c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2024-12-25 02:49:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

OpenZFS 7613 - ms_freetree[4] is only used in syncing context

Browse Source 
metaslab_t:ms_freetree[TXG_SIZE] is only used in syncing context. We
should replace it with two trees: the freeing tree (ranges that we are
freeing this syncing txg) and the freed tree (ranges which have been
freed this txg).

Authored by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Ported-by: Tim Chase <tim@chase2k.com>

OpenZFS-issue: https://www.illumos.org/issues/7613
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/a8698da2
Closes #5598
This commit is contained in:
Tim Chase 2017-01-26 17:27:19 -06:00 committed by Brian Behlendorf
parent 9c9531cb6f
commit 258553d3d7
2 changed files with 82 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
include/sys/metaslab_impl.h
View File

@ -254,21 +254,24 @@ struct metaslab_group {
#define MAX_LBAS 64 #define MAX_LBAS 64
/* /*
* Each metaslab maintains a set of in-core trees to track metaslab operations. * Each metaslab maintains a set of in-core trees to track metaslab
* The in-core free tree (ms_tree) contains the current list of free segments. * operations. The in-core free tree (ms_tree) contains the list of
* As blocks are allocated, the allocated segment are removed from the ms_tree * free segments which are eligible for allocation. As blocks are
* and added to a per txg allocation tree (ms_alloctree). As blocks are freed, * allocated, the allocated segments are removed from the ms_tree and
* they are added to the per txg free tree (ms_freetree). These per txg * added to a per txg allocation tree (ms_alloctree). This allows us to
* trees allow us to process all allocations and frees in syncing context * process all allocations in syncing context where it is safe to update
* where it is safe to update the on-disk space maps. One additional in-core * the on-disk space maps. Frees are also processed in syncing context.
* tree is maintained to track deferred frees (ms_defertree). Once a block * Most frees are generated from syncing context, and those that are not
* is freed it will move from the ms_freetree to the ms_defertree. A deferred * are held in the spa_free_bplist for processing in syncing context.
* free means that a block has been freed but cannot be used by the pool * An additional set of in-core trees is maintained to track deferred
* until TXG_DEFER_SIZE transactions groups later. For example, a block * frees (ms_defertree). Once a block is freed it will move from the
* that is freed in txg 50 will not be available for reallocation until * ms_freedtree to the ms_defertree. A deferred free means that a block
* txg 52 (50 + TXG_DEFER_SIZE). This provides a safety net for uberblock * has been freed but cannot be used by the pool until TXG_DEFER_SIZE
* rollback. A pool could be safely rolled back TXG_DEFERS_SIZE * transactions groups later. For example, a block that is freed in txg
* transactions groups and ensure that no block has been reallocated. * 50 will not be available for reallocation until txg 52 (50 +
* TXG_DEFER_SIZE). This provides a safety net for uberblock rollback.
* A pool could be safely rolled back TXG_DEFERS_SIZE transactions
* groups and ensure that no block has been reallocated.
* *
* The simplified transition diagram looks like this: * The simplified transition diagram looks like this:
* *
@ -276,33 +279,34 @@ struct metaslab_group {
* ALLOCATE * ALLOCATE
* | * |
* V * V
* free segment (ms_tree) --------> ms_alloctree ----> (write to space map) * free segment (ms_tree) -----> ms_alloctree[4] ----> (write to space map)
* ^ * ^
* | * | ms_freeingtree <--- FREE
* | ms_freetree <--- FREE
* | | * | |
* | v
* | ms_freedtree
* | | * | |
* | | * +-------- ms_defertree[2] <-------+---------> (write to space map)
* +----------- ms_defertree <-------+---------> (write to space map)
* *
* *
* Each metaslab's space is tracked in a single space map in the MOS, * Each metaslab's space is tracked in a single space map in the MOS,
* which is only updated in syncing context. Each time we sync a txg, * which is only updated in syncing context. Each time we sync a txg,
* we append the allocs and frees from that txg to the space map. * we append the allocs and frees from that txg to the space map. The
* The pool space is only updated once all metaslabs have finished syncing. * pool space is only updated once all metaslabs have finished syncing.
* *
* To load the in-core free tree we read the space map from disk. * To load the in-core free tree we read the space map from disk. This
* This object contains a series of alloc and free records that are * object contains a series of alloc and free records that are combined
* combined to make up the list of all free segments in this metaslab. These * to make up the list of all free segments in this metaslab. These
* segments are represented in-core by the ms_tree and are stored in an * segments are represented in-core by the ms_tree and are stored in an
* AVL tree. * AVL tree.
* *
* As the space map grows (as a result of the appends) it will * As the space map grows (as a result of the appends) it will
* eventually become space-inefficient. When the metaslab's in-core free tree * eventually become space-inefficient. When the metaslab's in-core
* is zfs_condense_pct/100 times the size of the minimal on-disk * free tree is zfs_condense_pct/100 times the size of the minimal
* representation, we rewrite it in its minimized form. If a metaslab * on-disk representation, we rewrite it in its minimized form. If a
* needs to condense then we must set the ms_condensing flag to ensure * metaslab needs to condense then we must set the ms_condensing flag to
* that allocations are not performed on the metaslab that is being written. * ensure that allocations are not performed on the metaslab that is
* being written.
*/ */
struct metaslab { struct metaslab {
kmutex_t ms_lock; kmutex_t ms_lock;
@ -314,10 +318,17 @@ struct metaslab {
uint64_t ms_fragmentation; uint64_t ms_fragmentation;
range_tree_t *ms_alloctree[TXG_SIZE]; range_tree_t *ms_alloctree[TXG_SIZE];
range_tree_t *ms_freetree[TXG_SIZE];
range_tree_t *ms_defertree[TXG_DEFER_SIZE];
range_tree_t *ms_tree; range_tree_t *ms_tree;
/*
* The following range trees are accessed only from syncing context.
* ms_free*tree only have entries while syncing, and are empty
* between syncs.
*/
range_tree_t *ms_freeingtree; /* to free this syncing txg */
range_tree_t *ms_freedtree; /* already freed this syncing txg */
range_tree_t *ms_defertree[TXG_DEFER_SIZE];
boolean_t ms_condensing; /* condensing? */ boolean_t ms_condensing; /* condensing? */
boolean_t ms_condense_wanted; boolean_t ms_condense_wanted;

