Gang He
2017-Nov-27 09:46 UTC
[Ocfs2-devel] [PATCH 2/3] ocfs2: add ocfs2_overwrite_io function
Add ocfs2_overwrite_io function, which is used to judge if
overwrite allocated blocks, otherwise, the write will bring extra
block allocation overhead.
Signed-off-by: Gang He <ghe at suse.com>
---
fs/ocfs2/extent_map.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++
fs/ocfs2/extent_map.h | 3 +++
2 files changed, 70 insertions(+)
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index e4719e0..98bf325 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -832,6 +832,73 @@ int ocfs2_fiemap(struct inode *inode, struct
fiemap_extent_info *fieinfo,
return ret;
}
+/* Is IO overwriting allocated blocks? */
+int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len,
+ int wait)
+{
+ int ret = 0, is_last;
+ u32 mapping_end, cpos;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_extent_rec rec;
+
+ if (wait)
+ ret = ocfs2_inode_lock(inode, &di_bh, 0);
+ else
+ ret = ocfs2_try_inode_lock(inode, &di_bh, 0);
+ if (ret)
+ goto out;
+
+ if (wait)
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+ else {
+ if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
+ ret = -EAGAIN;
+ goto out_unlock1;
+ }
+ }
+
+ if ((OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+ ((map_start + map_len) <= i_size_read(inode)))
+ goto out_unlock2;
+
+ cpos = map_start >> osb->s_clustersize_bits;
+ mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
+ map_start + map_len);
+ is_last = 0;
+ while (cpos < mapping_end && !is_last) {
+ ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos,
+ NULL, &rec, &is_last);
+ if (ret) {
+ mlog_errno(ret);
+ goto out_unlock2;
+ }
+
+ if (rec.e_blkno == 0ULL)
+ break;
+
+ if (rec.e_flags & OCFS2_EXT_REFCOUNTED)
+ break;
+
+ cpos = le32_to_cpu(rec.e_cpos) +
+ le16_to_cpu(rec.e_leaf_clusters);
+ }
+
+ if (cpos < mapping_end)
+ ret = 1;
+
+out_unlock2:
+ brelse(di_bh);
+
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+out_unlock1:
+ ocfs2_inode_unlock(inode, 0);
+
+out:
+ return (ret ? 0 : 1);
+}
+
int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence)
{
struct inode *inode = file->f_mapping->host;
diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h
index 67ea57d..fd9e86a 100644
--- a/fs/ocfs2/extent_map.h
+++ b/fs/ocfs2/extent_map.h
@@ -53,6 +53,9 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64
v_blkno, u64 *p_blkno,
int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 map_start, u64 map_len);
+int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len,
+ int wait);
+
int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin);
int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
--
1.8.5.6
Joseph Qi
2017-Nov-28 01:13 UTC
[Ocfs2-devel] [PATCH 2/3] ocfs2: add ocfs2_overwrite_io function
Hi Gang, On 17/11/27 17:46, Gang He wrote:> Add ocfs2_overwrite_io function, which is used to judge if > overwrite allocated blocks, otherwise, the write will bring extra > block allocation overhead. > > Signed-off-by: Gang He <ghe at suse.com> > --- > fs/ocfs2/extent_map.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++ > fs/ocfs2/extent_map.h | 3 +++ > 2 files changed, 70 insertions(+) > > diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c > index e4719e0..98bf325 100644 > --- a/fs/ocfs2/extent_map.c > +++ b/fs/ocfs2/extent_map.c > @@ -832,6 +832,73 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > return ret; > } > > +/* Is IO overwriting allocated blocks? */ > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait) > +{ > + int ret = 0, is_last; > + u32 mapping_end, cpos; > + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > + struct buffer_head *di_bh = NULL; > + struct ocfs2_extent_rec rec; > + > + if (wait) > + ret = ocfs2_inode_lock(inode, &di_bh, 0); > + else > + ret = ocfs2_try_inode_lock(inode, &di_bh, 0); > + if (ret) > + goto out; > + > + if (wait) > + down_read(&OCFS2_I(inode)->ip_alloc_sem); > + else { > + if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { > + ret = -EAGAIN; > + goto out_unlock1; > + } > + } > + > + if ((OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) && > + ((map_start + map_len) <= i_size_read(inode))) > + goto out_unlock2; > + > + cpos = map_start >> osb->s_clustersize_bits; > + mapping_end = ocfs2_clusters_for_bytes(inode->i_sb, > + map_start + map_len); > + is_last = 0; > + while (cpos < mapping_end && !is_last) { > + ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, > + NULL, &rec, &is_last); > + if (ret) { > + mlog_errno(ret); > + goto out_unlock2; > + } > + > + if (rec.e_blkno == 0ULL) > + break; > + > + if (rec.e_flags & OCFS2_EXT_REFCOUNTED) > + break; > + > + cpos = le32_to_cpu(rec.e_cpos) + > + le16_to_cpu(rec.e_leaf_clusters); > + } > + > + if (cpos < mapping_end) > + ret = 1; > + > +out_unlock2: > + brelse(di_bh); > + > + up_read(&OCFS2_I(inode)->ip_alloc_sem); > + > +out_unlock1:Should brelse(di_bh) be here?> + ocfs2_inode_unlock(inode, 0); > + > +out: > + return (ret ? 0 : 1);I don't think EAGAIN and other error code can be handled the same. We have to distinguish them. Thanks, Joseph> +} > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) > { > struct inode *inode = file->f_mapping->host; > diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h > index 67ea57d..fd9e86a 100644 > --- a/fs/ocfs2/extent_map.h > +++ b/fs/ocfs2/extent_map.h > @@ -53,6 +53,9 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, > int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > u64 map_start, u64 map_len); > > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait); > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin); > > int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster, >
