From fd5e033908b7b743b5650790f196761dd930f988 Mon Sep 17 00:00:00 2001 From: Kiyoshi Ueda Date: Mon, 22 Jun 2009 10:12:27 +0100 Subject: [PATCH] dm mpath: add queue length load balancer This patch adds a dynamic load balancer, dm-queue-length, which balances the number of in-flight I/Os across the paths. The code is based on the patch posted by Stefan Bader: https://www.redhat.com/archives/dm-devel/2005-October/msg00050.html Signed-off-by: Stefan Bader Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Alasdair G Kergon --- .../device-mapper/dm-queue-length.txt | 39 +++ drivers/md/Kconfig | 9 + drivers/md/Makefile | 1 + drivers/md/dm-queue-length.c | 263 ++++++++++++++++++ 4 files changed, 312 insertions(+) create mode 100644 Documentation/device-mapper/dm-queue-length.txt create mode 100644 drivers/md/dm-queue-length.c diff --git a/Documentation/device-mapper/dm-queue-length.txt b/Documentation/device-mapper/dm-queue-length.txt new file mode 100644 index 00000000000..f4db2562175 --- /dev/null +++ b/Documentation/device-mapper/dm-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/drivers/md/Kconfig b/drivers/md/Kconfig index 36e0675be9f..3b311d27334 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -249,6 +249,15 @@ config DM_MULTIPATH ---help--- Allow volume managers to support multipath hardware. +config DM_MULTIPATH_QL + tristate "I/O Path Selector based on the number of in-flight I/Os" + depends on DM_MULTIPATH + ---help--- + This path selector is a dynamic load balancer which selects + the path with the least number of in-flight I/Os. + + If unsure, say N. + config DM_DELAY tristate "I/O delaying target (EXPERIMENTAL)" depends on BLK_DEV_DM && EXPERIMENTAL diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 45cc5951d92..ff9f545dd51 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o obj-$(CONFIG_DM_CRYPT) += dm-crypt.o obj-$(CONFIG_DM_DELAY) += dm-delay.o obj-$(CONFIG_DM_MULTIPATH) += dm-multipath.o dm-round-robin.o +obj-$(CONFIG_DM_MULTIPATH_QL) += dm-queue-length.o obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o obj-$(CONFIG_DM_ZERO) += dm-zero.o diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-queue-length.c new file mode 100644 index 00000000000..f92b6cea9d9 --- /dev/null +++ b/drivers/md/dm-queue-length.c @@ -0,0 +1,263 @@ +/* + * Copyright (C) 2004-2005 IBM Corp. All Rights Reserved. + * Copyright (C) 2006-2009 NEC Corporation. + * + * dm-queue-length.c + * + * Module Author: Stefan Bader, IBM + * Modified by: Kiyoshi Ueda, NEC + * + * This file is released under the GPL. + * + * queue-length path selector - choose a path with the least number of + * in-flight I/Os. + */ + +#include "dm.h" +#include "dm-path-selector.h" + +#include +#include +#include +#include +#include + +#define DM_MSG_PREFIX "multipath queue-length" +#define QL_MIN_IO 128 +#define QL_VERSION "0.1.0" + +struct selector { + struct list_head valid_paths; + struct list_head failed_paths; +}; + +struct path_info { + struct list_head list; + struct dm_path *path; + unsigned repeat_count; + atomic_t qlen; /* the number of in-flight I/Os */ +}; + +static struct selector *alloc_selector(void) +{ + struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (s) { + INIT_LIST_HEAD(&s->valid_paths); + INIT_LIST_HEAD(&s->failed_paths); + } + + return s; +} + +static int ql_create(struct path_selector *ps, unsigned argc, char **argv) +{ + struct selector *s = alloc_selector(); + + if (!s) + return -ENOMEM; + + ps->context = s; + return 0; +} + +static void ql_free_paths(struct list_head *paths) +{ + struct path_info *pi, *next; + + list_for_each_entry_safe(pi, next, paths, list) { + list_del(&pi->list); + kfree(pi); + } +} + +static void ql_destroy(struct path_selector *ps) +{ + struct selector *s = ps->context; + + ql_free_paths(&s->valid_paths); + ql_free_paths(&s->failed_paths); + kfree(s); + ps->context = NULL; +} + +static int ql_status(struct path_selector *ps, struct dm_path *path, + status_type_t type, char *result, unsigned maxlen) +{ + unsigned sz = 0; + struct path_info *pi; + + /* When called with NULL path, return selector status/args. */ + if (!path) + DMEMIT("0 "); + else { + pi = path->pscontext; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%d ", atomic_read(&pi->qlen)); + break; + case STATUSTYPE_TABLE: + DMEMIT("%u ", pi->repeat_count); + break; + } + } + + return sz; +} + +static int ql_add_path(struct path_selector *ps, struct dm_path *path, + int argc, char **argv, char **error) +{ + struct selector *s = ps->context; + struct path_info *pi; + unsigned repeat_count = QL_MIN_IO; + + /* + * Arguments: [] + * : The number of I/Os before switching path. + * If not given, default (QL_MIN_IO) is used. + */ + if (argc > 1) { + *error = "queue-length ps: incorrect number of arguments"; + return -EINVAL; + } + + if ((argc == 1) && (sscanf(argv[0], "%u", &repeat_count) != 1)) { + *error = "queue-length ps: invalid repeat count"; + return -EINVAL; + } + + /* Allocate the path information structure */ + pi = kmalloc(sizeof(*pi), GFP_KERNEL); + if (!pi) { + *error = "queue-length ps: Error allocating path information"; + return -ENOMEM; + } + + pi->path = path; + pi->repeat_count = repeat_count; + atomic_set(&pi->qlen, 0); + + path->pscontext = pi; + + list_add_tail(&pi->list, &s->valid_paths); + + return 0; +} + +static void ql_fail_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move(&pi->list, &s->failed_paths); +} + +static int ql_reinstate_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + + list_move_tail(&pi->list, &s->valid_paths); + + return 0; +} + +/* + * Select a path having the minimum number of in-flight I/Os + */ +static struct dm_path *ql_select_path(struct path_selector *ps, + unsigned *repeat_count, size_t nr_bytes) +{ + struct selector *s = ps->context; + struct path_info *pi = NULL, *best = NULL; + + if (list_empty(&s->valid_paths)) + return NULL; + + /* Change preferred (first in list) path to evenly balance. */ + list_move_tail(s->valid_paths.next, &s->valid_paths); + + list_for_each_entry(pi, &s->valid_paths, list) { + if (!best || + (atomic_read(&pi->qlen) < atomic_read(&best->qlen))) + best = pi; + + if (!atomic_read(&best->qlen)) + break; + } + + if (!best) + return NULL; + + *repeat_count = best->repeat_count; + + return best->path; +} + +static int ql_start_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_inc(&pi->qlen); + + return 0; +} + +static int ql_end_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + + atomic_dec(&pi->qlen); + + return 0; +} + +static struct path_selector_type ql_ps = { + .name = "queue-length", + .module = THIS_MODULE, + .table_args = 1, + .info_args = 1, + .create = ql_create, + .destroy = ql_destroy, + .status = ql_status, + .add_path = ql_add_path, + .fail_path = ql_fail_path, + .reinstate_path = ql_reinstate_path, + .select_path = ql_select_path, + .start_io = ql_start_io, + .end_io = ql_end_io, +}; + +static int __init dm_ql_init(void) +{ + int r = dm_register_path_selector(&ql_ps); + + if (r < 0) + DMERR("register failed %d", r); + + DMINFO("version " QL_VERSION " loaded"); + + return r; +} + +static void __exit dm_ql_exit(void) +{ + int r = dm_unregister_path_selector(&ql_ps); + + if (r < 0) + DMERR("unregister failed %d", r); +} + +module_init(dm_ql_init); +module_exit(dm_ql_exit); + +MODULE_AUTHOR("Stefan Bader "); +MODULE_DESCRIPTION( + "(C) Copyright IBM Corp. 2004,2005 All Rights Reserved.\n" + DM_NAME " path selector to balance the number of in-flight I/Os" +); +MODULE_LICENSE("GPL");