81
module/zfs/metaslab.c
View File

@ -442,7 +442,6 @@ metaslab_verify_space(metaslab_t *msp, uint64_t txg)
{ {
spa_t *spa = msp->ms_group->mg_vd->vdev_spa; spa_t *spa = msp->ms_group->mg_vd->vdev_spa;
uint64_t allocated = 0; uint64_t allocated = 0;
uint64_t freed = 0;
uint64_t sm_free_space, msp_free_space; uint64_t sm_free_space, msp_free_space;
int t; int t;
@ -473,10 +472,9 @@ metaslab_verify_space(metaslab_t *msp, uint64_t txg)
allocated += allocated +=
range_tree_space(msp->ms_alloctree[(txg + t) & TXG_MASK]); range_tree_space(msp->ms_alloctree[(txg + t) & TXG_MASK]);
} }
freed = range_tree_space(msp->ms_freetree[TXG_CLEAN(txg) & TXG_MASK]);
msp_free_space = range_tree_space(msp->ms_tree) + allocated + msp_free_space = range_tree_space(msp->ms_tree) + allocated +
msp->ms_deferspace + freed; msp->ms_deferspace + range_tree_space(msp->ms_freedtree);
VERIFY3U(sm_free_space, ==, msp_free_space); VERIFY3U(sm_free_space, ==, msp_free_space);
} }
@ -1423,7 +1421,7 @@ metaslab_init(metaslab_group_t *mg, uint64_t id, uint64_t object, uint64_t txg,
/* /*
* We create the main range tree here, but we don't create the * We create the main range tree here, but we don't create the
* alloctree and freetree until metaslab_sync_done(). This serves * other range trees until metaslab_sync_done(). This serves
* two purposes: it allows metaslab_sync_done() to detect the * two purposes: it allows metaslab_sync_done() to detect the
* addition of new space; and for debugging, it ensures that we'd * addition of new space; and for debugging, it ensures that we'd
* data fault on any attempt to use this metaslab before it's ready. * data fault on any attempt to use this metaslab before it's ready.
@ -1483,10 +1481,11 @@ metaslab_fini(metaslab_t *msp)
metaslab_unload(msp); metaslab_unload(msp);
range_tree_destroy(msp->ms_tree); range_tree_destroy(msp->ms_tree);
range_tree_destroy(msp->ms_freeingtree);
range_tree_destroy(msp->ms_freedtree);
for (t = 0; t < TXG_SIZE; t++) { for (t = 0; t < TXG_SIZE; t++) {
range_tree_destroy(msp->ms_alloctree[t]); range_tree_destroy(msp->ms_alloctree[t]);
range_tree_destroy(msp->ms_freetree[t]);
} }
for (t = 0; t < TXG_DEFER_SIZE; t++) { for (t = 0; t < TXG_DEFER_SIZE; t++) {
@ -2103,7 +2102,6 @@ static void
metaslab_condense(metaslab_t *msp, uint64_t txg, dmu_tx_t *tx) metaslab_condense(metaslab_t *msp, uint64_t txg, dmu_tx_t *tx)
{ {
spa_t *spa = msp->ms_group->mg_vd->vdev_spa; spa_t *spa = msp->ms_group->mg_vd->vdev_spa;
range_tree_t *freetree = msp->ms_freetree[txg & TXG_MASK];
range_tree_t *condense_tree; range_tree_t *condense_tree;
space_map_t *sm = msp->ms_sm; space_map_t *sm = msp->ms_sm;
int t; int t;
@ -2135,9 +2133,9 @@ metaslab_condense(metaslab_t *msp, uint64_t txg, dmu_tx_t *tx)
/* /*
* Remove what's been freed in this txg from the condense_tree. * Remove what's been freed in this txg from the condense_tree.
* Since we're in sync_pass 1, we know that all the frees from * Since we're in sync_pass 1, we know that all the frees from
* this txg are in the freetree. * this txg are in the freeingtree.
*/ */
range_tree_walk(freetree, range_tree_remove, condense_tree); range_tree_walk(msp->ms_freeingtree, range_tree_remove, condense_tree);
for (t = 0; t < TXG_DEFER_SIZE; t++) { for (t = 0; t < TXG_DEFER_SIZE; t++) {
range_tree_walk(msp->ms_defertree[t], range_tree_walk(msp->ms_defertree[t],
@ -2193,9 +2191,6 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
