2003-04-01 13:19:14 +00:00
|
|
|
/*-
|
2017-11-27 15:17:37 +00:00
|
|
|
* SPDX-License-Identifier: BSD-3-Clause
|
|
|
|
*
|
2003-04-01 13:19:14 +00:00
|
|
|
* Copyright (c) 2003 Poul-Henning Kamp
|
|
|
|
* All rights reserved.
|
|
|
|
*
|
|
|
|
* This software was developed for the FreeBSD Project by Poul-Henning Kamp
|
|
|
|
* and NAI Labs, the Security Research Division of Network Associates, Inc.
|
|
|
|
* under DARPA/SPAWAR contract N66001-01-C-8035 ("CBOSS"), as part of the
|
|
|
|
* DARPA CHATS research program.
|
|
|
|
*
|
|
|
|
* 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. The names of the authors 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 AND CONTRIBUTORS ``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 OR CONTRIBUTORS 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.
|
|
|
|
*
|
|
|
|
* $FreeBSD$
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _GEOM_GEOM_DISK_H_
|
|
|
|
#define _GEOM_GEOM_DISK_H_
|
|
|
|
|
2017-10-04 15:09:49 +00:00
|
|
|
#define DISK_RR_UNKNOWN 0
|
|
|
|
#define DISK_RR_NON_ROTATING 1
|
|
|
|
#define DISK_RR_MIN 0x0401
|
|
|
|
#define DISK_RR_MAX 0xfffe
|
|
|
|
|
2003-04-01 13:19:14 +00:00
|
|
|
#ifdef _KERNEL
|
|
|
|
|
|
|
|
#include <sys/queue.h>
|
2003-04-02 20:41:18 +00:00
|
|
|
#include <sys/_lock.h>
|
|
|
|
#include <sys/_mutex.h>
|
2007-05-05 17:12:15 +00:00
|
|
|
#include <sys/disk.h>
|
2003-04-01 13:19:14 +00:00
|
|
|
|
2013-04-15 15:55:40 +00:00
|
|
|
#define G_DISK_CLASS_NAME "DISK"
|
|
|
|
|
2005-03-15 10:47:38 +00:00
|
|
|
struct disk;
|
|
|
|
|
2003-04-01 13:19:14 +00:00
|
|
|
typedef int disk_open_t(struct disk *);
|
|
|
|
typedef int disk_close_t(struct disk *);
|
|
|
|
typedef void disk_strategy_t(struct bio *bp);
|
Plumb device physical path reporting from CAM devices, through GEOM and
DEVFS, and make it accessible via the diskinfo utility.
Extend GEOM's generic attribute query mechanism into generic disk consumers.
sys/geom/geom_disk.c:
sys/geom/geom_disk.h:
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Allow disk providers to implement a new method which can override
the default BIO_GETATTR response, d_getattr(struct bio *). This
function returns -1 if not handled, otherwise it returns 0 or an
errno to be passed to g_io_deliver().
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Don't copy the serial number to dp->d_ident anymore, as the CAM XPT
is now responsible for returning this information via
d_getattr()->(a)dagetattr()->xpt_getatr().
sys/geom/geom_dev.c:
- Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM
attribute "GEOM::physpath", if possible. If the attribute request
returns a zero-length string, ENOENT is returned.
usr.sbin/diskinfo/diskinfo.c:
- If the DIOCGPHYSPATH ioctl is successful, report physical path
data when diskinfo is executed with the '-v' option.
Submitted by: will
Reviewed by: gibbs
Sponsored by: Spectra Logic Corporation
Add generic attribute change notification support to GEOM.
sys/sys/geom/geom.h:
Add a new attrchanged method field to both g_class
and g_geom.
sys/sys/geom/geom.h:
sys/geom/geom_event.c:
- Provide the g_attr_changed() function that providers
can use to advertise attribute changes.
