From patchwork Mon Feb 28 01:46:05 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Chris Mason X-Patchwork-Id: 593911 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 p1S1lL1b018864 for ; Mon, 28 Feb 2011 01:47:21 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752026Ab1B1BrT (ORCPT ); Sun, 27 Feb 2011 20:47:19 -0500 Received: from rcsinet10.oracle.com ([148.87.113.121]:34648 "EHLO rcsinet10.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751992Ab1B1BrS (ORCPT ); Sun, 27 Feb 2011 20:47:18 -0500 Received: from acsinet15.oracle.com (acsinet15.oracle.com [141.146.126.227]) by rcsinet10.oracle.com (Switch-3.4.2/Switch-3.4.2) with ESMTP id p1S1l6O2013020 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Mon, 28 Feb 2011 01:47:08 GMT Received: from acsmt355.oracle.com (acsmt355.oracle.com [141.146.40.155]) by acsinet15.oracle.com (Switch-3.4.2/Switch-3.4.1) with ESMTP id p1RNhTSi027433; Mon, 28 Feb 2011 01:47:05 GMT Received: from abhmt015.oracle.com by acsmt355.oracle.com with ESMTP id 1041834221298857568; Sun, 27 Feb 2011 17:46:08 -0800 Received: from localhost (/66.66.148.185) by default (Oracle Beehive Gateway v4.0) with ESMTP ; Sun, 27 Feb 2011 17:46:07 -0800 From: Chris Mason To: Mitch Harder Cc: =?utf-8?q?Maria_Wikstr=C3=B6m?= , "Zhong, Xin" , Johannes Hirte , "linux-btrfs@vger.kernel.org" Subject: [PATCH] btrfs file write debugging patch In-reply-to: Date: Sun, 27 Feb 2011 20:46:05 -0500 Message-Id: <1298857223-sup-5612@think> User-Agent: Sup/git X-Source-IP: acsmt355.oracle.com [141.146.40.155] X-Auth-Type: Internal IP X-CT-RefId: str=0001.0A090207.4D6AFE9A.0108:SCFMA4539814,ss=1,fgs=0 Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.6 (demeter1.kernel.org [140.211.167.41]); Mon, 28 Feb 2011 01:47:21 +0000 (UTC) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7084140..89a6a26 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -54,6 +54,13 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, int offset = pos & (PAGE_CACHE_SIZE - 1); int total_copied = 0; + if ((jiffies % 10) == 0) + return 0; + + if ((jiffies % 25) == 0) { + write_bytes /= 2; + } + while (write_bytes > 0) { size_t count = min_t(size_t, PAGE_CACHE_SIZE - offset, write_bytes); @@ -763,6 +770,26 @@ out: } /* + * on error we return an unlocked page and the error value + * on success we return a locked page and 0 + */ +static int prepare_uptodate_page(struct page *page, u64 pos) +{ + int ret = 0; + if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) { + ret = btrfs_readpage(NULL, page); + if (ret) + return ret; + lock_page(page); + if (!PageUptodate(page)) { + unlock_page(page); + return -EIO; + } + } + return 0; +} + +/* * this gets pages into the page cache and locks them down, it also properly * waits for data=ordered extents to finish before allowing the pages to be * modified. @@ -777,6 +804,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file, unsigned long index = pos >> PAGE_CACHE_SHIFT; struct inode *inode = fdentry(file)->d_inode; int err = 0; + int faili = 0; u64 start_pos; u64 last_pos; @@ -794,15 +822,24 @@ again: for (i = 0; i < num_pages; i++) { pages[i] = grab_cache_page(inode->i_mapping, index + i); if (!pages[i]) { - int c; - for (c = i - 1; c >= 0; c--) { - unlock_page(pages[c]); - page_cache_release(pages[c]); - } - return -ENOMEM; + faili = i - 1; + err = -ENOMEM; + goto fail; + } + + if (i == 0) + err = prepare_uptodate_page(pages[i], pos); + else if (i == num_pages - 1) + err = prepare_uptodate_page(pages[i], + pos + write_bytes); + if (err) { + page_cache_release(pages[i]); + faili = i - 1; + goto fail; } wait_on_page_writeback(pages[i]); } + err = 0; if (start_pos < inode->i_size) { struct btrfs_ordered_extent *ordered; lock_extent_bits(&BTRFS_I(inode)->io_tree, @@ -842,6 +879,14 @@ again: WARN_ON(!PageLocked(pages[i])); } return 0; +fail: + while (faili >= 0) { + unlock_page(pages[faili]); + page_cache_release(pages[faili]); + faili--; + } + return err; + } static ssize_t btrfs_file_aio_write(struct kiocb *iocb, @@ -851,7 +896,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, struct file *file = iocb->ki_filp; struct inode *inode = fdentry(file)->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; - struct page *pinned[2]; struct page **pages = NULL; struct iov_iter i; loff_t *ppos = &iocb->ki_pos; @@ -872,9 +916,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) || (file->f_flags & O_DIRECT)); - pinned[0] = NULL; - pinned[1] = NULL; - start_pos = pos; vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); @@ -962,32 +1003,6 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, first_index = pos >> PAGE_CACHE_SHIFT; last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT; - /* - * there are lots of better ways to do this, but this code - * makes sure the first and last page in the file range are - * up to date and ready for cow - */ - if ((pos & (PAGE_CACHE_SIZE - 1))) { - pinned[0] = grab_cache_page(inode->i_mapping, first_index); - if (!PageUptodate(pinned[0])) { - ret = btrfs_readpage(NULL, pinned[0]); - BUG_ON(ret); - wait_on_page_locked(pinned[0]); - } else { - unlock_page(pinned[0]); - } - } - if ((pos + iov_iter_count(&i)) & (PAGE_CACHE_SIZE - 1)) { - pinned[1] = grab_cache_page(inode->i_mapping, last_index); - if (!PageUptodate(pinned[1])) { - ret = btrfs_readpage(NULL, pinned[1]); - BUG_ON(ret); - wait_on_page_locked(pinned[1]); - } else { - unlock_page(pinned[1]); - } - } - while (iov_iter_count(&i) > 0) { size_t offset = pos & (PAGE_CACHE_SIZE - 1); size_t write_bytes = min(iov_iter_count(&i), @@ -1024,8 +1039,12 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, copied = btrfs_copy_from_user(pos, num_pages, write_bytes, pages, &i); - dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; + if (copied == 0) + dirty_pages = 0; + else + dirty_pages = (copied + offset + + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; if (num_pages > dirty_pages) { if (copied > 0) @@ -1069,10 +1088,6 @@ out: err = ret; kfree(pages); - if (pinned[0]) - page_cache_release(pinned[0]); - if (pinned[1]) - page_cache_release(pinned[1]); *ppos = pos; /*