writeback机制源码分析

writeback相关数据结构

与writeback相关的数据结构主要有：

1，backing_dev_info，该数据结构描述了backing_dev的所有信息，通常块设备的request queue中会包含backing_dev对象。

2，bdi_writeback，该数据结构封装了writeback的内核线程以及需要操作的inode队列。

3，wb_writeback_work，该数据结构封装了writeback的工作任务。

各数据结构之间的关系如下图所示：

下面对各个数据结构做简要介绍。

bdi information

bdi对象在块设备添加的时候需要注册到系统的bdi队列中。对于ext3而言，在mount的时候需要将底层块设备的bdi对象联系到ext3 root_inode中。bdi对象数据结构定义如下：

 

struct backing_dev_info {  
    struct list_head bdi_list;  
    unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
    unsigned long state;    /* Always use atomic bitops on this */
    unsigned int capabilities; /* Device capabilities */
    congested_fn *congested_fn; /* Function pointer if device is md/dm */
    void *congested_data;   /* Pointer to aux data for congested func */
     
    char *name;  
     
    struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];  
     
    unsigned long bw_time_stamp;    /* last time write bw is updated */
    unsigned long dirtied_stamp;  
    unsigned long written_stamp;    /* pages written at bw_time_stamp */
    unsigned long write_bandwidth;  /* the estimated write bandwidth */
    unsigned long avg_write_bandwidth; /* further smoothed write bw */
     
    /*  
     * The base dirty throttle rate, re-calculated on every 200ms.  
     * All the bdi tasks' dirty rate will be curbed under it.  
     * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit  
     * in small steps and is much more smooth/stable than the latter.  
     */
    unsigned long dirty_ratelimit;  
    unsigned long balanced_dirty_ratelimit;  
     
    struct prop_local_percpu completions;  
    int dirty_exceeded;  
     
    unsigned int min_ratio;  
    unsigned int max_ratio, max_prop_frac;  
     
    struct bdi_writeback wb;  /* default writeback info for this bdi，writeback对象 */
    spinlock_t wb_lock;   /* protects work_list */
     
    /* 任务链表 */
    struct list_head work_list;  
     
    struct device *dev;  
    /* 在laptop模式下应用的定时器 */
    struct timer_list laptop_mode_wb_timer;  
     
#ifdef CONFIG_DEBUG_FS  
    struct dentry *debug_dir;  
    struct dentry *debug_stats;  
#endif  
};

在bdi数据结构中定义了一个writeback对象，该对象是对writeback内核线程的描述，并且封装了需要处理的inode队列。在bdi数据结构中有一条work_list，该work队列维护了writeback内核线程需要处理的任务。如果该队列上没有work可以处理，那么writeback内核线程将会睡眠等待。

writeback

writeback对象封装了内核线程task以及需要处理的inode队列。当page cache/buffer cache需要刷新radix tree上的inode时，可以将该inode挂载到writeback对象的b_dirty队列上，然后唤醒writeback线程。在处理过程中，inode会被移到b_io队列上进行处理。多条链表的方式可以降低多线程之间的资源共享。writeback数据结构具体定义如下：

 

struct bdi_writeback {  
    struct backing_dev_info *bdi;   /* our parent bdi */
    unsigned int nr;  
     
    unsigned long last_old_flush;   /* last old data flush */
    unsigned long last_active;  /* last time bdi thread was active */
     
    struct task_struct *task;   /* writeback thread */
    struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
    struct list_head b_dirty;   /* dirty inodes */
    struct list_head b_io;      /* parked for writeback */
    struct list_head b_more_io; /* parked for more writeback */
    spinlock_t list_lock;       /* protects the b_* lists */
};

 

writeback work

wb_writeback_work数据结构是对writeback任务的封装，不同的任务可以采用不同的刷新策略。writeback线程的处理对象就是writeback_work。如果writeback_work队列为空，那么内核线程就可以睡眠了。Writeback_work的数据结构定义如下：

