@@ -3437,6 +3437,14 @@ 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;
+ /*
+ * In case of DAX write, we check if this is overwrite request, to avoid
+ * starting a journal txn in ext4_iomap_alloc()
+ */
+ if ((flags & IOMAP_WRITE) && IS_DAX(inode) &&
+ ext4_overwrite_io(inode, &map, true))
+ goto out_set;
+
if (flags & IOMAP_WRITE)
ret = ext4_iomap_alloc(inode, &map, flags);
else
@@ -3444,9 +3452,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
if (ret < 0)
return ret;
-
+out_set:
ext4_set_iomap(inode, iomap, &map, offset, length);
-
return 0;
}
Currently in case of DAX, we are starting a journal txn everytime for IOMAP_WRITE case. This can be optimized away in case of an overwrite (where the blocks were already allocated). This could give a significant performance boost for multi-threaded writes specially random writes. On PPC64 VM with simulated pmem 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> Suggested-by: Jan Kara <jack@suse.cz> Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com> --- fs/ext4/inode.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)