c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 02:27:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

ddt: add FDT feature and support for legacy and new on-disk formats

Browse Source 
This is the supporting infrastructure for the upcoming dedup features.

Traditionally, dedup objects live directly in the MOS root. While their
details vary (checksum, type and class), they are all the same "kind" of
thing - a store of dedup entries.

The new features are more varied than that, and are better thought of as
a set of related stores for the overall state of a dedup table.

This adds a new feature flag, SPA_FEATURE_FAST_DEDUP. Enabling this will
cause new DDTs to be created as a ZAP in the MOS root, named
DDT-<checksum>. The is used as the root object for the normal type/class
store objects, but will also be a place for any storage required by new
features.

This commit adds two new fields to ddt_t, for version and flags. These
are intended to describe the structure and features of the overall dedup
table, and are stored as-is in the DDT root. In this commit, flags are
always zero, but the intent is that they can be used to hang optional
logic or state onto for new dedup features. Version is always 1.

For a "legacy" dedup table, where no DDT root directory exists, the
version will be 0.

ddt_configure() is expected to determine the version and flags features
currently in operation based on whether or not the fast_dedup feature is
enabled, and from what's available on disk. In this way, its possible to
support both old and new tables.

This also provides a migration path. A legacy setup can be upgraded to
FDT by creating the DDT root ZAP, moving the existing objects into it,
and setting version and flags appropriately. There's no support for that
here, but it would be straightforward to add later and allows the
possibility that newer features could be applied to existing dedup
tables.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Rob Norris <rob.norris@klarasystems.com>
Sponsored-by: Klara, Inc.
Sponsored-by: iXsystems, Inc.
Closes #15892
This commit is contained in:
Rob Norris
2023-06-20 12:06:13 +10:00
committed by Brian Behlendorf
parent bdf4d6be1d
commit db2b1fdb79
10 changed files with 307 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/ddt.c
+250 -10
View File
@@ -39,6 +39,7 @@
#include <sys/zio_checksum.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
#include <sys/zfeature.h>
/*
* # DDT: Deduplication tables
@@ -185,6 +186,18 @@ static const char *const ddt_class_name[DDT_CLASSES] = {
"unique",
};
/*
* DDT feature flags automatically enabled for each on-disk version. Note that
* versions >0 cannot exist on disk without SPA_FEATURE_FAST_DEDUP enabled.
*/
static const uint64_t ddt_version_flags[] = {
[DDT_VERSION_LEGACY] = 0,
[DDT_VERSION_FDT] = 0,
};
/* Dummy version to signal that configure is still necessary */
#define DDT_VERSION_UNCONFIGURED (UINT64_MAX)
static void
ddt_object_create(ddt_t *ddt, ddt_type_t type, ddt_class_t class,
dmu_tx_t *tx)
@@ -196,14 +209,18 @@ ddt_object_create(ddt_t *ddt, ddt_type_t type, ddt_class_t class,
ZCHECKSUM_FLAG_DEDUP;
char name[DDT_NAMELEN];
ASSERT3U(ddt->ddt_dir_object, >, 0);
ddt_object_name(ddt, type, class, name);
ASSERT3U(*objectp, ==, 0);
VERIFY0(ddt_ops[type]->ddt_op_create(os, objectp, tx, prehash));
