mirror_zfs/module/zfs/vdev_root.c
Ryan Moeller 6fe3498ca3
Import vdev ashift optimization from FreeBSD
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
2020-08-21 12:53:17 -07:00

159 lines
4.0 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.
*/
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/vdev_impl.h>
#include <sys/zio.h>
#include <sys/fs/zfs.h>
/*
* Virtual device vector for the pool's root vdev.
*/
static uint64_t
vdev_root_core_tvds(vdev_t *vd)
{
uint64_t tvds = 0;
for (uint64_t c = 0; c < vd->vdev_children; c++) {
vdev_t *cvd = vd->vdev_child[c];
if (!cvd->vdev_ishole && !cvd->vdev_islog &&
cvd->vdev_ops != &vdev_indirect_ops) {
tvds++;
}
}
return (tvds);
}
/*
* We should be able to tolerate one failure with absolutely no damage
* to our metadata. Two failures will take out space maps, a bunch of
* indirect block trees, meta dnodes, dnodes, etc. Probably not a happy
* place to live. When we get smarter, we can liberalize this policy.
* e.g. If we haven't lost two consecutive top-level vdevs, then we are
* probably fine. Adding bean counters during alloc/free can make this
* future guesswork more accurate.
*/
static boolean_t
too_many_errors(vdev_t *vd, uint64_t numerrors)
{
uint64_t tvds;
if (numerrors == 0)
return (B_FALSE);
tvds = vdev_root_core_tvds(vd);
ASSERT3U(numerrors, <=, tvds);
if (numerrors == tvds)
return (B_TRUE);
return (numerrors > spa_missing_tvds_allowed(vd->vdev_spa));
}
static int
vdev_root_open(vdev_t *vd, uint64_t *asize, uint64_t *max_asize,
uint64_t *ashift, uint64_t *pshift)
{
spa_t *spa = vd->vdev_spa;
int lasterror = 0;
int numerrors = 0;
if (vd->vdev_children == 0) {
vd->vdev_stat.vs_aux = VDEV_AUX_BAD_LABEL;
return (SET_ERROR(EINVAL));
}
vdev_open_children(vd);
for (int c = 0; c < vd->vdev_children; c++) {
vdev_t *cvd = vd->vdev_child[c];
if (cvd->vdev_open_error && !cvd->vdev_islog &&
cvd->vdev_ops != &vdev_indirect_ops) {
lasterror = cvd->vdev_open_error;
numerrors++;
}
}
if (spa_load_state(spa) != SPA_LOAD_NONE)
spa_set_missing_tvds(spa, numerrors);
if (too_many_errors(vd, numerrors)) {
vd->vdev_stat.vs_aux = VDEV_AUX_NO_REPLICAS;
return (lasterror);
}
*asize = 0;
*max_asize = 0;
*ashift = 0;
*pshift = 0;
return (0);
}
static void
vdev_root_close(vdev_t *vd)
{
for (int c = 0; c < vd->vdev_children; c++)
vdev_close(vd->vdev_child[c]);
}
static void
vdev_root_state_change(vdev_t *vd, int faulted, int degraded)
{
if (too_many_errors(vd, faulted)) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
VDEV_AUX_NO_REPLICAS);
} else if (degraded || faulted) {
vdev_set_state(vd, B_FALSE, VDEV_STATE_DEGRADED, VDEV_AUX_NONE);
} else {
vdev_set_state(vd, B_FALSE, VDEV_STATE_HEALTHY, VDEV_AUX_NONE);
}
}
vdev_ops_t vdev_root_ops = {
.vdev_op_open = vdev_root_open,
.vdev_op_close = vdev_root_close,
.vdev_op_asize = vdev_default_asize,
.vdev_op_io_start = NULL, /* not applicable to the root */
.vdev_op_io_done = NULL, /* not applicable to the root */
.vdev_op_state_change = vdev_root_state_change,
.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_ROOT, /* name of this vdev type */
.vdev_op_leaf = B_FALSE /* not a leaf vdev */
};