From dddf30e3545b1a9b52383c43b1f4a582ebbf6e16 Mon Sep 17 00:00:00 2001 From: Alasdair Kergon Date: Tue, 15 Nov 2011 13:54:20 +0000 Subject: [PATCH] Include a copy of kernel DM documentation in doc/kernel --- WHATS_NEW_DM | 1 + doc/kernel/crypt.txt | 76 +++++++++ doc/kernel/delay.txt | 26 +++ doc/kernel/flakey.txt | 53 ++++++ doc/kernel/io.txt | 75 ++++++++ doc/kernel/kcopyd.txt | 47 +++++ doc/kernel/linear.txt | 61 +++++++ doc/kernel/log.txt | 54 ++++++ doc/kernel/persistent-data.txt | 84 +++++++++ doc/kernel/queue-length.txt | 39 +++++ doc/kernel/raid.txt | 108 ++++++++++++ doc/kernel/service-time.txt | 91 ++++++++++ doc/kernel/snapshot.txt | 168 ++++++++++++++++++ doc/kernel/striped.txt | 58 +++++++ doc/kernel/thin-provisioning.txt | 285 +++++++++++++++++++++++++++++++ doc/kernel/uevent.txt | 97 +++++++++++ doc/kernel/zero.txt | 37 ++++ 17 files changed, 1360 insertions(+) create mode 100644 doc/kernel/crypt.txt create mode 100644 doc/kernel/delay.txt create mode 100644 doc/kernel/flakey.txt create mode 100644 doc/kernel/io.txt create mode 100644 doc/kernel/kcopyd.txt create mode 100644 doc/kernel/linear.txt create mode 100644 doc/kernel/log.txt create mode 100644 doc/kernel/persistent-data.txt create mode 100644 doc/kernel/queue-length.txt create mode 100644 doc/kernel/raid.txt create mode 100644 doc/kernel/service-time.txt create mode 100644 doc/kernel/snapshot.txt create mode 100644 doc/kernel/striped.txt create mode 100644 doc/kernel/thin-provisioning.txt create mode 100644 doc/kernel/uevent.txt create mode 100644 doc/kernel/zero.txt diff --git a/WHATS_NEW_DM b/WHATS_NEW_DM index 407c2b819..40959714f 100644 --- a/WHATS_NEW_DM +++ b/WHATS_NEW_DM @@ -1,5 +1,6 @@ Version 1.02.68 - ================================== + Include a copy of kernel DM documentation in doc/kernel. Improve man page style for dmsetup. Fix _get_proc_number to be tolerant of malformed /proc/misc entries. Add ExecReload to dm-event.service for systemd to reload dmeventd properly. diff --git a/doc/kernel/crypt.txt b/doc/kernel/crypt.txt new file mode 100644 index 000000000..2c656ae43 --- /dev/null +++ b/doc/kernel/crypt.txt @@ -0,0 +1,76 @@ +dm-crypt +========= + +Device-Mapper's "crypt" target provides transparent encryption of block devices +using the kernel crypto API. + +Parameters: \ + [<#opt_params> ] + + + Encryption cipher and an optional IV generation mode. + (In format cipher[:keycount]-chainmode-ivopts:ivmode). + Examples: + des + aes-cbc-essiv:sha256 + twofish-ecb + + /proc/crypto contains supported crypto modes + + + Key used for encryption. It is encoded as a hexadecimal number. + You can only use key sizes that are valid for the selected cipher. + + + Multi-key compatibility mode. You can define keys and + then sectors are encrypted according to their offsets (sector 0 uses key0; + sector 1 uses key1 etc.). must be a power of two. + + + The IV offset is a sector count that is added to the sector number + before creating the IV. + + + This is the device that is going to be used as backend and contains the + encrypted data. You can specify it as a path like /dev/xxx or a device + number :. + + + Starting sector within the device where the encrypted data begins. + +<#opt_params> + Number of optional parameters. If there are no optional parameters, + the optional paramaters section can be skipped or #opt_params can be zero. + Otherwise #opt_params is the number of following arguments. + + Example of optional parameters section: + 1 allow_discards + +allow_discards + Block discard requests (a.k.a. TRIM) are passed through the crypt device. + The default is to ignore discard requests. + + WARNING: Assess the specific security risks carefully before enabling this + option. For example, allowing discards on encrypted devices may lead to + the leak of information about the ciphertext device (filesystem type, + used space etc.) if the discarded blocks can be located easily on the + device later. + +Example scripts +=============== +LUKS (Linux Unified Key Setup) is now the preferred way to set up disk +encryption with dm-crypt using the 'cryptsetup' utility, see +http://code.google.com/p/cryptsetup/ + +[[ +#!/bin/sh +# Create a crypt device using dmsetup +dmsetup create crypt1 --table "0 `blockdev --getsize $1` crypt aes-cbc-essiv:sha256 babebabebabebabebabebabebabebabe 0 $1 0" +]] + +[[ +#!/bin/sh +# Create a crypt device using cryptsetup and LUKS header with default cipher +cryptsetup luksFormat $1 +cryptsetup luksOpen $1 crypt1 +]] diff --git a/doc/kernel/delay.txt b/doc/kernel/delay.txt new file mode 100644 index 000000000..15adc5535 --- /dev/null +++ b/doc/kernel/delay.txt @@ -0,0 +1,26 @@ +dm-delay +======== + +Device-Mapper's "delay" target delays reads and/or writes +and maps them to different devices. + +Parameters: + [ ] + +With separate write parameters, the first set is only used for reads. +Delays are specified in milliseconds. + +Example scripts +=============== +[[ +#!/bin/sh +# Create device delaying rw operation for 500ms +echo "0 `blockdev --getsize $1` delay $1 0 500" | dmsetup create delayed +]] + +[[ +#!/bin/sh +# Create device delaying only write operation for 500ms and +# splitting reads and writes to different devices $1 $2 +echo "0 `blockdev --getsize $1` delay $1 0 0 $2 0 500" | dmsetup create delayed +]] diff --git a/doc/kernel/flakey.txt b/doc/kernel/flakey.txt new file mode 100644 index 000000000..6ff5c2327 --- /dev/null +++ b/doc/kernel/flakey.txt @@ -0,0 +1,53 @@ +dm-flakey +========= + +This target is the same as the linear target except that it exhibits +unreliable behaviour periodically. It's been found useful in simulating +failing devices for testing purposes. + +Starting from the time the table is loaded, the device is available for + seconds, then exhibits unreliable behaviour for seconds, and then this cycle repeats. + +Also, consider using this in combination with the dm-delay target too, +which can delay reads and writes and/or send them to different +underlying devices. + +Table parameters +---------------- + \ + [ []] + +Mandatory parameters: + : Full pathname to the underlying block-device, or a + "major:minor" device-number. + : Starting sector within the device. + : Number of seconds device is available. + : Number of seconds device returns errors. + +Optional feature parameters: + If no feature parameters are present, during the