piaojun
2017-Nov-28 01:50 UTC
[Ocfs2-devel] [PATCH 2/3] ocfs2: add ocfs2_overwrite_io function
Hi Gang, If ocfs2_overwrite_io is only called in 'nowait' scenarios, I wonder if we can discard 'int wait' just as ext4 does: static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len); thans, Jun On 2017/11/27 17:46, Gang He wrote:> Add ocfs2_overwrite_io function, which is used to judge if > overwrite allocated blocks, otherwise, the write will bring extra > block allocation overhead. > > Signed-off-by: Gang He <ghe at suse.com> > --- > fs/ocfs2/extent_map.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++ > fs/ocfs2/extent_map.h | 3 +++ > 2 files changed, 70 insertions(+) > > diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c > index e4719e0..98bf325 100644 > --- a/fs/ocfs2/extent_map.c > +++ b/fs/ocfs2/extent_map.c > @@ -832,6 +832,73 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > return ret; > } > > +/* Is IO overwriting allocated blocks? */ > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait) > +{ > + int ret = 0, is_last; > + u32 mapping_end, cpos; > + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > + struct buffer_head *di_bh = NULL; > + struct ocfs2_extent_rec rec; > + > + if (wait) > + ret = ocfs2_inode_lock(inode, &di_bh, 0); > + else > + ret = ocfs2_try_inode_lock(inode, &di_bh, 0); > + if (ret) > + goto out; > + > + if (wait) > + down_read(&OCFS2_I(inode)->ip_alloc_sem); > + else { > + if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { > + ret = -EAGAIN; > + goto out_unlock1; > + } > + } > + > + if ((OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) && > + ((map_start + map_len) <= i_size_read(inode))) > + goto out_unlock2; > + > + cpos = map_start >> osb->s_clustersize_bits; > + mapping_end = ocfs2_clusters_for_bytes(inode->i_sb, > + map_start + map_len); > + is_last = 0; > + while (cpos < mapping_end && !is_last) { > + ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, > + NULL, &rec, &is_last); > + if (ret) { > + mlog_errno(ret); > + goto out_unlock2; > + } > + > + if (rec.e_blkno == 0ULL) > + break; > + > + if (rec.e_flags & OCFS2_EXT_REFCOUNTED) > + break; > + > + cpos = le32_to_cpu(rec.e_cpos) + > + le16_to_cpu(rec.e_leaf_clusters); > + } > + > + if (cpos < mapping_end) > + ret = 1; > + > +out_unlock2: > + brelse(di_bh); > + > + up_read(&OCFS2_I(inode)->ip_alloc_sem); > + > +out_unlock1: > + ocfs2_inode_unlock(inode, 0); > + > +out: > + return (ret ? 0 : 1); > +} > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) > { > struct inode *inode = file->f_mapping->host; > diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h > index 67ea57d..fd9e86a 100644 > --- a/fs/ocfs2/extent_map.h > +++ b/fs/ocfs2/extent_map.h > @@ -53,6 +53,9 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, > int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > u64 map_start, u64 map_len); > > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait); > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin); > > int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster, >
alex chen
2017-Nov-28 02:19 UTC
[Ocfs2-devel] [PATCH 2/3] ocfs2: add ocfs2_overwrite_io function
Hi Gang, On 2017/11/27 17:46, Gang He wrote:> Add ocfs2_overwrite_io function, which is used to judge if > overwrite allocated blocks, otherwise, the write will bring extra > block allocation overhead. > > Signed-off-by: Gang He <ghe at suse.com> > --- > fs/ocfs2/extent_map.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++ > fs/ocfs2/extent_map.h | 3 +++ > 2 files changed, 70 insertions(+) > > diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c > index e4719e0..98bf325 100644 > --- a/fs/ocfs2/extent_map.c > +++ b/fs/ocfs2/extent_map.c > @@ -832,6 +832,73 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > return ret; > } > > +/* Is IO overwriting allocated blocks? */ > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait) > +{ > + int ret = 0, is_last; > + u32 mapping_end, cpos; > + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > + struct buffer_head *di_bh = NULL; > + struct ocfs2_extent_rec rec; > + > + if (wait) > + ret = ocfs2_inode_lock(inode, &di_bh, 0); > + else > + ret = ocfs2_try_inode_lock(inode, &di_bh, 