- Perform delivery of attribute change notifications
from a thread context via the standard GEOM event
mechanism.
sys/geom/geom_subr.c:
Inherit the attrchanged method from class to geom (class instance).
sys/geom/geom_disk.c:
Provide disk_attr_changed() to provide g_attr_changed() access
to consumers of the disk API.
sys/cam/scsi/scsi_pass.c:
sys/cam/scsi/scsi_da.c:
sys/geom/geom_dev.c:
sys/geom/geom_disk.c:
Use attribute changed events to track updates to physical path
information.
sys/cam/scsi/scsi_da.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, and
the updated buffer type references our physical path
attribute, emit a GEOM attribute changed event via the
disk_attr_changed() API.
sys/cam/scsi/scsi_pass.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, update
the physical patch devfs alias for this pass instance.
Submitted by: gibbs
Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
|
|
|
typedef int disk_getattr_t(struct bio *bp);
|
Fix a bug which causes a panic in daopen(). The panic is caused by
a da(4) instance going away while GEOM is still probing it.
In this case, the GEOM disk class instance has been created by
disk_create(), and the taste of the disk is queued in the GEOM
event queue.
While that event is queued, the da(4) instance goes away. When the
open call comes into the da(4) driver, it dereferences the freed
(but non-NULL) peripheral pointer provided by GEOM, which results
in a panic.
The solution is to add a callback to the GEOM disk code that is
called when all of its resources are cleaned up. This is
implemented inside GEOM by adding an optional callback that is
called when all consumers have detached from a provider, and the
provider is about to be deleted.
scsi_cd.c,
scsi_da.c: In the register routine for the cd(4) and da(4)
routines, acquire a reference to the CAM peripheral
instance just before we call disk_create().
Use the new GEOM disk d_gone() callback to register
a callback (dadiskgonecb()/cddiskgonecb()) that
decrements the peripheral reference count once GEOM
has finished cleaning up its resources.
In the cd(4) driver, clean up open and close
behavior slightly. GEOM makes sure we only get one
open() and one close call, so there is no need to
set an open flag and decrement the reference count
if we are not the first open.
In the cd(4) driver, use cam_periph_release_locked()
in a couple of error scenarios to avoid extra mutex
calls.
geom.h: Add a new, optional, providergone callback that
is called when a provider is about to be deleted.
geom_disk.h: Add a new d_gone() callback to the GEOM disk
interface.
Bump the DISK_VERSION to version 2. This probably
should have been done after a couple of previous
changes, especially the addition of the d_getattr()
callback.
geom_disk.c: Add a providergone callback for the disk class,
g_disk_providergone(), that calls the user's
d_gone() callback if it exists.
Bump the DISK_VERSION to 2.
geom_subr.c: In g_destroy_provider(), call the providergone
callback if it has been provided.
In g_new_geomf(), propagate the class's
providergone callback to the new geom instance.
blkfront.c: Callers of disk_create() are supposed to pass in
DISK_VERSION, not an explicit disk API version
number. Update the blkfront driver to do that.
disk.9: Update the disk(9) man page to include information
on the new d_gone() callback, as well as the
previously added d_getattr() callback, d_descr
field, and HBA PCI ID fields.
MFC after: 5 days
2012-06-24 04:29:03 +00:00
|
|
|
typedef void disk_gone_t(struct disk *);
|
2003-04-01 13:19:14 +00:00
|
|
|
typedef int disk_ioctl_t(struct disk *, u_long cmd, void *data,
|
|
|
|
int fflag, struct thread *td);
|
|
|
|
/* NB: disk_ioctl_t SHALL be cast'able to d_ioctl_t */
|
|
|
|
|
|
|
|
struct g_geom;
|
|
|
|
struct devstat;
|
|
|
|
|
2016-06-21 20:18:19 +00:00
|
|
|
typedef enum {
|
|
|
|
DISK_INIT_NONE,
|
|
|
|
DISK_INIT_START,
|
|
|
|
DISK_INIT_DONE
|
|
|
|
} disk_init_level;
|
|
|
|
|
Expose API to allow disks to ask for alias names in devfs.
