€•{      Œsphinx.addnodes”Œdocument”“”)”}”(Œ	rawsource”Œ ”Œchildren”]”(Œtranslations”ŒLanguagesNode”“”)”}”(hhh]”(h Œpending_xref”“”)”}”(hhh]”Œdocutils.nodes”ŒText”“”ŒChinese (Simplified)”…””}”Œparent”hsbaŒ
attributes”}”(Œids”]”Œclasses”]”Œnames”]”Œdupnames”]”Œbackrefs”]”Œ	refdomain”Œstd”Œreftype”Œdoc”Œ	reftarget”Œ&/translations/zh_CN/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuŒtagname”hhhubh)”}”(hhh]”hŒChinese (Traditional)”…””}”hh2sbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/zh_TW/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒItalian”…””}”hhFsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/it_IT/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒJapanese”…””}”hhZsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/ja_JP/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒKorean”…””}”hhnsbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/ko_KR/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒPortuguese (Brazilian)”…””}”hh‚sbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/pt_BR/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubh)”}”(hhh]”hŒSpanish”…””}”hh–sbah}”(h]”h ]”h"]”h$]”h&]”Œ	refdomain”h)Œreftype”h+Œ	reftarget”Œ&/translations/sp_SP/filesystems/zonefs”Œmodname”NŒ	classname”NŒrefexplicit”ˆuh1hhhubeh}”(h]”h ]”h"]”h$]”h&]”Œcurrent_language”ŒEnglish”uh1h
hhŒ	_document”hŒsource”NŒline”NubhŒcomment”“”)”}”(hŒ SPDX-License-Identifier: GPL-2.0”h]”hŒ SPDX-License-Identifier: GPL-2.0”…””}”hh·sbah}”(h]”h ]”h"]”h$]”h&]”Œ	xml:space”Œpreserve”uh1hµhhh²hh³Œ@/var/lib/git/docbuild/linux/Documentation/filesystems/zonefs.rst”h´KubhŒsection”“”)”}”(hhh]”(hŒtitle”“”)”}”(hŒ0ZoneFS - Zone filesystem for Zoned block devices”h]”hŒ0ZoneFS - Zone filesystem for Zoned block devices”…””}”(hhÏh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhhÊh²hh³hÇh´KubhÉ)”}”(hhh]”(hÎ)”}”(hŒIntroduction”h]”hŒIntroduction”…””}”(hhàh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhhÝh²hh³hÇh´KubhŒ	paragraph”“”)”}”(hX   zonefs is a very simple file system exposing each zone of a zoned block device
as a file. Unlike a regular POSIX-compliant file system with native zoned block
device support (e.g. f2fs), zonefs does not hide the sequential write
constraint of zoned block devices to the user. Files representing sequential
write zones of the device must be written sequentially starting from the end
of the file (append only writes).”h]”hX   zonefs is a very simple file system exposing each zone of a zoned block device
as a file. Unlike a regular POSIX-compliant file system with native zoned block
device support (e.g. f2fs), zonefs does not hide the sequential write
constraint of zoned block devices to the user. Files representing sequential
write zones of the device must be written sequentially starting from the end
of the file (append only writes).”…””}”(hhðh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K
hhÝh²hubhï)”}”(hXz  As such, zonefs is in essence closer to a raw block device access interface
than to a full-featured POSIX file system. The goal of zonefs is to simplify
the implementation of zoned block device support in applications by replacing
raw block device file accesses with a richer file API, avoiding relying on
direct block device file ioctls which may be more obscure to developers. One
example of this approach is the implementation of LSM (log-structured merge)
tree structures (such as used in RocksDB and LevelDB) on zoned block devices
by allowing SSTables to be stored in a zone file similarly to a regular file
system rather than as a range of sectors of the entire disk. The introduction
of the higher level construct "one file is one zone" can help reducing the
amount of changes needed in the application as well as introducing support for
different application programming languages.”h]”hX~  As such, zonefs is in essence closer to a raw block device access interface
than to a full-featured POSIX file system. The goal of zonefs is to simplify
the implementation of zoned block device support in applications by replacing
raw block device file accesses with a richer file API, avoiding relying on
direct block device file ioctls which may be more obscure to developers. One
example of this approach is the implementation of LSM (log-structured merge)
tree structures (such as used in RocksDB and LevelDB) on zoned block devices
by allowing SSTables to be stored in a zone file similarly to a regular file
system rather than as a range of sectors of the entire disk. The introduction
of the higher level construct â€œone file is one zoneâ€ can help reducing the
amount of changes needed in the application as well as introducing support for
different application programming languages.”…””}”(hhþh²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KhhÝh²hubhÉ)”}”(hhh]”(hÎ)”}”(hŒZoned block devices”h]”hŒZoned block devices”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj  h²hh³hÇh´Kubhï)”}”(hŒèZoned storage devices belong to a class of storage devices with an address
space that is divided into zones. A zone is a group of consecutive LBAs and all
zones are contiguous (there are no LBA gaps). Zones may have different types.”h]”hŒèZoned storage devices belong to a class of storage devices with an address
space that is divided into zones. A zone is a group of consecutive LBAs and all
zones are contiguous (there are no LBA gaps). Zones may have different types.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K!hj  h²hubhŒbullet_list”“”)”}”(hhh]”(hŒ	list_item”“”)”}”(hŒ«Conventional zones: there are no access constraints to LBAs belonging to
conventional zones. Any read or write access can be executed, similarly to a
regular block device.”h]”hï)”}”(hŒ«Conventional zones: there are no access constraints to LBAs belonging to
conventional zones. Any read or write access can be executed, similarly to a
regular block device.”h]”hŒ«Conventional zones: there are no access constraints to LBAs belonging to
conventional zones. Any read or write access can be executed, similarly to a
regular block device.”…””}”(hj6  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K%hj2  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj-  h²hh³hÇh´Nubj1  )”}”(hX   Sequential zones: these zones accept random reads but must be written
sequentially. Each sequential zone has a write pointer maintained by the
device that keeps track of the mandatory start LBA position of the next write
to the device. As a result of this write constraint, LBAs in a sequential zone
cannot be overwritten. Sequential zones must first be erased using a special
command (zone reset) before rewriting.
”h]”hï)”}”(hXŸ  Sequential zones: these zones accept random reads but must be written
sequentially. Each sequential zone has a write pointer maintained by the
device that keeps track of the mandatory start LBA position of the next write
to the device. As a result of this write constraint, LBAs in a sequential zone
cannot be overwritten. Sequential zones must first be erased using a special
command (zone reset) before rewriting.”h]”hXŸ  Sequential zones: these zones accept random reads but must be written
sequentially. Each sequential zone has a write pointer maintained by the
device that keeps track of the mandatory start LBA position of the next write
to the device. As a result of this write constraint, LBAs in a sequential zone
cannot be overwritten. Sequential zones must first be erased using a special
command (zone reset) before rewriting.”…””}”(hjN  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K(hjJ  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj-  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”Œbullet”Œ*”uh1j+  h³hÇh´K%hj  h²hubhï)”}”(hX   Zoned storage devices can be implemented using various recording and media
technologies. The most common form of zoned storage today uses the SCSI Zoned
Block Commands (ZBC) and Zoned ATA Commands (ZAC) interfaces on Shingled
Magnetic Recording (SMR) HDDs.”h]”hX   Zoned storage devices can be implemented using various recording and media
technologies. The most common form of zoned storage today uses the SCSI Zoned
Block Commands (ZBC) and Zoned ATA Commands (ZAC) interfaces on Shingled
Magnetic Recording (SMR) HDDs.”…””}”(hjj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K/hj  h²hubhï)”}”(hX4  Solid State Disks (SSD) storage devices can also implement a zoned interface
to, for instance, reduce internal write amplification due to garbage collection.
The NVMe Zoned NameSpace (ZNS) is a technical proposal of the NVMe standard
committee aiming at adding a zoned storage interface to the NVMe protocol.”h]”hX4  Solid State Disks (SSD) storage devices can also implement a zoned interface
to, for instance, reduce internal write amplification due to garbage collection.
