.\" $OpenBSD: disk.9,v 1.30 2011/10/06 22:22:11 jmc Exp $ .\" $NetBSD: disk.9,v 1.2 1996/04/08 20:41:25 jtc Exp $ .\" .\" Copyright (c) 1995, 1996 Jason R. Thorpe. .\" All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" 3. All advertising materials mentioning features or use of this software .\" must display the following acknowledgement: .\" This product includes software developed for the NetBSD Project .\" by Jason R. Thorpe. .\" 4. The name of the author may not be used to endorse or promote products .\" derived from this software without specific prior written permission. .\" .\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR .\" IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES .\" OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. .\" IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, .\" INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, .\" BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; .\" LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED .\" AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, .\" OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .Dd $Mdocdate: October 6 2011 $ .Dt DISK 9 .Os .Sh NAME .Nm disk .Nd generic disk framework .Sh SYNOPSIS .Fd #include .Fd #include .Fd #include .Ft void .Fn disk_init "void" .Ft void .Fn disk_attach "struct disk *" .Ft void .Fn disk_detach "struct disk *" .Ft void .Fn disk_busy "struct disk *" .Ft void .Fn disk_unbusy "struct disk *" "long bcount" "int read" .Sh DESCRIPTION The .Ox generic disk framework is designed to provide flexible, scalable, and consistent handling of disk state and metrics information. The fundamental component of this framework is the .Nm structure, which is defined as follows: .Bd -literal struct disk { TAILQ_ENTRY(disk) dk_link; /* link in global disklist */ struct rwlock dk_lock; /* disk lock */ struct mutex dk_mtx; /* busy/unbusy mtx */ char *dk_name; /* disk name */ struct device *dk_device; /* disk device structure. */ dev_t dk_devno; /* disk device number. */ int dk_flags; /* disk flags */ #define DKF_CONSTRUCTED 0x0001 #define DKF_OPENED 0x0002 #define DKF_NOLABELREAD 0x0004 /* * Metrics data; note that some metrics may have no meaning * on certain types of disks. */ int dk_busy; /* busy counter */ u_int64_t dk_rxfer; /* total number of read transfers */ u_int64_t dk_wxfer; /* total number of write transfers */ u_int64_t dk_seek; /* total independent seek operations */ u_int64_t dk_rbytes; /* total bytes read */ u_int64_t dk_wbytes; /* total bytes written */ struct timeval dk_attachtime; /* time disk was attached */ struct timeval dk_timestamp; /*time of first busy or any unbusy*/ struct timeval dk_time; /* total time spent busy */ int dk_bopenmask; /* block devices open */ int dk_copenmask; /* character devices open */ int dk_openmask; /* composite (bopen|copen) */ int dk_state; /* label state ### */ int dk_blkshift; /*shift to convert DEV_BSIZE to blks*/ int dk_byteshift; /* shift to convert bytes to blks */ /* * Disk label information. Storage for the in-core disk label * must be dynamically allocated, otherwise the size of this * structure becomes machine-dependent. */ struct disklabel *dk_label; }; .Ed .Pp The system maintains a global linked-list of all disks attached to the system. This list, called .Nm disklist , may grow or shrink over time as disks are dynamically added and removed from the system. An example of a driver which currently makes use of the detachment capability of the framework is the .Xr vnd 4 pseudo-device driver. .Pp The following is a brief description of each function in the framework: .Bl -tag -width "disk_unbusy()" .It Fn disk_init Initialize the disklist and other data structures used by the framework. Called by .Fn main before autoconfiguration. .It Fn disk_attach Attach a disk; allocate storage for the disklabel, set the .Dq attached time timestamp, insert the disk into the disklist, and increment the system disk count. .It Fn disk_detach Detach a disk; free storage for the disklabel, remove the disk from the disklist, and decrement the system disk count. If the count drops below zero, panic. .It Fn disk_busy Increment the disk's .Dq busy counter . If this counter goes from 0 to 1, set the timestamp corresponding to this transfer. .It Fn disk_unbusy Decrement a disk's busy counter. If the count drops below zero, print a warning message. Get the current time, subtract it from the disk's timestamp, and add the difference to the disk's running total. Set the disk's timestamp to the current time. If the provided byte count is greater than 0, add it to the disk's running total and increment the number of transfers performed by the disk. The third argument .Ar read specifies the direction of I/O; if non-zero it means reading from the disk, otherwise it means writing to the disk. .El .Pp The functions typically called by device drivers are .Fn disk_attach , .Fn disk_detach , .Fn disk_busy and .Fn disk_unbusy . .Sh USING THE FRAMEWORK This section includes a description on basic