periods of + unreliability, all I/O returns errors. + + drop_writes: + All write I/O is silently ignored. + Read I/O is handled correctly. + + corrupt_bio_byte : + During , replace of the data of + each matching bio with . + + : The offset of the byte to replace. + Counting starts at 1, to replace the first byte. + : Either 'r' to corrupt reads or 'w' to corrupt writes. + 'w' is incompatible with drop_writes. + : The value (from 0-255) to write. + : Perform the replacement only if bio->bi_rw has all the + selected flags set. + +Examples: + corrupt_bio_byte 32 r 1 0 + - replaces the 32nd byte of READ bios with the value 1 + + corrupt_bio_byte 224 w 0 32 + - replaces the 224th byte of REQ_META (=32) bios with the value 0 diff --git a/doc/kernel/io.txt b/doc/kernel/io.txt new file mode 100644 index 000000000..3b5d9a52c --- /dev/null +++ b/doc/kernel/io.txt @@ -0,0 +1,75 @@ +dm-io +===== + +Dm-io provides synchronous and asynchronous I/O services. There are three +types of I/O services available, and each type has a sync and an async +version. + +The user must set up an io_region structure to describe the desired location +of the I/O. Each io_region indicates a block-device along with the starting +sector and size of the region. + + struct io_region { + struct block_device *bdev; + sector_t sector; + sector_t count; + }; + +Dm-io can read from one io_region or write to one or more io_regions. Writes +to multiple regions are specified by an array of io_region structures. + +The first I/O service type takes a list of memory pages as the data buffer for +the I/O, along with an offset into the first page. + + struct page_list { + struct page_list *next; + struct page *page; + }; + + int dm_io_sync(unsigned int num_regions, struct io_region *where, int rw, + struct page_list *pl, unsigned int offset, + unsigned long *error_bits); + int dm_io_async(unsigned int num_regions, struct io_region *where, int rw, + struct page_list *pl, unsigned int offset, + io_notify_fn fn, void *context); + +The second I/O service type takes an array of bio vectors as the data buffer +for the I/O. This service can be handy if the caller has a pre-assembled bio, +but wants to direct different portions of the bio to different devices. + + int dm_io_sync_bvec(unsigned int num_regions, struct io_region *where, + int rw, struct bio_vec *bvec, + unsigned long *error_bits); + int dm_io_async_bvec(unsigned int num_regions, struct io_region *where, + int rw, struct bio_vec *bvec, + io_notify_fn fn, void *context); + +The third I/O service type takes a pointer to a vmalloc'd memory buffer as the +data buffer for the I/O. This service can be handy if the caller needs to do +I/O to a large region but doesn't want to allocate a large number of individual +memory pages. + + int dm_io_sync_vm(unsigned int num_regions, struct io_region *where, int rw, + void *data, unsigned long *error_bits); + int dm_io_async_vm(unsigned int num_regions, struct io_region *where, int rw, + void *data, io_notify_fn fn, void *context); + +Callers of the asynchronous I/O services must include the name of a completion +callback routine and a pointer to some context data for the I/O. + + typedef void (*io_notify_fn)(unsigned long error, void *context); + +The "error" parameter in this callback, as well as the "*error" parameter in +all of the synchronous versions, is a bitset (instead of a simple error value). +In the case of an write-I/O to multiple regions, this bitset allows dm-io to +indicate success or failure on each individual region. + +Before using any of the dm-io services, the user should call dm_io_get() +and specify the number of pages they expect to perform I/O on concurrently. +Dm-io will attempt to resize its mempool to make sure enough pages are +always available in order to avoid unnecessary waiting while performing I/O. + +When the user is finished using the dm-io services, they should call +dm_io_put() and specify the same number of pages that were given on the +dm_io_get() call. + diff --git a/doc/kernel/kcopyd.txt b/doc/kernel/kcopyd.txt new file mode 100644 index 000000000..820382c4c --- /dev/null +++ b/doc/kernel/kcopyd.txt @@ -0,0 +1,47 @@ +kcopyd +====== + +Kcopyd provides the ability to copy a range of sectors from one block-device +to one or more other block-devices, with an asynchronous completion +notification. It is used by dm-snapshot and dm-mirror. + +Users of kcopyd must first create a client and indicate how many memory pages +to set aside for their copy jobs. This is done with a call to +kcopyd_client_create(). + + int kcopyd_client_create(unsigned int num_pages, + struct kcopyd_client **result); + +To start a copy job, the user must set up io_region structures to describe +the source and destinations of the copy. Each io_region indicates a +block-device along with the starting sector and size of the region. The source +of the copy is given as one io_region structure, and the destinations of the +copy are given as an array of io_region structures. + + struct io_region { + struct block_device *bdev; + sector_t sector; + sector_t count; + }; + +To start the copy, the user calls kcopyd_copy(), passing in the client +pointer, pointers to the source and destination io_regions, the name of a +completion callback routine, and a pointer to some context data for the copy. + + int kcopyd_copy(struct kcopyd_client *kc, struct io_region *from, + unsigned int num_dests, struct io_region *dests, + unsigned int flags, kcopyd_notify_fn fn, void *context); + + typedef void (*kcopyd_notify_fn)(int read_err, unsigned int write_err, + void *context); + +When the copy completes, kcopyd will call the user's completion routine, +passing back the user's context pointer. It will also indicate if a read or +write error occurred during the copy. + +When a user is done with all their copy jobs, they should call +kcopyd_client_destroy() to delete the kcopyd client, which will release the +associated memory pages. + + void kcopyd_client_destroy(struct kcopyd_client *kc); + diff --git a/doc/kernel/linear.txt b/doc/kernel/linear.txt new file mode 100644 index 000000000..d5307d380 --- /dev/null +++ b/doc/kernel/linear.txt @@ -0,0 +1,61 @@ +dm-linear +========= + +Device-Mapper's "linear" target maps a linear range of the Device-Mapper +device onto a linear range of another device. This is the basic building +block of logical volume managers. + +Parameters: + : Full pathname to the underlying block-device, or a + "major:minor" device-number. + : Starting sector within the device. + + +Example scripts +=============== +[[ +#!