameter
+list which contains an 8-byte value provided by the application client to the
+device server to identify the I_T nexus.
+.RS
+.PP
+Alternatively, this can be set to \fBfile\fR, which will store the RESERVATION
+KEY registered by mpathpersist in the \fIprkeys_file\fR. multipathd will then
+use this key to register additional paths as they appear. When the
+registration is removed, the RESERVATION KEY is removed from the
+\fIprkeys_file\fR.
+.TP
+The default is: \fB<unset>\fR
+.RE
+.
+.
+.TP
+.B retain_attached_hw_handler
+(Obsolete for kernels >= 4.3) If set to
+.I yes
+and the SCSI layer has already attached a hardware_handler to the device,
+multipath will not force the device to use the hardware_handler specified by
+mutipath.conf. If the SCSI layer has not attached a hardware handler,
+multipath will continue to use its configured hardware handler.
+.RS
+.PP
+The default is: \fByes\fR
+.PP
+\fBImportant Note:\fR Linux kernel 4.3 or newer always behaves as if
+\fB"retain_attached_hw_handler yes"\fR was set.
+.RE
+.
+.
+.TP
+.B detect_prio
+If set to
+.I yes
+, multipath will try to detect if the device supports SCSI-3 ALUA. If so, the
+device will automatically use the \fIsysfs\fR prioritizer if the required sysf
+attributes \fIaccess_state\fR and \fIpreferred_path\fR are supported, or the
+\fIalua\fR prioritizer if not. If set to
+.I no
+, the prioritizer will be selected as usual.
+.RS
+.TP
+The default is: \fByes\fR
+.RE
+.
+.
+.TP
+.B detect_checker
+if set to
+.I yes
+, multipath will try to detect if the device supports SCSI-3 ALUA. If so, the
+device will automatically use the \fItur\fR checker. If set to
+.I no
+, the checker will be selected as usual.
+.RS
+.TP
+The default is: \fByes\fR
+.RE
+.
+.
+.TP
+.B force_sync
+If set to
+.I yes
+, multipathd will call the path checkers in sync mode only. This means that
+only one checker will run at a time. This is useful in the case where many
+multipathd checkers running in parallel causes significant CPU pressure.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B strict_timing
+If set to
+.I yes
+, multipathd will start a new path checker loop after exactly one second,
+so that each path check will occur at exactly \fIpolling_interval\fR
+seconds. On busy systems path checks might take longer than one second;
+here the missing ticks will be accounted for on the next round.
+A warning will be printed if path checks take longer than \fIpolling_interval\fR
+seconds.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B deferred_remove
+If set to
+.I yes
+, multipathd will do a deferred remove instead of a regular remove when the
+last path device has been deleted. This means that if the multipath device is
+still in use, it will be freed when the last user closes it. If path is added
+to the multipath device before the last user closes it, the deferred remove
+will be canceled.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B partition_delimiter
+If this value is not set, when multipath renames a device, it will act just
+like the kpartx default does, only adding a \fI"p"\fR to names ending in a
+number. If this parameter is set, multipath will act like kpartx does with
+the \fI-p\fR option is used, and always add delimiter.
+.RS
+.TP
+The default is: \fB<unset>\fR
+.RE
+.
+.
+.TP
+.B config_dir
+If set to anything other than "", multipath will search this directory
+alphabetically for file ending in ".conf" and it will read configuration
+information from them, just as if it was in \fI/etc/multipath.conf\fR.
+config_dir must either be "" or a fully qualified directory name.
+.RS
+.TP
+The default is: \fB/etc/multipath/conf.d/\fR
+.RE
+.
+.
+.TP
+.B marginal_path_double_failed_time
+One of the four parameters of supporting path check based on accounting IO
+error such as intermittent error. When a path failed event occurs twice in
+\fImarginal_path_double_failed_time\fR seconds due to an IO error and all the
+other three parameters are set, multipathd will fail the path and enqueue
+this path into a queue of which members are sent a couple of continuous
+direct reading asynchronous IOs at a fixed sample rate of 10HZ to start IO
+error accounting process.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B marginal_path_err_sample_time
+One of the four parameters of supporting path check based on accounting IO
+error such as intermittent error. If it is set to a value no less than 120,
+when a path fail event occurs twice in \fImarginal_path_double_failed_time\fR
+second due to an IO error, multipathd will fail the path and enqueue this
+path into a queue of which members are sent a couple of continuous direct
+reading asynchronous IOs at a fixed sample rate of 10HZ to start the IO
+accounting process for the path will last for
+\fImarginal_path_err_sample_time\fR.
+If the rate of IO error on a particular path is greater than the
+\fImarginal_path_err_rate_threshold\fR, then the path will not reinstate for
+\fImarginal_path_err_recheck_gap_time\fR seconds unless there is only one
+active path. After \fImarginal_path_err_recheck_gap_time\fR expires, the path
+will be requeueed for rechecking. If checking result is good enough, the
+path will be reinstated.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B marginal_path_err_rate_threshold
+The error rate threshold as a permillage (1/1000). One of the four parameters
+of supporting path check based on accounting IO error such as intermittent
+error. Refer to \fImarginal_path_err_sample_time\fR. If the rate of IO errors
+on a particular path is greater than this parameter, then the path will not
+reinstate for \fImarginal_path_err_rate_threshold\fR seconds unless there is
+only one active path.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B marginal_path_err_recheck_gap_time
+One of the four parameters of supporting path check based on accounting IO
+error such as intermittent error. Refer to
+\fImarginal_path_err_sample_time\fR. If this parameter is set to a positive
+value, the failed path of which the IO error rate is larger than
+\fImarginal_path_err_rate_threshold\fR will be kept in failed state for
+\fImarginal_path_err_recheck_gap_time\fR seconds. When
+\fImarginal_path_err_recheck_gap_time\fR seconds expires, the path will be
+requeueed for checking. If checking result is good enough, the path will be
+reinstated, or else it will keep failed.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B delay_watch_checks
+If set to a value greater than 0, multipathd will watch paths that have
+recently become valid for this many checks. If they fail again while they are
+being watched, when they next become valid, they will not be used until they
+have stayed up for \fIdelay_wait_checks\fR checks.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B delay_wait_checks
+If set to a value greater than 0, when a device that has recently come back
+online fails again within \fIdelay_watch_checks\fR checks, the next time it
+comes back online, it will marked and delayed, and not used until it has passed
+\fIdelay_wait_checks\fR checks.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B find_multipaths
+If set to
+.I yes
+, instead of trying to create a multipath device for every non-blacklisted
+path, multipath will only create a device if one of three condidions are
+met.
+.I 1
+There are at least two non-blacklisted paths with the same WWID,
+.I 2
+the user manually forces the creation, by specifying a device with the multipath
+command, or
+.I 3
+a path has the same WWID as a multipath device that was previously created
+while find_multipaths was set (even if that multipath device doesn't currently
+exist).
+Whenever a multipath device is created with find_multipaths set, multipath will
+remember the WWID of the device, so that it will automatically create the
+device again, as soon as it sees a path with that WWID. This should allow most
+users to have multipath automatically choose the correct paths to make into
+multipath devices, without having to edit the blacklist.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B uxsock_timeout
+CLI receive timeout in milliseconds. For larger systems CLI commands
+might timeout before the multipathd lock is released and the CLI command
+can be processed. This will result in errors like
+"timeout receiving packet" to be returned from CLI commands.
+In these cases it is recommended to increase the CLI timeout to avoid
+those issues.
+.RS
+.TP
+The default is: \fB1000\fR
+.RE
+.
+.
+.TP
+.B retrigger_tries
+Sets the number of times multipathd will try to retrigger a uevent to get the
+WWID.
+.RS
+.TP
+The default is: \fB3\fR
+.RE
+.
+.
+.TP
+.B retrigger_delay
+Sets the amount of time, in seconds, to wait between retriggers.
+.RS
+.TP
+The default is: \fB10\fR
+.RE
+.
+.
+.TP
+.B missing_uev_wait_timeout
+Controls how many seconds multipathd will wait, after a new multipath device
+is created, to receive a change event from udev for the device, before
+automatically enabling device reloads. Usually multipathd will delay reloads
+on a device until it receives a change uevent from the initial table load.
+.RS
+.TP
+The default is: \fB30\fR
+.RE
+.
+.
+.TP
+.B skip_kpartx
+If set to
+.I yes
+, kpartx will not automatically create partitions on the device.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B disable_changed_wwids
+If set to \fIyes\fR, multipathd will check the path wwid on change events, and
+if it has changed from the wwid of the multipath device, multipathd will
+disable access to the path until the wwid changes back.
