Add two new fcntls to enable/disable read-ahead:

- F_READAHEAD: specify the amount for sequential access.  The amount is
   specified in bytes and is rounded up to nearest block size.
 - F_RDAHEAD: Darwin compatible version that use 128KB as the sequential
   access size.

A third argument of zero disables the read-ahead behavior.

Please note that the read-ahead amount is also constrainted by sysctl
variable, vfs.read_max, which may need to be raised in order to better
utilize this feature.

Thanks Igor Sysoev for proposing the feature and submitting the original
version, and kib@ for his valuable comments.

Submitted by:	Igor Sysoev <is rambler-co ru>
Reviewed by:	kib@
MFC after:	1 month

lib/libc/sys/fcntl.2

@@ -28,7 +28,7 @@
 .\"     @(#)fcntl.2	8.2 (Berkeley) 1/12/94
 .\" $FreeBSD$
 .\"
-.Dd March 8, 2008
+.Dd September 28, 2009
 .Dt FCNTL 2
 .Os
 .Sh NAME
@@ -241,6 +241,22 @@ will be interrupted if the signal handler has not specified the
 .Dv SA_RESTART
 (see
 .Xr sigaction 2 ) .
+.It Dv F_READAHEAD
+Set or clear the read ahead amount for sequential access to the third
+argument,
+.Fa arg ,
+which is rounded up to the nearest block size.
+A zero value in
+.Fa arg
+turns off read ahead.
+.It Dv F_RDAHEAD
+Equivalent to Darwin counterpart which sets read ahead amount of 128KB
+when the third argument,
+.Fa arg
+is non-zero.
+A zero value in
+.Fa arg
+turns off read ahead.
 .El
 .Pp
 When a shared lock has been set on a segment of a file,

sys/kern/kern_descrip.c

@@ -421,6 +421,8 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg)
 	struct vnode *vp;
 	int error, flg, tmp;
 	int vfslocked;
+	u_int old, new;
+	uint64_t bsize;
 
 	vfslocked = 0;
 	error = 0;
@@ -686,6 +688,48 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg)
 		vfslocked = 0;
 		fdrop(fp, td);
 		break;
+
+	case F_RDAHEAD:
+		arg = arg ? 128 * 1024: 0;
+		/* FALLTHROUGH */
+	case F_READAHEAD:
+		FILEDESC_SLOCK(fdp);
+		if ((fp = fdtofp(fd, fdp)) == NULL) {
+			FILEDESC_SUNLOCK(fdp);
+			error = EBADF;
+			break;
+		}
+		if (fp->f_type != DTYPE_VNODE) {
+			FILEDESC_SUNLOCK(fdp);
+			error = EBADF;
+			break;
+		}
+		fhold(fp);
+		FILEDESC_SUNLOCK(fdp);
+		if (arg != 0) {
+			vp = fp->f_vnode;
+			vfslocked = VFS_LOCK_GIANT(vp->v_mount);
+			error = vn_lock(vp, LK_SHARED);
+			if (error != 0)
+				goto readahead_vnlock_fail;
+			bsize = fp->f_vnode->v_mount->mnt_stat.f_iosize;
+			VOP_UNLOCK(vp, 0);
+			fp->f_seqcount = (arg + bsize - 1) / bsize;
+			do {
+				new = old = fp->f_flag;
+				new |= FRDAHEAD;
+			} while (atomic_cmpset_rel_int(&fp->f_flag, old, new) == 0);
+readahead_vnlock_fail:
+			VFS_UNLOCK_GIANT(vfslocked);
+		} else {
+			do {
+				new = old = fp->f_flag;
+				new &= ~FRDAHEAD;
+			} while (atomic_cmpset_rel_int(&fp->f_flag, old, new) == 0);
+		}
+		fdrop(fp, td);
+		break;
+
 	default:
 		error = EINVAL;
 		break;

sys/kern/vfs_vnops.c

@@ -312,6 +312,9 @@ static int
 sequential_heuristic(struct uio *uio, struct file *fp)
 {
 
+	if (atomic_load_acq_int(&(fp->f_flag)) & FRDAHEAD)
+		return (fp->f_seqcount << IO_SEQSHIFT);
+
 	/*
 	 * Offset 0 is handled specially.  open() sets f_seqcount to 1 so
 	 * that the first I/O is normally considered to be slightly

sys/sys/fcntl.h

@@ -140,7 +140,7 @@ typedef	__pid_t		pid_t;
 /* bits to save after open */
 #define	FMASK	(FREAD|FWRITE|FAPPEND|FASYNC|FFSYNC|FNONBLOCK|O_DIRECT|FEXEC)
 /* bits settable by fcntl(F_SETFL, ...) */
-#define	FCNTLFLAGS	(FAPPEND|FASYNC|FFSYNC|FNONBLOCK|O_DIRECT)
+#define	FCNTLFLAGS	(FAPPEND|FASYNC|FFSYNC|FNONBLOCK|FRDAHEAD|O_DIRECT)
 
 #if defined(COMPAT_FREEBSD7) || defined(COMPAT_FREEBSD6) || \
     defined(COMPAT_FREEBSD5) || defined(COMPAT_FREEBSD4)
@@ -151,7 +151,8 @@ typedef	__pid_t		pid_t;
  */
 #define	FPOSIXSHM	O_NOFOLLOW
 #undef FCNTLFLAGS
-#define	FCNTLFLAGS	(FAPPEND|FASYNC|FFSYNC|FNONBLOCK|FPOSIXSHM|O_DIRECT)
+#define	FCNTLFLAGS	(FAPPEND|FASYNC|FFSYNC|FNONBLOCK|FPOSIXSHM|FRDAHEAD| \
+			 O_DIRECT)
 #endif
 #endif
 
@@ -176,6 +177,8 @@ typedef	__pid_t		pid_t;
  * different meaning for fcntl(2).
  */
 #if __BSD_VISIBLE
+/* Read ahead */
+#define	FRDAHEAD	O_CREAT
 #endif
 
 /* Defined by POSIX Extended API Set Part 2 */
@@ -218,6 +221,8 @@ typedef	__pid_t		pid_t;
 #define	F_SETLK		12		/* set record locking information */
 #define	F_SETLKW	13		/* F_SETLK; wait if blocked */
 #define	F_SETLK_REMOTE	14		/* debugging support for remote locks */
+#define	F_READAHEAD	15		/* read ahead */
+#define	F_RDAHEAD	16		/* Darwin compatible read ahead */
 
 /* file descriptor flags (F_GETFD, F_SETFD) */
 #define	FD_CLOEXEC	1		/* close-on-exec flag */