/bin/sh +# Create an identity mapping for a device +echo "0 `blockdev --getsize $1` linear $1 0" | dmsetup create identity +]] + + +[[ +#!/bin/sh +# Join 2 devices together +size1=`blockdev --getsize $1` +size2=`blockdev --getsize $2` +echo "0 $size1 linear $1 0 +$size1 $size2 linear $2 0" | dmsetup create joined +]] + + +[[ +#!/usr/bin/perl -w +# Split a device into 4M chunks and then join them together in reverse order. + +my $name = "reverse"; +my $extent_size = 4 * 1024 * 2; +my $dev = $ARGV[0]; +my $table = ""; +my $count = 0; + +if (!defined($dev)) { + die("Please specify a device.\n"); +} + +my $dev_size = `blockdev --getsize $dev`; +my $extents = int($dev_size / $extent_size) - + (($dev_size % $extent_size) ? 1 : 0); + +while ($extents > 0) { + my $this_start = $count * $extent_size; + $extents--; + $count++; + my $this_offset = $extents * $extent_size; + + $table .= "$this_start $extent_size linear $dev $this_offset\n"; +} + +`echo \"$table\" | dmsetup create $name`; +]] diff --git a/doc/kernel/log.txt b/doc/kernel/log.txt new file mode 100644 index 000000000..c155ac569 --- /dev/null +++ b/doc/kernel/log.txt @@ -0,0 +1,54 @@ +Device-Mapper Logging +===================== +The device-mapper logging code is used by some of the device-mapper +RAID targets to track regions of the disk that are not consistent. +A region (or portion of the address space) of the disk may be +inconsistent because a RAID stripe is currently being operated on or +a machine died while the region was being altered. In the case of +mirrors, a region would be considered dirty/inconsistent while you +are writing to it because the writes need to be replicated for all +the legs of the mirror and may not reach the legs at the same time. +Once all writes are complete, the region is considered clean again. + +There is a generic logging interface that the device-mapper RAID +implementations use to perform logging operations (see +dm_dirty_log_type in include/linux/dm-dirty-log.h). Various different +logging implementations are available and provide different +capabilities. The list includes: + +Type Files +==== ===== +disk drivers/md/dm-log.c +core drivers/md/dm-log.c +userspace drivers/md/dm-log-userspace* include/linux/dm-log-userspace.h + +The "disk" log type +------------------- +This log implementation commits the log state to disk. This way, the +logging state survives reboots/crashes. + +The "core" log type +------------------- +This log implementation keeps the log state in memory. The log state +will not survive a reboot or crash, but there may be a small boost in +performance. This method can also be used if no storage device is +available for storing log state. + +The "userspace" log type +------------------------ +This log type simply provides a way to export the log API to userspace, +so log implementations can be done there. This is done by forwarding most +logging requests to userspace, where a daemon receives and processes the +request. + +The structure used for communication between kernel and userspace are +located in include/linux/dm-log-userspace.h. Due to the frequency, +diversity, and 2-way communication nature of the exchanges between +kernel and userspace, 'connector' is used as the interface for +communication. + +There are currently two userspace log implementations that leverage this +framework - "clustered-disk" and "clustered-core". These implementations +provide a cluster-coherent log for shared-storage. Device-mapper mirroring +can be used in a shared-storage environment when the cluster log implementations +are employed. diff --git a/doc/kernel/persistent-data.txt b/doc/kernel/persistent-data.txt new file mode 100644 index 000000000..0e5df9b04 --- /dev/null +++ b/doc/kernel/persistent-data.txt @@ -0,0 +1,84 @@ +Introduction +============ + +The more-sophisticated device-mapper targets require complex metadata +that is managed in kernel. In late 2010 we were seeing that various +different targets were rolling their own data strutures, for example: + +- Mikulas Patocka's multisnap implementation +- Heinz Mauelshagen's thin provisioning target +- Another btree-based caching target posted to dm-devel +- Another multi-snapshot target based on a design of Daniel Phillips + +Maintaining these data structures takes a lot of work, so if possible +we'd like to reduce the number. + +The persistent-data library is an attempt to provide a re-usable +framework for people who want to store metadata in device-mapper +targets. It's currently used by the thin-provisioning target and an +upcoming hierarchical storage target. + +Overview +======== + +The main documentation is in the header files which can all be found +under drivers/md/persistent-data. + +The block manager +----------------- + +dm-block-manager.[hc] + +This provides access to the data on disk in fixed sized-blocks. There +is a read/write locking interface to prevent concurrent accesses, and +keep data that is being used in the cache. + +Clients of persistent-data are unlikely to use this directly. + +The transaction manager +----------------------- + +dm-transaction-manager.[hc] + +This restricts access to blocks and enforces copy-on-write semantics. +The only way you can get hold of a writable block through the +transaction manager is by shadowing an existing block (ie. doing +copy-on-write) or allocating a fresh one. Shadowing is elided within +the same transaction so performance is reasonable. The commit method +ensures that all data is flushed before it writes the superblock. +On power failure your metadata will be as it was when last committed. + +The Space Maps +-------------- + +dm-space-map.h +dm-space-map-metadata.[hc] +dm-space-map-disk.[hc] + +On-disk data structures that keep track of reference counts of blocks. +Also acts as the allocator of new blocks. Currently two +implementations: a simpler one for managing blocks on a different +device (eg. thinly-provisioned data blocks); and one for managing +the metadata space. The latter is complicated by the need to store +its own data within the space it's managing. + +The data structures +------------------- + +dm-btree.