The NVMe Zoned NameSpace (ZNS) is a technical proposal of the NVMe standard
committee aiming at adding a zoned storage interface to the NVMe protocol.”…””}”(hjx  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K4hj  h²hubeh}”(h]”Œzoned-block-devices”ah ]”h"]”Œzoned block devices”ah$]”h&]”uh1hÈhhÝh²hh³hÇh´Kubeh}”(h]”Œintroduction”ah ]”h"]”Œintroduction”ah$]”h&]”uh1hÈhhÊh²hh³hÇh´KubhÉ)”}”(hhh]”(hÎ)”}”(hŒZonefs Overview”h]”hŒZonefs Overview”…””}”(hj™  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj–  h²hh³hÇh´K:ubhï)”}”(hX:  Zonefs exposes the zones of a zoned block device as files. The files
representing zones are grouped by zone type, which are themselves represented
by sub-directories. This file structure is built entirely using zone information
provided by the device and so does not require any complex on-disk metadata
structure.”h]”hX:  Zonefs exposes the zones of a zoned block device as files. The files
representing zones are grouped by zone type, which are themselves represented
by sub-directories. This file structure is built entirely using zone information
provided by the device and so does not require any complex on-disk metadata
structure.”…””}”(hj§  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K<hj–  h²hubhÉ)”}”(hhh]”(hÎ)”}”(hŒOn-disk metadata”h]”hŒOn-disk metadata”…””}”(hj¸  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjµ  h²hh³hÇh´KCubhï)”}”(hX  zonefs on-disk metadata is reduced to an immutable super block which
persistently stores a magic number and optional feature flags and values. On
mount, zonefs uses blkdev_report_zones() to obtain the device zone configuration
and populates the mount point with a static file tree solely based on this
information. File sizes come from the device zone type and write pointer
position managed by the device itself.”h]”hX  zonefs on-disk metadata is reduced to an immutable super block which
persistently stores a magic number and optional feature flags and values. On
mount, zonefs uses blkdev_report_zones() to obtain the device zone configuration
and populates the mount point with a static file tree solely based on this
information. File sizes come from the device zone type and write pointer
position managed by the device itself.”…””}”(hjÆ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KEhjµ  h²hubhï)”}”(hXj  The super block is always written on disk at sector 0. The first zone of the
device storing the super block is never exposed as a zone file by zonefs. If
the zone containing the super block is a sequential zone, the mkzonefs format
tool always "finishes" the zone, that is, it transitions the zone to a full
state to make it read-only, preventing any data write.”h]”hXn  The super block is always written on disk at sector 0. The first zone of the
device storing the super block is never exposed as a zone file by zonefs. If
the zone containing the super block is a sequential zone, the mkzonefs format
tool always â€œfinishesâ€ the zone, that is, it transitions the zone to a full
state to make it read-only, preventing any data write.”…””}”(hjÔ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KLhjµ  h²hubeh}”(h]”Œon-disk-metadata”ah ]”h"]”Œon-disk metadata”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´KCubhÉ)”}”(hhh]”(hÎ)”}”(hŒZone type sub-directories”h]”hŒZone type sub-directories”…””}”(hjí  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjê  h²hh³hÇh´KSubhï)”}”(hŒ{Files representing zones of the same type are grouped together under the same
sub-directory automatically created on mount.”h]”hŒ{Files representing zones of the same type are grouped together under the same
sub-directory automatically created on mount.”…””}”(hjû  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KUhjê  h²hubhï)”}”(hXl  For conventional zones, the sub-directory "cnv" is used. This directory is
however created if and only if the device has usable conventional zones. If
the device only has a single conventional zone at sector 0, the zone will not
be exposed as a file as it will be used to store the zonefs super block. For
such devices, the "cnv" sub-directory will not be created.”h]”hXt  For conventional zones, the sub-directory â€œcnvâ€ is used. This directory is
however created if and only if the device has usable conventional zones. If
the device only has a single conventional zone at sector 0, the zone will not
be exposed as a file as it will be used to store the zonefs super block. For
such devices, the â€œcnvâ€ sub-directory will not be created.”…””}”(hj	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KXhjê  h²hubhï)”}”(hŒ<For sequential write zones, the sub-directory "seq" is used.”h]”hŒ@For sequential write zones, the sub-directory â€œseqâ€ is used.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K^hjê  h²hubhï)”}”(hŒ¬These two directories are the only directories that exist in zonefs. Users
cannot create other directories and cannot rename nor delete the "cnv" and
"seq" sub-directories.”h]”hŒ´These two directories are the only directories that exist in zonefs. Users
cannot create other directories and cannot rename nor delete the â€œcnvâ€ and
â€œseqâ€ sub-directories.”…””}”(hj%  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K`hjê  h²hubhï)”}”(hŒ¸The size of the directories indicated by the st_size field of struct stat,
obtained with the stat() or fstat() system calls, indicates the number of files
existing under the directory.”h]”hŒ¸The size of the directories indicated by the st_size field of struct stat,
obtained with the stat() or fstat() system calls, indicates the number of files
existing under the directory.”…””}”(hj3  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kdhjê  h²hubeh}”(h]”Œzone-type-sub-directories”ah ]”h"]”Œzone type sub-directories”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´KSubhÉ)”}”(hhh]”(hÎ)”}”(hŒ
Zone files”h]”hŒ
Zone files”…””}”(hjL  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjI  h²hh³hÇh´Kiubhï)”}”(hX  Zone files are named using the number of the zone they represent within the set
of zones of a particular type. That is, both the "cnv" and "seq" directories
contain files named "0", "1", "2", ... The file numbers also represent
increasing zone start sector on the device.”h]”hX#  Zone files are named using the number of the zone they represent within the set
of zones of a particular type. That is, both the â€œcnvâ€ and â€œseqâ€ directories
contain files named â€œ0â€, â€œ1â€, â€œ2â€, ... The file numbers also represent
increasing zone start sector on the device.”…””}”(hjZ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KkhjI  h²hubhï)”}”(hŒÄAll read and write operations to zone files are not allowed beyond the file
maximum size, that is, beyond the zone capacity. Any access exceeding the zone
capacity is failed with the -EFBIG error.”h]”hŒÄAll read and write operations to zone files are not allowed beyond the file
maximum size, that is, beyond the zone capacity. Any access exceeding the zone
capacity is failed with the -EFBIG error.”…””}”(hjh  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KphjI  h²hubhï)”}”(hŒdCreating, deleting, renaming or modifying any attribute of files and
sub-directories is not allowed.”h]”hŒdCreating, deleting, renaming or modifying any attribute of files and
sub-directories is not allowed.”…””}”(hjv  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KthjI  h²hubhï)”}”(hŒ“The number of blocks of a file as reported by stat() and fstat() indicates the
capacity of the zone file, or in other words, the maximum file size.”h]”hŒ“The number of blocks of a file as reported by stat() and fstat() indicates the
capacity of the zone file, or in other words, the maximum file size.”…””}”(hj„  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KwhjI  h²hubeh}”(h]”Œ
zone-files”ah ]”h"]”Œ
zone files”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´KiubhÉ)”}”(hhh]”(hÎ)”}”(hŒConventional zone files”h]”hŒConventional zone files”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjš  h²hh³hÇh´K{ubhï)”}”(hŒThe size of conventional zone files is fixed to the size of the zone they
represent. Conventional zone files cannot be truncated.”h]”hŒThe size of conventional zone files is fixed to the size of the zone they
represent. Conventional zone files cannot be truncated.”…””}”(hj«  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K}hjš  h²hubhï)”}”(hŒáThese files can be randomly read and written using any type of I/O operation:
buffered I/Os, direct I/Os, memory mapped I/Os (mmap), etc. There are no I/O
constraint for these files beyond the file size limit mentioned above.”h]”hŒáThese files can be randomly read and written using any type of I/O operation:
buffered I/Os, direct I/Os, memory mapped I/Os (mmap), etc. There are no I/O
constraint for these files beyond the file size limit mentioned above.”…””}”(hj¹  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K€hjš  h²hubeh}”(h]”Œconventional-zone-files”ah ]”h"]”Œconventional zone files”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´K{ubhÉ)”}”(hhh]”(hÎ)”}”(hŒSequential zone files”h]”hŒSequential zone files”…””}”(hjÒ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjÏ  h²hh³hÇh´K…ubhï)”}”(hŒ™The size of sequential zone files grouped in the "seq" sub-directory represents
the file's zone write pointer position relative to the zone start sector.”h]”hŒŸThe size of sequential zone files grouped in the â€œseqâ€ sub-directory represents
the fileâ€™s zone write pointer position relative to the zone start sector.”…””}”(hjà  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K‡hjÏ  h²hubhï)”}”(hX{  Sequential zone files can only be written sequentially, starting from the file
end, that is, write operations can only be append writes. Zonefs makes no
attempt at accepting random writes and will fail any write request that has a
start offset not corresponding to the end of the file, or to the end of the last
write issued and still in-flight (for asynchronous I/O operations).”h]”hX{  Sequential zone files can only be written sequentially, starting from the file
end, that is, write operations can only be append writes. Zonefs makes no
attempt at accepting random writes and will fail any write request that has a
start offset not corresponding to the end of the file, or to the end of the last
write issued and still in-flight (for asynchronous I/O operations).”…””}”(hjî  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KŠhjÏ  h²hubhï)”}”(hXM  Since dirty page writeback by the page cache does not guarantee a sequential
write pattern, zonefs prevents buffered writes and writeable shared mappings
on sequential files. Only direct I/O writes are accepted for these files.
