Hi everyone,

This is dm-ioband version 0.0.3 release.

Dm-ioband is an I/O bandwidth controller implemented as a device-mapper driver,
which gives specified bandwidth to each job running on the same physical
device.

Changes since 0.0.2 (23rd January):
   - Ported to linux-2.6.24.
   - Rename the name of this device-mapper device as "ioband."
   - The output format of "dmsetup table" can be recognized by "dmsetup
     create/load/reload."
   - Add a new feature to block processes requesting BIOs in case the number
     of the uncompleted BIOs becomes too large.
   - Gid can be used as an ioband group type.
   - Support "dmsetup suspend --noflush."
   - Fix the problem that "dmsetup detach" doesn't wait the completion of
     all the BIOs in the detaching group.
   - Fix the problem that "dmsetup message attach" can't accept ID 0.
   - Code cleanups. Use prefix "dm_" for the global symbols.
   - Add examples in the document.

Thanks,
Ryo Tsuruta
_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers

Here is the patch of dm-ioband.

Based on 2.6.24
Signed-off-by: Ryo Tsuruta <ryov@valinux.co.jp>
Signed-off-by: Hirokazu Takahashi <taka@valinux.co.jp>

diff -uprN linux-2.6.24.orig/drivers/md/Kconfig linux-2.6.24/drivers/md/Kconfig
--- linux-2.6.24.orig/drivers/md/Kconfig	2008-01-25 07:58:37.000000000 +0900
+++ linux-2.6.24/drivers/md/Kconfig	2008-02-05 19:09:41.000000000 +0900
@@ -288,4 +288,17 @@ config DM_UEVENT
 	---help---
 	Generate udev events for DM events.
 
+config DM_IOBAND
+	tristate "I/O bandwidth control (EXPERIMENTAL)"
+	depends on BLK_DEV_DM && EXPERIMENTAL
+	---help---
+	This device-mapper target allows to define how the
+	available bandwith of a storage device should be
+	shared between processes, cgroups, the partitions or the LUNs.
+
+	Information on how to use dm-ioband is available in:
+	   <file:Documentation/device-mapper/ioband.txt>.
+
+	If unsure, say N.
+
 endif # MD
diff -uprN linux-2.6.24.orig/drivers/md/Makefile linux-2.6.24/drivers/md/Makefile
--- linux-2.6.24.orig/drivers/md/Makefile	2008-01-25 07:58:37.000000000 +0900
+++ linux-2.6.24/drivers/md/Makefile	2008-02-05 19:09:41.000000000 +0900
@@ -9,6 +9,7 @@ dm-snapshot-objs := dm-snap.o dm-excepti
 dm-mirror-objs	:= dm-log.o dm-raid1.o
 dm-rdac-objs	:= dm-mpath-rdac.o
 dm-hp-sw-objs	:= dm-mpath-hp-sw.o
+dm-ioband-objs	:= dm-ioband-ctl.o dm-ioband-policy.o dm-ioband-type.o
 md-mod-objs     := md.o bitmap.o
 raid456-objs	:= raid5.o raid6algos.o raid6recov.o raid6tables.o \
 		   raid6int1.o raid6int2.o raid6int4.o \
@@ -41,6 +42,7 @@ obj-$(CONFIG_DM_MULTIPATH_RDAC)	+= dm-rd
 obj-$(CONFIG_DM_SNAPSHOT)	+= dm-snapshot.o
 obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
+obj-$(CONFIG_DM_IOBAND)		+= dm-ioband.o
 