[hc] +dm-btree-remove.c +dm-btree-spine.c +dm-btree-internal.h + +Currently there is only one data structure, a hierarchical btree. +There are plans to add more. For example, something with an +array-like interface would see a lot of use. + +The btree is 'hierarchical' in that you can define it to be composed +of nested btrees, and take multiple keys. For example, the +thin-provisioning target uses a btree with two levels of nesting. +The first maps a device id to a mapping tree, and that in turn maps a +virtual block to a physical block. + +Values stored in the btrees can have arbitrary size. Keys are always +64bits, although nesting allows you to use multiple keys. diff --git a/doc/kernel/queue-length.txt b/doc/kernel/queue-length.txt new file mode 100644 index 000000000..f4db25621 --- /dev/null +++ b/doc/kernel/queue-length.txt @@ -0,0 +1,39 @@ +dm-queue-length +=============== + +dm-queue-length is a path selector module for device-mapper targets, +which selects a path with the least number of in-flight I/Os. +The path selector name is 'queue-length'. + +Table parameters for each path: [] + : The number of I/Os to dispatch using the selected + path before switching to the next path. + If not given, internal default is used. To check + the default value, see the activated table. + +Status for each path: + : 'A' if the path is active, 'F' if the path is failed. + : The number of path failures. + : The number of in-flight I/Os on the path. + + +Algorithm +========= + +dm-queue-length increments/decrements 'in-flight' when an I/O is +dispatched/completed respectively. +dm-queue-length selects a path with the minimum 'in-flight'. + + +Examples +======== +In case that 2 paths (sda and sdb) are used with repeat_count == 128. + +# echo "0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 queue-length 0 2 1 8:0 128 8:16 128 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 1 8:0 A 0 0 8:16 A 0 0 diff --git a/doc/kernel/raid.txt b/doc/kernel/raid.txt new file mode 100644 index 000000000..2a8c11331 --- /dev/null +++ b/doc/kernel/raid.txt @@ -0,0 +1,108 @@ +dm-raid +------- + +The device-mapper RAID (dm-raid) target provides a bridge from DM to MD. +It allows the MD RAID drivers to be accessed using a device-mapper +interface. + +The target is named "raid" and it accepts the following parameters: + + <#raid_params> \ + <#raid_devs> [.. ] + +: + raid1 RAID1 mirroring + raid4 RAID4 dedicated parity disk + raid5_la RAID5 left asymmetric + - rotating parity 0 with data continuation + raid5_ra RAID5 right asymmetric + - rotating parity N with data continuation + raid5_ls RAID5 left symmetric + - rotating parity 0 with data restart + raid5_rs RAID5 right symmetric + - rotating parity N with data restart + raid6_zr RAID6 zero restart + - rotating parity zero (left-to-right) with data restart + raid6_nr RAID6 N restart + - rotating parity N (right-to-left) with data restart + raid6_nc RAID6 N continue + - rotating parity N (right-to-left) with data continuation + + Refererence: Chapter 4 of + http://www.snia.org/sites/default/files/SNIA_DDF_Technical_Position_v2.0.pdf + +<#raid_params>: The number of parameters that follow. + + consists of + Mandatory parameters: + : Chunk size in sectors. This parameter is often known as + "stripe size". It is the only mandatory parameter and + is placed first. + + followed by optional parameters (in any order): + [sync|nosync] Force or prevent RAID initialization. + + [rebuild ] Rebuild drive number idx (first drive is 0). + + [daemon_sleep ] + Interval between runs of the bitmap daemon that + clear bits. A longer interval means less bitmap I/O but + resyncing after a failure is likely to take longer. + + [min_recovery_rate ] Throttle RAID initialization + [max_recovery_rate ] Throttle RAID initialization + [write_mostly ] Drive index is write-mostly + [max_write_behind ] See '-write-behind=' (man mdadm) + [stripe_cache ] Stripe cache size (higher RAIDs only) + [region_size ] + The region_size multiplied by the number of regions is the + logical size of the array. The bitmap records the device + synchronisation state for each region. + +<#raid_devs>: The number of devices composing the array. + Each device consists of two entries. The first is the device + containing the metadata (if any); the second is the one containing the + data. + + If a drive has failed or is missing at creation time, a '-' can be + given for both the metadata and data drives for a given position. + + +Example tables +-------------- +# RAID4 - 4 data drives, 1 parity (no metadata devices) +# No metadata devices specified to hold superblock/bitmap info +# Chunk size of 1MiB +# (Lines separated for easy reading) + +0 1960893648 raid \ + raid4 1 2048 \ + 5 - 8:17 - 8:33 - 8:49 - 8:65 - 8:81 + +# RAID4 - 4 data drives, 1 parity (with metadata devices) +# Chunk size of 1MiB, force RAID initialization, +# min recovery rate at 20 kiB/sec/disk + +0 1960893648 raid \ + raid4 4 2048 sync min_recovery_rate 20 \ + 5 8:17 8:18 8:33 8:34 8:49 8:50 8:65 8:66 8:81 8:82 + +'dmsetup table' displays the table used to construct the mapping. +The optional parameters are always printed in the order listed +above with "sync" or "nosync" always output ahead of the other +arguments, regardless of the order used when originally loading the table. +Arguments that can be repeated are ordered by value. + +'dmsetup status' yields information on the state and health of the +array. +The output is as follows: +1: raid \ +2: <#devices> <1 health char for each dev> + +Line 1 is the standard output produced by device-mapper. +Line 2 is produced by the raid target, and best explained by example: + 0 1960893648 raid raid4 5 AAAAA 2/490221568 +Here we can see the RAID type is raid4, there are 5 devices - all of +which are 'A'live, and the array is 2/490221568 complete with recovery. +Faulty or missing devices are marked 'D'. Devices that are out-of-sync +are marked 'a'. diff --git a/doc/kernel/service-time.txt b/doc/kernel/service-time.txt new file mode 100644 index 000000000..fb1d4a0cf --- /dev/null +++ b/doc/kernel/service-time.txt @@ -0,0 +1,91 @@ +dm-service-time +=============== + +dm-service-time is a path selector module for device-mapper targets, +which selects a path with the shortest estimated service time for +the incoming I/O. + +The service time for each path is estimated by dividing the total size +of in-flight