0); > + if (ret) > + goto out; > + > + if (wait) > + down_read(&OCFS2_I(inode)->ip_alloc_sem); > + else { > + if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { > + ret = -EAGAIN; > + goto out_unlock1; > + } > + } > + > + if ((OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) && > + ((map_start + map_len) <= i_size_read(inode))) > + goto out_unlock2; > + > + cpos = map_start >> osb->s_clustersize_bits; > + mapping_end = ocfs2_clusters_for_bytes(inode->i_sb, > + map_start + map_len); > + is_last = 0; > + while (cpos < mapping_end && !is_last) { > + ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, > + NULL, &rec, &is_last); > + if (ret) { > + mlog_errno(ret); > + goto out_unlock2; > + } > + > + if (rec.e_blkno == 0ULL) > + break;I think here the blocks is not overwrite, because the hold is found and the blocks should be allocated.> + > + if (rec.e_flags & OCFS2_EXT_REFCOUNTED) > + break; > + > + cpos = le32_to_cpu(rec.e_cpos) + > + le16_to_cpu(rec.e_leaf_clusters); > + } > + > + if (cpos < mapping_end) > + ret = 1; > + > +out_unlock2:I think the 'out_up_read' is more readable than the 'out_unlock2' .> + brelse(di_bh); > + > + up_read(&OCFS2_I(inode)->ip_alloc_sem); > + > +out_unlock1:We should release buffer head here.> + ocfs2_inode_unlock(inode, 0); > + > +out: > + return (ret ? 0 : 1); > +} > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) > { > struct inode *inode = file->f_mapping->host; > diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h > index 67ea57d..fd9e86a 100644 > --- a/fs/ocfs2/extent_map.h > +++ b/fs/ocfs2/extent_map.h > @@ -53,6 +53,9 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, > int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > u64 map_start, u64 map_len); > > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait); > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin); > > int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster, >
Changwei Ge
2017-Nov-28 02:48 UTC
[Ocfs2-devel] [PATCH 2/3] ocfs2: add ocfs2_overwrite_io function
Hi, Gang On 2017/11/27 17:48, Gang He wrote:> Add ocfs2_overwrite_io function, which is used to judge if > overwrite allocated blocks, otherwise, the write will bring extra > block allocation overhead. >Can you elaborate how this overhead is introduced? Forgive me, I don't figure it. Thanks, Changwei> Signed-off-by: Gang He <ghe at suse.com> > --- > fs/ocfs2/extent_map.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++++ > fs/ocfs2/extent_map.h | 3 +++ > 2 files changed, 70 insertions(+) > > diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c > index e4719e0..98bf325 100644 > --- a/fs/ocfs2/extent_map.c > +++ b/fs/ocfs2/extent_map.c > @@ -832,6 +832,73 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > return ret; > } > > +/* Is IO overwriting allocated blocks? */ > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait) > +{ > + int ret = 0, is_last; > + u32 mapping_end, cpos; > + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); > + struct buffer_head *di_bh = NULL; > + struct ocfs2_extent_rec rec; > + > + if (wait) > + ret = ocfs2_inode_lock(inode, &di_bh, 0); > + else > + ret = ocfs2_try_inode_lock(inode, &di_bh, 0); > + if (ret) > + goto out; > + > + if (wait) > + down_read(&OCFS2_I(inode)->ip_alloc_sem); > + else { > + if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { > + ret = -EAGAIN; > + goto out_unlock1; > + } > + } > + > + if ((OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) && > + ((map_start + map_len) <= i_size_read(inode))) > + goto out_unlock2; > + > + cpos = map_start >> osb->s_clustersize_bits; > + mapping_end = ocfs2_clusters_for_bytes(inode->i_sb, > + map_start + map_len); > + is_last = 0; > + while (cpos < mapping_end && !is_last) { > + ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, > + NULL, &rec, &is_last); > + if (ret) { > + mlog_errno(ret); > + goto out_unlock2; > + } > + > + if (rec.e_blkno == 0ULL) > + break; > + > + if (rec.e_flags & OCFS2_EXT_REFCOUNTED) > + break; > + > + cpos = le32_to_cpu(rec.e_cpos) + > + le16_to_cpu(rec.e_leaf_clusters); > + } > + > + if (cpos < mapping_end) > + ret = 1; > + > +out_unlock2: > + brelse(di_bh); > + > + up_read(&OCFS2_I(inode)->ip_alloc_sem); > + > +out_unlock1: > + ocfs2_inode_unlock(inode, 0); > + > +out: > + return (ret ? 0 : 1); > +} > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int whence) > { > struct inode *inode = file->f_mapping->host; > diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h > index 67ea57d..fd9e86a 100644 > --- a/fs/ocfs2/extent_map.h > +++ b/fs/ocfs2/extent_map.h > @@ -53,6 +53,9 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, > int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, > u64 map_start, u64 map_len); > > +int ocfs2_overwrite_io(struct inode *inode, u64 map_start, u64 map_len, > + int wait); > + > int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin); > > int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster, >