From patchwork Tue Nov 9 22:43:15 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hugo Mills X-Patchwork-Id: 318532 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id oAC1I1aQ023460 for ; Fri, 12 Nov 2010 01:18:02 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757358Ab0KLBRx (ORCPT ); Thu, 11 Nov 2010 20:17:53 -0500 Received: from frost.carfax.org.uk ([212.13.194.111]:4308 "EHLO frost.carfax.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754001Ab0KLBRw (ORCPT ); Thu, 11 Nov 2010 20:17:52 -0500 X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter1.kernel.org [140.211.167.41]); Fri, 12 Nov 2010 01:18:02 +0000 (UTC) X-Greylist: delayed 1901 seconds by postgrey-1.27 at vger.kernel.org; Thu, 11 Nov 2010 20:17:51 EST Received: from intmx.carfax.org.uk ([10.0.0.5] helo=vlad.carfax.org.uk ident=Debian-exim) by frost.carfax.org.uk with esmtp (Exim 4.69) (envelope-from <0435dceee4613994f662ac4e3f423bf4274136a4@carfax.org.uk>) id 1PGhmI-0006tb-Ec; Fri, 12 Nov 2010 00:46:06 +0000 Received: from hrm by vlad.carfax.org.uk with local (Exim 4.72) (envelope-from <0435dceee4613994f662ac4e3f423bf4274136a4@vlad.carfax.org.uk>) id 1PGhmI-0001yO-3B; Fri, 12 Nov 2010 00:46:06 +0000 Message-Id: <0435dceee4613994f662ac4e3f423bf4274136a4.1289522188.git.hugo@carfax.org.uk> In-Reply-To: References: From: Hugo Mills Date: Tue, 9 Nov 2010 22:43:15 +0000 Subject: [PATCH v2 1/2] Balance progress monitoring. To: linux-btrfs@vger.kernel.org, Goffredo Baroncelli , Chris Mason , liubo X-frost.carfax.org.uk-Spam-Score: -0.0 (/) X-frost.carfax.org.uk-Spam-Report: Spam detection software, running on the system "spamd2.lon.bitfolk.com", has identified this incoming email as possible spam. The original message has been attached to this so you can view it (if it isn't spam) or label similar future email. If you have any questions, see the administrator of that system for details. Content preview: 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. Signed-off-by: Hugo Mills --- 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 | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++- 5 files changed, 111 insertions(+), 2 deletions(-) [...] Content analysis details: (-0.0 points, 5.0 required) pts rule name description ---- ---------------------- -------------------------------------------------- -0.0 T_RP_MATCHES_RCVD Envelope sender domain matches handover relay domain Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 8db9234..67fb603 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -841,6 +841,11 @@ struct btrfs_block_group_cache { struct list_head cluster_list; }; +struct btrfs_balance_info { + u64 expected; + u64 completed; +}; + struct reloc_control; struct btrfs_device; struct btrfs_fs_devices; @@ -1050,6 +1055,10 @@ struct btrfs_fs_info { 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; }; /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b40dfe4..87d9315 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1590,6 +1590,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, 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; @@ -1615,6 +1616,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, 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); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 463d91b..c247985 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2220,6 +2220,38 @@ static noinline long btrfs_ioctl_wait_sync(struct file *file, void __user *argp) return btrfs_wait_for_commit(root, transid); } +/* + * 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) { @@ -2255,6 +2287,8 @@ long btrfs_ioctl(struct file *file, unsigned int 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: diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 17c99eb..b2103b2 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -145,6 +145,11 @@ struct btrfs_ioctl_space_args { 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, \ @@ -189,4 +194,6 @@ struct btrfs_ioctl_space_args { #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_ASYNC _IOW(BTRFS_IOCTL_MAGIC, 23, \ struct btrfs_ioctl_async_vol_args) +#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 25, \ + struct btrfs_ioctl_balance_progress) #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 91851b5..f00edc1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1904,6 +1904,7 @@ int btrfs_balance(struct btrfs_root *dev_root) 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; @@ -1911,6 +1912,20 @@ int btrfs_balance(struct btrfs_root *dev_root) mutex_lock(&dev_root->fs_info->volume_mutex); dev_root = dev_root->fs_info->dev_root; + bal_info = kmalloc( + sizeof(struct btrfs_balance_info), + GFP_NOFS); + if (!bal_info) { + ret = -ENOSPC; + goto error_no_status; + } + spin_lock(&dev_root->fs_info->balance_info_lock); + dev_root->fs_info->balance_info = bal_info; + bal_info->expected = -1; /* One less than actually counted, + because chunk 0 is special */ + bal_info->completed = 0; + spin_unlock(&dev_root->fs_info->balance_info_lock); + /* step one make some room on all the devices */ list_for_each_entry(device, devices, dev_list) { old_size = device->total_bytes; @@ -1934,10 +1949,42 @@ int btrfs_balance(struct btrfs_root *dev_root) 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; + 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; + + spin_lock(&dev_root->fs_info->balance_info_lock); + bal_info->expected++; + spin_unlock(&dev_root->fs_info->balance_info_lock); + } + + btrfs_free_path(path); + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOSPC; + 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; @@ -1975,10 +2022,20 @@ int btrfs_balance(struct btrfs_root *dev_root) found_key.offset); BUG_ON(ret && ret != -ENOSPC); key.offset = found_key.offset - 1; + spin_lock(&dev_root->fs_info->balance_info_lock); + bal_info->completed++; + spin_unlock(&dev_root->fs_info->balance_info_lock); + printk(KERN_INFO "btrfs: balance: %llu/%llu block groups completed\n", + bal_info->completed, bal_info->expected); } 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; }