zonefs relies on the sequential delivery of write I/O requests to the device
implemented by the block layer elevator. An elevator implementing the sequential
write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature)
must be used. This type of elevator (e.g. mq-deadline) is set by default
for zoned block devices on device initialization.”h]”hXM  Since dirty page writeback by the page cache does not guarantee a sequential
write pattern, zonefs prevents buffered writes and writeable shared mappings
on sequential files. Only direct I/O writes are accepted for these files.
zonefs relies on the sequential delivery of write I/O requests to the device
implemented by the block layer elevator. An elevator implementing the sequential
write feature for zoned block device (ELEVATOR_F_ZBD_SEQ_WRITE elevator feature)
must be used. This type of elevator (e.g. mq-deadline) is set by default
for zoned block devices on device initialization.”…””}”(hjü  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KhjÏ  h²hubhï)”}”(hŒ¥There are no restrictions on the type of I/O used for read operations in
sequential zone files. Buffered I/Os, direct I/Os and shared read mappings are
all accepted.”h]”hŒ¥There are no restrictions on the type of I/O used for read operations in
sequential zone files. Buffered I/Os, direct I/Os and shared read mappings are
all accepted.”…””}”(hj
  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K™hjÏ  h²hubhï)”}”(hX  Truncating sequential zone files is allowed only down to 0, in which case, the
zone is reset to rewind the file zone write pointer position to the start of
the zone, or up to the zone capacity, in which case the file's zone is
transitioned to the FULL state (finish zone operation).”h]”hX  Truncating sequential zone files is allowed only down to 0, in which case, the
zone is reset to rewind the file zone write pointer position to the start of
the zone, or up to the zone capacity, in which case the fileâ€™s zone is
transitioned to the FULL state (finish zone operation).”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KhjÏ  h²hubeh}”(h]”Œsequential-zone-files”ah ]”h"]”Œsequential zone files”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´K…ubhÉ)”}”(hhh]”(hÎ)”}”(hŒFormat options”h]”hŒFormat options”…””}”(hj1  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj.  h²hh³hÇh´K£ubhï)”}”(hŒBSeveral optional features of zonefs can be enabled at format time.”h]”hŒBSeveral optional features of zonefs can be enabled at format time.”…””}”(hj?  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K¥hj.  h²hubj,  )”}”(hhh]”(j1  )”}”(hŒœConventional zone aggregation: ranges of contiguous conventional zones can be
aggregated into a single larger file instead of the default one file per zone.”h]”hï)”}”(hŒœConventional zone aggregation: ranges of contiguous conventional zones can be
aggregated into a single larger file instead of the default one file per zone.”h]”hŒœConventional zone aggregation: ranges of contiguous conventional zones can be
aggregated into a single larger file instead of the default one file per zone.”…””}”(hjT  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K§hjP  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjM  h²hh³hÇh´Nubj1  )”}”(hŒsFile ownership: The owner UID and GID of zone files is by default 0 (root)
but can be changed to any valid UID/GID.”h]”hï)”}”(hŒsFile ownership: The owner UID and GID of zone files is by default 0 (root)
but can be changed to any valid UID/GID.”h]”hŒsFile ownership: The owner UID and GID of zone files is by default 0 (root)
but can be changed to any valid UID/GID.”…””}”(hjl  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K©hjh  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjM  h²hh³hÇh´Nubj1  )”}”(hŒLFile access permissions: the default 640 access permissions can be changed.
”h]”hï)”}”(hŒKFile access permissions: the default 640 access permissions can be changed.”h]”hŒKFile access permissions: the default 640 access permissions can be changed.”…””}”(hj„  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K«hj€  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjM  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´K§hj.  h²hubeh}”(h]”Œformat-options”ah ]”h"]”Œformat options”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´K£ubhÉ)”}”(hhh]”(hÎ)”}”(hŒIO error handling”h]”hŒIO error handling”…””}”(hj©  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj¦  h²hh³hÇh´K®ubhï)”}”(hX  Zoned block devices may fail I/O requests for reasons similar to regular block
devices, e.g. due to bad sectors. However, in addition to such known I/O
failure pattern, the standards governing zoned block devices behavior define
additional conditions that result in I/O errors.”h]”hX  Zoned block devices may fail I/O requests for reasons similar to regular block
devices, e.g. due to bad sectors. However, in addition to such known I/O
failure pattern, the standards governing zoned block devices behavior define
additional conditions that result in I/O errors.”…””}”(hj·  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K°hj¦  h²hubj,  )”}”(hhh]”(j1  )”}”(hX&  A zone may transition to the read-only condition (BLK_ZONE_COND_READONLY):
While the data already written in the zone is still readable, the zone can
no longer be written. No user action on the zone (zone management command or
read/write access) can change the zone condition back to a normal read/write
state. While the reasons for the device to transition a zone to read-only
state are not defined by the standards, a typical cause for such transition
would be a defective write head on an HDD (all zones under this head are
changed to read-only).
”h]”hï)”}”(hX%  A zone may transition to the read-only condition (BLK_ZONE_COND_READONLY):
While the data already written in the zone is still readable, the zone can
no longer be written. No user action on the zone (zone management command or
read/write access) can change the zone condition back to a normal read/write
state. While the reasons for the device to transition a zone to read-only
state are not defined by the standards, a typical cause for such transition
would be a defective write head on an HDD (all zones under this head are
changed to read-only).”h]”hX%  A zone may transition to the read-only condition (BLK_ZONE_COND_READONLY):
While the data already written in the zone is still readable, the zone can
no longer be written. No user action on the zone (zone management command or
read/write access) can change the zone condition back to a normal read/write
state. While the reasons for the device to transition a zone to read-only
state are not defined by the standards, a typical cause for such transition
would be a defective write head on an HDD (all zones under this head are
changed to read-only).”…””}”(hjÌ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KµhjÈ  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hXÍ  A zone may transition to the offline condition (BLK_ZONE_COND_OFFLINE):
An offline zone cannot be read nor written. No user action can transition an
offline zone back to an operational good state. Similarly to zone read-only
transitions, the reasons for a drive to transition a zone to the offline
condition are undefined. A typical cause would be a defective read-write head
on an HDD causing all zones on the platter under the broken head to be
inaccessible.
”h]”hï)”}”(hXÌ  A zone may transition to the offline condition (BLK_ZONE_COND_OFFLINE):
An offline zone cannot be read nor written. No user action can transition an
offline zone back to an operational good state. Similarly to zone read-only
transitions, the reasons for a drive to transition a zone to the offline
condition are undefined. A typical cause would be a defective read-write head
on an HDD causing all zones on the platter under the broken head to be
inaccessible.”h]”hXÌ  A zone may transition to the offline condition (BLK_ZONE_COND_OFFLINE):
An offline zone cannot be read nor written. No user action can transition an
offline zone back to an operational good state. Similarly to zone read-only
transitions, the reasons for a drive to transition a zone to the offline
condition are undefined. A typical cause would be a defective read-write head
on an HDD causing all zones on the platter under the broken head to be
inaccessible.”…””}”(hjä  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K¾hjà  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hXp  Unaligned write errors: These errors result from the host issuing write
requests with a start sector that does not correspond to a zone write pointer
position when the write request is executed by the device. Even though zonefs
enforces sequential file write for sequential zones, unaligned write errors
may still happen in the case of a partial failure of a very large direct I/O
operation split into multiple BIOs/requests or asynchronous I/O operations.