I/Os on a path with the performance value of the path. +The performance value is a relative throughput value among all paths +in a path-group, and it can be specified as a table argument. + +The path selector name is 'service-time'. + +Table parameters for each path: [ []] + : The number of I/Os to dispatch using the selected + path before switching to the next path. + If not given, internal default is used. To check + the default value, see the activated table. + : The relative throughput value of the path + among all paths in the path-group. + The valid range is 0-100. + If not given, minimum value '1' is used. + If '0' is given, the path isn't selected while + other paths having a positive value are available. + +Status for each path: \ + + : 'A' if the path is active, 'F' if the path is failed. + : The number of path failures. + : The size of in-flight I/Os on the path. + : The relative throughput value of the path + among all paths in the path-group. + + +Algorithm +========= + +dm-service-time adds the I/O size to 'in-flight-size' when the I/O is +dispatched and subtracts when completed. +Basically, dm-service-time selects a path having minimum service time +which is calculated by: + + ('in-flight-size' + 'size-of-incoming-io') / 'relative_throughput' + +However, some optimizations below are used to reduce the calculation +as much as possible. + + 1. If the paths have the same 'relative_throughput', skip + the division and just compare the 'in-flight-size'. + + 2. If the paths have the same 'in-flight-size', skip the division + and just compare the 'relative_throughput'. + + 3. If some paths have non-zero 'relative_throughput' and others + have zero 'relative_throughput', ignore those paths with zero + 'relative_throughput'. + +If such optimizations can't be applied, calculate service time, and +compare service time. +If calculated service time is equal, the path having maximum +'relative_throughput' may be better. So compare 'relative_throughput' +then. + + +Examples +======== +In case that 2 paths (sda and sdb) are used with repeat_count == 128 +and sda has an average throughput 1GB/s and sdb has 4GB/s, +'relative_throughput' value may be '1' for sda and '4' for sdb. + +# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 1 8:16 128 4 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 1 8:16 A 0 0 4 + + +Or '2' for sda and '8' for sdb would be also true. + +# echo "0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8" \ + dmsetup create test +# +# dmsetup table +test: 0 10 multipath 0 0 1 1 service-time 0 2 2 8:0 128 2 8:16 128 8 +# +# dmsetup status +test: 0 10 multipath 2 0 0 0 1 1 E 0 2 2 8:0 A 0 0 2 8:16 A 0 0 8 diff --git a/doc/kernel/snapshot.txt b/doc/kernel/snapshot.txt new file mode 100644 index 000000000..0d5bc46dc --- /dev/null +++ b/doc/kernel/snapshot.txt @@ -0,0 +1,168 @@ +Device-mapper snapshot support +============================== + +Device-mapper allows you, without massive data copying: + +*) To create snapshots of any block device i.e. mountable, saved states of +the block device which are also writable without interfering with the +original content; +*) To create device "forks", i.e. multiple different versions of the +same data stream. +*) To merge a snapshot of a block device back into the snapshot's origin +device. + +In the first two cases, dm copies only the chunks of data that get +changed and uses a separate copy-on-write (COW) block device for +storage. + +For snapshot merge the contents of the COW storage are merged back into +the origin device. + + +There are three dm targets available: +snapshot, snapshot-origin, and snapshot-merge. + +*) snapshot-origin + +which will normally have one or more snapshots based on it. +Reads will be mapped directly to the backing device. For each write, the +original data will be saved in the of each snapshot to keep +its visible content unchanged, at least until the fills up. + + +*) snapshot + +A snapshot of the block device is created. Changed chunks of + sectors will be stored on the . Writes will +only go to the . Reads will come from the or +from for unchanged data. will often be +smaller than the origin and if it fills up the snapshot will become +useless and be disabled, returning errors. So it is important to monitor +the amount of free space and expand the before it fills up. + + is P (Persistent) or N (Not persistent - will not survive +after reboot). +The difference is that for transient snapshots less metadata must be +saved on disk - they can be kept in memory by the kernel. + + +* snapshot-merge + +takes the same table arguments as the snapshot target except it only +works with persistent snapshots. This target assumes the role of the +"snapshot-origin" target and must not be loaded if the "snapshot-origin" +is still present for . + +Creates a merging snapshot that takes control of the changed chunks +stored in the of an existing snapshot, through a handover +procedure, and merges these chunks back into the . Once merging +has started (in the background) the may be opened and the merge +will continue while I/O is flowing to it. Changes to the are +deferred until the merging snapshot's corresponding chunk(s) have been +merged. Once merging has started the snapshot device, associated with +the "snapshot" target, will return -EIO when accessed. + + +How snapshot is used by LVM2 +============================ +When you create the first LVM2 snapshot of a volume, four dm devices are used: + +1) a device containing the original mapping table of the source volume; +2) a device used as the ; +3) a "snapshot" device, combining #1 and #2, which is the visible snapshot + volume; +4) the "original" volume (which uses the device number used by the original + source volume), whose table is replaced by a "snapshot-origin" mapping + from device #1. + +A fixed naming scheme is used, so with the following commands: + +lvcreate -L 1G -n base volumeGroup +lvcreate -L 100M --snapshot -n snap volumeGroup/base + +we'll have this situation (with volumes in above order): + +# dmsetup table|grep volumeGroup + +volumeGroup-base-real: 0 2097152 linear 8:19 384 +volumeGroup-snap-cow: 0 204800 linear 8:19 2097536 +volumeGroup-snap: 0 2097152 snapshot 254:11 254:12 P 16 +volumeGroup-base: 0 2097152 snapshot-origin 254:11 + +# ls -lL /dev/mapper/volumeGroup-* +brw------- 