ASSERT3U(*objectp, !=, 0);
VERIFY0(zap_add(os, DMU_POOL_DIRECTORY_OBJECT, name,
sizeof (uint64_t), 1, objectp, tx));
ASSERT3U(ddt->ddt_version, !=, DDT_VERSION_UNCONFIGURED);
VERIFY0(zap_add(os, ddt->ddt_dir_object, name, sizeof (uint64_t), 1,
objectp, tx));
VERIFY0(zap_add(os, spa->spa_ddt_stat_object, name,
sizeof (uint64_t), sizeof (ddt_histogram_t) / sizeof (uint64_t),
@@ -220,13 +237,15 @@ ddt_object_destroy(ddt_t *ddt, ddt_type_t type, ddt_class_t class,
uint64_t count;
char name[DDT_NAMELEN];
ASSERT3U(ddt->ddt_dir_object, >, 0);
ddt_object_name(ddt, type, class, name);
ASSERT3U(*objectp, !=, 0);
ASSERT(ddt_histogram_empty(&ddt->ddt_histogram[type][class]));
VERIFY0(ddt_object_count(ddt, type, class, &count));
VERIFY0(count);
VERIFY0(zap_remove(os, DMU_POOL_DIRECTORY_OBJECT, name, tx));
VERIFY0(zap_remove(os, ddt->ddt_dir_object, name, tx));
VERIFY0(zap_remove(os, spa->spa_ddt_stat_object, name, tx));
VERIFY0(ddt_ops[type]->ddt_op_destroy(os, *objectp, tx));
memset(&ddt->ddt_object_stats[type][class], 0, sizeof (ddt_object_t));
@@ -243,9 +262,18 @@ ddt_object_load(ddt_t *ddt, ddt_type_t type, ddt_class_t class)
char name[DDT_NAMELEN];
int error;
if (ddt->ddt_dir_object == 0) {
/*
* If we're configured but the containing dir doesn't exist
* yet, then this object can't possibly exist either.
*/
ASSERT3U(ddt->ddt_version, !=, DDT_VERSION_UNCONFIGURED);
return (SET_ERROR(ENOENT));
}
ddt_object_name(ddt, type, class, name);
error = zap_lookup(ddt->ddt_os, DMU_POOL_DIRECTORY_OBJECT, name,
error = zap_lookup(ddt->ddt_os, ddt->ddt_dir_object, name,
sizeof (uint64_t), 1, &ddt->ddt_object[type][class]);
if (error != 0)
return (error);
@@ -684,6 +712,8 @@ ddt_prefetch_all(spa_t *spa)
}
}
static int ddt_configure(ddt_t *ddt, boolean_t new);
ddt_entry_t *
ddt_lookup(ddt_t *ddt, const blkptr_t *bp, boolean_t add)
{
@@ -697,6 +727,15 @@ ddt_lookup(ddt_t *ddt, const blkptr_t *bp, boolean_t add)
ASSERT(MUTEX_HELD(&ddt->ddt_lock));
if (ddt->ddt_version == DDT_VERSION_UNCONFIGURED) {
/*
* This is the first use of this DDT since the pool was
* created; finish getting it ready for use.
*/
VERIFY0(ddt_configure(ddt, B_TRUE));
ASSERT3U(ddt->ddt_version, !=, DDT_VERSION_UNCONFIGURED);
}
ddt_key_fill(&search, bp);
/* Find an existing live entry */
@@ -837,6 +876,181 @@ ddt_key_compare(const void *x1, const void *x2)
return (TREE_ISIGN(cmp));
}
/* Create the containing dir for this DDT and bump the feature count */
static void
ddt_create_dir(ddt_t *ddt, dmu_tx_t *tx)
{
ASSERT3U(ddt->ddt_dir_object, ==, 0);
ASSERT3U(ddt->ddt_version, ==, DDT_VERSION_FDT);
char name[DDT_NAMELEN];
snprintf(name, DDT_NAMELEN, DMU_POOL_DDT_DIR,
zio_checksum_table[ddt->ddt_checksum].ci_name);
ddt->ddt_dir_object = zap_create_link(ddt->ddt_os,
DMU_OTN_ZAP_METADATA, DMU_POOL_DIRECTORY_OBJECT, name, tx);
VERIFY0(zap_add(ddt->ddt_os, ddt->ddt_dir_object, DDT_DIR_VERSION,
sizeof (uint64_t), 1, &ddt->ddt_version, tx));
VERIFY0(zap_add(ddt->ddt_os, ddt->ddt_dir_object, DDT_DIR_FLAGS,
sizeof (uint64_t), 1, &ddt->ddt_flags, tx));
spa_feature_incr(ddt->ddt_spa, SPA_FEATURE_FAST_DEDUP, tx);
}
/* Destroy the containing dir and deactivate the feature */
static void
ddt_destroy_dir(ddt_t *ddt, dmu_tx_t *tx)
{
ASSERT3U(ddt->ddt_dir_object, !=, 0);
ASSERT3U(ddt->ddt_dir_object, !=, DMU_POOL_DIRECTORY_OBJECT);