 quiet_cmd_unroll = UNROLL  $@
       cmd_unroll = $(PERL) $(srctree)/$(src)/unroll.pl $(UNROLL) \
diff -uprN linux-2.6.24.orig/drivers/md/dm-ioband-ctl.c linux-2.6.24/drivers/md/dm-ioband-ctl.c
--- linux-2.6.24.orig/drivers/md/dm-ioband-ctl.c	1970-01-01 09:00:00.000000000 +0900
+++ linux-2.6.24/drivers/md/dm-ioband-ctl.c	2008-02-05 19:09:41.000000000 +0900
@@ -0,0 +1,947 @@
+/*
+ * Copyright (C) 2008 VA Linux Systems Japan K.K.
+ * Authors: Hirokazu Takahashi <taka@valinux.co.jp>
+ *          Ryo Tsuruta <ryov@valinux.co.jp>
+ *
+ *  I/O bandwidth control
+ *
+ * This file is released under the GPL.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/raid/md.h>
+#include "dm.h"
+#include "dm-bio-list.h"
+#include "dm-ioband.h"
+
+#define DM_MSG_PREFIX "ioband"
+
+static LIST_HEAD(ioband_device_list);
+/* to protect ioband_device_list */
+static DEFINE_SPINLOCK(ioband_devicelist_lock);
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,24)
+static void ioband_conduct(void *);
+#else
+static void ioband_conduct(struct work_struct *);
+#endif
+static void ioband_hold_bio(struct ioband_group *, struct bio *);
+static struct bio *ioband_pop_bio(struct ioband_group *);
+static int ioband_set_param(struct ioband_group *, char *, char *);
+static int ioband_group_attach(struct ioband_group *, int);
+
+int ioband_debug;	/* just for debugging */
+
+static void policy_init(struct ioband_device *dp, char *name)
+{
+	struct policy_type *p;
+	for (p = dm_ioband_policy_type; (p->p_name); p++) {
+		if (!strcmp(name, p->p_name))
+			break;
+	}
+
+	p->p_policy_init(dp);
+	if (!dp->g_hold_bio)
+		dp->g_hold_bio = ioband_hold_bio;
+	if (!dp->g_pop_bio)
+		dp->g_pop_bio = ioband_pop_bio;
+}
+
+static struct ioband_device *alloc_ioband_device(int devgroup_id, char *name,
+				int io_throttle, int io_limit)
+
+{
+	struct ioband_device *dp = NULL;
+	struct ioband_device *p;
+	struct ioband_device *new;
+	unsigned long flags;
+
+	new = kzalloc(sizeof(struct ioband_device), GFP_KERNEL);
+	if (!new)
+		goto try_to_find;
+
+	/*
+	 * Prepare its own workqueue as generic_make_request() may potentially
+	 * block the workqueue when submitting BIOs.
+	 */
+	new->g_ioband_wq = create_workqueue("kioband");
+	if (!new->g_ioband_wq) {
+		kfree(new);
+		new = NULL;
+		goto try_to_find;
+	}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,24)
+	INIT_WORK(&new->g_conductor, ioband_conduct, new);
+#else
+	INIT_WORK(&new->g_conductor, ioband_conduct);
+#endif
+	INIT_LIST_HEAD(&new->g_groups);
+	INIT_LIST_HEAD(&new->g_list);
+	spin_lock_init(&new->g_lock);
+	new->g_devgroup = devgroup_id;
+	new->g_io_throttle = io_throttle;
+	new->g_io_limit = io_limit;
+	new->g_plug_bio = 0;
+	new->g_issued = 0;
+	new->g_blocked = 0;
+	new->g_ref = 0;
+	new->g_flags = 0;
+	memset(new->g_name, 0, sizeof(new->g_name));
+	new->g_hold_bio = NULL;
+	new->g_pop_bio = NULL;
+	init_waitqueue_head(&new->g_waitq);
+
+try_to_find:
+	spin_lock_irqsave(&ioband_devicelist_lock, flags);
+	list_for_each_entry(p, &ioband_device_list, g_list) {
+		if (p->g_devgroup == devgroup_id) {
+			dp = p;
+			break;
+		}
+	}
+	if (!dp && (new)) {
+		policy_init(new, name);
+		dp = new;
+		new = NULL;
+		list_add_tail(&dp->g_list, &ioband_device_list);
+	}
+	spin_unlock_irqrestore(&ioband_devicelist_lock, flags);
+
+	if (new) {
+		destroy_workqueue(new->g_ioband_wq);
+		kfree(new);
+	}
+
+	return dp;
+}
+
+static inline void release_ioband_device(struct ioband_device *dp)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ioband_devicelist_lock, flags);
+	if (!list_empty(&dp->g_groups)) {
+		spin_unlock_irqrestore(&ioband_devicelist_lock, flags);
+		return;
+	}
+	list_del(&dp->g_list);
+	spin_unlock_irqrestore(&ioband_devicelist_lock, flags);
+	destroy_workqueue(dp->g_ioband_wq);