use of the framework and example usage of its functions. Actual implementation of a device driver which utilizes the framework may vary. .Pp A special routine, .Fn disk_init , is provided to perform basic initialization of data structures used by the framework. It is called exactly once by the system, in .Fn main , before device autoconfiguration. .Pp Each device in the system uses a .Dq softc structure which contains autoconfiguration and state information for that device. In the case of disks, the softc should also contain one instance of the disk structure, e.g.: .Bd -literal struct foo_softc { struct device *sc_dev; /* generic device information */ struct disk *sc_dk; /* generic disk information */ [ . . . more . . . ] }; .Ed .Pp In order for the system to gather metrics data about a disk, the disk must be registered with the system. The .Fn disk_attach routine performs all of the functions currently required to register a disk with the system including allocation of disklabel storage space, recording of the time since boot that the disk was attached, and insertion into the disklist. Note that since this function allocates storage space for the disklabel, it must be called before the disklabel is read from the media or used in any other way. Before .Fn disk_attach is called, a portion of the disk structure must be initialized with data specific to that disk. For example, in the .Dq foo disk driver, the following would be performed in the autoconfiguration .Dq attach routine: .Bd -literal void fooattach(parent, self, aux) struct device *parent, *self; void *aux; { struct foo_softc *sc = (struct foo_softc *)self; [ . . . ] /* Initialize and attach the disk structure. */ sc->sc_dk.dk_driver = &foodkdriver; sc->sc_dk.dk_name = sc->sc_dev.dv_xname; disk_attach(&sc->sc_dk); /* Read geometry and fill in pertinent parts of disklabel. */ [ . . . ] } .Ed .Pp The .Nm foodkdriver above is the disk's .Dq driver switch. This switch currently includes a pointer to the disk's .Dq strategy routine. This switch needs to have global scope and should be initialized as follows: .Bd -literal void foostrategy(struct buf *); struct dkdriver foodkdriver = { foostrategy }; .Ed .Pp Once the disk is attached, metrics may be gathered on that disk. In order to gather metrics data, the driver must tell the framework when the disk starts and stops operations. This functionality is provided by the .Fn disk_busy and .Fn disk_unbusy routines. The .Fn disk_busy routine should be called immediately before a command to the disk is sent, e.g.: .Bd -literal void foostart(sc) struct foo_softc *sc; { [ . . . ] /* Get buffer from drive's transfer queue. */ [ . . . ] /* Build command to send to drive. */ [ . . . ] /* Tell the disk framework we're going busy. */ disk_busy(&sc->sc_dk); /* Send command to the drive. */ [ . . . ] } .Ed .Pp When .Fn disk_busy is called, a timestamp is taken if the disk's busy counter moves from 0 to 1, indicating the disk has gone from an idle to non-idle state. Note that .Fn disk_busy must be called at .Fn splbio . At the end of a transaction, the .Fn disk_unbusy routine should be called. This routine performs some consistency checks, such as ensuring that the calls to .Fn disk_busy and .Fn disk_unbusy are balanced. This routine also performs the actual metrics calculation. A timestamp is taken, and the difference from the timestamp taken in .Fn disk_busy is added to the disk's total running time. The disk's timestamp is then updated in case there is more than one pending transfer on the disk. A byte count is also added to the disk's running total, and if greater than zero, the number of transfers the disk has performed is incremented. .Bd -literal void foodone(xfer) struct foo_xfer *xfer; { struct foo_softc = (struct foo_softc *)xfer->xf_softc; struct buf *bp = xfer->xf_buf; long nbytes; [ . . . ] /* * Get number of bytes transferred. If there is no buf * associated with the xfer, we are being called at the * end of a non-I/O command. */ if (bp == NULL) nbytes = 0; else nbytes = bp->b_bcount - bp->b_resid; [ . . . ] /* Notify the disk framework that we've completed the transfer. */ disk_unbusy(&sc->sc_dk, nbytes); [ . . . ] } .Ed .Pp Like .Fn disk_busy , .Fn disk_unbusy must be called at .Fn splbio . .Sh CODE REFERENCES The disk framework itself is implemented within the file .Pa sys/kern/subr_disk.c . Data structures and function prototypes for the framework are located in .Pa sys/sys/disk.h . .Pp The .Ox machine-independent SCSI disk and CD-ROM drivers utilize the disk framework. They are located in .Pa sys/scsi/sd.c and .Pa sys/scsi/cd.c . .Pp The .Ox .Xr raid 4 and .Xr vnd 4 drivers utilize the detachment capability of the framework. They are located in .Pa sys/dev/raidframe/ and .Pa sys/dev/vnd.c . .Sh SEE ALSO .Xr raid 4 , .Xr vnd 4 , .Xr spl 9 .Sh HISTORY The .Ox generic disk framework first appeared in .Nx 1.2 . .Sh AUTHORS The .Ox generic disk framework was architected and implemented within .Nx by .An Jason R. Thorpe Aq thorpej@NetBSD.ORG .