mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2025-05-23 06:54:58 +03:00
246e5883bb
When forced to resort to ganging, ZFS currently allocates three child blocks, each one third of the size of the original. This is true regardless of whether larger allocations could be made, which would allow us to have fewer gang leaves. This improves performance when fragmentation is high enough to require ganging, but not so high that all the free ranges are only just big enough to hold a third of the recordsize. This is also useful for improving the behavior of a future change to allow larger gang headers. We add the ability for the allocation codepath to allocate a range of sizes instead of a single fixed size. We then use this to pre-allocate the DVAs for the gang children. If those allocations fail, we fall back to the normal write path, which will likely re-gang. Signed-off-by: Paul Dagnelie <paul.dagnelie@klarasystems.com> Co-authored-by: Paul Dagnelie <paul.dagnelie@klarasystems.com> Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Tony Hutter <hutter2@llnl.gov>
170 lines
4.4 KiB
C
170 lines
4.4 KiB
C
// SPDX-License-Identifier: CDDL-1.0
|
|
/*
|
|
* 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 https://opensource.org/licenses/CDDL-1.0.
|
|
* 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_init = NULL,
|
|
.vdev_op_fini = NULL,
|
|
.vdev_op_open = vdev_root_open,
|
|
.vdev_op_close = vdev_root_close,
|
|
.vdev_op_psize_to_asize = vdev_default_asize,
|
|
.vdev_op_asize_to_psize = vdev_default_psize,
|
|
.vdev_op_min_asize = vdev_default_min_asize,
|
|
.vdev_op_min_alloc = NULL,
|
|
.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_rebuild_asize = NULL,
|
|
.vdev_op_metaslab_init = NULL,
|
|
.vdev_op_config_generate = NULL,
|
|
.vdev_op_nparity = NULL,
|
|
.vdev_op_ndisks = NULL,
|
|
.vdev_op_type = VDEV_TYPE_ROOT, /* name of this vdev type */
|
|
.vdev_op_leaf = B_FALSE /* not a leaf vdev */
|
|
};
|