Implement disk_add_alias to allow aliases to be added to disks. All
disk have a primary name (say "foo") can also have secondary names
(say "bar") such that all instances of "foo" also have a "bar"
alias. So if you have foo0, foo0p1, foo1, foo1s1 and foo1s1a nodes
created by the foo driver and gpart, device nodes bar0, bar0p1, bar1,
bar1s1 and bar1s1a will appear as symlinks back to the original nodes.
This generalizes to multiple aliases. However, since the unit number
follows the primary name, multiple device drivers can't create the
same aliases unless those drives coorinate the unit number space (eg
you couldn't add an alias 'disk' to both 'da' and 'ada' because it's
possible to have da0 and ada0, because 'disk0' is ambiguous).
Differential Revision: https://reviews.freebsd.org/D11873
2017-08-07 21:12:38 +00:00
|
|
|
struct disk_alias {
|
|
|
|
LIST_ENTRY(disk_alias) da_next;
|
|
|
|
const char *da_alias;
|
|
|
|
};
|
|
|
|
|
2003-04-01 13:19:14 +00:00
|
|
|
struct disk {
|
|
|
|
/* Fields which are private to geom_disk */
|
|
|
|
struct g_geom *d_geom;
|
|
|
|
struct devstat *d_devstat;
|
2016-06-21 20:18:19 +00:00
|
|
|
int d_goneflag;
|
2004-02-18 21:36:53 +00:00
|
|
|
int d_destroyed;
|
2016-06-21 20:18:19 +00:00
|
|
|
disk_init_level d_init_level;
|
2003-04-01 13:19:14 +00:00
|
|
|
|
|
|
|
/* Shared fields */
|
|
|
|
u_int d_flags;
|
|
|
|
const char *d_name;
|
|
|
|
u_int d_unit;
|
2003-04-02 20:41:18 +00:00
|
|
|
struct bio_queue_head *d_queue;
|
|
|
|
struct mtx *d_lock;
|
2003-04-01 13:19:14 +00:00
|
|
|
|
|
|
|
/* Disk methods */
|
|
|
|
disk_open_t *d_open;
|
|
|
|
disk_close_t *d_close;
|
|
|
|
disk_strategy_t *d_strategy;
|
|
|
|
disk_ioctl_t *d_ioctl;
|
|
|
|
dumper_t *d_dump;
|
Plumb device physical path reporting from CAM devices, through GEOM and
DEVFS, and make it accessible via the diskinfo utility.
Extend GEOM's generic attribute query mechanism into generic disk consumers.
sys/geom/geom_disk.c:
sys/geom/geom_disk.h:
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Allow disk providers to implement a new method which can override
the default BIO_GETATTR response, d_getattr(struct bio *). This
function returns -1 if not handled, otherwise it returns 0 or an
errno to be passed to g_io_deliver().
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Don't copy the serial number to dp->d_ident anymore, as the CAM XPT
is now responsible for returning this information via
d_getattr()->(a)dagetattr()->xpt_getatr().
sys/geom/geom_dev.c:
- Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM
attribute "GEOM::physpath", if possible. If the attribute request
returns a zero-length string, ENOENT is returned.
usr.sbin/diskinfo/diskinfo.c:
- If the DIOCGPHYSPATH ioctl is successful, report physical path
data when diskinfo is executed with the '-v' option.
Submitted by: will
Reviewed by: gibbs
Sponsored by: Spectra Logic Corporation
Add generic attribute change notification support to GEOM.
sys/sys/geom/geom.h:
Add a new attrchanged method field to both g_class
and g_geom.
sys/sys/geom/geom.h:
sys/geom/geom_event.c:
- Provide the g_attr_changed() function that providers
can use to advertise attribute changes.
- Perform delivery of attribute change notifications
from a thread context via the standard GEOM event
mechanism.
sys/geom/geom_subr.c:
Inherit the attrchanged method from class to geom (class instance).
sys/geom/geom_disk.c:
Provide disk_attr_changed() to provide g_attr_changed() access
to consumers of the disk API.
sys/cam/scsi/scsi_pass.c:
sys/cam/scsi/scsi_da.c:
sys/geom/geom_dev.c:
sys/geom/geom_disk.c:
Use attribute changed events to track updates to physical path
information.
sys/cam/scsi/scsi_da.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, and
the updated buffer type references our physical path
attribute, emit a GEOM attribute changed event via the
disk_attr_changed() API.
sys/cam/scsi/scsi_pass.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, update
the physical patch devfs alias for this pass instance.