 

struct wb_writeback_work {  
    long nr_pages;  
    struct super_block *sb; /* superblock对象 */
    unsigned long *older_than_this;  
    enum writeback_sync_modes sync_mode;  
    unsigned int tagged_writepages:1;  
    unsigned int for_kupdate:1;  
    unsigned int range_cyclic:1;  
    unsigned int for_background:1;  
    enum wb_reason reason;      /* why was writeback initiated? */
          
    struct list_head list;      /* pending work list，链入bdi-> work_list队列 */
    struct completion *done;    /* set if the caller waits，work完成时通知调用者 */
};

 

writeback主要函数分析

writeback机制的主要函数包括如下两个方面：

1，管理bdi对象并且fork相应的writeback内核线程处理cache数据的刷新工作。

2，writeback内核线程处理函数，实现dirty page的刷新操作

writeback线程管理

Linux中有一个内核守护线程，该线程用来管理系统bdi队列，并且负责为block device创建writeback thread。当bdi中有dirty page并且还没有为bdi分配内核线程的时候，bdi_forker_thread程序会为其分配线程资源；当一个writeback线程长时间处于空闲状态时，bdi_forker_thread程序会释放该线程资源。

writeback线程管理程序分析如下：

static int bdi_forker_thread(void *ptr)  
{  
    struct bdi_writeback *me = ptr;  
     
    current->flags |= PF_SWAPWRITE;  
    set_freezable();  
     
    /*  
     * Our parent may run at a different priority, just set us to normal  
     */
    set_user_nice(current, 0);  
     
    for (;;) {  
        struct task_struct *task = NULL;  
        struct backing_dev_info *bdi;  
        enum {  
            NO_ACTION,   /* Nothing to do */
            FORK_THREAD, /* Fork bdi thread */
            KILL_THREAD, /* Kill inactive bdi thread */
        } action = NO_ACTION;  
     
        /*  
         * Temporary measure, we want to make sure we don't see  
         * dirty data on the default backing_dev_info  
         */
        if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) {  
            del_timer(&me->wakeup_timer);  
            wb_do_writeback(me, 0);  
        }  
     
        spin_lock_bh(&bdi_lock);  
        /*  
         * In the following loop we are going to check whether we have  
         * some work to do without any synchronization with tasks  
         * waking us up to do work for them. Set the task state here  
         * so that we don't miss wakeups after verifying conditions.  
         */
        set_current_state(TASK_INTERRUPTIBLE);  
        /* 遍历所有的bdi对象，检查这些bdi是否存在脏数据，如果有脏数据，那么需要为其fork线程，然后做writeback操作 */
        list_for_each_entry(bdi, &bdi_list, bdi_list) {  
            bool have_dirty_io;  
     
            if (!bdi_cap_writeback_dirty(bdi) ||  
                 bdi_cap_flush_forker(bdi))  
                continue;  
     
            WARN(!test_bit(BDI_registered, &bdi->state),  
                 "bdi %p/%s is not registered!\n", bdi, bdi->name);  
            /* 检查是否存在脏数据 */
            have_dirty_io = !list_empty(&bdi->work_list) ||  
                    wb_has_dirty_io(&bdi->wb);  
     
            /*  
             * If the bdi has work to do, but the thread does not  
             * exist - create it.  
             */
            if (!bdi->wb.task && have_dirty_io) {  
                /*  
                 * Set the pending bit - if someone will try to  
                 * unregister this bdi - it'll wait on this bit.  
                 */
                /* 如果有脏数据，并且不存在线程，那么接下来做线程的FORK操作 */
                set_bit(BDI_pending, &bdi->state);  
                action = FORK_THREAD;  
                break;  
            }  
     
            spin_lock(&bdi->wb_lock);  
     
            /*  
             * If there is no work to do and the bdi thread was  
             * inactive long enough - kill it. The wb_lock is taken  
             * to make sure no-one adds more work to this bdi and  
             * wakes the bdi thread up.  
             */
            /* 如果一个bdi长时间没有脏数据，那么执行线程的KILL操作，结束掉该bdi对应的writeback线程 */
            if (bdi->wb.task && !have_dirty_io &&  
                time_after(jiffies, bdi->wb.last_active +  
                        bdi_longest_inactive())) {  
                task = bdi->wb.task;  
                bdi->wb.task = NULL;  
                spin_unlock(&bdi->wb_lock);  
                set_bit(BDI_pending, &bdi->state);  
                action = KILL_THREAD;  
                break;  
            }  
            spin_unlock(&bdi->wb_lock);  
        }  
        spin_unlock_bh(&bdi_lock);  
     