If one of the write request within the set of sequential write requests
issued to the device fails, all write requests queued after it will
become unaligned and fail.
”h]”hï)”}”(hXo  Unaligned write errors: These errors result from the host issuing write
requests with a start sector that does not correspond to a zone write pointer
position when the write request is executed by the device. Even though zonefs
enforces sequential file write for sequential zones, unaligned write errors
may still happen in the case of a partial failure of a very large direct I/O
operation split into multiple BIOs/requests or asynchronous I/O operations.
If one of the write request within the set of sequential write requests
issued to the device fails, all write requests queued after it will
become unaligned and fail.”h]”hXo  Unaligned write errors: These errors result from the host issuing write
requests with a start sector that does not correspond to a zone write pointer
position when the write request is executed by the device. Even though zonefs
enforces sequential file write for sequential zones, unaligned write errors
may still happen in the case of a partial failure of a very large direct I/O
operation split into multiple BIOs/requests or asynchronous I/O operations.
If one of the write request within the set of sequential write requests
issued to the device fails, all write requests queued after it will
become unaligned and fail.”…””}”(hjü  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KÆhjø  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hX¾  Delayed write errors: similarly to regular block devices, if the device side
write cache is enabled, write errors may occur in ranges of previously
completed writes when the device write cache is flushed, e.g. on fsync().
Similarly to the previous immediate unaligned write error case, delayed write
errors can propagate through a stream of cached sequential data for a zone
causing all data to be dropped after the sector that caused the error.
”h]”hï)”}”(hX½  Delayed write errors: similarly to regular block devices, if the device side
write cache is enabled, write errors may occur in ranges of previously
completed writes when the device write cache is flushed, e.g. on fsync().
Similarly to the previous immediate unaligned write error case, delayed write
errors can propagate through a stream of cached sequential data for a zone
causing all data to be dropped after the sector that caused the error.”h]”hX½  Delayed write errors: similarly to regular block devices, if the device side
write cache is enabled, write errors may occur in ranges of previously
completed writes when the device write cache is flushed, e.g. on fsync().
Similarly to the previous immediate unaligned write error case, delayed write
errors can propagate through a stream of cached sequential data for a zone
causing all data to be dropped after the sector that caused the error.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KÐhj  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´Kµhj¦  h²hubhï)”}”(hXM  All I/O errors detected by zonefs are notified to the user with an error code
return for the system call that triggered or detected the error. The recovery
actions taken by zonefs in response to I/O errors depend on the I/O type (read
vs write) and on the reason for the error (bad sector, unaligned writes or zone
condition change).”h]”hXM  All I/O errors detected by zonefs are notified to the user with an error code
return for the system call that triggered or detected the error. The recovery
actions taken by zonefs in response to I/O errors depend on the I/O type (read
vs write) and on the reason for the error (bad sector, unaligned writes or zone
condition change).”…””}”(hj.  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´K×hj¦  h²hubj,  )”}”(hhh]”(j1  )”}”(hX/  For read I/O errors, zonefs does not execute any particular recovery action,
but only if the file zone is still in a good condition and there is no
inconsistency between the file inode size and its zone write pointer position.
If a problem is detected, I/O error recovery is executed (see below table).
”h]”hï)”}”(hX.  For read I/O errors, zonefs does not execute any particular recovery action,
but only if the file zone is still in a good condition and there is no
inconsistency between the file inode size and its zone write pointer position.
If a problem is detected, I/O error recovery is executed (see below table).”h]”hX.  For read I/O errors, zonefs does not execute any particular recovery action,
but only if the file zone is still in a good condition and there is no
inconsistency between the file inode size and its zone write pointer position.
If a problem is detected, I/O error recovery is executed (see below table).”…””}”(hjC  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KÝhj?  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj<  h²hh³hÇh´Nubj1  )”}”(hŒDFor write I/O errors, zonefs I/O error recovery is always executed.
”h]”hï)”}”(hŒCFor write I/O errors, zonefs I/O error recovery is always executed.”h]”hŒCFor write I/O errors, zonefs I/O error recovery is always executed.”…””}”(hj[  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´KâhjW  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj<  h²hh³hÇh´Nubj1  )”}”(hŒ`A zone condition change to read-only or offline also always triggers zonefs
I/O error recovery.
”h]”hï)”}”(hŒ_A zone condition change to read-only or offline also always triggers zonefs
I/O error recovery.”h]”hŒ_A zone condition change to read-only or offline also always triggers zonefs
I/O error recovery.”…””}”(hjs  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kähjo  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj<  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´KÝhj¦  h²hubhï)”}”(hŒUZonefs minimal I/O error recovery may change a file size and file access
permissions.”h]”hŒUZonefs minimal I/O error recovery may change a file size and file access
permissions.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kçhj¦  h²hubj,  )”}”(hhh]”(j1  )”}”(hX‰  File size changes:
Immediate or delayed write errors in a sequential zone file may cause the file
inode size to be inconsistent with the amount of data successfully written in
the file zone. For instance, the partial failure of a multi-BIO large write
operation will cause the zone write pointer to advance partially, even though
the entire write operation will be reported as failed to the user. In such
case, the file inode size must be advanced to reflect the zone write pointer
change and eventually allow the user to restart writing at the end of the
file.
A file size may also be reduced to reflect a delayed write error detected on
fsync(): in this case, the amount of data effectively written in the zone may
be less than originally indicated by the file inode size. After such I/O
error, zonefs always fixes the file inode size to reflect the amount of data
persistently stored in the file zone.
”h]”hï)”}”(hXˆ  File size changes:
Immediate or delayed write errors in a sequential zone file may cause the file
inode size to be inconsistent with the amount of data successfully written in
the file zone. For instance, the partial failure of a multi-BIO large write
operation will cause the zone write pointer to advance partially, even though
the entire write operation will be reported as failed to the user. In such
case, the file inode size must be advanced to reflect the zone write pointer
change and eventually allow the user to restart writing at the end of the
file.
A file size may also be reduced to reflect a delayed write error detected on
fsync(): in this case, the amount of data effectively written in the zone may
be less than originally indicated by the file inode size. After such I/O
error, zonefs always fixes the file inode size to reflect the amount of data
persistently stored in the file zone.”h]”hXˆ  File size changes:
Immediate or delayed write errors in a sequential zone file may cause the file
inode size to be inconsistent with the amount of data successfully written in
the file zone. For instance, the partial failure of a multi-BIO large write
operation will cause the zone write pointer to advance partially, even though
the entire write operation will be reported as failed to the user. In such
case, the file inode size must be advanced to reflect the zone write pointer
change and eventually allow the user to restart writing at the end of the
file.
A file size may also be reduced to reflect a delayed write error detected on
fsync(): in this case, the amount of data effectively written in the zone may
be less than originally indicated by the file inode size. After such I/O
error, zonefs always fixes the file inode size to reflect the amount of data
persistently stored in the file zone.”…””}”(hj¢  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kêhjž  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj›  h²hh³hÇh´Nubj1  )”}”(hX*  Access permission changes:
A zone condition change to read-only is indicated with a change in the file
access permissions to render the file read-only. This disables changes to the
file attributes and data modification. For offline zones, all permissions
(read and write) to the file are disabled.
