mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-18 18:31:00 +03:00
619f097693
PROBLEM ======== The first access to a block incurs a performance penalty on some platforms (e.g. AWS's EBS, VMware VMDKs). Therefore we recommend that volumes are "thick provisioned", where supported by the platform (VMware). This can create a large delay in getting a new virtual machines up and running (or adding storage to an existing Engine). If the thick provision step is omitted, write performance will be suboptimal until all blocks on the LUN have been written. SOLUTION ========= This feature introduces a way to 'initialize' the disks at install or in the background to make sure we don't incur this first read penalty. When an entire LUN is added to ZFS, we make all space available immediately, and allow ZFS to find unallocated space and zero it out. This works with concurrent writes to arbitrary offsets, ensuring that we don't zero out something that has been (or is in the middle of being) written. This scheme can also be applied to existing pools (affecting only free regions on the vdev). Detailed design: - new subcommand:zpool initialize [-cs] <pool> [<vdev> ...] - start, suspend, or cancel initialization - Creates new open-context thread for each vdev - Thread iterates through all metaslabs in this vdev - Each metaslab: - select a metaslab - load the metaslab - mark the metaslab as being zeroed - walk all free ranges within that metaslab and translate them to ranges on the leaf vdev - issue a "zeroing" I/O on the leaf vdev that corresponds to a free range on the metaslab we're working on - continue until all free ranges for this metaslab have been "zeroed" - reset/unmark the metaslab being zeroed - if more metaslabs exist, then repeat above tasks. - if no more metaslabs, then we're done. - progress for the initialization is stored on-disk in the vdev’s leaf zap object. The following information is stored: - the last offset that has been initialized - the state of the initialization process (i.e. active, suspended, or canceled) - the start time for the initialization - progress is reported via the zpool status command and shows information for each of the vdevs that are initializing Porting notes: - Added zfs_initialize_value module parameter to set the pattern written by "zpool initialize". - Added zfs_vdev_{initializing,removal}_{min,max}_active module options. Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: John Wren Kennedy <john.kennedy@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: loli10K <ezomori.nozomu@gmail.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Richard Lowe <richlowe@richlowe.net> Signed-off-by: Tim Chase <tim@chase2k.com> Ported-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/9102 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/c3963210eb Closes #8230
157 lines
3.7 KiB
C
157 lines
3.7 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)
|
|
{
|
|
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) {
|
|
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;
|
|
|
|
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_root_open,
|
|
vdev_root_close,
|
|
vdev_default_asize,
|
|
NULL, /* io_start - not applicable to the root */
|
|
NULL, /* io_done - not applicable to the root */
|
|
vdev_root_state_change,
|
|
NULL,
|
|
NULL,
|
|
NULL,
|
|
NULL,
|
|
NULL,
|
|
VDEV_TYPE_ROOT, /* name of this vdev type */
|
|
B_FALSE /* not a leaf vdev */
|
|
};
|