        /* Keep working if default bdi still has things to do */
        if (!list_empty(&me->bdi->work_list))  
            __set_current_state(TASK_RUNNING);  
        /* 执行线程的FORK和KILL操作 */
        switch (action) {  
        case FORK_THREAD:  
            /* FORK一个bdi_writeback_thread线程，该线程的名字为flush-major:minor */
            __set_current_state(TASK_RUNNING);  
            task = kthread_create(bdi_writeback_thread, &bdi->wb,  
                          "flush-%s", dev_name(bdi->dev));  
            if (IS_ERR(task)) {  
                /*  
                 * If thread creation fails, force writeout of  
                 * the bdi from the thread. Hopefully 1024 is  
                 * large enough for efficient IO.  
                 */
                writeback_inodes_wb(&bdi->wb, 1024,  
                            WB_REASON_FORKER_THREAD);  
            } else {  
                /*  
                 * The spinlock makes sure we do not lose  
                 * wake-ups when racing with 'bdi_queue_work()'.  
                 * And as soon as the bdi thread is visible, we  
                 * can start it.  
                 */
                spin_lock_bh(&bdi->wb_lock);  
                bdi->wb.task = task;  
                spin_unlock_bh(&bdi->wb_lock);  
                wake_up_process(task);  
            }  
            bdi_clear_pending(bdi);  
            break;  
     
        case KILL_THREAD:  
            /* KILL一个线程 */
            __set_current_state(TASK_RUNNING);  
            kthread_stop(task);  
            bdi_clear_pending(bdi);  
            break;  
     
        case NO_ACTION:  
            /* 如果没有可执行的动作，那么调度本线程睡眠一段时间 */
            if (!wb_has_dirty_io(me) || !dirty_writeback_interval)  
                /*  
                 * There are no dirty data. The only thing we  
                 * should now care about is checking for  
                 * inactive bdi threads and killing them. Thus,  
                 * let's sleep for longer time, save energy and  
                 * be friendly for battery-driven devices.  
                 */
                schedule_timeout(bdi_longest_inactive());  
            else
                schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));  
            try_to_freeze();  
            break;  
        }  
    }  
     
    return 0;  
}

writeback线程

writeback线程是bdi_forker_thread 创建的，该线程的任务就是处理等待的数据回刷任务。线程处理函数为bdi_writeback_thread，其会调用wb_do_writeback函数完成具体操作，该函数分析如下：

long wb_do_writeback(struct bdi_writeback *wb, int force_wait)  
{  
    struct backing_dev_info *bdi = wb->bdi;  
    struct wb_writeback_work *work;  
    long wrote = 0;  
     
    set_bit(BDI_writeback_running, &wb->bdi->state);  
    /* 处理等待的work，所有等待work pengding在bdi->work_list上 */
    while ((work = get_next_work_item(bdi)) != NULL) {  
        /*  
         * Override sync mode, in case we must wait for completion  
         * because this thread is exiting now.  
         */
        if (force_wait)  
            work->sync_mode = WB_SYNC_ALL;  
     
        trace_writeback_exec(bdi, work);  
        /* 调用wb_writeback函数处理相应的inode */
        wrote += wb_writeback(wb, work);  
     
        /*  
         * Notify the caller of completion if this is a synchronous  
         * work item, otherwise just free it.  
         */
        /* 通知上层软件，相应的work已经完成 */
        if (work->done)  
            complete(work->done);  
        else
            kfree(work);  
    }  
     
    /*  
     * Check for periodic writeback, kupdated() style  
     */
    /* 处理周期性的dirty page刷新作业，buffer cache就会走这条路径，在下面的函数中会创建work，并且调用wb_writeback函数进行处理 */
    wrote += wb_check_old_data_flush(wb);  
    wrote += wb_check_background_flush(wb);  
    clear_bit(BDI_writeback_running, &wb->bdi->state);  
     
    return wrote;  
}

小结

本文在linux-3.2的基础上对writeback代码进行了浏览。整体上来讲，writeback机制是比较简单的，其核心是通过一个常驻内核线程为bdi对象分配writeback线程，实现对cache中dirty page的数据回刷。