From: Zhang Yi yi.zhang@huawei.com
mainline inclusion from mainline-5.15-rc4 commit cc883236b79297f6266ca6f4e7f24f3fd3c736c1 category: perf bugzilla: 182881 https://gitee.com/openeuler/kernel/issues/I4DDEL
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
---------------------------
After we factor out the inline data write procedure from ext4_da_write_end(), we don't need to start journal handle for the cases of both buffer overwrite and append-write. If we need to update i_disksize, mark_inode_dirty() do start handle and update inode buffer. So we could just remove all the journal handle codes in the delalloc write procedure.
After this patch, we could get a lot of performance improvement. Below is the Unixbench comparison data test on my machine with 'Intel Xeon Gold 5120' CPU and nvme SSD backend.
Test cmd:
./Run -c 56 -i 3 fstime fsbuffer fsdisk
Before this patch:
System Benchmarks Partial Index BASELINE RESULT INDEX File Copy 1024 bufsize 2000 maxblocks 3960.0 422965.0 1068.1 File Copy 256 bufsize 500 maxblocks 1655.0 105077.0 634.9 File Copy 4096 bufsize 8000 maxblocks 5800.0 1429092.0 2464.0 ====== System Benchmarks Index Score (Partial Only) 1186.6
After this patch:
System Benchmarks Partial Index BASELINE RESULT INDEX File Copy 1024 bufsize 2000 maxblocks 3960.0 732716.0 1850.3 File Copy 256 bufsize 500 maxblocks 1655.0 184940.0 1117.5 File Copy 4096 bufsize 8000 maxblocks 5800.0 2427152.0 4184.7 ====== System Benchmarks Index Score (Partial Only) 2053.0
Signed-off-by: Zhang Yi yi.zhang@huawei.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Link: https://lore.kernel.org/r/20210716122024.1105856-5-yi.zhang@huawei.com Reviewed-by: Yang Erkun yangerkun@huawei.com
Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- fs/ext4/inode.c | 60 +++++-------------------------------------------- 1 file changed, 5 insertions(+), 55 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 49926b9c52cb..94c9a4d01102 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2914,19 +2914,6 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; }
-/* We always reserve for an inode update; the superblock could be there too */ -static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) -{ - if (likely(ext4_has_feature_large_file(inode->i_sb))) - return 1; - - if (pos + len <= 0x7fffffffULL) - return 1; - - /* We might need to update the superblock to set LARGE_FILE */ - return 2; -} - static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2935,7 +2922,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, struct page *page; pgoff_t index; struct inode *inode = mapping->host; - handle_t *handle;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; @@ -2961,41 +2947,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, return 0; }
- /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page - * is being written back. So grab it first before we start - * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. - */ -retry_grab: +retry: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; - unlock_page(page); - - /* - * With delayed allocation, we don't log the i_disksize update - * if there is delayed block allocation. But we still need - * to journalling the i_disksize update if writes to the end - * of file which has an already mapped buffer. - */ -retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_da_write_credits(inode, pos, len)); - if (IS_ERR(handle)) { - put_page(page); - return PTR_ERR(handle); - }
- lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - put_page(page); - ext4_journal_stop(handle); - goto retry_grab; - } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page);
@@ -3007,20 +2963,18 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, #endif if (ret < 0) { unlock_page(page); - ext4_journal_stop(handle); + put_page(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode);
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry_journal; - - put_page(page); + goto retry; return ret; }
@@ -3057,8 +3011,6 @@ static int ext4_da_write_end(struct file *file, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - int ret; - handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; @@ -3097,9 +3049,7 @@ static int ext4_da_write_end(struct file *file, ext4_da_should_update_i_disksize(page, end)) ext4_update_i_disksize(inode, new_i_size);
- copied = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - ret = ext4_journal_stop(handle); - return ret ? ret : copied; + return generic_write_end(file, mapping, pos, len, copied, page, fsdata); }
/*