Submitted by: gibbs
Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
|
|
|
disk_getattr_t *d_getattr;
|
Fix a bug which causes a panic in daopen(). The panic is caused by
a da(4) instance going away while GEOM is still probing it.
In this case, the GEOM disk class instance has been created by
disk_create(), and the taste of the disk is queued in the GEOM
event queue.
While that event is queued, the da(4) instance goes away. When the
open call comes into the da(4) driver, it dereferences the freed
(but non-NULL) peripheral pointer provided by GEOM, which results
in a panic.
The solution is to add a callback to the GEOM disk code that is
called when all of its resources are cleaned up. This is
implemented inside GEOM by adding an optional callback that is
called when all consumers have detached from a provider, and the
provider is about to be deleted.
scsi_cd.c,
scsi_da.c: In the register routine for the cd(4) and da(4)
routines, acquire a reference to the CAM peripheral
instance just before we call disk_create().
Use the new GEOM disk d_gone() callback to register
a callback (dadiskgonecb()/cddiskgonecb()) that
decrements the peripheral reference count once GEOM
has finished cleaning up its resources.
In the cd(4) driver, clean up open and close
behavior slightly. GEOM makes sure we only get one
open() and one close call, so there is no need to
set an open flag and decrement the reference count
if we are not the first open.
In the cd(4) driver, use cam_periph_release_locked()
in a couple of error scenarios to avoid extra mutex
calls.
geom.h: Add a new, optional, providergone callback that
is called when a provider is about to be deleted.
geom_disk.h: Add a new d_gone() callback to the GEOM disk
interface.
Bump the DISK_VERSION to version 2. This probably
should have been done after a couple of previous
changes, especially the addition of the d_getattr()
callback.
geom_disk.c: Add a providergone callback for the disk class,
g_disk_providergone(), that calls the user's
d_gone() callback if it exists.
Bump the DISK_VERSION to 2.
geom_subr.c: In g_destroy_provider(), call the providergone
callback if it has been provided.
In g_new_geomf(), propagate the class's
providergone callback to the new geom instance.
blkfront.c: Callers of disk_create() are supposed to pass in
DISK_VERSION, not an explicit disk API version
number. Update the blkfront driver to do that.
disk.9: Update the disk(9) man page to include information
on the new d_gone() callback, as well as the
previously added d_getattr() callback, d_descr
field, and HBA PCI ID fields.
MFC after: 5 days
2012-06-24 04:29:03 +00:00
|
|
|
disk_gone_t *d_gone;
|
2003-04-01 13:19:14 +00:00
|
|
|
|
|
|
|
/* Info fields from driver to geom_disk.c. Valid when open */
|
|
|
|
u_int d_sectorsize;
|
|
|
|
off_t d_mediasize;
|
|
|
|
u_int d_fwsectors;
|
|
|
|
u_int d_fwheads;
|
|
|
|
u_int d_maxsize;
|
2013-04-26 16:22:54 +00:00
|
|
|
off_t d_delmaxsize;
|
2018-10-27 16:14:42 +00:00
|
|
|
off_t d_stripeoffset;
|
|
|
|
off_t d_stripesize;
|
2007-05-05 17:12:15 +00:00
|
|
|
char d_ident[DISK_IDENT_SIZE];
|
2011-02-26 14:58:54 +00:00
|
|
|
char d_descr[DISK_IDENT_SIZE];
|
2010-07-25 15:43:52 +00:00
|
|
|
uint16_t d_hba_vendor;
|
|
|
|
uint16_t d_hba_device;
|
|
|
|
uint16_t d_hba_subvendor;
|
|
|
|
uint16_t d_hba_subdevice;
|
Improve ZFS N-way mirror read performance by using load and locality
information.
