Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752540AbYKMDOB (ORCPT ); Wed, 12 Nov 2008 22:14:01 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751874AbYKMDNv (ORCPT ); Wed, 12 Nov 2008 22:13:51 -0500 Received: from fms-01.valinux.co.jp ([210.128.90.1]:54598 "EHLO mail.valinux.co.jp" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751252AbYKMDNu (ORCPT ); Wed, 12 Nov 2008 22:13:50 -0500 Date: Thu, 13 Nov 2008 12:14:33 +0900 (JST) Message-Id: <20081113.121433.632868945383117577.ryov@valinux.co.jp> To: linux-kernel@vger.kernel.org, dm-devel@redhat.com, containers@lists.linux-foundation.org, virtualization@lists.linux-foundation.org, xen-devel@lists.xensource.com Cc: agk@sourceware.org, balbir@linux.vnet.ibm.com, xemul@openvz.org, kamezawa.hiroyu@jp.fujitsu.com, fernando@oss.ntt.co.jp Subject: [PATCH 6/8] bio-cgroup: The body of bio-cgroup From: Ryo Tsuruta In-Reply-To: <20081113.121357.75173118738921642.ryov@valinux.co.jp> References: <20081113.121254.625859878544534829.ryov@valinux.co.jp> <20081113.121322.653026525707351102.ryov@valinux.co.jp> <20081113.121357.75173118738921642.ryov@valinux.co.jp> X-Mailer: Mew version 6.1 on Emacs 22.2 / Mule 5.0 (SAKAKI) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 16046 Lines: 544 This is the body of bio-cgroup. Signed-off-by: Hirokazu Takahashi diff -dupr linux-2.6.28-rc2.bc1/block/blk-ioc.c linux-2.6.28-rc2/block/blk-ioc.c --- linux-2.6.28-rc2.bc1/block/blk-ioc.c 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/block/blk-ioc.c 2008-11-12 11:20:33.000000000 +0900 @@ -84,24 +84,28 @@ void exit_io_context(void) } } +void init_io_context(struct io_context *ioc) +{ + atomic_set(&ioc->refcount, 1); + atomic_set(&ioc->nr_tasks, 1); + spin_lock_init(&ioc->lock); + ioc->ioprio_changed = 0; + ioc->ioprio = 0; + ioc->last_waited = jiffies; /* doesn't matter... */ + ioc->nr_batch_requests = 0; /* because this is 0 */ + ioc->aic = NULL; + INIT_RADIX_TREE(&ioc->radix_root, GFP_ATOMIC | __GFP_HIGH); + INIT_HLIST_HEAD(&ioc->cic_list); + ioc->ioc_data = NULL; +} + struct io_context *alloc_io_context(gfp_t gfp_flags, int node) { struct io_context *ret; ret = kmem_cache_alloc_node(iocontext_cachep, gfp_flags, node); - if (ret) { - atomic_set(&ret->refcount, 1); - atomic_set(&ret->nr_tasks, 1); - spin_lock_init(&ret->lock); - ret->ioprio_changed = 0; - ret->ioprio = 0; - ret->last_waited = jiffies; /* doesn't matter... */ - ret->nr_batch_requests = 0; /* because this is 0 */ - ret->aic = NULL; - INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH); - INIT_HLIST_HEAD(&ret->cic_list); - ret->ioc_data = NULL; - } + if (ret) + init_io_context(ret); return ret; } diff -dupr linux-2.6.28-rc2.bc1/include/linux/biotrack.h linux-2.6.28-rc2/include/linux/biotrack.h --- linux-2.6.28-rc2.bc1/include/linux/biotrack.h 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/include/linux/biotrack.h 2008-11-12 21:22:20.000000000 +0900 @@ -0,0 +1,82 @@ +#include +#include +#include + +#ifndef _LINUX_BIOTRACK_H +#define _LINUX_BIOTRACK_H + +#ifdef CONFIG_CGROUP_BIO + +struct io_context; +struct block_device; + +struct bio_cgroup { + struct cgroup_subsys_state css; + int id; + struct io_context *io_context; /* default io_context */ +/* struct radix_tree_root io_context_root; per device io_context */ +}; + +static inline void __init_bio_page_cgroup(struct page_cgroup *pc) +{ + pc->bio_cgroup_id = 0; +} + +static inline int bio_cgroup_disabled(void) +{ + return bio_cgroup_subsys.disabled; +} + +extern void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm); +extern void bio_cgroup_reset_owner(struct page *page, struct mm_struct *mm); +extern void bio_cgroup_reset_owner_pagedirty(struct page *page, + struct mm_struct *mm); +extern void bio_cgroup_copy_owner(struct page *page, struct page *opage); + +extern struct io_context *get_bio_cgroup_iocontext(struct bio *bio); +extern int get_bio_cgroup_id(struct bio *bio); + +#else /* CONFIG_CGROUP_BIO */ + +struct