mirror_zfs/module/zfs/zfeature_common.c
George Wilson 93cf20764a Illumos #4101, #4102, #4103, #4105, #4106
4101 metaslab_debug should allow for fine-grained control
4102 space_maps should store more information about themselves
4103 space map object blocksize should be increased
4105 removing a mirrored log device results in a leaked object
4106 asynchronously load metaslab
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Sebastien Roy <seb@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>

Prior to this patch, space_maps were preferred solely based on the
amount of free space left in each. Unfortunately, this heuristic didn't
contain any information about the make-up of that free space, which
meant we could keep preferring and loading a highly fragmented space map
that wouldn't actually have enough contiguous space to satisfy the
allocation; then unloading that space_map and repeating the process.

This change modifies the space_map's to store additional information
about the contiguous space in the space_map, so that we can use this
information to make a better decision about which space_map to load.
This requires reallocating all space_map objects to increase their
bonus buffer size sizes enough to fit the new metadata.

The above feature can be enabled via a new feature flag introduced by
this change: com.delphix:spacemap_histogram

In addition to the above, this patch allows the space_map block size to
be increase. Currently the block size is set to be 4K in size, which has
certain implications including the following:

    * 4K sector devices will not see any compression benefit
    * large space_maps require more metadata on-disk
    * large space_maps require more time to load (typically random reads)

Now the space_map block size can adjust as needed up to the maximum size
set via the space_map_max_blksz variable.

A bug was fixed which resulted in potentially leaking an object when
removing a mirrored log device. The previous logic for vdev_remove() did
not deal with removing top-level vdevs that are interior vdevs (i.e.
mirror) correctly. The problem would occur when removing a mirrored log
device, and result in the DTL space map object being leaked; because
top-level vdevs don't have DTL space map objects associated with them.

References:
  https://www.illumos.org/issues/4101
  https://www.illumos.org/issues/4102
  https://www.illumos.org/issues/4103
  https://www.illumos.org/issues/4105
  https://www.illumos.org/issues/4106
  https://github.com/illumos/illumos-gate/commit/0713e23

Porting notes:

A handful of kmem_alloc() calls were converted to kmem_zalloc(). Also,
the KM_PUSHPAGE and TQ_PUSHPAGE flags were used as necessary.

Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #2488
2014-07-22 09:39:16 -07:00

171 lines
4.3 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 (c) 2013 by Delphix. All rights reserved.
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
*/
#ifdef _KERNEL
#include <sys/systm.h>
#else
#include <errno.h>
#include <string.h>
#endif
#include <sys/debug.h>
#include <sys/fs/zfs.h>
#include <sys/inttypes.h>
#include <sys/types.h>
#include "zfeature_common.h"
/*
* Set to disable all feature checks while opening pools, allowing pools with
* unsupported features to be opened. Set for testing only.
*/
boolean_t zfeature_checks_disable = B_FALSE;
zfeature_info_t spa_feature_table[SPA_FEATURES];
/*
* Valid characters for feature guids. This list is mainly for aesthetic
* purposes and could be expanded in the future. There are different allowed
* characters in the guids reverse dns portion (before the colon) and its
* short name (after the colon).
*/
static int
valid_char(char c, boolean_t after_colon)
{
return ((c >= 'a' && c <= 'z') ||
(c >= '0' && c <= '9') ||
c == (after_colon ? '_' : '.'));
}
/*
* Every feature guid must contain exactly one colon which separates a reverse
* dns organization name from the feature's "short" name (e.g.
* "com.company:feature_name").
*/
boolean_t
zfeature_is_valid_guid(const char *name)
{
int i;
boolean_t has_colon = B_FALSE;
i = 0;
while (name[i] != '\0') {
char c = name[i++];
if (c == ':') {
if (has_colon)
return (B_FALSE);
has_colon = B_TRUE;
continue;
}
if (!valid_char(c, has_colon))
return (B_FALSE);
}
return (has_colon);
}
boolean_t
zfeature_is_supported(const char *guid)
{
if (zfeature_checks_disable)
return (B_TRUE);
return (0 == zfeature_lookup_guid(guid, NULL));
}
int
zfeature_lookup_guid(const char *guid, zfeature_info_t **res)
{
int i;
for (i = 0; i < SPA_FEATURES; i++) {
zfeature_info_t *feature = &spa_feature_table[i];
if (strcmp(guid, feature->fi_guid) == 0) {
if (res != NULL)
*res = feature;
return (0);
}
}
return (ENOENT);
}
int
zfeature_lookup_name(const char *name, zfeature_info_t **res)
{
int i;
for (i = 0; i < SPA_FEATURES; i++) {
zfeature_info_t *feature = &spa_feature_table[i];
if (strcmp(name, feature->fi_uname) == 0) {
if (res != NULL)
*res = feature;
return (0);
}
}
return (ENOENT);
}
static void
zfeature_register(int fid, const char *guid, const char *name, const char *desc,
boolean_t readonly, boolean_t mos, zfeature_info_t **deps)
{
zfeature_info_t *feature = &spa_feature_table[fid];
static zfeature_info_t *nodeps[] = { NULL };
ASSERT(name != NULL);
ASSERT(desc != NULL);
ASSERT(!readonly || !mos);
ASSERT3U(fid, <, SPA_FEATURES);
ASSERT(zfeature_is_valid_guid(guid));
if (deps == NULL)
deps = nodeps;
feature->fi_guid = guid;
feature->fi_uname = name;
feature->fi_desc = desc;
feature->fi_can_readonly = readonly;
feature->fi_mos = mos;
feature->fi_depends = deps;
}
void
zpool_feature_init(void)
{
zfeature_register(SPA_FEATURE_ASYNC_DESTROY,
"com.delphix:async_destroy", "async_destroy",
"Destroy filesystems asynchronously.", B_TRUE, B_FALSE, NULL);
zfeature_register(SPA_FEATURE_EMPTY_BPOBJ,
"com.delphix:empty_bpobj", "empty_bpobj",
"Snapshots use less space.", B_TRUE, B_FALSE, NULL);
zfeature_register(SPA_FEATURE_LZ4_COMPRESS,
"org.illumos:lz4_compress", "lz4_compress",
"LZ4 compression algorithm support.", B_FALSE, B_FALSE, NULL);
zfeature_register(SPA_FEATURE_SPACEMAP_HISTOGRAM,
"com.delphix:spacemap_histogram", "spacemap_histogram",
"Spacemaps maintain space histograms.", B_TRUE, B_FALSE, NULL);
}