The existing algorithm selects a preferred leaf vdev based on offset of the zio
request modulo the number of members in the mirror. It assumes the devices are
of equal performance and that spreading the requests randomly over both drives
will be sufficient to saturate them. In practice this results in the leaf vdevs
being under utilized.
The new algorithm takes into the following additional factors:
* Load of the vdevs (number outstanding I/O requests)
* The locality of last queued I/O vs the new I/O request.
Within the locality calculation additional knowledge about the underlying vdev
is considered such as; is the device backing the vdev a rotating media device.
This results in performance increases across the board as well as significant
increases for predominantly streaming loads and for configurations which don't
have evenly performing devices.
The following are results from a setup with 3 Way Mirror with 2 x HD's and
1 x SSD from a basic test running multiple parrallel dd's.
With pre-fetch disabled (vfs.zfs.prefetch_disable=1):
== Stripe Balanced (default) ==
Read 15360MB using bs: 1048576, readers: 3, took 161 seconds @ 95 MB/s
== Load Balanced (zfslinux) ==
Read 15360MB using bs: 1048576, readers: 3, took 297 seconds @ 51 MB/s
== Load Balanced (locality freebsd) ==
Read 15360MB using bs: 1048576, readers: 3, took 54 seconds @ 284 MB/s
With pre-fetch enabled (vfs.zfs.prefetch_disable=0):
== Stripe Balanced (default) ==
Read 15360MB using bs: 1048576, readers: 3, took 91 seconds @ 168 MB/s
== Load Balanced (zfslinux) ==
Read 15360MB using bs: 1048576, readers: 3, took 108 seconds @ 142 MB/s
== Load Balanced (locality freebsd) ==
Read 15360MB using bs: 1048576, readers: 3, took 48 seconds @ 320 MB/s
In addition to the performance changes the code was also restructured, with
the help of Justin Gibbs, to provide a more logical flow which also ensures
vdevs loads are only calculated from the set of valid candidates.
The following additional sysctls where added to allow the administrator
to tune the behaviour of the load algorithm:
* vfs.zfs.vdev.mirror.rotating_inc
* vfs.zfs.vdev.mirror.rotating_seek_inc
* vfs.zfs.vdev.mirror.rotating_seek_offset
* vfs.zfs.vdev.mirror.non_rotating_inc
* vfs.zfs.vdev.mirror.non_rotating_seek_inc
These changes where based on work started by the zfsonlinux developers:
https://github.com/zfsonlinux/zfs/pull/1487
Reviewed by: gibbs, mav, will
MFC after: 2 weeks
Sponsored by: Multiplay
2013-10-23 09:54:58 +00:00
|
|
|
uint16_t d_rotation_rate;
|
2003-04-01 13:19:14 +00:00
|
|
|
|
|
|
|
/* Fields private to the driver */
|
|
|
|
void *d_drv1;
|
Expose API to allow disks to ask for alias names in devfs.
Implement disk_add_alias to allow aliases to be added to disks. All
disk have a primary name (say "foo") can also have secondary names
(say "bar") such that all instances of "foo" also have a "bar"
alias. So if you have foo0, foo0p1, foo1, foo1s1 and foo1s1a nodes
created by the foo driver and gpart, device nodes bar0, bar0p1, bar1,
bar1s1 and bar1s1a will appear as symlinks back to the original nodes.
This generalizes to multiple aliases. However, since the unit number
follows the primary name, multiple device drivers can't create the
same aliases unless those drives coorinate the unit number space (eg
you couldn't add an alias 'disk' to both 'da' and 'ada' because it's
possible to have da0 and ada0, because 'disk0' is ambiguous).