+	kfree(dp);
+}
+
+static struct ioband_group *ioband_group_find(struct ioband_group *head,int id)
+{
+	struct ioband_group *p;
+	struct ioband_group *gp = NULL;
+
+	list_for_each_entry(p, &head->c_group_list, c_group_list) {
+		if (p->c_id == id || id == IOBAND_ID_ANY)
+			gp = p;
+	}
+	return gp;
+}
+
+static int ioband_group_init(struct ioband_group *gp,
+		struct ioband_group *head, struct ioband_device *dp, int id)
+{
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&gp->c_list);
+	bio_list_init(&gp->c_blocked_bios);
+	gp->c_id = id;	/* should be verified */
+	gp->c_blocked = 0;
+	memset(gp->c_stat, 0, sizeof(gp->c_stat));
+	init_waitqueue_head(&gp->c_waitq);
+	gp->c_flags = 0;
+
+	INIT_LIST_HEAD(&gp->c_group_list);
+
+	gp->c_banddev = dp;
+
+	spin_lock_irqsave(&dp->g_lock, flags);
+	if (head && ioband_group_find(head, id)) {
+		spin_unlock_irqrestore(&dp->g_lock, flags);
+		DMWARN("ioband_group: id=%d already exists.", id);
+		return -EEXIST;
+	}
+	dp->g_ref++;
+	list_add_tail(&gp->c_list, &dp->g_groups);
+
+	dp->g_group_ctr(gp);
+
+	if (head) {
+		list_add_tail(&gp->c_group_list, &head->c_group_list);
+		gp->c_dev = head->c_dev;
+		gp->c_target = head->c_target;
+	}
+
+	spin_unlock_irqrestore(&dp->g_lock, flags);
+
+	return 0;
+}
+
+static inline void ioband_group_release(struct ioband_group *gp)
+{
+	struct ioband_device *dp = gp->c_banddev;
+
+	list_del(&gp->c_list);
+	list_del(&gp->c_group_list);
+	dp->g_ref--;
+	dp->g_group_dtr(gp);
+	kfree(gp);
+}
+
+static void ioband_group_destroy_all(struct ioband_group *gp)
+{
+	struct ioband_device *dp = gp->c_banddev;
+	struct ioband_group *group;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dp->g_lock, flags);
+	while ((group = ioband_group_find(gp, IOBAND_ID_ANY)))
+		ioband_group_release(group);
+	ioband_group_release(gp);
+	spin_unlock_irqrestore(&dp->g_lock, flags);
+}
+
+static void ioband_group_stop(struct ioband_group *gp)
+{
+	struct ioband_device *dp = gp->c_banddev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dp->g_lock, flags);
+	set_group_down(gp);
+	spin_unlock_irqrestore(&dp->g_lock, flags);
+	queue_work(dp->g_ioband_wq, &dp->g_conductor);
+	flush_workqueue(dp->g_ioband_wq);
+}
+
+static void ioband_group_stop_all(struct ioband_group *head, int suspend)
+{
+	struct ioband_device *dp = head->c_banddev;
+	struct ioband_group *p;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dp->g_lock, flags);
+	list_for_each_entry(p, &head->c_group_list, c_group_list) {
+		set_group_down(p);
+		if (suspend) {
+			set_group_suspended(p);
+			dprintk(KERN_ERR "ioband suspend: gp(%p)\n", p);
+		}
+
+	}
+	set_group_down(head);
+	if (suspend) {
+		set_group_suspended(head);
+		dprintk(KERN_ERR "ioband suspend: gp(%p)\n", head);
+	}
+	spin_unlock_irqrestore(&dp->g_lock, flags);
+	queue_work(dp->g_ioband_wq, &dp->g_conductor);
+	flush_workqueue(dp->g_ioband_wq);
+}
+
+static void ioband_group_resume_all(struct ioband_group *head)
+{
+	struct ioband_device *dp = head->c_banddev;
+	struct ioband_group *p;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dp->g_lock, flags);
+	list_for_each_entry(p, &head->c_group_list, c_group_list) {
+		clear_group_down(p);
+		clear_group_suspended(p);
+		dprintk(KERN_ERR "ioband resume: gp(%p)\n", p);
+	}
+	clear_group_down(head);
+	clear_group_suspended(head);
+	dprintk(KERN_ERR "ioband resume: gp(%p)\n", head);
+	spin_unlock_irqrestore(&dp->g_lock, flags);
+}
+
+/*
+ * Create a new band device:
+ *   parameters:  <device> <device-group-id> [<io_throttle>] [<io_limit>]
+ */
+static int ioband_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+{
+	struct ioband_group *gp;
+	struct ioband_device *dp;
+	int io_throttle = DEFAULT_IO_THROTTLE;
+	int io_limit = DEFAULT_IO_LIMIT;
+	int devgroup_id;
+	int val;
+	in