+.RS
+.TP
+The default is: \fBno\fR
+.RE
+.
+.
+.TP
+.B remove_retries
+This sets how may times multipath will retry removing a device that is in-use.
+Between each attempt, multipath will sleep 1 second.
+.RS
+.TP
+The default is: \fB0\fR
+.RE
+.
+.
+.TP
+.B max_sectors_kb
+Sets the max_sectors_kb device parameter on all path devices and the multipath
+device to the specified value.
+.RS
+.TP
+The default is: \fB<device dependent>\fR
+.RE
+.
+.
+.TP
+.B ghost_delay
+Sets the number of seconds that multipath will wait after creating a device
+with only ghost paths before marking it ready for use in systemd. This gives
+the active paths time to appear before the multipath runs the hardware handler
+to switch the ghost paths to active ones. Setting this to \fI0\fR or \fIon\fR
+makes multipath immediately mark a device with only ghost paths as ready.
+.RS
+.TP
+The default is \fBno\fR
+.RE
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "blacklist section"
+.\" ----------------------------------------------------------------------------
+.
+The \fIblacklist\fR section is used to exclude specific device from inclusion in
+the multipath topology. It is most commonly used to exclude local disks or LUNs
+for the array controller.
+.LP
+.
+.
+The following keywords are recognized:
+.TP 17
+.B devnode
+Regular expression of the device nodes to be excluded.
+.RS
+.TP
+The default is: \fB^(ram|raw|loop|fd|md|dm-|sr|scd|st|dcssblk)[0-9]\fR and \fB^(td|hd|vd)[a-z]\fR
+.RE
+.TP
+.B wwid
+The \fIWorld Wide Identification\fR of a device.
+.TP
+.B property
+Regular expression of the udev property to be excluded.
+.TP
+.B device
+Subsection for the device description. This subsection recognizes the
+.B vendor
+and
+.B product
+keywords. For a full description of these keywords please see the
+\fIdevices\fR section description.
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "blacklist_exceptions section"
+.\" ----------------------------------------------------------------------------
+.
+The \fIblacklist_exceptions\fR section is used to revert the actions of the
+\fIblacklist\fR section. For example to include specific device in the
+multipath topology. This allows one to selectively include devices which
+would normally be excluded via the \fIblacklist\fR section.
+.LP
+.
+.
+The following keywords are recognized:
+.TP 17
+.B devnode
+Regular expression of the device nodes to be whitelisted.
+.TP
+.B wwid
+The \fIWorld Wide Identification\fR of a device.
+.TP
+.B property
+Regular expression of the udev property to be whitelisted.
+.RS
+.TP
+The default is: \fB(SCSI_IDENT_|ID_WWN)\fR
+.RE
+.TP
+.B device
+Subsection for the device description. This subsection recognizes the
+.B vendor
+and
+.B product
+keywords. For a full description of these keywords please see the \fIdevices\fR
+section description.
+.LP
+The \fIproperty\fR blacklist and whitelist handling is different from the usual
+handling in the sense that the whitelist \fIhas\fR to be set, otherwise the
+device will be blacklisted. In these cases the message \fIblacklisted, udev
+property missing\fR will be displayed.
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "multipaths section"
+.\" ----------------------------------------------------------------------------
+.
+The only recognized attribute for the \fImultipaths\fR section is the
+\fImultipath\fR subsection.
+.LP
+.
+.
+The \fImultipath\fR subsection recognizes the following attributes:
+.TP 17
+.B wwid
+(Mandatory) Index of the container.
+.TP
+.B alias
+Symbolic name for the multipath map.
+.LP
+.
+.