Differential Revision: https://reviews.freebsd.org/D11873
2017-08-07 21:12:38 +00:00
|
|
|
|
|
|
|
/* Fields private to geom_disk, to be moved on next version bump */
|
|
|
|
LIST_HEAD(,disk_alias) d_aliases;
|
2003-04-01 13:19:14 +00:00
|
|
|
};
|
|
|
|
|
2018-01-15 11:20:00 +00:00
|
|
|
#define DISKFLAG_RESERVED 0x0001 /* Was NEEDSGIANT */
|
|
|
|
#define DISKFLAG_OPEN 0x0002
|
|
|
|
#define DISKFLAG_CANDELETE 0x0004
|
|
|
|
#define DISKFLAG_CANFLUSHCACHE 0x0008
|
|
|
|
#define DISKFLAG_UNMAPPED_BIO 0x0010
|
|
|
|
#define DISKFLAG_DIRECT_COMPLETION 0x0020
|
|
|
|
#define DISKFLAG_CANZONE 0x0080
|
|
|
|
#define DISKFLAG_WRITE_PROTECT 0x0100
|
2003-04-01 13:19:14 +00:00
|
|
|
|
2004-02-18 21:36:53 +00:00
|
|
|
struct disk *disk_alloc(void);
|
|
|
|
void disk_create(struct disk *disk, int version);
|
2003-04-01 13:19:14 +00:00
|
|
|
void disk_destroy(struct disk *disk);
|
Fix a bug that caused some /dev entries to continue to exist after
the underlying drive had been hot-unplugged from the system. Here
is a specific example. Filesystem code had opened /dev/da1s1e.
Subsequently, the drive was hot-unplugged. This (correctly) caused
all of the associated /dev/da1* entries to be deleted. When the
filesystem later realized that the drive was gone it closed the
device, reducing the write-access counts to 0 on the geom providers
for da1s1e, da1s1, and da1. This caused geom to re-taste the
providers, resulting in the devices being created again. When the
drive was hot-plugged back in, it resulted in duplicate /dev entries
for da1s1e, da1s1, and da1.
This fix adds a new disk_gone() function which is called by CAM when a
drive goes away. It orphans all of the providers associated with the
drive, setting an error condition of ENXIO in each one. In addition,
we prevent a re-taste on last close for writing if an error condition
has been set in the provider.
Sponsored by: Isilon Systems
Reviewed by: phk
MFC after: 1 week
2005-11-18 02:43:49 +00:00
|
|
|
void disk_gone(struct disk *disk);
|
Plumb device physical path reporting from CAM devices, through GEOM and
DEVFS, and make it accessible via the diskinfo utility.
Extend GEOM's generic attribute query mechanism into generic disk consumers.
sys/geom/geom_disk.c:
sys/geom/geom_disk.h:
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Allow disk providers to implement a new method which can override
the default BIO_GETATTR response, d_getattr(struct bio *). This
function returns -1 if not handled, otherwise it returns 0 or an
errno to be passed to g_io_deliver().
sys/cam/scsi/scsi_da.c:
sys/cam/ata/ata_da.c:
- Don't copy the serial number to dp->d_ident anymore, as the CAM XPT
is now responsible for returning this information via
d_getattr()->(a)dagetattr()->xpt_getatr().
sys/geom/geom_dev.c:
- Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM
attribute "GEOM::physpath", if possible. If the attribute request
returns a zero-length string, ENOENT is returned.
usr.sbin/diskinfo/diskinfo.c:
- If the DIOCGPHYSPATH ioctl is successful, report physical path
data when diskinfo is executed with the '-v' option.
Submitted by: will
Reviewed by: gibbs
Sponsored by: Spectra Logic Corporation
Add generic attribute change notification support to GEOM.
sys/sys/geom/geom.h:
Add a new attrchanged method field to both g_class
and g_geom.
sys/sys/geom/geom.h:
sys/geom/geom_event.c:
- Provide the g_attr_changed() function that providers
can use to advertise attribute changes.
