On 10/30/2010 09:39 PM, Hugo Mills wrote:
> This patch introduces a basic form of progress monitoring for balance
> operations, by counting the number of block groups remaining. The
> information is exposed to userspace by an ioctl.
>
IMO, tracking the information of blocks which are balancing also makes sense.
For example, the block information's blocknr.
It can help us monitor better.
> Signed-off-by: Hugo Mills <hugo@xxxxxxxxxxxxx>
>
> ---
> This patch replaces the one previously posted, correcting a minor error.
>
> fs/btrfs/ctree.h | 9 ++++++++
> fs/btrfs/disk-io.c | 2 +
> fs/btrfs/ioctl.c | 34 ++++++++++++++++++++++++++++++++
> fs/btrfs/ioctl.h | 7 ++++++
> fs/btrfs/volumes.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++--
> 5 files changed, 105 insertions(+), 2 deletions(-)
>
> Index: linux-mainline/fs/btrfs/ctree.h
> ===================================================================
> --- linux-mainline.orig/fs/btrfs/ctree.h 2010-10-26 18:03:38.000000000 +0100
> +++ linux-mainline/fs/btrfs/ctree.h 2010-10-30 14:35:25.306450922 +0100
> @@ -803,6 +803,11 @@
> struct list_head cluster_list;
> };
>
> +struct btrfs_balance_info {
> + u64 expected;
> + u64 completed;
> +};
> +
> struct reloc_control;
> struct btrfs_device;
> struct btrfs_fs_devices;
> @@ -1010,6 +1015,10 @@
> unsigned metadata_ratio;
>
> void *bdev_holder;
> +
> + /* Keep track of any rebalance operations on this FS */
> + spinlock_t balance_info_lock;
> + struct btrfs_balance_info *balance_info;
> };
>
> /*
> Index: linux-mainline/fs/btrfs/ioctl.c
> ===================================================================
> --- linux-mainline.orig/fs/btrfs/ioctl.c 2010-10-26 18:03:38.000000000 +0100
> +++ linux-mainline/fs/btrfs/ioctl.c 2010-10-30 14:35:25.396447198 +0100
> @@ -1984,6 +1984,38 @@
> return 0;
> }
>
> +/*
> + * Return the current status of any balance operation
> + */
> +long btrfs_ioctl_balance_progress(
> + struct btrfs_fs_info *fs_info,
> + struct btrfs_ioctl_balance_progress __user *user_dest)
> +{
> + int ret = 0;
> + struct btrfs_ioctl_balance_progress dest;
> +
> + spin_lock(&fs_info->balance_info_lock);
> + if (!fs_info->balance_info) {
> + ret = -EINVAL;
> + goto error;
> + }
> +
> + dest.expected = fs_info->balance_info->expected;
> + dest.completed = fs_info->balance_info->completed;
> +
> + spin_unlock(&fs_info->balance_info_lock);
> +
> + if (copy_to_user(user_dest, &dest,
> + sizeof(struct btrfs_ioctl_balance_progress)))
> + return -EFAULT;
> +
> + return 0;
> +
> +error:
> + spin_unlock(&fs_info->balance_info_lock);
> + return ret;
> +}
> +
> long btrfs_ioctl(struct file *file, unsigned int
> cmd, unsigned long arg)
> {
> @@ -2017,6 +2049,8 @@
> return btrfs_ioctl_rm_dev(root, argp);
> case BTRFS_IOC_BALANCE:
> return btrfs_balance(root->fs_info->dev_root);
> + case BTRFS_IOC_BALANCE_PROGRESS:
> + return btrfs_ioctl_balance_progress(root->fs_info, argp);
> case BTRFS_IOC_CLONE:
> return btrfs_ioctl_clone(file, arg, 0, 0, 0);
> case BTRFS_IOC_CLONE_RANGE:
> Index: linux-mainline/fs/btrfs/ioctl.h
> ===================================================================
> --- linux-mainline.orig/fs/btrfs/ioctl.h 2010-10-26 18:03:38.000000000 +0100
> +++ linux-mainline/fs/btrfs/ioctl.h 2010-10-30 14:35:25.316450509 +0100
> @@ -138,6 +138,11 @@
> struct btrfs_ioctl_space_info spaces[0];
> };
>
> +struct btrfs_ioctl_balance_progress {
> + __u64 expected;
> + __u64 completed;
> +};
> +
> #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
> struct btrfs_ioctl_vol_args)
> #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
> @@ -178,4 +183,6 @@
> #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, u64)
> #define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \
> struct btrfs_ioctl_space_args)
> +#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 21, \
> + struct btrfs_ioctl_balance_progress)
> #endif
> Index: linux-mainline/fs/btrfs/volumes.c
> ===================================================================
> --- linux-mainline.orig/fs/btrfs/volumes.c 2010-10-26 18:03:38.000000000 +0100
> +++ linux-mainline/fs/btrfs/volumes.c 2010-10-30 14:35:25.326450096 +0100
> @@ -1902,6 +1902,7 @@
> struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root;
> struct btrfs_trans_handle *trans;
> struct btrfs_key found_key;
> + struct btrfs_balance_info *bal_info;
>
> if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
> return -EROFS;
> @@ -1909,6 +1910,18 @@
> mutex_lock(&dev_root->fs_info->volume_mutex);
> dev_root = dev_root->fs_info->dev_root;
>
> + dev_root->fs_info->balance_info = kmalloc(
> + sizeof(struct btrfs_balance_info),
> + GFP_NOFS);
> + if (!dev_root->fs_info->balance_info) {
> + ret = -ENOSPC;
-ENOMEM is better, for it comes from a kmalloc().