ASSERT3U(ddt->ddt_version, ==, DDT_VERSION_FDT);
char name[DDT_NAMELEN];
snprintf(name, DDT_NAMELEN, DMU_POOL_DDT_DIR,
zio_checksum_table[ddt->ddt_checksum].ci_name);
for (ddt_type_t type = 0; type < DDT_TYPES; type++) {
for (ddt_class_t class = 0; class < DDT_CLASSES; class++) {
ASSERT(!ddt_object_exists(ddt, type, class));
}
}
uint64_t count;
ASSERT0(zap_count(ddt->ddt_os, ddt->ddt_dir_object, &count));
ASSERT0(zap_contains(ddt->ddt_os, ddt->ddt_dir_object,
DDT_DIR_VERSION));
ASSERT0(zap_contains(ddt->ddt_os, ddt->ddt_dir_object, DDT_DIR_FLAGS));
ASSERT3U(count, ==, 2);
VERIFY0(zap_remove(ddt->ddt_os, DMU_POOL_DIRECTORY_OBJECT, name, tx));
VERIFY0(zap_destroy(ddt->ddt_os, ddt->ddt_dir_object, tx));
ddt->ddt_dir_object = 0;
spa_feature_decr(ddt->ddt_spa, SPA_FEATURE_FAST_DEDUP, tx);
}
/*
* Determine, flags and on-disk layout from what's already stored. If there's
* nothing stored, then if new is false, returns ENOENT, and if true, selects
* based on pool config.
*/
static int
ddt_configure(ddt_t *ddt, boolean_t new)
{
spa_t *spa = ddt->ddt_spa;
char name[DDT_NAMELEN];
int error;
ASSERT3U(spa_load_state(spa), !=, SPA_LOAD_CREATE);
boolean_t fdt_enabled =
spa_feature_is_enabled(spa, SPA_FEATURE_FAST_DEDUP);
boolean_t fdt_active =
spa_feature_is_active(spa, SPA_FEATURE_FAST_DEDUP);
/*
* First, look for the global DDT stats object. If its not there, then
* there's never been a DDT written before ever, and we know we're
* starting from scratch.
*/
error = zap_lookup(spa->spa_meta_objset, DMU_POOL_DIRECTORY_OBJECT,
DMU_POOL_DDT_STATS, sizeof (uint64_t), 1,
&spa->spa_ddt_stat_object);
if (error != 0) {
if (error != ENOENT)
return (error);
goto not_found;
}
if (fdt_active) {
/*
* Now look for a DDT directory. If it exists, then it has
* everything we need.
*/
snprintf(name, DDT_NAMELEN, DMU_POOL_DDT_DIR,
zio_checksum_table[ddt->ddt_checksum].ci_name);
error = zap_lookup(spa->spa_meta_objset,
DMU_POOL_DIRECTORY_OBJECT, name, sizeof (uint64_t), 1,
&ddt->ddt_dir_object);
if (error == 0) {
ASSERT3U(spa->spa_meta_objset, ==, ddt->ddt_os);
error = zap_lookup(ddt->ddt_os, ddt->ddt_dir_object,
DDT_DIR_VERSION, sizeof (uint64_t), 1,
&ddt->ddt_version);
if (error != 0)
return (error);
error = zap_lookup(ddt->ddt_os, ddt->ddt_dir_object,
DDT_DIR_FLAGS, sizeof (uint64_t), 1,
&ddt->ddt_flags);
if (error != 0)
return (error);
if (ddt->ddt_version != DDT_VERSION_FDT) {
zfs_dbgmsg("ddt_configure: spa=%s ddt_dir=%s "
"unknown version %llu", spa_name(spa),
name, (u_longlong_t)ddt->ddt_version);
return (SET_ERROR(EINVAL));
}
if ((ddt->ddt_flags & ~DDT_FLAG_MASK) != 0) {
zfs_dbgmsg("ddt_configure: spa=%s ddt_dir=%s "
"version=%llu unknown flags %llx",
spa_name(spa), name,
(u_longlong_t)ddt->ddt_flags,
(u_longlong_t)ddt->ddt_version);
return (SET_ERROR(EINVAL));
}
return (0);
}
if (error != ENOENT)
return (error);
}
/* Any object in the root indicates a traditional setup. */
for (ddt_type_t type = 0; type < DDT_TYPES; type++) {
for (ddt_class_t class = 0; class < DDT_CLASSES; class++) {
ddt_object_name(ddt, type, class, name);
uint64_t obj;
error = zap_lookup(spa->spa_meta_objset,
DMU_POOL_DIRECTORY_OBJECT, name, sizeof (uint64_t),
1, &obj);
if (error == ENOENT)
continue;
if (error != 0)
return (error);
ddt->ddt_version = DDT_VERSION_LEGACY;
ddt->ddt_flags = ddt_version_flags[ddt->ddt_version];