- Perform delivery of attribute change notifications
from a thread context via the standard GEOM event
mechanism.
sys/geom/geom_subr.c:
Inherit the attrchanged method from class to geom (class instance).
sys/geom/geom_disk.c:
Provide disk_attr_changed() to provide g_attr_changed() access
to consumers of the disk API.
sys/cam/scsi/scsi_pass.c:
sys/cam/scsi/scsi_da.c:
sys/geom/geom_dev.c:
sys/geom/geom_disk.c:
Use attribute changed events to track updates to physical path
information.
sys/cam/scsi/scsi_da.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, and
the updated buffer type references our physical path
attribute, emit a GEOM attribute changed event via the
disk_attr_changed() API.
sys/cam/scsi/scsi_pass.c:
Add AC_ADVINFO_CHANGED to the registered asynchronous CAM
events for this driver. When this event occurs, update
the physical patch devfs alias for this pass instance.
Submitted by: gibbs
Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
|
|
|
void disk_attr_changed(struct disk *dp, const char *attr, int flag);
|
2012-07-29 11:51:48 +00:00
|
|
|
void disk_media_changed(struct disk *dp, int flag);
|
|
|
|
void disk_media_gone(struct disk *dp, int flag);
|
2012-10-29 17:52:43 +00:00
|
|
|
int disk_resize(struct disk *dp, int flag);
|
Expose API to allow disks to ask for alias names in devfs.
Implement disk_add_alias to allow aliases to be added to disks. All
disk have a primary name (say "foo") can also have secondary names
(say "bar") such that all instances of "foo" also have a "bar"
alias. So if you have foo0, foo0p1, foo1, foo1s1 and foo1s1a nodes
created by the foo driver and gpart, device nodes bar0, bar0p1, bar1,
bar1s1 and bar1s1a will appear as symlinks back to the original nodes.
This generalizes to multiple aliases. However, since the unit number
follows the primary name, multiple device drivers can't create the
same aliases unless those drives coorinate the unit number space (eg
you couldn't add an alias 'disk' to both 'da' and 'ada' because it's
possible to have da0 and ada0, because 'disk0' is ambiguous).
Differential Revision: https://reviews.freebsd.org/D11873
2017-08-07 21:12:38 +00:00
|
|
|
void disk_add_alias(struct disk *disk, const char *);
|
2003-04-01 13:19:14 +00:00
|
|
|
|
2004-02-18 21:36:53 +00:00
|
|
|
#define DISK_VERSION_00 0x58561059
|
2007-05-05 17:12:15 +00:00
|
|
|
#define DISK_VERSION_01 0x5856105a
|
Fix a bug which causes a panic in daopen(). The panic is caused by
a da(4) instance going away while GEOM is still probing it.
In this case, the GEOM disk class instance has been created by
disk_create(), and the taste of the disk is queued in the GEOM
event queue.
While that event is queued, the da(4) instance goes away. When the
open call comes into the da(4) driver, it dereferences the freed
(but non-NULL) peripheral pointer provided by GEOM, which results
in a panic.
The solution is to add a callback to the GEOM disk code that is
called when all of its resources are cleaned up. This is
implemented inside GEOM by adding an optional callback that is
called when all consumers have detached from a provider, and the
provider is about to be deleted.
scsi_cd.c,
scsi_da.c: In the register routine for the cd(4) and da(4)
routines, acquire a reference to the CAM peripheral
instance just before we call disk_create().
Use the new GEOM disk d_gone() callback to register
a callback (dadiskgonecb()/cddiskgonecb()) that
decrements the peripheral reference count once GEOM
has finished cleaning up its resources.
In the cd(4) driver, clean up open and close
behavior slightly. GEOM makes sure we only get one
open() and one close call, so there is no need to
set an open flag and decrement the reference count
if we are not the first open.
In the cd(4) driver, use cam_periph_release_locked()
in a couple of error scenarios to avoid extra mutex
calls.
geom.h: Add a new, optional, providergone callback that
is called when a provider is about to be deleted.
geom_disk.h: Add a new d_gone() callback to the GEOM disk
interface.
Bump the DISK_VERSION to version 2. This probably
should have been done after a couple of previous
changes, especially the addition of the d_getattr()
callback.
geom_disk.c: Add a providergone callback for the disk class,
g_disk_providergone(), that calls the user's
d_gone() callback if it exists.