1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real +brw------- 1 root root 254, 12 29 ago 18:15 /dev/mapper/volumeGroup-snap-cow +brw------- 1 root root 254, 13 29 ago 18:15 /dev/mapper/volumeGroup-snap +brw------- 1 root root 254, 10 29 ago 18:14 /dev/mapper/volumeGroup-base + + +How snapshot-merge is used by LVM2 +================================== +A merging snapshot assumes the role of the "snapshot-origin" while +merging. As such the "snapshot-origin" is replaced with +"snapshot-merge". The "-real" device is not changed and the "-cow" +device is renamed to -cow to aid LVM2's cleanup of the +merging snapshot after it completes. The "snapshot" that hands over its +COW device to the "snapshot-merge" is deactivated (unless using lvchange +--refresh); but if it is left active it will simply return I/O errors. + +A snapshot will merge into its origin with the following command: + +lvconvert --merge volumeGroup/snap + +we'll now have this situation: + +# dmsetup table|grep volumeGroup + +volumeGroup-base-real: 0 2097152 linear 8:19 384 +volumeGroup-base-cow: 0 204800 linear 8:19 2097536 +volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16 + +# ls -lL /dev/mapper/volumeGroup-* +brw------- 1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real +brw------- 1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow +brw------- 1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base + + +How to determine when a merging is complete +=========================================== +The snapshot-merge and snapshot status lines end with: + / + +Both and include both data and metadata. +During merging, the number of sectors allocated gets smaller and +smaller. Merging has finished when the number of sectors holding data +is zero, in other words == . + +Here is a practical example (using a hybrid of lvm and dmsetup commands): + +# lvs + LV VG Attr LSize Origin Snap% Move Log Copy% Convert + base volumeGroup owi-a- 4.00g + snap volumeGroup swi-a- 1.00g base 18.97 + +# dmsetup status volumeGroup-snap +0 8388608 snapshot 397896/2097152 1560 + ^^^^ metadata sectors + +# lvconvert --merge -b volumeGroup/snap + Merging of volume snap started. + +# lvs volumeGroup/snap + LV VG Attr LSize Origin Snap% Move Log Copy% Convert + base volumeGroup Owi-a- 4.00g 17.23 + +# dmsetup status volumeGroup-base +0 8388608 snapshot-merge 281688/2097152 1104 + +# dmsetup status volumeGroup-base +0 8388608 snapshot-merge 180480/2097152 712 + +# dmsetup status volumeGroup-base +0 8388608 snapshot-merge 16/2097152 16 + +Merging has finished. + +# lvs + LV VG Attr LSize Origin Snap% Move Log Copy% Convert + base volumeGroup owi-a- 4.00g diff --git a/doc/kernel/striped.txt b/doc/kernel/striped.txt new file mode 100644 index 000000000..f34d3236b --- /dev/null +++ b/doc/kernel/striped.txt @@ -0,0 +1,58 @@ +dm-stripe +========= + +Device-Mapper's "striped" target is used to create a striped (i.e. RAID-0) +device across one or more underlying devices. Data is written in "chunks", +with consecutive chunks rotating among the underlying devices. This can +potentially provide improved I/O throughput by utilizing several physical +devices in parallel. + +Parameters: [ ]+ + : Number of underlying devices. + : Size of each chunk of data. Must be a power-of-2 and at + least as large as the system's PAGE_SIZE. + : Full pathname to the underlying block-device, or a + "major:minor" device-number. + : Starting sector within the device. + +One or more underlying devices can be specified. The striped device size must +be a multiple of the chunk size and a multiple of the number of underlying +devices. + + +Example scripts +=============== + +[[ +#!/usr/bin/perl -w +# Create a striped device across any number of underlying devices. The device +# will be called "stripe_dev" and have a chunk-size of 128k. + +my $chunk_size = 128 * 2; +my $dev_name = "stripe_dev"; +my $num_devs = @ARGV; +my @devs = @ARGV; +my ($min_dev_size, $stripe_dev_size, $i); + +if (!$num_devs) { + die("Specify at least one device\n"); +} + +$min_dev_size = `blockdev --getsize $devs[0]`; +for ($i = 1; $i < $num_devs; $i++) { + my $this_size = `blockdev --getsize $devs[$i]`; + $min_dev_size = ($min_dev_size < $this_size) ? + $min_dev_size : $this_size; +} + +$stripe_dev_size = $min_dev_size * $num_devs; +$stripe_dev_size -= $stripe_dev_size % ($chunk_size * $num_devs); + +$table = "0 $stripe_dev_size striped $num_devs $chunk_size"; +for ($i = 0; $i < $num_devs; $i++) { + $table .= " $devs[$i] 0"; +} + +`echo $table | dmsetup create $dev_name`; +]] + diff --git a/doc/kernel/thin-provisioning.txt b/doc/kernel/thin-provisioning.txt new file mode 100644 index 000000000..801d9d1cf --- /dev/null +++ b/doc/kernel/thin-provisioning.txt @@ -0,0 +1,285 @@ +Introduction +============ + +This document descibes a collection of device-mapper targets that +between them implement thin-provisioning and snapshots. + +The main highlight of this implementation, compared to the previous +implementation of snapshots, is that it allows many virtual devices to +be stored on the same data volume. This simplifies administration and +allows the sharing of data between volumes, thus reducing disk usage. + +Another significant feature is support for an arbitrary depth of +recursive snapshots (snapshots of snapshots of snapshots ...). The +previous implementation of snapshots did this by chaining together +lookup tables, and so performance was O(depth). This new +implementation uses a single data structure to avoid this degradation +with depth. Fragmentation may still be an issue, however, in some +scenarios. + +Metadata is stored on a separate device from data, giving the +administrator some freedom, for example to: + +- Improve metadata resilience by storing metadata on a mirrored volume + but data on a non-mirrored one. + +- Improve performance by storing the metadata on SSD. + +Status +====== + +These targets are very much still in the EXPERIMENTAL state. Please +do not yet rely on them in production. But do experiment and offer us +feedback. Different use cases will have different performance +characteristics, for example due to fragmentation of the data volume. + +If you find this software is not performing as expected please mail +dm-devel@redhat.com with details and we'll try our best to improve +things for you. + +Userspace tools for checking and repairing the metadata are