Here is the document of dm-ioband.

Based on 2.6.24
Signed-off-by: Ryo Tsuruta <ryov@valinux.co.jp>
Signed-off-by: Hirokazu Takahashi <taka@valinux.co.jp>

diff -uprN linux-2.6.24.orig/Documentation/device-mapper/ioband.txt linux-2.6.24/Documentation/device-mapper/ioband.txt
--- linux-2.6.24.orig/Documentation/device-mapper/ioband.txt	1970-01-01 09:00:00.000000000 +0900
+++ linux-2.6.24/Documentation/device-mapper/ioband.txt	2008-02-05 19:09:41.000000000 +0900
@@ -0,0 +1,728 @@
+======================
+Document for dm-ioband
+======================
+
+Contents:
+  What's dm-ioband all about?
+  Differences from the CFQ I/O scheduler
+  How dm-ioband works
+  Setup and Installation
+  Getting started
+  Command Reference
+  Examples
+  TODO
+
+
+What's dm-ioband all about?
+===========================
+dm-ioband is an I/O bandwidth controller implemented as a device-mapper driver.
+Several jobs using the same physical device have to share the bandwidth of
+the device. dm-ioband gives bandwidth to each job according to its weight, 
+which each job can set its own value to.
+
+At this time, a job is a group of processes with the same pid or pgrp or uid.
+There is also a plan to make it support cgroup. A job can also be a virtual
+machine such as KVM or Xen.
+
+  +------+ +------+ +------+   +------+ +------+ +------+ 
+  |cgroup| |cgroup| | the  |   | pid  | | pid  | | the  |  jobs
+  |  A   | |  B   | |others|   |  X   | |  Y   | |others| 
+  +--|---+ +--|---+ +--|---+   +--|---+ +--|---+ +--|---+   
+  +--V----+---V---+----V---+   +--V----+---V---+----V---+   
+  | group | group | default|   | group | group | default|  ioband groups
+  |       |       |  group |   |       |       |  group | 
+  +-------+-------+--------+   +-------+-------+--------+
+  |        ioband1         |   |       ioband2          |  ioband devices
+  +-----------|------------+   +-----------|------------+
+  +-----------V--------------+-------------V------------+
+  |                          |                          |
+  |          sdb1            |           sdb2           |  physical devices
+  +--------------------------+--------------------------+
+
+
+Differences from the CFQ I/O scheduler
+======================================
+
+Dm-ioband is flexible to configure the bandwidth settings. 
+
+Dm-ioband can work with any type of I/O scheduler such as the NOOP scheduler,
+which is often chosen for high-end storages, since it is implemented outside
+the I/O scheduling layer. It allows both of partition based bandwidth control
+and job --- a group of processes --- based control. In addition, it can
+set different configuration on each physical device to control its bandwidth.
+
+Meanwhile the current implementation of the CFQ scheduler has seven IO priority
+levels and all jobs whose processes have the same IO priority share the
+bandwidth assigned to this level between them. And IO priority is an attribute
+of a process so that it equally effects to all block devices.
+
+
+How dm-ioband works.
+====================
+Every ioband device has one ioband group, which by default is called the
+default group.
+
+Ioband devices can also have extra ioband groups in them. Each ioband group