”h]”hï)”}”(hX)  Access permission changes:
A zone condition change to read-only is indicated with a change in the file
access permissions to render the file read-only. This disables changes to the
file attributes and data modification. For offline zones, all permissions
(read and write) to the file are disabled.”h]”hX)  Access permission changes:
A zone condition change to read-only is indicated with a change in the file
access permissions to render the file read-only. This disables changes to the
file attributes and data modification. For offline zones, all permissions
(read and write) to the file are disabled.”…””}”(hjº  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kùhj¶  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj›  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´Kêhj¦  h²hubhï)”}”(hŒóFurther action taken by zonefs I/O error recovery can be controlled by the user
with the "errors=xxx" mount option. The table below summarizes the result of
zonefs I/O error processing depending on the mount option and on the zone
conditions::”h]”hŒöFurther action taken by zonefs I/O error recovery can be controlled by the user
with the â€œerrors=xxxâ€ mount option. The table below summarizes the result of
zonefs I/O error processing depending on the mount option and on the zone
conditions:”…””}”(hjÔ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Kÿhj¦  h²hubhŒliteral_block”“”)”}”(hX  +--------------+-----------+-----------------------------------------+
|              |           |            Post error state             |
| "errors=xxx" |  device   |                 access permissions      |
|    mount     |   zone    | file         file          device zone  |
|    option    | condition | size     read    write    read    write |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     no       yes     yes   |
| remount-ro   | read-only | as is    yes     no       yes     no    |
| (default)    | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     no       yes     yes   |
| zone-ro      | read-only | as is    yes     no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      |   0      no      no       yes     yes   |
| zone-offline | read-only |   0      no      no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     yes      yes     yes   |
| repair       | read-only | as is    yes     no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+”h]”hX  +--------------+-----------+-----------------------------------------+
|              |           |            Post error state             |
| "errors=xxx" |  device   |                 access permissions      |
|    mount     |   zone    | file         file          device zone  |
|    option    | condition | size     read    write    read    write |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     no       yes     yes   |
| remount-ro   | read-only | as is    yes     no       yes     no    |
| (default)    | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     no       yes     yes   |
| zone-ro      | read-only | as is    yes     no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      |   0      no      no       yes     yes   |
| zone-offline | read-only |   0      no      no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+
|              | good      | fixed    yes     yes      yes     yes   |
| repair       | read-only | as is    yes     no       yes     no    |
|              | offline   |   0      no      no       no      no    |
+--------------+-----------+-----------------------------------------+”…””}”hjä  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´Mhj¦  h²hubhï)”}”(hŒFurther notes:”h]”hŒFurther notes:”…””}”(hjò  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mhj¦  h²hubj,  )”}”(hhh]”(j1  )”}”(hŒƒThe "errors=remount-ro" mount option is the default behavior of zonefs I/O
error processing if no errors mount option is specified.”h]”hï)”}”(hŒƒThe "errors=remount-ro" mount option is the default behavior of zonefs I/O
error processing if no errors mount option is specified.”h]”hŒ‡The â€œerrors=remount-roâ€ mount option is the default behavior of zonefs I/O
error processing if no errors mount option is specified.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mhj  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubj1  )”}”(hŒŸWith the "errors=remount-ro" mount option, the change of the file access
permissions to read-only applies to all files. The file system is remounted
read-only.”h]”hï)”}”(hŒŸWith the "errors=remount-ro" mount option, the change of the file access
permissions to read-only applies to all files. The file system is remounted
read-only.”h]”hŒ£With the â€œerrors=remount-roâ€ mount option, the change of the file access
permissions to read-only applies to all files. The file system is remounted
read-only.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mhj  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubj1  )”}”(hŒðAccess permission and file size changes due to the device transitioning zones
to the offline condition are permanent. Remounting or reformatting the device
with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good
state.”h]”hï)”}”(hŒðAccess permission and file size changes due to the device transitioning zones
to the offline condition are permanent. Remounting or reformatting the device
with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good
state.”h]”hŒðAccess permission and file size changes due to the device transitioning zones
to the offline condition are permanent. Remounting or reformatting the device
with mkfs.zonefs (mkzonefs) will not change back offline zone files to a good
state.”…””}”(hj7  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M"hj3  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubj1  )”}”(hŒÇFile access permission changes to read-only due to the device transitioning
zones to the read-only condition are permanent. Remounting or reformatting
the device will not re-enable file write access.”h]”hï)”}”(hŒÇFile access permission changes to read-only due to the device transitioning
zones to the read-only condition are permanent. Remounting or reformatting
the device will not re-enable file write access.”h]”hŒÇFile access permission changes to read-only due to the device transitioning
zones to the read-only condition are permanent. Remounting or reformatting
the device will not re-enable file write access.”…””}”(hjO  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M&hjK  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubj1  )”}”(hX  File access permission changes implied by the remount-ro, zone-ro and
zone-offline mount options are temporary for zones in a good condition.
Unmounting and remounting the file system will restore the previous default
(format time values) access rights to the files affected.”h]”hï)”}”(hX  File access permission changes implied by the remount-ro, zone-ro and
zone-offline mount options are temporary for zones in a good condition.
Unmounting and remounting the file system will restore the previous default
(format time values) access rights to the files affected.”h]”hX  File access permission changes implied by the remount-ro, zone-ro and
zone-offline mount options are temporary for zones in a good condition.
Unmounting and remounting the file system will restore the previous default
(format time values) access rights to the files affected.”…””}”(hjg  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M)hjc  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubj1  )”}”(hX  The repair mount option triggers only the minimal set of I/O error recovery
actions, that is, file size fixes for zones in a good condition. Zones
indicated as being read-only or offline by the device still imply changes to
the zone file access permissions as noted in the table above.
”h]”hï)”}”(hX  The repair mount option triggers only the minimal set of I/O error recovery
actions, that is, file size fixes for zones in a good condition. Zones
indicated as being read-only or offline by the device still imply changes to
the zone file access permissions as noted in the table above.”h]”hX  The repair mount option triggers only the minimal set of I/O error recovery
actions, that is, file size fixes for zones in a good condition. Zones
indicated as being read-only or offline by the device still imply changes to
the zone file access permissions as noted in the table above.”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M-hj{  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hj   h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´Mhj¦  h²hubeh}”(h]”Œio-error-handling”ah ]”h"]”Œio error handling”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´K®ubhÉ)”}”(hhh]”(hÎ)”}”(hŒMount options”h]”hŒMount options”…””}”(hj¤  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj¡  h²hh³hÇh´M3ubhï)”}”(hŒIzonefs defines several mount options:
* errors=<behavior>
* explicit-open”h]”hŒIzonefs defines several mount options:
* errors=<behavior>
* explicit-open”…””}”(hj²  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M5hj¡  h²hubhÉ)”}”(hhh]”(hÎ)”}”(hŒ"errors=<behavior>" option”h]”hŒâ€œerrors=<behavior>â€ option”…””}”(hjÃ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhjÀ  h²hh³hÇh´M:ubhï)”}”(hŒÌThe "errors=<behavior>" option mount option allows the user to specify zonefs
behavior in response to I/O errors, inode size inconsistencies or zone
condition changes. The defined behaviors are as follow:”h]”hŒÐThe â€œerrors=<behavior>â€ option mount option allows the user to specify zonefs
behavior in response to I/O errors, inode size inconsistencies or zone
condition changes. The defined behaviors are as follow:”…””}”(hjÑ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M<hjÀ  h²hubj,  )”}”(hhh]”(j1  )”}”(hŒremount-ro (default)”h]”hï)”}”(hjä  h]”hŒremount-ro (default)”…””}”(hjæ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M@hjâ  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjß  h²hh³hÇh´Nubj1  )”}”(hŒzone-ro”h]”hï)”}”(hjû  h]”hŒzone-ro”…””}”(hjý  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MAhjù  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjß  h²hh³hÇh´Nubj1  )”}”(hŒzone-offline”h]”hï)”}”(hj  h]”hŒzone-offline”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MBhj  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjß  h²hh³hÇh´Nubj1  )”}”(hŒrepair
”h]”hï)”}”(hŒrepair”h]”hŒrepair”…””}”(hj+  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MChj'  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjß  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´M@hjÀ  h²hubhï)”}”(hX  The run-time I/O error actions defined for each behavior are detailed in the
previous section. Mount time I/O errors will cause the mount operation to fail.
The handling of read-only zones also differs between mount-time and run-time.
If a read-only zone is found at mount time, the zone is always treated in the
same manner as offline zones, that is, all accesses are disabled and the zone
file size set to 0. This is necessary as the write pointer of read-only zones
is defined as invalib by the ZBC and ZAC standards, making it impossible to
discover the amount of data that has been written to the zone. In the case of a
read-only zone discovered at run-time, as indicated in the previous section.
The size of the zone file is left unchanged from its last updated value.”h]”hX  The run-time I/O error actions defined for each behavior are detailed in the
previous section. Mount time I/O errors will cause the mount operation to fail.
The handling of read-only zones also differs between mount-time and run-time.