under +development. + +Cookbook +======== + +This section describes some quick recipes for using thin provisioning. +They use the dmsetup program to control the device-mapper driver +directly. End users will be advised to use a higher-level volume +manager such as LVM2 once support has been added. + +Pool device +----------- + +The pool device ties together the metadata volume and the data volume. +It maps I/O linearly to the data volume and updates the metadata via +two mechanisms: + +- Function calls from the thin targets + +- Device-mapper 'messages' from userspace which control the creation of new + virtual devices amongst other things. + +Setting up a fresh pool device +------------------------------ + +Setting up a pool device requires a valid metadata device, and a +data device. If you do not have an existing metadata device you can +make one by zeroing the first 4k to indicate empty metadata. + + dd if=/dev/zero of=$metadata_dev bs=4096 count=1 + +The amount of metadata you need will vary according to how many blocks +are shared between thin devices (i.e. through snapshots). If you have +less sharing than average you'll need a larger-than-average metadata device. + +As a guide, we suggest you calculate the number of bytes to use in the +metadata device as 48 * $data_dev_size / $data_block_size but round it up +to 2MB if the answer is smaller. The largest size supported is 16GB. + +If you're creating large numbers of snapshots which are recording large +amounts of change, you may need find you need to increase this. + +Reloading a pool table +---------------------- + +You may reload a pool's table, indeed this is how the pool is resized +if it runs out of space. (N.B. While specifying a different metadata +device when reloading is not forbidden at the moment, things will go +wrong if it does not route I/O to exactly the same on-disk location as +previously.) + +Using an existing pool device +----------------------------- + + dmsetup create pool \ + --table "0 20971520 thin-pool $metadata_dev $data_dev \ + $data_block_size $low_water_mark" + +$data_block_size gives the smallest unit of disk space that can be +allocated at a time expressed in units of 512-byte sectors. People +primarily interested in thin provisioning may want to use a value such +as 1024 (512KB). People doing lots of snapshotting may want a smaller value +such as 128 (64KB). If you are not zeroing newly-allocated data, +a larger $data_block_size in the region of 256000 (128MB) is suggested. +$data_block_size must be the same for the lifetime of the +metadata device. + +$low_water_mark is expressed in blocks of size $data_block_size. If +free space on the data device drops below this level then a dm event +will be triggered which a userspace daemon should catch allowing it to +extend the pool device. Only one such event will be sent. +Resuming a device with a new table itself triggers an event so the +userspace daemon can use this to detect a situation where a new table +already exceeds the threshold. + +Thin provisioning +----------------- + +i) Creating a new thinly-provisioned volume. + + To create a new thinly- provisioned volume you must send a message to an + active pool device, /dev/mapper/pool in this example. + + dmsetup message /dev/mapper/pool 0 "create_thin 0" + + Here '0' is an identifier for the volume, a 24-bit number. It's up + to the caller to allocate and manage these identifiers. If the + identifier is already in use, the message will fail with -EEXIST. + +ii) Using a thinly-provisioned volume. + + Thinly-provisioned volumes are activated using the 'thin' target: + + dmsetup create thin --table "0 2097152 thin /dev/mapper/pool 0" + + The last parameter is the identifier for the thinp device. + +Internal snapshots +------------------ + +i) Creating an internal snapshot. + + Snapshots are created with another message to the pool. + + N.B. If the origin device that you wish to snapshot is active, you + must suspend it before creating the snapshot to avoid corruption. + This is NOT enforced at the moment, so please be careful! + + dmsetup suspend /dev/mapper/thin + dmsetup message /dev/mapper/pool 0 "create_snap 1 0" + dmsetup resume /dev/mapper/thin + + Here '1' is the identifier for the volume, a 24-bit number. '0' is the + identifier for the origin device. + +ii) Using an internal snapshot. + + Once created, the user doesn't have to worry about any connection + between the origin and the snapshot. Indeed the snapshot is no + different from any other thinly-provisioned device and can be + snapshotted itself via the same method. It's perfectly legal to + have only one of them active, and there's no ordering requirement on + activating or removing them both. (This differs from conventional + device-mapper snapshots.) + + Activate it exactly the same way as any other thinly-provisioned volume: + + dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1" + +Deactivation +------------ + +All devices using a pool must be deactivated before the pool itself +can be. + + dmsetup remove thin + dmsetup remove snap + dmsetup remove pool + +Reference +========= + +'thin-pool' target +------------------ + +i) Constructor + + thin-pool \ + [ []*] + + Optional feature arguments: + - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks. + + Data block size must be between 64KB (128 sectors) and 1GB + (2097152 sectors) inclusive. + + +ii) Status + + / + / + + + transaction id: + A 64-bit number used by userspace to help synchronise with metadata + from volume managers. + + used data blocks / total data blocks + If the number of free blocks drops below the pool's low water mark a + dm event will be sent to userspace. This event is edge-triggered and + it will occur only once after each resume so volume manager writers + should register for the event and then check the target's status. + + held metadata root: + The location, in sectors, of the metadata root that has been + 'held' for userspace read access. '-' indicates there is no + held root. This feature is not yet implemented so '-' is + always returned. + +iii) Messages + + create_thin + + Create a new thinly-provisioned device. + is an arbitrary unique 24-bit identifier chosen by + the caller. + + create_snap + + Create a new snapshot of another thinly-provisioned device. + is an arbitrary unique 24-bit identifier chosen by + the