Bump the DISK_VERSION to 2.
geom_subr.c: In g_destroy_provider(), call the providergone
callback if it has been provided.
In g_new_geomf(), propagate the class's
providergone callback to the new geom instance.
blkfront.c: Callers of disk_create() are supposed to pass in
DISK_VERSION, not an explicit disk API version
number. Update the blkfront driver to do that.
disk.9: Update the disk(9) man page to include information
on the new d_gone() callback, as well as the
previously added d_getattr() callback, d_descr
field, and HBA PCI ID fields.
MFC after: 5 days
2012-06-24 04:29:03 +00:00
|
|
|
#define DISK_VERSION_02 0x5856105b
|
2013-07-03 23:46:30 +00:00
|
|
|
#define DISK_VERSION_03 0x5856105c
|
Improve ZFS N-way mirror read performance by using load and locality
information.
The existing algorithm selects a preferred leaf vdev based on offset of the zio
request modulo the number of members in the mirror. It assumes the devices are
of equal performance and that spreading the requests randomly over both drives
will be sufficient to saturate them. In practice this results in the leaf vdevs
being under utilized.
The new algorithm takes into the following additional factors:
* Load of the vdevs (number outstanding I/O requests)
* The locality of last queued I/O vs the new I/O request.
Within the locality calculation additional knowledge about the underlying vdev
is considered such as; is the device backing the vdev a rotating media device.
This results in performance increases across the board as well as significant
increases for predominantly streaming loads and for configurations which don't
have evenly performing devices.
The following are results from a setup with 3 Way Mirror with 2 x HD's and
1 x SSD from a basic test running multiple parrallel dd's.
With pre-fetch disabled (vfs.zfs.prefetch_disable=1):
== Stripe Balanced (default) ==
Read 15360MB using bs: 1048576, readers: 3, took 161 seconds @ 95 MB/s
== Load Balanced (zfslinux) ==
Read 15360MB using bs: 1048576, readers: 3, took 297 seconds @ 51 MB/s
== Load Balanced (locality freebsd) ==
Read 15360MB using bs: 1048576, readers: 3, took 54 seconds @ 284 MB/s
With pre-fetch enabled (vfs.zfs.prefetch_disable=0):
== Stripe Balanced (default) ==
Read 15360MB using bs: 1048576, readers: 3, took 91 seconds @ 168 MB/s
== Load Balanced (zfslinux) ==
Read 15360MB using bs: 1048576, readers: 3, took 108 seconds @ 142 MB/s
== Load Balanced (locality freebsd) ==
Read 15360MB using bs: 1048576, readers: 3, took 48 seconds @ 320 MB/s
In addition to the performance changes the code was also restructured, with
the help of Justin Gibbs, to provide a more logical flow which also ensures
vdevs loads are only calculated from the set of valid candidates.
The following additional sysctls where added to allow the administrator
to tune the behaviour of the load algorithm:
* vfs.zfs.vdev.mirror.rotating_inc
* vfs.zfs.vdev.mirror.rotating_seek_inc
* vfs.zfs.vdev.mirror.rotating_seek_offset
* vfs.zfs.vdev.mirror.non_rotating_inc
* vfs.zfs.vdev.mirror.non_rotating_seek_inc
These changes where based on work started by the zfsonlinux developers:
https://github.com/zfsonlinux/zfs/pull/1487
Reviewed by: gibbs, mav, will
MFC after: 2 weeks
Sponsored by: Multiplay
2013-10-23 09:54:58 +00:00
|
|
|
#define DISK_VERSION_04 0x5856105d
|
2016-06-21 20:18:19 +00:00
|
|
|
#define DISK_VERSION_05 0x5856105e
|
2018-10-27 16:14:42 +00:00
|
|
|
#define DISK_VERSION_06 0x5856105f
|
|
|
|
#define DISK_VERSION DISK_VERSION_06
|
2003-04-01 13:19:14 +00:00
|
|
|
|
|
|
|
#endif /* _KERNEL */
|
|
|
|
#endif /* _GEOM_GEOM_DISK_H_ */
|