+has a job to support and a weight. Proportional to the weight, dm-ioband gives
+tokens to the group.
+
+A group passes on I/O requests that its job issues to the underlying
+layer so long as it has tokens left, while requests are blocked
+if there aren't any tokens left in the group. One token is consumed each
+time the group passes on a request. dm-ioband will refill groups with tokens
+once all of groups that have requests on a given physical device use up their
+tokens.
+
+With this approach, a job running on an ioband group with large weight is
+guaranteed to be able to issue a large number of I/O requests.
+
+
+Setup and Installation
+======================
+
+Build a kernel with these options enabled:
+
+  CONFIG_MD
+  CONFIG_BLK_DEV_DM
+  CONFIG_DM_IOBAND
+
+If compiled as module, use modprobe to load dm-ioband.
+
+  # make modules
+  # make modules_install
+  # depmod -a
+  # modprobe dm-ioband
+
+"dmsetup targets" command shows all available device-mapper targets.
+"ioband" is displayed if dm-ioband has been loaded.
+
+  # dmsetup targets
+  ioband           v0.0.3
+
+
+Getting started
+===============
+The following is a brief description how to control the I/O bandwidth of
+disks. In this description, we'll take one disk with two partitions as an
+example target.
+
+
+Create and map ioband devices
+-----------------------------
+Create two ioband devices "ioband1" and "ioband2" and map them to "/dev/sda1"
+and "/dev/sda2" respectively.
+
+ # echo "0 $(blockdev --getsize /dev/sda1) ioband /dev/sda1 1" | \
+     dmsetup create ioband1
+ # echo "0 $(blockdev --getsize /dev/sda2) ioband /dev/sda2 1" | \
+     dmsetup create ioband2
+
+If the commands are successful then the device files "/dev/mapper/ioband1"
+and "/dev/mapper/ioband2" will have been created.
+
+
+Bandwidth control
+-----------------
+In this example, weights of 40 and 10 will be assigned to "ioband1" and
+"ioband2" respectively. This is done using the following commands:
+
+ # dmsetup message ioband1 0 weight 40
+ # dmsetup message ioband2 0 weight 10
+
+After these commands, "ioband1" can use 80% --- 40/(40+10)*100 --- of the
+bandwidth of the physical disk "/dev/sda" while "ioband2" can use 20%.
+
+
+Additional bandwidth control
+----------------------------
+In this example two extra ioband groups are created on "ioband1".
+The first group consists of all the processes with user-id 1000 and the
+second group consists of all the processes with user-id 2000. Their
+weights are 30 and 20 respectively.
+
+ # dmsetup message ioband1 0 type user
+ # dmsetup message ioband1 0 attach 1000
+ # dmsetup message ioband1 0 attach 2000
+ # dmsetup message ioband1 0 weight 1000:30
+ # dmsetup message ioband1 0 weight 2000:20
+
+Now the processes in the user-id 1000 group can use 30% ---
+30/(30+20+40+10)*100 --- of the bandwidth of the physical disk.
+
+ ioband device   ioband group                   weight
+ ioband1         user id 1000                     30
+ ioband1         user id 2000                     20
+ ioband1         default group(the other users)   40
+ ioband2         default group                    10
+
+
+Remove the ioband devices
+-------------------------