caller. + is the identifier of the thinly-provisioned device + of which the new device will be a snapshot. + + delete + + Deletes a thin device. Irreversible. + + trim + + Delete mappings from the end of a thin device. Irreversible. + You might want to use this if you're reducing the size of + your thinly-provisioned device. In many cases, due to the + sharing of blocks between devices, it is not possible to + determine in advance how much space 'trim' will release. (In + future a userspace tool might be able to perform this + calculation.) + + set_transaction_id + + Userland volume managers, such as LVM, need a way to + synchronise their external metadata with the internal metadata of the + pool target. The thin-pool target offers to store an + arbitrary 64-bit transaction id and return it on the target's + status line. To avoid races you must provide what you think + the current transaction id is when you change it with this + compare-and-swap message. + +'thin' target +------------- + +i) Constructor + + thin + + pool dev: + the thin-pool device, e.g. /dev/mapper/my_pool or 253:0 + + dev id: + the internal device identifier of the device to be + activated. + +The pool doesn't store any size against the thin devices. If you +load a thin target that is smaller than you've been using previously, +then you'll have no access to blocks mapped beyond the end. If you +load a target that is bigger than before, then extra blocks will be +provisioned as and when needed. + +If you wish to reduce the size of your thin device and potentially +regain some space then send the 'trim' message to the pool. + +ii) Status + + diff --git a/doc/kernel/uevent.txt b/doc/kernel/uevent.txt new file mode 100644 index 000000000..07edbd85c --- /dev/null +++ b/doc/kernel/uevent.txt @@ -0,0 +1,97 @@ +The device-mapper uevent code adds the capability to device-mapper to create +and send kobject uevents (uevents). Previously device-mapper events were only +available through the ioctl interface. The advantage of the uevents interface +is the event contains environment attributes providing increased context for +the event avoiding the need to query the state of the device-mapper device after +the event is received. + +There are two functions currently for device-mapper events. The first function +listed creates the event and the second function sends the event(s). + +void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, + const char *path, unsigned nr_valid_paths) + +void dm_send_uevents(struct list_head *events, struct kobject *kobj) + + +The variables added to the uevent environment are: + +Variable Name: DM_TARGET +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: +Value: Name of device-mapper target that generated the event. + +Variable Name: DM_ACTION +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: +Value: Device-mapper specific action that caused the uevent action. + PATH_FAILED - A path has failed. + PATH_REINSTATED - A path has been reinstated. + +Variable Name: DM_SEQNUM +Uevent Action(s): KOBJ_CHANGE +Type: unsigned integer +Description: A sequence number for this specific device-mapper device. +Value: Valid unsigned integer range. + +Variable Name: DM_PATH +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: Major and minor number of the path device pertaining to this +event. +Value: Path name in the form of "Major:Minor" + +Variable Name: DM_NR_VALID_PATHS +Uevent Action(s): KOBJ_CHANGE +Type: unsigned integer +Description: +Value: Valid unsigned integer range. + +Variable Name: DM_NAME +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: Name of the device-mapper device. +Value: Name + +Variable Name: DM_UUID +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: UUID of the device-mapper device. +Value: UUID. (Empty string if there isn't one.) + +An example of the uevents generated as captured by udevmonitor is shown +below. + +1.) Path failure. +UEVENT[1192521009.711215] change@/block/dm-3 +ACTION=change +DEVPATH=/block/dm-3 +SUBSYSTEM=block +DM_TARGET=multipath +DM_ACTION=PATH_FAILED +DM_SEQNUM=1 +DM_PATH=8:32 +DM_NR_VALID_PATHS=0 +DM_NAME=mpath2 +DM_UUID=mpath-35333333000002328 +MINOR=3 +MAJOR=253 +SEQNUM=1130 + +2.) Path reinstate. +UEVENT[1192521132.989927] change@/block/dm-3 +ACTION=change +DEVPATH=/block/dm-3 +SUBSYSTEM=block +DM_TARGET=multipath +DM_ACTION=PATH_REINSTATED +DM_SEQNUM=2 +DM_PATH=8:32 +DM_NR_VALID_PATHS=1 +DM_NAME=mpath2 +DM_UUID=mpath-35333333000002328 +MINOR=3 +MAJOR=253 +SEQNUM=1131 diff --git a/doc/kernel/zero.txt b/doc/kernel/zero.txt new file mode 100644 index 000000000..20fb38e7f --- /dev/null +++ b/doc/kernel/zero.txt @@ -0,0 +1,37 @@ +dm-zero +======= + +Device-Mapper's "zero" target provides a block-device that always returns +zero'd data on reads and silently drops writes. This is similar behavior to +/dev/zero, but as a block-device instead of a character-device. + +Dm-zero has no target-specific parameters. + +One very interesting use of dm-zero is for creating "sparse" devices in +conjunction with dm-snapshot. A sparse device reports a device-size larger +than the amount of actual storage space available for that device. A user can +write data anywhere within the sparse device and read it back like a normal +device. Reads to previously unwritten areas will return a zero'd buffer. When +enough data has been written to fill up the actual storage space, the sparse +device is deactivated. This can be very useful for testing device and +filesystem limitations. + +To create a sparse device, start by creating a dm-zero device that's the +desired size of the sparse device. For this example, we'll assume a 10TB +sparse device. + +TEN_TERABYTES=`expr 10 \* 1024 \* 1024 \* 1024 \* 2` # 10 TB in sectors +echo "0 $TEN_TERABYTES zero" | dmsetup create zero1 + +Then create a snapshot of the zero device, using any available block-device as +the COW device. The size of the COW device will determine the amount of real +space available to the sparse device. For this example, we'll assume /dev/sdb1 +is an available 10GB partition. + +echo "0 $TEN_TERABYTES snapshot /dev/mapper/zero1 /dev/sdb1 p 128" | \ + dmsetup create sparse1 + +This will create a 10TB sparse device called /dev/mapper/sparse1 that has +10GB of actual storage space available. If more than 10GB of data is written +to this device, it will start returning I/O errors. +