mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 10:01:01 +03:00
6fe3498ca3
Many modern devices use physical allocation units that are much
larger than the minimum logical allocation size accessible by
external commands. Two prevalent examples of this are 512e disk
drives (512b logical sector, 4K physical sector) and flash devices
(512b logical sector, 4K or larger allocation block size, and 128k
or larger erase block size). Operations that modify less than the
physical sector size result in a costly read-modify-write or garbage
collection sequence on these devices.
Simply exporting the true physical sector of the device to ZFS would
yield optimal performance, but has two serious drawbacks:
1. Existing pools created with devices that have different logical
and physical block sizes, but were configured to use the logical
block size (e.g. because the OS version used for pool construction
reported the logical block size instead of the physical block
size) will suddenly find that the vdev allocation size has
increased. This can be easily tolerated for active members of
the array, but ZFS would prevent replacement of a vdev with
another identical device because it now appears that the smaller
allocation size required by the pool is not supported by the new
device.
2. The device's physical block size may be too large to be supported
by ZFS. The optimal allocation size for the vdev may be quite
large. For example, a RAID controller may export a vdev that
requires read-modify-write cycles unless accessed using 64k
aligned/sized requests. ZFS currently has an 8k minimum block
size limit.
Reporting both the logical and physical allocation sizes for vdevs
solves these problems. A device may be used so long as the logical
block size is compatible with the configuration. By comparing the
logical and physical block sizes, new configurations can be optimized
and administrators can be notified of any existing pools that are
sub-optimal.
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Matthew Macy <mmacy@freebsd.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10619
114 lines
3.2 KiB
C
114 lines
3.2 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright 2010 Sun Microsystems, Inc. All rights reserved.
|
|
* Use is subject to license terms.
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2012, 2016 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
/*
|
|
* The 'missing' vdev is a special vdev type used only during import. It
|
|
* signifies a placeholder in the root vdev for some vdev that we know is
|
|
* missing. We pass it down to the kernel to allow the rest of the
|
|
* configuration to parsed and an attempt made to open all available devices.
|
|
* Because its GUID is always 0, we know that the guid sum will mismatch and we
|
|
* won't be able to open the pool anyway.
|
|
*/
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/vdev_impl.h>
|
|
#include <sys/fs/zfs.h>
|
|
#include <sys/zio.h>
|
|
|
|
/* ARGSUSED */
|
|
static int
|
|
vdev_missing_open(vdev_t *vd, uint64_t *psize, uint64_t *max_psize,
|
|
uint64_t *ashift, uint64_t *pshift)
|
|
{
|
|
/*
|
|
* Really this should just fail. But then the root vdev will be in the
|
|
* faulted state with VDEV_AUX_NO_REPLICAS, when what we really want is
|
|
* VDEV_AUX_BAD_GUID_SUM. So we pretend to succeed, knowing that we
|
|
* will fail the GUID sum check before ever trying to open the pool.
|
|
*/
|
|
*psize = 0;
|
|
*max_psize = 0;
|
|
*ashift = 0;
|
|
*pshift = 0;
|
|
return (0);
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_close(vdev_t *vd)
|
|
{
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_io_start(zio_t *zio)
|
|
{
|
|
zio->io_error = SET_ERROR(ENOTSUP);
|
|
zio_execute(zio);
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_io_done(zio_t *zio)
|
|
{
|
|
}
|
|
|
|
vdev_ops_t vdev_missing_ops = {
|
|
.vdev_op_open = vdev_missing_open,
|
|
.vdev_op_close = vdev_missing_close,
|
|
.vdev_op_asize = vdev_default_asize,
|
|
.vdev_op_io_start = vdev_missing_io_start,
|
|
.vdev_op_io_done = vdev_missing_io_done,
|
|
.vdev_op_state_change = NULL,
|
|
.vdev_op_need_resilver = NULL,
|
|
.vdev_op_hold = NULL,
|
|
.vdev_op_rele = NULL,
|
|
.vdev_op_remap = NULL,
|
|
.vdev_op_xlate = NULL,
|
|
.vdev_op_type = VDEV_TYPE_MISSING, /* name of this vdev type */
|
|
.vdev_op_leaf = B_TRUE /* leaf vdev */
|
|
};
|
|
|
|
vdev_ops_t vdev_hole_ops = {
|
|
.vdev_op_open = vdev_missing_open,
|
|
.vdev_op_close = vdev_missing_close,
|
|
.vdev_op_asize = vdev_default_asize,
|
|
.vdev_op_io_start = vdev_missing_io_start,
|
|
.vdev_op_io_done = vdev_missing_io_done,
|
|
.vdev_op_state_change = NULL,
|
|
.vdev_op_need_resilver = NULL,
|
|
.vdev_op_hold = NULL,
|
|
.vdev_op_rele = NULL,
|
|
.vdev_op_remap = NULL,
|
|
.vdev_op_xlate = NULL,
|
|
.vdev_op_type = VDEV_TYPE_HOLE, /* name of this vdev type */
|
|
.vdev_op_leaf = B_TRUE /* leaf vdev */
|
|
};
|