spa_t *spa = vd->vdev_spa; spa_t *spa = vd->vdev_spa;
objset_t *mos = spa_meta_objset(spa); objset_t *mos = spa_meta_objset(spa);
range_tree_t *alloctree = msp->ms_alloctree[txg & TXG_MASK]; range_tree_t *alloctree = msp->ms_alloctree[txg & TXG_MASK];
range_tree_t **freetree = &msp->ms_freetree[txg & TXG_MASK];
range_tree_t **freed_tree =
&msp->ms_freetree[TXG_CLEAN(txg) & TXG_MASK];
dmu_tx_t *tx; dmu_tx_t *tx;
uint64_t object = space_map_object(msp->ms_sm); uint64_t object = space_map_object(msp->ms_sm);
@ -2204,14 +2199,14 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
/* /*
* This metaslab has just been added so there's no work to do now. * This metaslab has just been added so there's no work to do now.
*/ */
if (*freetree == NULL) { if (msp->ms_freeingtree == NULL) {
ASSERT3P(alloctree, ==, NULL); ASSERT3P(alloctree, ==, NULL);
return; return;
} }
ASSERT3P(alloctree, !=, NULL); ASSERT3P(alloctree, !=, NULL);
ASSERT3P(*freetree, !=, NULL); ASSERT3P(msp->ms_freeingtree, !=, NULL);
ASSERT3P(*freed_tree, !=, NULL); ASSERT3P(msp->ms_freedtree, !=, NULL);
/* /*
* Normally, we don't want to process a metaslab if there * Normally, we don't want to process a metaslab if there
@ -2219,14 +2214,14 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
* is being forced to condense we need to let it through. * is being forced to condense we need to let it through.
*/ */
if (range_tree_space(alloctree) == 0 && if (range_tree_space(alloctree) == 0 &&
range_tree_space(*freetree) == 0 && range_tree_space(msp->ms_freeingtree) == 0 &&
!msp->ms_condense_wanted) !msp->ms_condense_wanted)
return; return;
/* /*
* The only state that can actually be changing concurrently with * The only state that can actually be changing concurrently with
* metaslab_sync() is the metaslab's ms_tree. No other thread can * metaslab_sync() is the metaslab's ms_tree. No other thread can
* be modifying this txg's alloctree, freetree, freed_tree, or * be modifying this txg's alloctree, freeingtree, freedtree, or
* space_map_phys_t. Therefore, we only hold ms_lock to satify * space_map_phys_t. Therefore, we only hold ms_lock to satify
* space map ASSERTs. We drop it whenever we call into the DMU, * space map ASSERTs. We drop it whenever we call into the DMU,
* because the DMU can call down to us (e.g. via zio_free()) at * because the DMU can call down to us (e.g. via zio_free()) at
@ -2263,7 +2258,7 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
metaslab_condense(msp, txg, tx); metaslab_condense(msp, txg, tx);
} else { } else {
space_map_write(msp->ms_sm, alloctree, SM_ALLOC, tx); space_map_write(msp->ms_sm, alloctree, SM_ALLOC, tx);
space_map_write(msp->ms_sm, *freetree, SM_FREE, tx); space_map_write(msp->ms_sm, msp->ms_freeingtree, SM_FREE, tx);
} }
if (msp->ms_loaded) { if (msp->ms_loaded) {
@ -2285,7 +2280,7 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
* to accurately reflect all free space even if some space * to accurately reflect all free space even if some space
* is not yet available for allocation (i.e. deferred). * is not yet available for allocation (i.e. deferred).
*/ */
space_map_histogram_add(msp->ms_sm, *freed_tree, tx); space_map_histogram_add(msp->ms_sm, msp->ms_freedtree, tx);
/* /*
* Add back any deferred free space that has not been * Add back any deferred free space that has not been
@ -2307,7 +2302,7 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
