summaryrefslogtreecommitdiffstats
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
authorRitesh Harjani <riteshh@linux.ibm.com>2020-09-18 10:36:35 +0530
committerTheodore Ts'o <tytso@mit.edu>2020-10-18 10:36:58 -0400
commit9faac62d40131521973192e46a82d5066bb42c09 (patch)
treeaae393faf4ef585b38c70aedc85fd69a2b222ba9 /fs/ext4/inode.c
parent7eb90a2d6a4817d73165a2a1addd5ead2fcb74b1 (diff)
downloadlinux-9faac62d40131521973192e46a82d5066bb42c09.tar.gz
linux-9faac62d40131521973192e46a82d5066bb42c09.tar.bz2
linux-9faac62d40131521973192e46a82d5066bb42c09.zip
ext4: optimize file overwrites
In case if the file already has underlying blocks/extents allocated then we don't need to start a journal txn and can directly return the underlying mapping. Currently ext4_iomap_begin() is used by both DAX & DIO path. We can check if the write request is an overwrite & then directly return the mapping information. This could give a significant perf boost for multi-threaded writes specially random overwrites. On PPC64 VM with simulated pmem(DAX) device, ~10x perf improvement could be seen in random writes (overwrite). Also bcoz this optimizes away the spinlock contention during jbd2 slab cache allocation (jbd2_journal_handle). On x86 VM, ~2x perf improvement was observed. Reported-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com> Link: https://lore.kernel.org/r/88e795d8a4d5cd22165c7ebe857ba91d68d8813e.1600401668.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c18
1 files changed, 15 insertions, 3 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f1ee0229ac12..f81f45f5db73 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3436,14 +3436,26 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
- if (flags & IOMAP_WRITE)
+ if (flags & IOMAP_WRITE) {
+ /*
+ * We check here if the blocks are already allocated, then we
+ * don't need to start a journal txn and we can directly return
+ * the mapping information. This could boost performance
+ * especially in multi-threaded overwrite requests.
+ */
+ if (offset + length <= i_size_read(inode)) {
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret > 0 && (map.m_flags & EXT4_MAP_MAPPED))
+ goto out;
+ }
ret = ext4_iomap_alloc(inode, &map, flags);
- else
+ } else {
ret = ext4_map_blocks(NULL, inode, &map, 0);
+ }
if (ret < 0)
return ret;
-
+out:
ext4_set_iomap(inode, iomap, &map, offset, length);
return 0;