From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-f169.google.com ([209.85.212.169]:34562 "EHLO mail-wi0-f169.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751612AbaAMNlQ (ORCPT ); Mon, 13 Jan 2014 08:41:16 -0500 Received: by mail-wi0-f169.google.com with SMTP id e4so1141215wiv.4 for ; Mon, 13 Jan 2014 05:41:15 -0800 (PST) From: Filipe David Borba Manana To: linux-btrfs@vger.kernel.org Cc: Filipe David Borba Manana Subject: [PATCH v2] Btrfs: faster file extent item search in clone ioctl Date: Mon, 13 Jan 2014 13:38:58 +0000 Message-Id: <1389620338-17424-1-git-send-email-fdmanana@gmail.com> In-Reply-To: <1389475828-19339-1-git-send-email-fdmanana@gmail.com> References: <1389475828-19339-1-git-send-email-fdmanana@gmail.com> Sender: linux-btrfs-owner@vger.kernel.org List-ID: When we are looking for file extent items that intersect the cloning range, for each one that falls completely outside the range, don't release the path and do another full tree search - just move on to the next slot and copy the file extent item into our buffer only if the item intersects the cloning range. Also leave the btree node/leaf locks in spinning mode to not make other tasks sleep since we process each leaf very quickly. Signed-off-by: Filipe David Borba Manana --- V2: Set path->leave_spinning to 1. fs/btrfs/ioctl.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3970f32..e3b72da 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2893,7 +2893,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, vfree(buf); return ret; } - + path->leave_spinning = 1; path->reada = 2; /* clone data */ key.objectid = btrfs_ino(src); @@ -2911,6 +2911,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode, goto out; nritems = btrfs_header_nritems(path->nodes[0]); +process_slot: if (path->slots[0] >= nritems) { ret = btrfs_next_leaf(BTRFS_I(src)->root, path); if (ret < 0) @@ -2937,11 +2938,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode, u8 comp; u64 endoff; - size = btrfs_item_size_nr(leaf, slot); - read_extent_buffer(leaf, buf, - btrfs_item_ptr_offset(leaf, slot), - size); - extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); comp = btrfs_file_extent_compression(leaf, extent); @@ -2960,11 +2956,19 @@ static int btrfs_clone(struct inode *src, struct inode *inode, datal = btrfs_file_extent_ram_bytes(leaf, extent); } - btrfs_release_path(path); if (key.offset + datal <= off || - key.offset >= off + len - 1) - goto next; + key.offset >= off + len - 1) { + path->slots[0]++; + goto process_slot; + } + + size = btrfs_item_size_nr(leaf, slot); + read_extent_buffer(leaf, buf, + btrfs_item_ptr_offset(leaf, slot), + size); + + btrfs_release_path(path); memcpy(&new_key, &key, sizeof(new_key)); new_key.objectid = btrfs_ino(inode); @@ -3135,7 +3139,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode, } ret = btrfs_end_transaction(trans, root); } -next: btrfs_release_path(path); key.offset++; } -- 1.7.9.5