fs: place f_ref to 3rd cache line in struct file to resolve false sharing

When running syscall pread in a high core count system, f_ref contends
with the reading of f_mode, f_op, f_mapping, f_inode, f_flags in the
same cache line.

This change places f_ref to the 3rd cache line where fields are not
updated as frequently as the 1st cache line, and the contention is
grealy reduced according to tests. In addition, the size of file
object is kept in 3 cache lines.

This change has been tested with rocksdb benchmark readwhilewriting case
in 1 socket 64 physical core 128 logical core baremetal machine, with
build config CONFIG_RANDSTRUCT_NONE=y
Command:
./db_bench --benchmarks="readwhilewriting" --threads $cnt --duration 60
The throughput(ops/s) is improved up to ~21%.
=====
thread		baseline	compare
16		 100%		 +1.3%
32		 100%		 +2.2%
64		 100%		 +7.2%
128		 100%		 +20.9%

It was also tested with UnixBench: syscall, fsbuffer, fstime,
fsdisk cases that has been used for file struct layout tuning, no
regression was observed.

Signed-off-by: Pan Deng <pan.deng@intel.com>
Link: https://lore.kernel.org/r/20250228020059.3023375-1-pan.deng@intel.com
Tested-by: Lipeng Zhu <lipeng.zhu@intel.com>
Reviewed-by: Tianyou Li <tianyou.li@intel.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 70c985f3d787c89cfaa601dedf12fa54dc8dcd40..9ab789cd1531be25db8a0eea80058ba18c3492cf 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1058,7 +1058,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 
 /**
  * struct file - Represents a file
- * @f_ref: reference count
  * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context.
  * @f_mode: FMODE_* flags often used in hotpaths
  * @f_op: file operations
@@ -1068,12 +1067,12 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  * @f_flags: file flags
  * @f_iocb_flags: iocb flags
  * @f_cred: stashed credentials of creator/opener
+ * @f_owner: file owner
  * @f_path: path of the file
  * @f_pos_lock: lock protecting file position
  * @f_pipe: specific to pipes
  * @f_pos: file position
  * @f_security: LSM security context of this file
- * @f_owner: file owner
  * @f_wb_err: writeback error
  * @f_sb_err: per sb writeback errors
  * @f_ep: link of all epoll hooks for this file
@@ -1081,9 +1080,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
  * @f_llist: work queue entrypoint
  * @f_ra: file's readahead state
  * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.)
+ * @f_ref: reference count
  */
 struct file {
-       file_ref_t                      f_ref;
        spinlock_t                      f_lock;
        fmode_t                         f_mode;
        const struct file_operations    *f_op;
@@ -1093,6 +1092,7 @@ struct file {
        unsigned int                    f_flags;
        unsigned int                    f_iocb_flags;
        const struct cred               *f_cred;
+       struct fown_struct              *f_owner;
        /* --- cacheline 1 boundary (64 bytes) --- */
        struct path                     f_path;
        union {
@@ -1106,7 +1106,6 @@ struct file {
        void                            *f_security;
 #endif
        /* --- cacheline 2 boundary (128 bytes) --- */
-       struct fown_struct              *f_owner;
        errseq_t                        f_wb_err;
        errseq_t                        f_sb_err;
 #ifdef CONFIG_EPOLL
@@ -1118,6 +1117,7 @@ struct file {
                struct file_ra_state    f_ra;
                freeptr_t               f_freeptr;
        };
+       file_ref_t                      f_ref;
        /* --- cacheline 3 boundary (192 bytes) --- */
 } __randomize_layout
   __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */