From: Steven Whitehouse Date: Tue, 30 Jan 2018 09:39:36 +0000 Subject: [Cluster-devel] [PATCH v2 2/6] gfs2: Remove ordered write mode handling from gfs2_trans_add_data In-Reply-To: <20180129221844.19476-3-agruenba@redhat.com> References: <20180129221844.19476-1-agruenba@redhat.com> <20180129221844.19476-3-agruenba@redhat.com> Message-ID: <21c3f771-05ac-bf62-be28-ef4273ffec2d@redhat.com> List-Id: To: cluster-devel.redhat.com MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Hi, On 29/01/18 22:18, Andreas Gruenbacher wrote: > In journaled data mode, we need to add each buffer head to the current > transaction. In ordered write mode, we only need to add the inode to > the ordered inode list. So far, both cases are handled in > gfs2_trans_add_data. This makes the code look misleading and is > inefficient for small block sizes as well. Handle both cases separately > instead. > > Signed-off-by: Andreas Gruenbacher > --- > fs/gfs2/aops.c | 7 ++++--- > fs/gfs2/bmap.c | 12 ++++++++---- > fs/gfs2/log.h | 7 ++++++- > fs/gfs2/quota.c | 5 ++++- > fs/gfs2/trans.c | 27 ++++++++------------------- > 5 files changed, 30 insertions(+), 28 deletions(-) > > diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c > index 8ed34aa9997c..84db5759fe3d 100644 > --- a/fs/gfs2/aops.c > +++ b/fs/gfs2/aops.c > @@ -54,8 +54,7 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, > continue; > if (start >= to) > break; > - if (gfs2_is_jdata(ip)) > - set_buffer_uptodate(bh); > + set_buffer_uptodate(bh); > gfs2_trans_add_data(ip->i_gl, bh); > } > } > @@ -891,8 +890,10 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, > goto out2; > } > > - if (!gfs2_is_writeback(ip)) > + if (gfs2_is_jdata(ip)) > gfs2_page_add_databufs(ip, page, pos & ~PAGE_MASK, len); > + else > + gfs2_ordered_add_inode(ip); > > ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); > page = NULL; Does this still work for data=writeback? I know we don't support that mode, but it can be useful for testing, so we should probably keep it, Steve. > diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c > index 86863792f36a..72e22b99ade7 100644 > --- a/fs/gfs2/bmap.c > +++ b/fs/gfs2/bmap.c > @@ -89,10 +89,12 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, > map_bh(bh, inode->i_sb, block); > > set_buffer_uptodate(bh); > - if (!gfs2_is_jdata(ip)) > - mark_buffer_dirty(bh); > - if (!gfs2_is_writeback(ip)) > + if (gfs2_is_jdata(ip)) > gfs2_trans_add_data(ip->i_gl, bh); > + else { > + mark_buffer_dirty(bh); > + gfs2_ordered_add_inode(ip); > + } > > if (release) { > unlock_page(page); > @@ -951,8 +953,10 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from, > err = 0; > } > > - if (!gfs2_is_writeback(ip)) > + if (gfs2_is_jdata(ip)) > gfs2_trans_add_data(ip->i_gl, bh); > + else > + gfs2_ordered_add_inode(ip); > > zero_user(page, offset, length); > mark_buffer_dirty(bh); > diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h > index 93b52ac1ca1f..1634c67bd660 100644 > --- a/fs/gfs2/log.h > +++ b/fs/gfs2/log.h > @@ -14,6 +14,7 @@ > #include > #include > #include "incore.h" > +#include "inode.h" > > /** > * gfs2_log_lock - acquire the right to mess with the log manager > @@ -50,8 +51,12 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp, > > static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip) > { > - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); > + struct gfs2_sbd *sdp; > > + if (!gfs2_is_ordered(ip)) > + return; > + > + sdp = GFS2_SB(&ip->i_inode); > if (!test_bit(GIF_ORDERED, &ip->i_flags)) { > spin_lock(&sdp->sd_ordered_lock); > if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags)) > diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c > index 7a98abd340ee..e8585dfd209f 100644 > --- a/fs/gfs2/quota.c > +++ b/fs/gfs2/quota.c > @@ -735,7 +735,10 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, > if (!buffer_uptodate(bh)) > goto unlock_out; > } > - gfs2_trans_add_data(ip->i_gl, bh); > + if (gfs2_is_jdata(ip)) > + gfs2_trans_add_data(ip->i_gl, bh); > + else > + gfs2_ordered_add_inode(ip); > > /* If we need to write to the next block as well */ > if (to_write > (bsize - boff)) { > diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c > index c75cacaa349b..064c9a0ef046 100644 > --- a/fs/gfs2/trans.c > +++ b/fs/gfs2/trans.c > @@ -143,32 +143,21 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl, > * @gl: The inode glock associated with the buffer > * @bh: The buffer to add > * > - * This is used in two distinct cases: > - * i) In ordered write mode > - * We put the data buffer on a list so that we can ensure that it's > - * synced to disk at the right time > - * ii) In journaled data mode > - * We need to journal the data block in the same way as metadata in > - * the functions above. The difference is that here we have a tag > - * which is two __be64's being the block number (as per meta data) > - * and a flag which says whether the data block needs escaping or > - * not. This means we need a new log entry for each 251 or so data > - * blocks, which isn't an enormous overhead but twice as much as > - * for normal metadata blocks. > + * This is used in journaled data mode. > + * We need to journal the data block in the same way as metadata in > + * the functions above. The difference is that here we have a tag > + * which is two __be64's being the block number (as per meta data) > + * and a flag which says whether the data block needs escaping or > + * not. This means we need a new log entry for each 251 or so data > + * blocks, which isn't an enormous overhead but twice as much as > + * for normal metadata blocks. > */ > void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh) > { > struct gfs2_trans *tr = current->journal_info; > struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; > - struct address_space *mapping = bh->b_page->mapping; > - struct gfs2_inode *ip = GFS2_I(mapping->host); > struct gfs2_bufdata *bd; > > - if (!gfs2_is_jdata(ip)) { > - gfs2_ordered_add_inode(ip); > - return; > - } > - > lock_buffer(bh); > if (buffer_pinned(bh)) { > set_bit(TR_TOUCHED, &tr->tr_flags);