+The following attributes are optional; if not set the default values
+are taken from the \fIdefaults\fR or \fIdevices\fR section:
+.sp 1
+.PD .1v
+.RS
+.TP 18
+.B path_grouping_policy
+.TP
+.B path_selector
+.TP
+.B prio
+.TP
+.B prio_args
+.TP
+.B failback
+.TP
+.B rr_weight
+.TP
+.B no_path_retry
+.TP
+.B rr_min_io
+.TP
+.B rr_min_io_rq
+.TP
+.B flush_on_last_del
+.TP
+.B features
+.TP
+.B reservation_key
+.TP
+.B user_friendly_names
+.TP
+.B deferred_remove
+.TP
+.B marginal_path_err_sample_time
+.TP
+.B marginal_path_err_rate_threshold
+.TP
+.B marginal_path_err_recheck_gap_time
+.TP
+.B marginal_path_double_failed_time
+.TP
+.B delay_watch_checks
+.TP
+.B delay_wait_checks
+.TP
+.B skip_kpartx
+.TP
+.B max_sectors_kb
+.TP
+.B ghost_delay
+.RE
+.PD
+.LP
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "devices section"
+.\" ----------------------------------------------------------------------------
+.
+The only recognized attribute for the \fIdevices\fR section is the \fIdevice\fR
+subsection.
+.LP
+.
+.
+The \fIdevice\fR subsection recognizes the following attributes:
+.TP
+vendor, product, revision and product_blacklist are POSIX Extended regex.
+.TP 17
+.B vendor
+(Mandatory) Vendor identifier.
+.TP
+.B product
+(Mandatory) Product identifier.
.TP
.B revision
-(Optional) Revision identfier
+Revision identfier.
.TP
.B product_blacklist
-(Optional) Product strings to blacklist for this vendor
+Product strings to blacklist for this vendor.
+.TP
+.B alias_prefix
+The user_friendly_names prefix to use for this
+device type, instead of the default "mpath".
.TP
.B hardware_handler
-(Optional) The hardware handler to use for this device type.
+The hardware handler to use for this device type.
The following hardware handler are implemented:
.RS
.TP 12
-.B 1 emc
-Hardware handler for EMC storage arrays.
+.I 1 emc
+(Hardware-dependent)
+Hardware handler for DGC class arrays as CLARiiON CX/AX and EMC VNX and Unity
+families.
+.TP
+.I 1 rdac
+(Hardware-dependent)
+Hardware handler for LSI/Engenio/NetApp RDAC class as NetApp SANtricity E/EF
+Series, and OEM arrays from IBM DELL SGI STK and SUN.
+.TP
+.I 1 hp_sw
+(Hardware-dependent)
+Hardware handler for HP/COMPAQ/DEC HSG80 and MSA/HSV arrays with
+Active/Standby mode exclusively.
+.TP
+.I 1 alua
+(Hardware-dependent)
+Hardware handler for SCSI-3 ALUA compatible arrays.
+.PP
+The default is: \fB<unset>\fR
+.PP
+\fBImportant Note:\fR Linux kernels 4.3 and newer automatically attach a device
+handler to known devices (which includes all devices supporting SCSI-3 ALUA)
+and disallow changing the handler
+afterwards. Setting \fBhardware_handler\fR for such devices on these kernels
+has no effect.
.RE
+.
+.
.LP
The following attributes are optional; if not set the default values
-are taken from the
-.I defaults
+are taken from the \fIdefaults\fR
section:
.sp 1
.PD .1v
.TP 18
.B path_grouping_policy
.TP
+.B uid_attribute
+.TP
+.B path_selector
+.TP
+.B path_checker
+.TP
+.B prio
+.TP
+.B prio_args
+.TP
+.B features
+.TP
+.B failback
+.TP
+.B rr_weight
+.TP
+.B no_path_retry
+.TP
+.B rr_min_io
+.TP
+.B rr_min_io_rq
+.TP
+.B fast_io_fail_tmo
+.TP
+.B dev_loss_tmo
+.TP
+.B flush_on_last_del
+.TP
+.B retain_attached_hw_handler
+.TP
+.B detect_prio
+.TP
+.B detect_checker
+.TP
+.B deferred_remove
+.TP
+.B marginal_path_err_sample_time
+.TP
+.B marginal_path_err_rate_threshold
+.TP
+.B marginal_path_err_recheck_gap_time
+.TP
+.B marginal_path_double_failed_time
+.TP
+.B delay_watch_checks
+.TP
+.B delay_wait_checks
+.TP
+.B skip_kpartx
+.TP
+.B max_sectors_kb
+.TP
+.B ghost_delay
+.RE
+.PD
+.LP
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "overrides section"
+.\" ----------------------------------------------------------------------------
+.
