LU-4198 clio: turn on lockless for some kind of IO

[fs/lustre-release.git] / lustre / llite / vvp_io.c

diff --git a/lustre/llite/vvp_io.c b/lustre/llite/vvp_io.c
index 9ae162f..ac3965f 100644 (file)
--- a/lustre/llite/vvp_io.c
+++ b/lustre/llite/vvp_io.c
@@ -568,6 +568,16 @@ static int vvp_io_rw_lock(const struct lu_env *env, struct cl_io *io,
                ast_flags |= CEF_NONBLOCK;
        if (io->ci_lock_no_expand)
                ast_flags |= CEF_LOCK_NO_EXPAND;
+       if (vio->vui_fd) {
+               /* Group lock held means no lockless any more */
+               if (vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)
+                       io->ci_ignore_lockless = 1;
+
+               if (ll_file_nolock(vio->vui_fd->fd_file) ||
+                   (vio->vui_fd->fd_flags & LL_FILE_LOCKLESS_IO &&
+                    !io->ci_ignore_lockless))
+                       ast_flags |= CEF_NEVER;
+       }
 
        result = vvp_mmap_locks(env, vio, io);
        if (result == 0)
@@ -719,7 +729,7 @@ static int vvp_io_setattr_start(const struct lu_env *env,
        struct ll_inode_info    *lli   = ll_i2info(inode);
 
        if (cl_io_is_trunc(io)) {
-               down_write(&lli->lli_trunc_sem);
+               trunc_sem_down_write(&lli->lli_trunc_sem);
                inode_lock(inode);
                inode_dio_wait(inode);
        } else {
@@ -745,7 +755,7 @@ static void vvp_io_setattr_end(const struct lu_env *env,
                vvp_do_vmtruncate(inode, io->u.ci_setattr.sa_attr.lvb_size);
                inode_dio_write_done(inode);
                inode_unlock(inode);
-               up_write(&lli->lli_trunc_sem);
+               trunc_sem_up_write(&lli->lli_trunc_sem);
        } else {
                inode_unlock(inode);
        }
@@ -768,17 +778,17 @@ static void vvp_io_setattr_fini(const struct lu_env *env,
 static int vvp_io_read_start(const struct lu_env *env,
                             const struct cl_io_slice *ios)
 {
-       struct vvp_io           *vio   = cl2vvp_io(env, ios);
-       struct cl_io            *io    = ios->cis_io;
-       struct cl_object        *obj   = io->ci_obj;
-       struct inode            *inode = vvp_object_inode(obj);
-       struct ll_inode_info    *lli   = ll_i2info(inode);
-       struct file             *file  = vio->vui_fd->fd_file;
-       loff_t  pos = io->u.ci_rd.rd.crw_pos;
-       long    cnt = io->u.ci_rd.rd.crw_count;
-       long    tot = vio->vui_tot_count;
-       int     exceed = 0;
-       int     result;
+       struct vvp_io *vio = cl2vvp_io(env, ios);
+       struct cl_io *io = ios->cis_io;
+       struct cl_object *obj = io->ci_obj;
+       struct inode *inode = vvp_object_inode(obj);
+       struct ll_inode_info *lli = ll_i2info(inode);
+       struct file *file = vio->vui_fd->fd_file;
+       loff_t pos = io->u.ci_rd.rd.crw_pos;
+       size_t cnt = io->u.ci_rd.rd.crw_count;
+       size_t tot = vio->vui_tot_count;
+       int exceed = 0;
+       int result;
        ENTRY;
 
        CLOBINVRNT(env, obj, vvp_object_invariant(obj));
@@ -788,7 +798,7 @@ static int vvp_io_read_start(const struct lu_env *env,
                pos, pos + cnt);
 
        if (vio->vui_io_subtype == IO_NORMAL)
-               down_read(&lli->lli_trunc_sem);
+               trunc_sem_down_read(&lli->lli_trunc_sem);
 
        if (io->ci_async_readahead) {
                file_accessed(file);
@@ -816,15 +826,15 @@ static int vvp_io_read_start(const struct lu_env *env,
        /* initialize read-ahead window once per syscall */
        if (!vio->vui_ra_valid) {
                vio->vui_ra_valid = true;
-               vio->vui_ra_start = cl_index(obj, pos);
-               vio->vui_ra_count = cl_index(obj, tot + PAGE_SIZE - 1);
+               vio->vui_ra_start_idx = cl_index(obj, pos);
+               vio->vui_ra_pages = cl_index(obj, tot + PAGE_SIZE - 1);
                /* If both start and end are unaligned, we read one more page
                 * than the index math suggests. */
-               if (pos % PAGE_SIZE != 0 && (pos + tot) % PAGE_SIZE != 0)
-                       vio->vui_ra_count++;
+               if ((pos & ~PAGE_MASK) != 0 && ((pos + tot) & ~PAGE_MASK) != 0)
+                       vio->vui_ra_pages++;
 
-               CDEBUG(D_READA, "tot %ld, ra_start %lu, ra_count %lu\n", tot,
-                      vio->vui_ra_start, vio->vui_ra_count);
+               CDEBUG(D_READA, "tot %zu, ra_start %lu, ra_count %lu\n",
+                      tot, vio->vui_ra_start_idx, vio->vui_ra_pages);
        }
 
        /* BUG: 5972 */
@@ -1186,7 +1196,7 @@ static int vvp_io_write_start(const struct lu_env *env,
        ENTRY;
 
        if (vio->vui_io_subtype == IO_NORMAL)
-               down_read(&lli->lli_trunc_sem);
+               trunc_sem_down_read(&lli->lli_trunc_sem);
 
        if (!can_populate_pages(env, io, inode))
                RETURN(0);
@@ -1306,7 +1316,7 @@ static void vvp_io_rw_end(const struct lu_env *env,
        struct ll_inode_info    *lli = ll_i2info(inode);
 
        if (vio->vui_io_subtype == IO_NORMAL)
-               up_read(&lli->lli_trunc_sem);
+               trunc_sem_up_read(&lli->lli_trunc_sem);
 }
 
 static int vvp_io_kernel_fault(struct vvp_fault_io *cfio)
@@ -1371,7 +1381,7 @@ static int vvp_io_fault_start(const struct lu_env *env,
        pgoff_t                  last_index;
        ENTRY;
 
-       down_read(&lli->lli_trunc_sem);
+       trunc_sem_down_read_nowait(&lli->lli_trunc_sem);
 
         /* offset of the last byte on the page */
         offset = cl_offset(obj, fio->ft_index + 1) - 1;
@@ -1521,7 +1531,7 @@ static void vvp_io_fault_end(const struct lu_env *env,
 
        CLOBINVRNT(env, ios->cis_io->ci_obj,
                   vvp_object_invariant(ios->cis_io->ci_obj));
-       up_read(&lli->lli_trunc_sem);
+       trunc_sem_up_read(&lli->lli_trunc_sem);
 }
 
 static int vvp_io_fsync_start(const struct lu_env *env,
@@ -1545,7 +1555,7 @@ static int vvp_io_read_ahead(const struct lu_env *env,
                struct vvp_io *vio = cl2vvp_io(env, ios);
 
                if (unlikely(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
-                       ra->cra_end = CL_PAGE_EOF;
+                       ra->cra_end_idx = CL_PAGE_EOF;
                        result = +1; /* no need to call down */
                }
        }