Virtualization - Apr 2009 - [PATCH 1/5] bio-cgroup: Introduction

Hi all,

This is a new release of bio-cgroup which provides an IO tracking
mechanism. The patches can be applied to the kernel 2.6.30-rc1 and you
can also download them from the following site.
http://people.valinux.co.jp/~ryov/bio-cgroup/

What's bio-cgroup all about?
===========================
With this feature, you can determine the owners of any type of
I/Os. This makes dm-ioband_--_I/O_bandwidth_controller_-- be able to
control the Block I/O bandwidths even when it accepts delayed write
requests. Dm-ioband can find the owner cgroup of each request. It is
also possible that the other people who work on the i/o bandwidth
throttling use this functionality to control asynchronous I/Os with a
little enhancement.

Setting up bio-cgroup
====================
You have to apply the patch dm-ioband_v1.9.0 before applying this
series of bio-cgroup patches.
And you have to select the following config options when compiling
kernel.

      CONFIG_CGROUPS=y
      CONFIG_CGROUP_BIO=y

And I recommend you should also select the options for cgroup memory
subsystem, because it makes it possible to give some I/O bandwidth and
some memory to a certain cgroup to control delayed write requests and
the processes in the cgroup will be able to make pages dirty only
inside the cgroup even when the given bandwidth is narrow.

      CONFIG_RESOURCE_COUNTERS=y
      CONFIG_CGROUP_MEM_RES_CTLR=y

Using bio-cgroup
===============
The following shows how to use dm-ioband with cgroups. Please assume
that you want make two cgroups, which we call "bio cgroup" here, to
track down block I/Os and assign them to ioband device "ioband1".

First, mount the bio cgroup filesystem.

      # mount -t cgroup -o bio none /cgroup/bio

Then, make new bio cgroups and put some processes in them.

      # mkdir /cgroup/bio/bgroup1
      # mkdir /cgroup/bio/bgroup2
      # echo 1234 > /cgroup/bio/bgroup1/tasks
      # echo 5678 > /cgroup/bio/bgroup1/tasks

Now, check the ID of each bio cgroup which is just created.

      # cat /cgroup/bio/bgroup1/bio.id
      2
      # cat /cgroup/bio/bgroup2/bio.id
      3

Finally, attach the cgroups to "ioband1" and assign them weights.

      # dmsetup message ioband1 0 type cgroup
      # dmsetup message ioband1 0 attach 2
      # dmsetup message ioband1 0 attach 3
      # dmsetup message ioband1 0 weight 2:30
      # dmsetup message ioband1 0 weight 3:60

You can also make use of the dm-ioband administration tool
iobandctl.py. You can set up the device with the tool as follows.
In this case, you don't need to know the IDs of the cgroups.

      # iobandctl.py group /dev/mapper/ioband1 cgroup \
        /cgroup/bio/bgroup1:30 /cgroup/bio/bgroup2:60

This patch makes the page_cgroup framework be able to be used even if
the compile option of the cgroup memory controller is off.
So bio-cgroup can use this framework without the memory controller.

Based on 2.6.30-rc1
Signed-off-by: Hirokazu Takahashi <taka at valinux.co.jp>
Signed-off-by: Ryo Tsuruta <ryov at valinux.co.jp>

---
 include/linux/memcontrol.h  |    6 ++++++
 include/linux/mmzone.h      |    4 ++--
 include/linux/page_cgroup.h |    8 +++++---
 init/Kconfig                |    4 ++++
 mm/Makefile                 |    3 ++-
 mm/memcontrol.c             |    6 ++++++
 mm/page_cgroup.c            |    3 +--
 7 files changed, 26 insertions(+), 8 deletions(-)

Index: linux-2.6.30-rc1/include/linux/memcontrol.h
==================================================================---
linux-2.6.30-rc1.orig/include/linux/memcontrol.h
+++ linux-2.6.30-rc1/include/linux/memcontrol.h
@@ -37,6 +37,8 @@ struct mm_struct;
  * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
  */
 