> + goto error_no_status;
> + }
> + bal_info = dev_root->fs_info->balance_info;
> + bal_info->expected = -1; /* One less than actually counted,
> + because chunk 0 is special */
> + bal_info->completed = 0;
> +
> /* step one make some room on all the devices */
> list_for_each_entry(device, devices, dev_list) {
> old_size = device->total_bytes;
> @@ -1932,10 +1945,40 @@
> btrfs_end_transaction(trans, dev_root);
> }
>
> - /* step two, relocate all the chunks */
> + /* step two, count the chunks */
> path = btrfs_alloc_path();
> - BUG_ON(!path);
> + if (!path) {
> + ret = -ENOSPC;
ditto
> + goto error;
> + }
> +
> + key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
> + key.offset = (u64)-1;
> + key.type = BTRFS_CHUNK_ITEM_KEY;
> +
> + ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
> + if (ret <= 0) {
> + printk(KERN_ERR "btrfs: Failed to find the last chunk.\n");
> + BUG();
> + }
> +
> + while (1) {
> + ret = btrfs_previous_item(chunk_root, path, 0,
> + BTRFS_CHUNK_ITEM_KEY);
> + if (ret)
> + break;
> +
> + bal_info->expected++;
> + }
> +
> + btrfs_free_path(path);
> + path = btrfs_alloc_path();
> + if (!path) {
> + ret = -ENOSPC;
ditto
> + goto error;
> + }
>
> + /* step three, relocate all the chunks */
> key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
> key.offset = (u64)-1;
> key.type = BTRFS_CHUNK_ITEM_KEY;
> @@ -1976,10 +2019,18 @@
> found_key.offset);
> BUG_ON(ret && ret != -ENOSPC);
> key.offset = found_key.offset - 1;
> + bal_info->completed++;
> + printk(KERN_INFO "btrfs: balance: %llu/%llu block groups completed\n",
> + bal_info->completed, bal_info->expected);
Would you please printk found_key.offset which balance code is processing?
That would be helpful.
thanks,
liubo
> }
> ret = 0;
> error:
> btrfs_free_path(path);
> + spin_lock(&dev_root->fs_info->balance_info_lock);
> + kfree(dev_root->fs_info->balance_info);
> + dev_root->fs_info->balance_info = NULL;
> + spin_unlock(&dev_root->fs_info->balance_info_lock);
> +error_no_status:
> mutex_unlock(&dev_root->fs_info->volume_mutex);
> return ret;
> }
> Index: linux-mainline/fs/btrfs/disk-io.c
> ===================================================================
> --- linux-mainline.orig/fs/btrfs/disk-io.c 2010-10-29 17:19:12.000000000 +0100
> +++ linux-mainline/fs/btrfs/disk-io.c 2010-10-29 17:20:02.022161666 +0100
> @@ -1591,6 +1591,7 @@
> spin_lock_init(&fs_info->ref_cache_lock);
> spin_lock_init(&fs_info->fs_roots_radix_lock);
> spin_lock_init(&fs_info->delayed_iput_lock);
> + spin_lock_init(&fs_info->balance_info_lock);
>
> init_completion(&fs_info->kobj_unregister);
> fs_info->tree_root = tree_root;
> @@ -1616,6 +1617,7 @@
> fs_info->sb = sb;
> fs_info->max_inline = 8192 * 1024;
> fs_info->metadata_ratio = 0;
> + fs_info->balance_info = NULL;
>
> fs_info->thread_pool_size = min_t(unsigned long,
> num_online_cpus() + 2, 8);
>
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