ddt->ddt_dir_object = DMU_POOL_DIRECTORY_OBJECT;
return (0);
}
}
not_found:
if (!new)
return (SET_ERROR(ENOENT));
/* Nothing on disk, so set up for the best version we can */
if (fdt_enabled) {
ddt->ddt_version = DDT_VERSION_FDT;
ddt->ddt_flags = ddt_version_flags[ddt->ddt_version];
ddt->ddt_dir_object = 0; /* create on first use */
} else {
ddt->ddt_version = DDT_VERSION_LEGACY;
ddt->ddt_flags = ddt_version_flags[ddt->ddt_version];
ddt->ddt_dir_object = DMU_POOL_DIRECTORY_OBJECT;
}
return (0);
}
static ddt_t *
ddt_table_alloc(spa_t *spa, enum zio_checksum c)
{
@@ -853,6 +1067,7 @@ ddt_table_alloc(spa_t *spa, enum zio_checksum c)
ddt->ddt_checksum = c;
ddt->ddt_spa = spa;
ddt->ddt_os = spa->spa_meta_objset;
ddt->ddt_version = DDT_VERSION_UNCONFIGURED;
return (ddt);
}
@@ -889,7 +1104,6 @@ ddt_load(spa_t *spa)
error = zap_lookup(spa->spa_meta_objset, DMU_POOL_DIRECTORY_OBJECT,
DMU_POOL_DDT_STATS, sizeof (uint64_t), 1,
&spa->spa_ddt_stat_object);
if (error)
return (error == ENOENT ? 0 : error);
@@ -898,6 +1112,12 @@ ddt_load(spa_t *spa)
continue;
ddt_t *ddt = spa->spa_ddt[c];
error = ddt_configure(ddt, B_FALSE);
if (error == ENOENT)
continue;
if (error != 0)
return (error);
for (ddt_type_t type = 0; type < DDT_TYPES; type++) {
for (ddt_class_t class = 0; class < DDT_CLASSES;
class++) {
@@ -912,10 +1132,11 @@ ddt_load(spa_t *spa)
*/
memcpy(&ddt->ddt_histogram_cache, ddt->ddt_histogram,
sizeof (ddt->ddt_histogram));
spa->spa_dedup_dspace = ~0ULL;
spa->spa_dedup_dsize = ~0ULL;
}
spa->spa_dedup_dspace = ~0ULL;
spa->spa_dedup_dsize = ~0ULL;
return (0);
}
@@ -1147,25 +1368,44 @@ ddt_sync_table(ddt_t *ddt, dmu_tx_t *tx, uint64_t txg)
DMU_POOL_DDT_STATS, tx);
}
if (ddt->ddt_version == DDT_VERSION_FDT && ddt->ddt_dir_object == 0)
ddt_create_dir(ddt, tx);
while ((dde = avl_destroy_nodes(&ddt->ddt_tree, &cookie)) != NULL) {
ddt_sync_entry(ddt, dde, tx, txg);
ddt_free(dde);
}
uint64_t count = 0;
for (ddt_type_t type = 0; type < DDT_TYPES; type++) {
uint64_t add, count = 0;
uint64_t add, tcount = 0;
for (ddt_class_t class = 0; class < DDT_CLASSES; class++) {
if (ddt_object_exists(ddt, type, class)) {
ddt_object_sync(ddt, type, class, tx);
VERIFY0(ddt_object_count(ddt, type, class,
&add));
count += add;
tcount += add;
}
}
for (ddt_class_t class = 0; class < DDT_CLASSES; class++) {
if (count == 0 && ddt_object_exists(ddt, type, class))
if (tcount == 0 && ddt_object_exists(ddt, type, class))
ddt_object_destroy(ddt, type, class, tx);
}
count += tcount;
}
if (count == 0) {
/*
* No entries left on the DDT, so reset the version for next
* time. This allows us to handle the feature being changed
* since the DDT was originally created. New entries should get
* whatever the feature currently demands.
*/
if (ddt->ddt_version == DDT_VERSION_FDT)
ddt_destroy_dir(ddt, tx);
ddt->ddt_version = DDT_VERSION_UNCONFIGURED;
ddt->ddt_flags = 0;
}
memcpy(&ddt->ddt_histogram_cache, ddt->ddt_histogram,
module/zfs/zio_compress.c
+4
View File
@@ -48,6 +48,10 @@ static unsigned long zio_decompress_fail_fraction = 0;
/*
* Compression vectors.
*
* NOTE: DO NOT CHANGE THE NAMES OF THESE COMPRESSION FUNCTIONS.
* THEY ARE USED AS ZAP KEY NAMES BY FAST DEDUP AND THEREFORE
* PART OF THE ON-DISK FORMAT.
*/
zio_compress_info_t zio_compress_table[ZIO_COMPRESS_FUNCTIONS] = {
{"inherit", 0, NULL, NULL, NULL},