bio_cgroup; + +static inline void __init_bio_page_cgroup(struct page_cgroup *pc) +{ +} + +static inline int bio_cgroup_disabled(void) +{ + return 1; +} + +static inline void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_reset_owner(struct page *page, + struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_reset_owner_pagedirty(struct page *page, + struct mm_struct *mm) +{ +} + +static inline void bio_cgroup_copy_owner(struct page *page, struct page *opage) +{ +} + +static inline struct io_context *get_bio_cgroup_iocontext(struct bio *bio) +{ + return NULL; +} + +static inline int get_bio_cgroup_id(struct bio *bio) +{ + return 0; +} + +#endif /* CONFIG_CGROUP_BIO */ + +#endif /* _LINUX_BIOTRACK_H */ diff -dupr linux-2.6.28-rc2.bc1/include/linux/cgroup_subsys.h linux-2.6.28-rc2/include/linux/cgroup_subsys.h --- linux-2.6.28-rc2.bc1/include/linux/cgroup_subsys.h 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/include/linux/cgroup_subsys.h 2008-11-12 11:20:33.000000000 +0900 @@ -43,6 +43,12 @@ SUBSYS(mem_cgroup) /* */ +#ifdef CONFIG_CGROUP_BIO +SUBSYS(bio_cgroup) +#endif + +/* */ + #ifdef CONFIG_CGROUP_DEVICE SUBSYS(devices) #endif diff -dupr linux-2.6.28-rc2.bc1/include/linux/iocontext.h linux-2.6.28-rc2/include/linux/iocontext.h --- linux-2.6.28-rc2.bc1/include/linux/iocontext.h 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/include/linux/iocontext.h 2008-11-12 11:20:33.000000000 +0900 @@ -104,6 +104,7 @@ int put_io_context(struct io_context *io void exit_io_context(void); struct io_context *get_io_context(gfp_t gfp_flags, int node); struct io_context *alloc_io_context(gfp_t gfp_flags, int node); +void init_io_context(struct io_context *ioc); void copy_io_context(struct io_context **pdst, struct io_context **psrc); #else static inline void exit_io_context(void) diff -dupr linux-2.6.28-rc2.bc1/include/linux/page_cgroup.h linux-2.6.28-rc2/include/linux/page_cgroup.h --- linux-2.6.28-rc2.bc1/include/linux/page_cgroup.h 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/include/linux/page_cgroup.h 2008-11-12 11:20:33.000000000 +0900 @@ -17,6 +17,9 @@ struct page_cgroup { struct mem_cgroup *mem_cgroup; struct list_head lru; /* per cgroup LRU list */ #endif +#ifdef CONFIG_CGROUP_BIO + int bio_cgroup_id; +#endif }; void __init pgdat_page_cgroup_init(struct pglist_data *pgdat); diff -dupr linux-2.6.28-rc2.bc1/init/Kconfig linux-2.6.28-rc2/init/Kconfig --- linux-2.6.28-rc2.bc1/init/Kconfig 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/init/Kconfig 2008-11-12 11:20:33.000000000 +0900 @@ -425,9 +425,20 @@ config CGROUP_MEM_RES_CTLR This config option also selects MM_OWNER config option, which could in turn add some fork/exit overhead. +config CGROUP_BIO + bool "Block I/O cgroup subsystem" + depends on CGROUPS && BLOCK + select MM_OWNER + help + Provides a Resource Controller which enables to track the onwner + of every Block I/O requests. + The information this subsystem provides can be used from any + kind of module such as dm-ioband device mapper modules or + the cfq-scheduler. + config CGROUP_PAGE def_bool y - depends on CGROUP_MEM_RES_CTLR + depends on CGROUP_MEM_RES_CTLR || CGROUP_BIO config MM_OWNER bool diff -dupr linux-2.6.28-rc2.bc1/mm/biotrack.c linux-2.6.28-rc2/mm/biotrack.c --- linux-2.6.28-rc2.bc1/mm/biotrack.c 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/mm/biotrack.c 2008-11-12 11:20:33.000000000 +0900 @@ -0,0 +1,274 @@ +/* biotrack.c - Block I/O Tracking + * + * Copyright (C) VA Linux Systems Japan, 2008 + * Developed by Hirokazu Takahashi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include + +/* + * The block I/O tracking mechanism is implemented on the cgroup memory + * controller framework. It helps to find the the owner of an I/O request + * because every I/O request has a target page and the owner of the page + * can be easily determined on the framework. + */ + +/* Return the bio_cgroup that associates with a cgroup. */ +static inline struct