+The overrides section recognizes the following optional attributes; if not set
+the values are taken from the \fIdevices\fR or \fIdefaults\fR sections:
+.sp 1
+.PD .1v
+.RS
+.TP 18
+.B path_grouping_policy
+.TP
+.B uid_attribute
+.TP
.B getuid_callout
.TP
.B path_selector
.TP
.B path_checker
.TP
+.B alias_prefix
+.TP
.B features
.TP
-.B prio_callout
+.B prio
+.TP
+.B prio_args
.TP
.B failback
.TP
.TP
.B rr_min_io
.TP
+.B rr_min_io_rq
+.TP
+.B flush_on_last_del
+.TP
.B fast_io_fail_tmo
.TP
.B dev_loss_tmo
+.TP
+.B user_friendly_names
+.TP
+.B retain_attached_hw_handler
+.TP
+.B detect_prio
+.TP
+.B detect_checker
+.TP
+.B deferred_remove
+.TP
+.B marginal_path_err_sample_time
+.TP
+.B marginal_path_err_rate_threshold
+.TP
+.B marginal_path_err_recheck_gap_time
+.TP
+.B marginal_path_double_failed_time
+.TP
+.B delay_watch_checks
+.TP
+.B delay_wait_checks
+.TP
+.B skip_kpartx
+.TP
+.B ghost_delay
.RE
.PD
.LP
+.
+.
+.\" ----------------------------------------------------------------------------
+.SH "WWID generation"
+.\" ----------------------------------------------------------------------------
+.
+Multipath uses a \fIWorld Wide Identification\fR (WWID) to determine
+which paths belong to the same device. Each path presenting the same
+WWID is assumed to point to the same device.
+.LP
+The WWID is generated by three methods (in the order of preference):
+.TP 17
+.B getuid_callout
+Use the specified external program; cf \fIgetuid_callout\fR above.
+Care should be taken when using this method; the external program
+needs to be loaded from disk for execution, which might lead to
+deadlock situations in an all-paths-down scenario.
+.TP
+.B uid_attribute
+Use the value of the specified udev attribute; cf \fIuid_attribute\fR
+above. This method is preferred to \fIgetuid_callout\fR as multipath
+does not need to call any external programs here. However, under
+certain circumstances udev might not be able to generate the requested
+variable.
+.TP
+.B vpd_pg83
+If none of the \fIgetuid_callout\fR or \fIuid_attribute\fR parameters
+are present multipath will try to use the sysfs attribute
+\fIvpd_pg83\fR to generate the WWID.
+.
+.
+.\" ----------------------------------------------------------------------------
.SH "KNOWN ISSUES"
-The usage of
-.B queue_if_no_path
-option can lead to
-.B D state
-processes being hung and not killable in situations where all the paths to the LUN go offline.
-It is advisable to use the
-.B no_path_retry
-option instead.
+.\" ----------------------------------------------------------------------------
+.
+The usage of \fIqueue_if_no_path\fR option can lead to \fID state\fR
+processes being hung and not killable in situations where all the paths to the
+LUN go offline. It is advisable to use the \fIno_path_retry\fR option instead.
+.P
+The use of \fIqueue_if_no_path\fR or \fIno_path_retry\fR might lead to a
+deadlock if the \fIdev_loss_tmo\fR setting results in a device being removed
+while I/O is still queued. The multipath daemon will update the \fIdev_loss_tmo\fR
+setting accordingly to avoid this deadlock. Hence if both values are
+specified the order of precedence is \fIno_path_retry, queue_if_no_path, dev_loss_tmo\fR.
+.
+.
+.\" ----------------------------------------------------------------------------
.SH "SEE ALSO"
+.\" ----------------------------------------------------------------------------
+.
.BR udev (8),
-.BR dmsetup (8)
-.BR multipath (8)
-.BR multipathd (8)
+.BR dmsetup (8),
+.BR multipath (8),
+.BR multipathd (8).
+.
+.
+.\" ----------------------------------------------------------------------------
.SH AUTHORS
-.B multipath
-was developed by Christophe Varoqui, <christophe.varoqui@opensvc.com> and others.
+.\" ----------------------------------------------------------------------------
+.
+\fImultipath-tools\fR was developed by Christophe Varoqui, <christophe.varoqui@opensvc.com>
+and others.
+.\" EOF
projects / platform / upstream / multipath-tools.git / blobdiff