If a read-only zone is found at mount time, the zone is always treated in the
same manner as offline zones, that is, all accesses are disabled and the zone
file size set to 0. This is necessary as the write pointer of read-only zones
is defined as invalib by the ZBC and ZAC standards, making it impossible to
discover the amount of data that has been written to the zone. In the case of a
read-only zone discovered at run-time, as indicated in the previous section.
The size of the zone file is left unchanged from its last updated value.”…””}”(hjE  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MEhjÀ  h²hubeh}”(h]”Œerrors-behavior-option”ah ]”h"]”Œ"errors=<behavior>" option”ah$]”h&]”uh1hÈhj¡  h²hh³hÇh´M:ubhÉ)”}”(hhh]”(hÎ)”}”(hŒ"explicit-open" option”h]”hŒâ€œexplicit-openâ€ option”…””}”(hj^  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj[  h²hh³hÇh´MQubhï)”}”(hXš  A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on
the number of zones that can be active, that is, zones that are in the
implicit open, explicit open or closed conditions.  This potential limitation
translates into a risk for applications to see write IO errors due to this
limit being exceeded if the zone of a file is not already active when a write
request is issued by the user.”h]”hXš  A zoned block device (e.g. an NVMe Zoned Namespace device) may have limits on
the number of zones that can be active, that is, zones that are in the
implicit open, explicit open or closed conditions.  This potential limitation
translates into a risk for applications to see write IO errors due to this
limit being exceeded if the zone of a file is not already active when a write
request is issued by the user.”…””}”(hjl  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MShj[  h²hubhï)”}”(hXÏ  To avoid these potential errors, the "explicit-open" mount option forces zones
to be made active using an open zone command when a file is opened for writing
for the first time. If the zone open command succeeds, the application is then
guaranteed that write requests can be processed. Conversely, the
"explicit-open" mount option will result in a zone close command being issued
to the device on the last close() of a zone file if the zone is not full nor
empty.”h]”hX×  To avoid these potential errors, the â€œexplicit-openâ€ mount option forces zones
to be made active using an open zone command when a file is opened for writing
for the first time. If the zone open command succeeds, the application is then
guaranteed that write requests can be processed. Conversely, the
â€œexplicit-openâ€ mount option will result in a zone close command being issued
to the device on the last close() of a zone file if the zone is not full nor
empty.”…””}”(hjz  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MZhj[  h²hubeh}”(h]”Œexplicit-open-option”ah ]”h"]”Œ"explicit-open" option”ah$]”h&]”uh1hÈhj¡  h²hh³hÇh´MQubeh}”(h]”Œmount-options”ah ]”h"]”Œmount options”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´M3ubhÉ)”}”(hhh]”(hÎ)”}”(hŒRuntime sysfs attributes”h]”hŒRuntime sysfs attributes”…””}”(hj›  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj˜  h²hh³hÇh´Mcubhï)”}”(hŒÒzonefs defines several sysfs attributes for mounted devices.  All attributes
are user readable and can be found in the directory /sys/fs/zonefs/<dev>/,
where <dev> is the name of the mounted zoned block device.”h]”hŒÒzonefs defines several sysfs attributes for mounted devices.  All attributes
are user readable and can be found in the directory /sys/fs/zonefs/<dev>/,
where <dev> is the name of the mounted zoned block device.”…””}”(hj©  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mehj˜  h²hubhï)”}”(hŒ&The attributes defined are as follows.”h]”hŒ&The attributes defined are as follows.”…””}”(hj·  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mihj˜  h²hubj,  )”}”(hhh]”(j1  )”}”(hXŠ  **max_wro_seq_files**:  This attribute reports the maximum number of
sequential zone files that can be open for writing.  This number corresponds
to the maximum number of explicitly or implicitly open zones that the device
supports.  A value of 0 means that the device has no limit and that any zone
(any file) can be open for writing and written at any time, regardless of the
state of other zones.  When the *explicit-open* mount option is used, zonefs
will fail any open() system call requesting to open a sequential zone file for
writing when the number of sequential zone files already open for writing has
reached the *max_wro_seq_files* limit.”h]”hï)”}”(hXŠ  **max_wro_seq_files**:  This attribute reports the maximum number of
sequential zone files that can be open for writing.  This number corresponds
to the maximum number of explicitly or implicitly open zones that the device
supports.  A value of 0 means that the device has no limit and that any zone
(any file) can be open for writing and written at any time, regardless of the
state of other zones.  When the *explicit-open* mount option is used, zonefs
will fail any open() system call requesting to open a sequential zone file for
writing when the number of sequential zone files already open for writing has
reached the *max_wro_seq_files* limit.”h]”(hŒstrong”“”)”}”(hŒ**max_wro_seq_files**”h]”hŒmax_wro_seq_files”…””}”(hjÒ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jÐ  hjÌ  ubhX…  :  This attribute reports the maximum number of
sequential zone files that can be open for writing.  This number corresponds
to the maximum number of explicitly or implicitly open zones that the device
supports.  A value of 0 means that the device has no limit and that any zone
(any file) can be open for writing and written at any time, regardless of the
state of other zones.  When the ”…””}”(hjÌ  h²hh³Nh´NubhŒemphasis”“”)”}”(hŒ*explicit-open*”h]”hŒexplicit-open”…””}”(hjæ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÌ  ubhŒÇ mount option is used, zonefs
will fail any open() system call requesting to open a sequential zone file for
writing when the number of sequential zone files already open for writing has
reached the ”…””}”(hjÌ  h²hh³Nh´Nubjå  )”}”(hŒ*max_wro_seq_files*”h]”hŒmax_wro_seq_files”…””}”(hjø  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÌ  ubhŒ limit.”…””}”(hjÌ  h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MkhjÈ  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hXö  **nr_wro_seq_files**:  This attribute reports the current number of sequential
zone files open for writing.  When the "explicit-open" mount option is used,
this number can never exceed *max_wro_seq_files*.  If the *explicit-open*
mount option is not used, the reported number can be greater than
*max_wro_seq_files*.  In such case, it is the responsibility of the
application to not write simultaneously more than *max_wro_seq_files*
sequential zone files.  Failure to do so can result in write errors.”h]”hï)”}”(hXö  **nr_wro_seq_files**:  This attribute reports the current number of sequential
zone files open for writing.  When the "explicit-open" mount option is used,
this number can never exceed *max_wro_seq_files*.  If the *explicit-open*
mount option is not used, the reported number can be greater than
*max_wro_seq_files*.  In such case, it is the responsibility of the
application to not write simultaneously more than *max_wro_seq_files*
sequential zone files.  Failure to do so can result in write errors.”h]”(jÑ  )”}”(hŒ**nr_wro_seq_files**”h]”hŒnr_wro_seq_files”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jÐ  hj  ubhŒ©:  This attribute reports the current number of sequential
zone files open for writing.  When the â€œexplicit-openâ€ mount option is used,
this number can never exceed ”…””}”(hj  h²hh³Nh´Nubjå  )”}”(hŒ*max_wro_seq_files*”h]”hŒmax_wro_seq_files”…””}”(hj0  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hj  ubhŒ
.  If the ”…””}”(hj  h²hh³Nh´Nubjå  )”}”(hŒ*explicit-open*”h]”hŒexplicit-open”…””}”(hjB  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hj  ubhŒC
mount option is not used, the reported number can be greater than
”…””}”(hj  h²hh³Nh´Nubjå  )”}”(hŒ*max_wro_seq_files*”h]”hŒmax_wro_seq_files”…””}”(hjT  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hj  ubhŒc.  In such case, it is the responsibility of the
application to not write simultaneously more than ”…””}”(hj  h²hh³Nh´Nubjå  )”}”(hŒ*max_wro_seq_files*”h]”hŒmax_wro_seq_files”…””}”(hjf  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hj  ubhŒE
sequential zone files.  Failure to do so can result in write errors.”…””}”(hj  h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mthj  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hX  **max_active_seq_files**:  This attribute reports the maximum number of
sequential zone files that are in an active state, that is, sequential zone
files that are partially written (not empty nor full) or that have a zone that
is explicitly open (which happens only if the *explicit-open* mount option is
used).  This number is always equal to the maximum number of active zones that
the device supports.  A value of 0 means that the mounted device has no limit
on the number of sequential zone files that can be active.”h]”hï)”}”(hX  **max_active_seq_files**:  This attribute reports the maximum number of
sequential zone files that are in an active state, that is, sequential zone
files that are partially written (not empty nor full) or that have a zone that
is explicitly open (which happens only if the *explicit-open* mount option is
used).  This number is always equal to the maximum number of active zones that
the device supports.  A value of 0 means that the mounted device has no limit
on the number of sequential zone files that can be active.”h]”(jÑ  )”}”(hŒ**max_active_seq_files**”h]”hŒmax_active_seq_files”…””}”(hjŒ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jÐ  hjˆ  ubhŒù:  This attribute reports the maximum number of
sequential zone files that are in an active state, that is, sequential zone
files that are partially written (not empty nor full) or that have a zone that
is explicitly open (which happens only if the ”…””}”(hjˆ  h²hh³Nh´Nubjå  )”}”(hŒ*explicit-open*”h]”hŒexplicit-open”…””}”(hjž  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjˆ  ubhŒè mount option is
used).  This number is always equal to the maximum number of active zones that
the device supports.  A value of 0 means that the mounted device has no limit
on the number of sequential zone files that can be active.”…””}”(hjˆ  h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M{hj„  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubj1  )”}”(hX+  **nr_active_seq_files**:  This attributes reports the current number of
sequential zone files that are active. If *max_active_seq_files* is not 0,
then the value of *nr_active_seq_files* can never exceed the value of
*nr_active_seq_files*, regardless of the use of the *explicit-open* mount
option.