bio_cgroup *cgroup_bio(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, bio_cgroup_subsys_id), + struct bio_cgroup, css); +} + +/* Return the bio_cgroup that associates with a process. */ +static inline struct bio_cgroup *bio_cgroup_from_task(struct task_struct *p) +{ + return container_of(task_subsys_state(p, bio_cgroup_subsys_id), + struct bio_cgroup, css); +} + +static struct idr bio_cgroup_id; +static DEFINE_SPINLOCK(bio_cgroup_idr_lock); +static struct io_context default_bio_io_context; +static struct bio_cgroup default_bio_cgroup = { + .id = 0, + .io_context = &default_bio_io_context, +}; + +/* + * This function is used to make a given page have the bio-cgroup id of + * the owner of this page. + */ +void bio_cgroup_set_owner(struct page *page, struct mm_struct *mm) +{ + struct bio_cgroup *biog; + struct page_cgroup *pc; + + if (bio_cgroup_disabled()) + return; + pc = lookup_page_cgroup(page); + if (unlikely(!pc)) + return; + + pc->bio_cgroup_id = 0; /* 0: default bio_cgroup id */ + if (!mm) + return; + /* + * Locking "pc" isn't necessary here since the current process is + * the only one that can access the members related to bio_cgroup. + */ + rcu_read_lock(); + biog = bio_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!biog)) + goto out; + /* + * css_get(&bio->css) isn't called to increment the reference + * count of this bio_cgroup "biog" so pc->bio_cgroup_id might turn + * invalid even if this page is still active. + * This approach is chosen to minimize the overhead. + */ + pc->bio_cgroup_id = biog->id; +out: + rcu_read_unlock(); +} + +/* + * Change the owner of a given page if necessary. + */ +void bio_cgroup_reset_owner(struct page *page, struct mm_struct *mm) +{ + /* + * A little trick: + * Just call bio_cgroup_set_owner() for pages which are already + * active since the bio_cgroup_id member of page_cgroup can be + * updated without any locks. This is because an integer type of + * variable can be set a new value at once on modern cpus. + */ + bio_cgroup_set_owner(page, mm); +} + +/* + * Change the owner of a given page. This function is only effective for + * pages in the pagecache. + */ +void bio_cgroup_reset_owner_pagedirty(struct page *page, struct mm_struct *mm) +{ + if (PageSwapCache(page) || PageAnon(page)) + return; + if (current->flags & PF_MEMALLOC) + return; + + bio_cgroup_reset_owner(page, mm); +} + +/* + * Assign "page" the same owner as "opage." + */ +void bio_cgroup_copy_owner(struct page *npage, struct page *opage) +{ + struct page_cgroup *npc, *opc; + + if (bio_cgroup_disabled()) + return; + npc = lookup_page_cgroup(npage); + if (unlikely(!npc)) + return; + opc = lookup_page_cgroup(opage); + if (unlikely(!opc)) + return; + + /* + * Do this without any locks. The reason is the same as + * bio_cgroup_reset_owner(). + */ + npc->bio_cgroup_id = opc->bio_cgroup_id; +} + +/* Create a new bio-cgroup. */ +static struct cgroup_subsys_state * +bio_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct bio_cgroup *biog; + struct io_context *ioc; + int ret; + + if (!cgrp->parent) { + biog = &default_bio_cgroup; + init_io_context(biog->io_context); + /* Increment the referrence count not to be released ever. */ + atomic_inc(&biog->io_context->refcount); + idr_init(&bio_cgroup_id); + return &biog->css; + } + + biog = kzalloc(sizeof(*biog), GFP_KERNEL); + ioc = alloc_io_context(GFP_KERNEL, -1); + if (!ioc || !biog) { + ret = -ENOMEM; + goto out_err; + } + biog->io_context = ioc; +retry: + if (!idr_pre_get(&bio_cgroup_id, GFP_KERNEL)) { + ret = -EAGAIN; + goto out_err; + } + spin_lock_irq(&bio_cgroup_idr_lock); + ret = idr_get_new_above(&bio_cgroup_id, (void *)biog, 1, &biog->id); + spin_unlock_irq(&bio_cgroup_idr_lock); + if (ret == -EAGAIN) + goto retry; + else if (ret) + goto out_err; + + return &biog->css; +out_err: + if (biog) + kfree(biog); + if (ioc) + put_io_context(ioc); + return ERR_PTR(ret); +} + +/* Delete the bio-cgroup. */ +static void