+extern void __init_mem_page_cgroup(struct page_cgroup *pc);
+
 extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 /* for swap handling */
@@ -120,6 +122,10 @@ extern bool mem_cgroup_oom_called(struct
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct mem_cgroup;
 
+static inline void __init_mem_page_cgroup(struct page_cgroup *pc)
+{
+}
+
 static inline int mem_cgroup_newpage_charge(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
Index: linux-2.6.30-rc1/include/linux/mmzone.h
==================================================================---
linux-2.6.30-rc1.orig/include/linux/mmzone.h
+++ linux-2.6.30-rc1/include/linux/mmzone.h
@@ -607,7 +607,7 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 	struct page_cgroup *node_page_cgroup;
 #endif
 #endif
@@ -958,7 +958,7 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 	/*
 	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
 	 * section. (see memcontrol.h/page_cgroup.h about this.)
Index: linux-2.6.30-rc1/include/linux/page_cgroup.h
==================================================================---
linux-2.6.30-rc1.orig/include/linux/page_cgroup.h
+++ linux-2.6.30-rc1/include/linux/page_cgroup.h
@@ -1,7 +1,7 @@
 #ifndef __LINUX_PAGE_CGROUP_H
 #define __LINUX_PAGE_CGROUP_H
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#ifdef CONFIG_CGROUP_PAGE
 #include <linux/bit_spinlock.h>
 /*
  * Page Cgroup can be considered as an extended mem_map.
@@ -12,9 +12,11 @@
  */
 struct page_cgroup {
 	unsigned long flags;
-	struct mem_cgroup *mem_cgroup;
 	struct page *page;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+	struct mem_cgroup *mem_cgroup;
 	struct list_head lru;		/* per cgroup LRU list */
+#endif
 };
 
 void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat);
@@ -71,7 +73,7 @@ static inline void unlock_page_cgroup(st
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+#else /* CONFIG_CGROUP_PAGE */
 struct page_cgroup;
 
 static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
Index: linux-2.6.30-rc1/init/Kconfig
==================================================================---
linux-2.6.30-rc1.orig/init/Kconfig
+++ linux-2.6.30-rc1/init/Kconfig
@@ -608,6 +608,10 @@ config CGROUP_MEM_RES_CTLR_SWAP
 
 endif # CGROUPS
 
+config CGROUP_PAGE
+	def_bool y
+	depends on CGROUP_MEM_RES_CTLR
+
 config MM_OWNER
 	bool
 
Index: linux-2.6.30-rc1/mm/Makefile
==================================================================---
linux-2.6.30-rc1.orig/mm/Makefile
+++ linux-2.6.30-rc1/mm/Makefile
@@ -37,4 +37,5 @@ else
 obj-$(CONFIG_SMP) += allocpercpu.o
 endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
+obj-$(CONFIG_CGROUP_PAGE) += page_cgroup.o
Index: linux-2.6.30-rc1/mm/memcontrol.c
==================================================================---
linux-2.6.30-rc1.orig/mm/memcontrol.c
+++ linux-2.6.30-rc1/mm/memcontrol.c
@@ -128,6 +128,12 @@ struct mem_cgroup_lru_info {
 	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
 };
 
+void __meminit __init_mem_page_cgroup(struct page_cgroup *pc)
+{
+	pc->mem_cgroup = NULL;
+	INIT_LIST_HEAD(&pc->lru);
+}
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
Index: linux-2.6.30-rc1/mm/page_cgroup.c
==================================================================---
linux-2.6.30-rc1.orig/mm/page_cgroup.c
+++ linux-2.6.30-rc1/mm/page_cgroup.c
@@ -14,9 +14,8 @@ static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
 {
 	pc->flags = 0;
-	pc->mem_cgroup = NULL;
 	pc->page = pfn_to_page(pfn);
-	INIT_LIST_HEAD(&pc->lru);
+	__init_mem_page_cgroup(pc);
 }
 static unsigned long total_usage;