”h]”hï)”}”(hX*  **nr_active_seq_files**:  This attributes reports the current number of
sequential zone files that are active. If *max_active_seq_files* is not 0,
then the value of *nr_active_seq_files* can never exceed the value of
*nr_active_seq_files*, regardless of the use of the *explicit-open* mount
option.”h]”(jÑ  )”}”(hŒ**nr_active_seq_files**”h]”hŒnr_active_seq_files”…””}”(hjÄ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jÐ  hjÀ  ubhŒ[:  This attributes reports the current number of
sequential zone files that are active. If ”…””}”(hjÀ  h²hh³Nh´Nubjå  )”}”(hŒ*max_active_seq_files*”h]”hŒmax_active_seq_files”…””}”(hjÖ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÀ  ubhŒ is not 0,
then the value of ”…””}”(hjÀ  h²hh³Nh´Nubjå  )”}”(hŒ*nr_active_seq_files*”h]”hŒnr_active_seq_files”…””}”(hjè  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÀ  ubhŒ can never exceed the value of
”…””}”(hjÀ  h²hh³Nh´Nubjå  )”}”(hŒ*nr_active_seq_files*”h]”hŒnr_active_seq_files”…””}”(hjú  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÀ  ubhŒ, regardless of the use of the ”…””}”(hjÀ  h²hh³Nh´Nubjå  )”}”(hŒ*explicit-open*”h]”hŒexplicit-open”…””}”(hj  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1jä  hjÀ  ubhŒ mount
option.”…””}”(hjÀ  h²hh³Nh´Nubeh}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M‚hj¼  ubah}”(h]”h ]”h"]”h$]”h&]”uh1j0  hjÅ  h²hh³hÇh´Nubeh}”(h]”h ]”h"]”h$]”h&]”jh  ji  uh1j+  h³hÇh´Mkhj˜  h²hubeh}”(h]”Œruntime-sysfs-attributes”ah ]”h"]”Œruntime sysfs attributes”ah$]”h&]”uh1hÈhj–  h²hh³hÇh´Mcubeh}”(h]”Œzonefs-overview”ah ]”h"]”Œzonefs overview”ah$]”h&]”uh1hÈhhÊh²hh³hÇh´K:ubhÉ)”}”(hhh]”(hÎ)”}”(hŒZonefs User Space Tools”h]”hŒZonefs User Space Tools”…””}”(hjC  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj@  h²hh³hÇh´M‰ubhï)”}”(hŒqThe mkzonefs tool is used to format zoned block devices for use with zonefs.
This tool is available on Github at:”h]”hŒqThe mkzonefs tool is used to format zoned block devices for use with zonefs.
This tool is available on Github at:”…””}”(hjQ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M‹hj@  h²hubhï)”}”(hŒ-https://github.com/damien-lemoal/zonefs-tools”h]”hŒ	reference”“”)”}”(hja  h]”hŒ-https://github.com/damien-lemoal/zonefs-tools”…””}”(hje  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”Œrefuri”ja  uh1jc  hj_  ubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MŽhj@  h²hubhï)”}”(hŒ‘zonefs-tools also includes a test suite which can be run against any zoned
block device, including null_blk block device created with zoned mode.”h]”hŒ‘zonefs-tools also includes a test suite which can be run against any zoned
block device, including null_blk block device created with zoned mode.”…””}”(hjy  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mhj@  h²hubhÉ)”}”(hhh]”(hÎ)”}”(hŒExamples”h]”hŒExamples”…””}”(hjŠ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hÍhj‡  h²hh³hÇh´M”ubhï)”}”(hŒ}The following formats a 15TB host-managed SMR HDD with 256 MB zones
with the conventional zones aggregation feature enabled::”•ô%      h]”hŒ|The following formats a 15TB host-managed SMR HDD with 256 MB zones
with the conventional zones aggregation feature enabled:”…””}”(hj˜  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M–hj‡  h²hubjã  )”}”(hŒ±# mkzonefs -o aggr_cnv /dev/sdX
# mount -t zonefs /dev/sdX /mnt
# ls -l /mnt/
total 0
dr-xr-xr-x 2 root root     1 Nov 25 13:23 cnv
dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq”h]”hŒ±# mkzonefs -o aggr_cnv /dev/sdX
# mount -t zonefs /dev/sdX /mnt
# ls -l /mnt/
total 0
dr-xr-xr-x 2 root root     1 Nov 25 13:23 cnv
dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq”…””}”hj¦  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M™hj‡  h²hubhï)”}”(hŒàThe size of the zone files sub-directories indicate the number of files
existing for each type of zones. In this example, there is only one
conventional zone file (all conventional zones are aggregated under a single
file)::”h]”hŒßThe size of the zone files sub-directories indicate the number of files
existing for each type of zones. In this example, there is only one
conventional zone file (all conventional zones are aggregated under a single
file):”…””}”(hj´  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M hj‡  h²hubjã  )”}”(hŒS# ls -l /mnt/cnv
total 137101312
-rw-r----- 1 root root 140391743488 Nov 25 13:23 0”h]”hŒS# ls -l /mnt/cnv
total 137101312
-rw-r----- 1 root root 140391743488 Nov 25 13:23 0”…””}”hjÂ  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M¥hj‡  h²hubhï)”}”(hŒFThis aggregated conventional zone file can be used as a regular file::”h]”hŒEThis aggregated conventional zone file can be used as a regular file:”…””}”(hjÐ  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M©hj‡  h²hubjã  )”}”(hŒ7# mkfs.ext4 /mnt/cnv/0
# mount -o loop /mnt/cnv/0 /data”h]”hŒ7# mkfs.ext4 /mnt/cnv/0
# mount -o loop /mnt/cnv/0 /data”…””}”hjÞ  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M«hj‡  h²hubhï)”}”(hŒcThe "seq" sub-directory grouping files for sequential write zones has in this
example 55356 zones::”h]”hŒfThe â€œseqâ€ sub-directory grouping files for sequential write zones has in this
example 55356 zones:”…””}”(hjì  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´M®hj‡  h²hubjã  )”}”(hŒ÷# ls -lv /mnt/seq
total 14511243264
-rw-r----- 1 root root 0 Nov 25 13:23 0
-rw-r----- 1 root root 0 Nov 25 13:23 1
-rw-r----- 1 root root 0 Nov 25 13:23 2
...
-rw-r----- 1 root root 0 Nov 25 13:23 55354
-rw-r----- 1 root root 0 Nov 25 13:23 55355”h]”hŒ÷# ls -lv /mnt/seq
total 14511243264
-rw-r----- 1 root root 0 Nov 25 13:23 0
-rw-r----- 1 root root 0 Nov 25 13:23 1
-rw-r----- 1 root root 0 Nov 25 13:23 2
...