bio_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct bio_cgroup *biog = cgroup_bio(cgrp); + + put_io_context(biog->io_context); + + spin_lock_irq(&bio_cgroup_idr_lock); + idr_remove(&bio_cgroup_id, biog->id); + spin_unlock_irq(&bio_cgroup_idr_lock); + + kfree(biog); +} + +static struct bio_cgroup *find_bio_cgroup(int id) +{ + struct bio_cgroup *biog; + spin_lock_irq(&bio_cgroup_idr_lock); + /* + * It might fail to find A bio-group associated with "id" since it + * is allowed to remove the bio-cgroup even when some of I/O requests + * this group issued haven't completed yet. + */ + biog = (struct bio_cgroup *)idr_find(&bio_cgroup_id, id); + spin_unlock_irq(&bio_cgroup_idr_lock); + return biog; +} + +/* Determine the bio-cgroup id of a given bio. */ +int get_bio_cgroup_id(struct bio *bio) +{ + struct page_cgroup *pc; + struct page *page = bio_iovec_idx(bio, 0)->bv_page; + int id = 0; + + pc = lookup_page_cgroup(page); + if (pc) + id = pc->bio_cgroup_id; + return id; +} + +/* Determine the iocontext of the bio-cgroup that issued a given bio. */ +struct io_context *get_bio_cgroup_iocontext(struct bio *bio) +{ + struct bio_cgroup *biog = NULL; + struct io_context *ioc; + int id = 0; + + id = get_bio_cgroup_id(bio); + if (id) + biog = find_bio_cgroup(id); + if (!biog) + biog = &default_bio_cgroup; + ioc = biog->io_context; /* default io_context for this cgroup */ + atomic_inc(&ioc->refcount); + return ioc; +} +EXPORT_SYMBOL(get_bio_cgroup_iocontext); +EXPORT_SYMBOL(get_bio_cgroup_id); + +static u64 bio_id_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct bio_cgroup *biog = cgroup_bio(cgrp); + return (u64) biog->id; +} + + +static struct cftype bio_files[] = { + { + .name = "id", + .read_u64 = bio_id_read, + }, +}; + +static int bio_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, bio_files, ARRAY_SIZE(bio_files)); +} + +struct cgroup_subsys bio_cgroup_subsys = { + .name = "bio", + .create = bio_cgroup_create, + .destroy = bio_cgroup_destroy, + .populate = bio_cgroup_populate, + .subsys_id = bio_cgroup_subsys_id, +}; + diff -dupr linux-2.6.28-rc2.bc1/mm/page_cgroup.c linux-2.6.28-rc2/mm/page_cgroup.c --- linux-2.6.28-rc2.bc1/mm/page_cgroup.c 2008-11-11 14:53:41.000000000 +0900 +++ linux-2.6.28-rc2/mm/page_cgroup.c 2008-11-12 11:20:33.000000000 +0900 @@ -9,6 +9,7 @@ #include #include #include +#include static void __meminit __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn) @@ -16,6 +17,7 @@ __init_page_cgroup(struct page_cgroup *p pc->flags = 0; pc->page = pfn_to_page(pfn); __init_mem_page_cgroup(pc); + __init_bio_page_cgroup(pc); } static unsigned long total_usage; @@ -70,7 +72,7 @@ void __init page_cgroup_init(void) int nid, fail; - if (mem_cgroup_disabled()) + if (mem_cgroup_disabled() && bio_cgroup_disabled()) return; for_each_online_node(nid) { @@ -79,12 +81,12 @@ void __init page_cgroup_init(void) goto fail; } printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage); - printk(KERN_INFO "please try cgroup_disable=memory option if you" + printk(KERN_INFO "please try cgroup_disable=memory,bio option if you" " don't want\n"); return; fail: printk(KERN_CRIT "allocation of page_cgroup was failed.\n"); - printk(KERN_CRIT "please try cgroup_disable=memory boot option\n"); + printk(KERN_CRIT "please try cgroup_disable=memory,bio boot options\n"); panic("Out of memory"); } @@ -230,7 +232,7 @@ void __init page_cgroup_init(void) unsigned long pfn; int fail = 0; - if (mem_cgroup_disabled()) + if (mem_cgroup_disabled() && bio_cgroup_disabled()) return; for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) { @@ -245,7 +247,7 @@ void __init page_cgroup_init(void) hotplug_memory_notifier(page_cgroup_callback, 0); } printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage); - printk(KERN_INFO "please try cgroup_disable=memory option if you don't" + printk(KERN_INFO "please try cgroup_disable=memory,bio option if you don't" " want\n"); } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/