From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wr0-f194.google.com ([209.85.128.194]:37062 "EHLO mail-wr0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932287AbdHWRXt (ORCPT ); Wed, 23 Aug 2017 13:23:49 -0400 Received: by mail-wr0-f194.google.com with SMTP id 72so84612wrc.4 for ; Wed, 23 Aug 2017 10:23:48 -0700 (PDT) From: Timofey Titovets To: linux-btrfs@vger.kernel.org Cc: Timofey Titovets Subject: [RFC PATCH] Btrfs: clear_dirty only on pages in compression range Date: Wed, 23 Aug 2017 20:23:29 +0300 Message-Id: <20170823172329.5794-1-nefelim4ag@gmail.com> Sender: linux-btrfs-owner@vger.kernel.org List-ID: At now while compressing data range code touch dirty page status on whole range on each 128kb iteration, that's costs time As we care only about page status in range that will be compressed in current iteration, let's touch dirty status only for actual compression range Signed-off-by: Timofey Titovets --- fs/btrfs/inode.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b92478fe7ec..cb7779b08aaf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -449,6 +449,7 @@ static noinline void compress_file_range(struct inode *inode, u64 num_bytes; u64 blocksize = fs_info->sectorsize; u64 actual_end; + u64 compress_range_end; u64 isize = i_size_read(inode); int ret = 0; struct page **pages = NULL; @@ -500,6 +501,8 @@ static noinline void compress_file_range(struct inode *inode, num_bytes = max(blocksize, num_bytes); total_in = 0; ret = 0; + compress_range_end = start + min_t(u64, BTRFS_MAX_UNCOMPRESSED, + end - start); /* * we do compression for mount -o compress and when the @@ -528,7 +531,8 @@ static noinline void compress_file_range(struct inode *inode, * If the compression fails for any reason, we set the pages * dirty again later on. */ - extent_range_clear_dirty_for_io(inode, start, end); + extent_range_clear_dirty_for_io(inode, start, + compress_range_end); redirty = 1; ret = btrfs_compress_pages(compress_type, inode->i_mapping, start, @@ -667,7 +671,7 @@ static noinline void compress_file_range(struct inode *inode, /* unlocked later on in the async handlers */ if (redirty) - extent_range_redirty_for_io(inode, start, end); + extent_range_redirty_for_io(inode, start, compress_range_end); add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0, BTRFS_COMPRESS_NONE); *num_added += 1; -- 2.14.1