-rw-r----- 1 root root 0 Nov 25 13:23 55354
-rw-r----- 1 root root 0 Nov 25 13:23 55355”…””}”hjú  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M±hj‡  h²hubhï)”}”(hŒ‰For sequential write zone files, the file size changes as data is appended at
the end of the file, similarly to any regular file system::”h]”hŒˆFor sequential write zone files, the file size changes as data is appended at
the end of the file, similarly to any regular file system:”…””}”(hj	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Mºhj‡  h²hubjã  )”}”(hŒì# dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct
1+0 records in
1+0 records out
4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s

# ls -l /mnt/seq/0
-rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0”h]”hŒì# dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct
1+0 records in
1+0 records out
4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s

# ls -l /mnt/seq/0
-rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0”…””}”hj	  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M½hj‡  h²hubhï)”}”(hŒ\The written file can be truncated to the zone size, preventing any further
write operation::”h]”hŒ[The written file can be truncated to the zone size, preventing any further
write operation:”…””}”(hj$	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MÅhj‡  h²hubjã  )”}”(hŒn# truncate -s 268435456 /mnt/seq/0
# ls -l /mnt/seq/0
-rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0”h]”hŒn# truncate -s 268435456 /mnt/seq/0
# ls -l /mnt/seq/0
-rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0”…””}”hj2	  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´MÈhj‡  h²hubhï)”}”(hŒgTruncation to 0 size allows freeing the file zone storage space and restart
append-writes to the file::”h]”hŒfTruncation to 0 size allows freeing the file zone storage space and restart
append-writes to the file:”…””}”(hj@	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MÌhj‡  h²hubjã  )”}”(hŒ^# truncate -s 0 /mnt/seq/0
# ls -l /mnt/seq/0
-rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0”h]”hŒ^# truncate -s 0 /mnt/seq/0
# ls -l /mnt/seq/0
-rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0”…””}”hjN	  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´MÏhj‡  h²hubhï)”}”(hŒ¢Since files are statically mapped to zones on the disk, the number of blocks
of a file as reported by stat() and fstat() indicates the capacity of the file
zone::”h]”hŒ¡Since files are statically mapped to zones on the disk, the number of blocks
of a file as reported by stat() and fstat() indicates the capacity of the file
zone:”…””}”(hj\	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´MÓhj‡  h²hubjã  )”}”(hXs  # stat /mnt/seq/0
File: /mnt/seq/0
Size: 0             Blocks: 524288     IO Block: 4096   regular empty file
Device: 870h/2160d  Inode: 50431       Links: 1
Access: (0640/-rw-r-----)  Uid: (    0/    root)   Gid: (    0/    root)
Access: 2019-11-25 13:23:57.048971997 +0900
Modify: 2019-11-25 13:52:25.553805765 +0900
Change: 2019-11-25 13:52:25.553805765 +0900
Birth: -”h]”hXs  # stat /mnt/seq/0
File: /mnt/seq/0
Size: 0             Blocks: 524288     IO Block: 4096   regular empty file
Device: 870h/2160d  Inode: 50431       Links: 1
Access: (0640/-rw-r-----)  Uid: (    0/    root)   Gid: (    0/    root)
Access: 2019-11-25 13:23:57.048971997 +0900
Modify: 2019-11-25 13:52:25.553805765 +0900
Change: 2019-11-25 13:52:25.553805765 +0900
Birth: -”…””}”hjj	  sbah}”(h]”h ]”h"]”h$]”h&]”hÅhÆuh1jâ  h³hÇh´M×hj‡  h²hubhï)”}”(hX@  The number of blocks of the file ("Blocks") in units of 512B blocks gives the
maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone
capacity in this example. Of note is that the "IO block" field always
indicates the minimum I/O size for writes and corresponds to the device
physical sector size.”h]”hXH  The number of blocks of the file (â€œBlocksâ€) in units of 512B blocks gives the
maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone
capacity in this example. Of note is that the â€œIO blockâ€ field always
indicates the minimum I/O size for writes and corresponds to the device
physical sector size.”…””}”(hjx	  h²hh³Nh´Nubah}”(h]”h ]”h"]”h$]”h&]”uh1hîh³hÇh´Máhj‡  h²hubeh}”(h]”Œexamples”ah ]”h"]”Œexamples”ah$]”h&]”uh1hÈhj@  h²hh³hÇh´M”ubeh}”(h]”Œzonefs-user-space-tools”ah ]”h"]”Œzonefs user space tools”ah$]”h&]”uh1hÈhhÊh²hh³hÇh´M‰ubeh}”(h]”Œ.zonefs-zone-filesystem-for-zoned-block-devices”ah ]”h"]”Œ0zonefs - zone filesystem for zoned block devices”ah$]”h&]”uh1hÈhhh²hh³hÇh´Kubeh}”(h]”h ]”h"]”h$]”h&]”Œsource”hÇuh1hŒcurrent_source”NŒcurrent_line”NŒsettings”Œdocutils.frontend”ŒValues”“”)”}”(hÍNŒ	generator”NŒ	datestamp”NŒsource_link”NŒ
source_url”NŒtoc_backlinks”Œentry”Œfootnote_backlinks”KŒsectnum_xform”KŒstrip_comments”NŒstrip_elements_with_classes”NŒstrip_classes”NŒreport_level”KŒ
halt_level”KŒexit_status_level”KŒdebug”NŒwarning_stream”NŒ	traceback”ˆŒinput_encoding”Œ	utf-8-sig”Œinput_encoding_error_handler”Œstrict”Œoutput_encoding”Œutf-8”Œoutput_encoding_error_handler”jÁ	  Œerror_encoding”Œutf-8”Œerror_encoding_error_handler”Œbackslashreplace”Œlanguage_code”Œen”Œrecord_dependencies”NŒconfig”NŒ	id_prefix”hŒauto_id_prefix”Œid”Œdump_settings”NŒdump_internals”NŒdump_transforms”NŒdump_pseudo_xml”NŒexpose_internals”NŒstrict_visitor”NŒ_disable_config”NŒ_source”hÇŒ_destination”NŒ_config_files”]”Œ7/var/lib/git/docbuild/linux/Documentation/docutils.conf”aŒfile_insertion_enabled”ˆŒraw_enabled”KŒline_length_limit”M'Œpep_references”NŒpep_base_url”Œhttps://peps.python.org/”Œpep_file_url_template”Œpep-%04d”Œrfc_references”NŒrfc_base_url”Œ&https://datatracker.ietf.org/doc/html/”Œ	tab_width”KŒtrim_footnote_reference_space”‰Œsyntax_highlight”Œlong”Œsmart_quotes”ˆŒsmartquotes_locales”]”Œcharacter_level_inline_markup”‰Œdoctitle_xform”‰Œdocinfo_xform”KŒsectsubtitle_xform”‰Œimage_loading”Œlink”Œembed_stylesheet”‰Œcloak_email_addresses”ˆŒsection_self_link”‰Œenv”NubŒreporter”NŒindirect_targets”]”Œsubstitution_defs”}”Œsubstitution_names”}”Œrefnames”}”Œrefids”}”Œnameids”}”(j›	  j˜	  j“  j  j‹  jˆ  j=  j:  jç  jä  jF  jC  j—  j”  jÌ  jÉ  j+  j(  j£  j   jž  j›  j•  j’  jX  jU  j  jŠ  j5  j2  j“	  j	  j‹	  jˆ	  uŒ	nametypes”}”(j›	  ‰j“  ‰j‹  ‰j=  ‰jç  ‰jF  ‰j—  ‰jÌ  ‰j+  ‰j£  ‰jž  ‰j•  ‰jX  ‰j  ‰j5  ‰j“	  ‰j‹	  ‰uh}”(j˜	  hÊj  hÝjˆ  j  j:  j–  jä  jµ  jC  jê  j”  jI  jÉ  jš  j(  jÏ  j   j.  j›  j¦  j’  j¡  jU  jÀ  jŠ  j[  j2  j˜  j	  j@  jˆ	  j‡  uŒfootnote_refs”}”Œcitation_refs”}”Œautofootnotes”]”Œautofootnote_refs”]”Œsymbol_footnotes”]”Œsymbol_footnote_refs”]”Œ	footnotes”]”Œ	citations”]”Œautofootnote_start”KŒsymbol_footnote_start”K Œ
id_counter”Œcollections”ŒCounter”“”}”…”R”Œparse_messages”]”Œtransform_messages”]”Œtransformer”NŒinclude_log”]”Œ
decoration”Nh²hub.