+Remove the ioband devices when no longer used.
+
+  # dmsetup remove ioband1
+  # dmsetup remove ioband2
+
+
+Command Reference
+=================
+
+
+Create an ioband device
+-----------------------
+SYNOPSIS
+  dmsetup create IOBAND_DEVICE
+
+DESCRIPTION
+  Create an ioband device with the given name IOBAND_DEVICE. The following
+  arguments, which dmsetup command reads from standard input, are also
+  required.
+
+      Logical starting sector. This must be "0."
+      The number of sectors to use.
+      "ioband" as a target type.
+      The path name of the physical device.
+      Device group ID.
+      I/O throttling value (optional)
+      I/O limiting value (optional)
+
+  The same device group ID must be set among the ioband devices that share
+  the same bandwidth, which means they work on the same physical disk.
+  "The number of sectors to use" should be "the number of sectors the physical
+  device." I/O throttling value and I/O limiting value, which are described
+  later in this document, are optional.
+
+  If the command is successful, the device file
+  "/dev/device-mapper/IOBAND_DEVICE" will have been created.
+  An ioband group is also created and attached to IOBAND_DEVICE as the default
+  ioband group.
+
+EXAMPLE
+  Create an ioband device with the following parameters:
+    physical device = "/dev/sda1"
+    ioband device name = "ioband1"
+    device group ID = "1"
+    I/O throttling value = "10"
+    I/O limiting value = "200"
+
+    # echo "0 $(blockdev --getsize /dev/sda1) ioband /dev/sda1 1 10 200" | \
+        dmsetup create ioband1
+
+  Create two device groups (ID=1,2). The bandwidths of these device groups
+  will be individually controlled.
+
+    # echo "0 $(blockdev --getsize /dev/sda1) ioband /dev/sda1 1" | \
+        dmsetup create ioband1
+    # echo "0 $(blockdev --getsize /dev/sda2) ioband /dev/sda2 1" | \
+        dmsetup create ioband2
+    # echo "0 $(blockdev --getsize /dev/sdb3) ioband /dev/sdb3 2" | \
+        dmsetup create ioband3
+    # echo "0 $(blockdev --getsize /dev/sdb4) ioband /dev/sdb4 2" | \
+        dmsetup create ioband4
+
+
+Remove the ioband device
+------------------------
+SYNOPSIS
+  dmsetup remove IOBAND_DEVICE
+
+DESCRIPTION
+  Remove the specified ioband device IOBAND_DEVICE. All the band groups
+  attached to the ioband device are also removed automatically.
+
+EXAMPLE
+  Remove ioband device "ioband1."
+
+  # dmsetup remove ioband1
+
+
+Set an ioband group type
+--------------------------
+SYNOPSIS
+  dmsetup message IOBAND_DEVICE 0 type TYPE
+
+DESCRIPTION
+  Set the ioband group type of the specified ioband device IOBAND_DEVICE. TYPE
+  must be one of "user", "gid", "pid" or "pgrp." Once the type is set, new
+  ioband groups can be created on IOBAND_DEVICE.
+
+EXAMPLE
+  Set the ioband group type of ioband device "ioband1" to "user."
+
+  # dmsetup message ioband1 0 type user
+
+
+Create an ioband group
+----------------------
+SYNOPSIS
+  dmsetup message IOBAND_DEVICE 0 attach ID
+
+DESCRIPTION
+  Create an ioband group and attach it to IOBAND_DEVICE.
+  ID specifies user-id, group-id, process-id or process-group-id depending
+  the ioband group type of IOBAND_