* then we will lose some accuracy but will correct it the next * then we will lose some accuracy but will correct it the next
* time we load the space map. * time we load the space map.
*/ */
space_map_histogram_add(msp->ms_sm, *freetree, tx); space_map_histogram_add(msp->ms_sm, msp->ms_freeingtree, tx);
metaslab_group_histogram_add(mg, msp); metaslab_group_histogram_add(mg, msp);
metaslab_group_histogram_verify(mg); metaslab_group_histogram_verify(mg);
@ -2315,20 +2310,21 @@ metaslab_sync(metaslab_t *msp, uint64_t txg)
/* /*
* For sync pass 1, we avoid traversing this txg's free range tree * For sync pass 1, we avoid traversing this txg's free range tree
* and instead will just swap the pointers for freetree and * and instead will just swap the pointers for freeingtree and
* freed_tree. We can safely do this since the freed_tree is * freedtree. We can safely do this since the freed_tree is
* guaranteed to be empty on the initial pass. * guaranteed to be empty on the initial pass.
*/ */
if (spa_sync_pass(spa) == 1) { if (spa_sync_pass(spa) == 1) {
range_tree_swap(freetree, freed_tree); range_tree_swap(&msp->ms_freeingtree, &msp->ms_freedtree);
} else { } else {
range_tree_vacate(*freetree, range_tree_add, *freed_tree); range_tree_vacate(msp->ms_freeingtree,
range_tree_add, msp->ms_freedtree);
} }
range_tree_vacate(alloctree, NULL, NULL); range_tree_vacate(alloctree, NULL, NULL);
ASSERT0(range_tree_space(msp->ms_alloctree[txg & TXG_MASK])); ASSERT0(range_tree_space(msp->ms_alloctree[txg & TXG_MASK]));
ASSERT0(range_tree_space(msp->ms_alloctree[TXG_CLEAN(txg) & TXG_MASK])); ASSERT0(range_tree_space(msp->ms_alloctree[TXG_CLEAN(txg) & TXG_MASK]));
ASSERT0(range_tree_space(msp->ms_freetree[txg & TXG_MASK])); ASSERT0(range_tree_space(msp->ms_freeingtree));
mutex_exit(&msp->ms_lock); mutex_exit(&msp->ms_lock);
@ -2350,7 +2346,6 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
metaslab_group_t *mg = msp->ms_group; metaslab_group_t *mg = msp->ms_group;
vdev_t *vd = mg->mg_vd; vdev_t *vd = mg->mg_vd;
spa_t *spa = vd->vdev_spa; spa_t *spa = vd->vdev_spa;
range_tree_t **freed_tree;
range_tree_t **defer_tree; range_tree_t **defer_tree;
int64_t alloc_delta, defer_delta; int64_t alloc_delta, defer_delta;
uint64_t free_space; uint64_t free_space;
@ -2363,20 +2358,24 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
/* /*
* If this metaslab is just becoming available, initialize its * If this metaslab is just becoming available, initialize its
* alloctrees, freetrees, and defertree and add its capacity to * range trees and add its capacity to the vdev.
* the vdev.
*/ */
if (msp->ms_freetree[TXG_CLEAN(txg) & TXG_MASK] == NULL) { if (msp->ms_freedtree == NULL) {
for (t = 0; t < TXG_SIZE; t++) { for (t = 0; t < TXG_SIZE; t++) {
ASSERT(msp->ms_alloctree[t] == NULL); ASSERT(msp->ms_alloctree[t] == NULL);
ASSERT(msp->ms_freetree[t] == NULL);
msp->ms_alloctree[t] = range_tree_create(NULL, msp, msp->ms_alloctree[t] = range_tree_create(NULL, msp,
&msp->ms_lock); &msp->ms_lock);
msp->ms_freetree[t] = range_tree_create(NULL, msp,
&msp->ms_lock);
} }
ASSERT3P(msp->ms_freeingtree, ==, NULL);
msp->ms_freeingtree = range_tree_create(NULL, msp,
&msp->ms_lock);
ASSERT3P(msp->ms_freedtree, ==, NULL);
msp->ms_freedtree = range_tree_create(NULL, msp,
&msp->ms_lock);
for (t = 0; t < TXG_DEFER_SIZE; t++) { for (t = 0; t < TXG_DEFER_SIZE; t++) {
ASSERT(msp->ms_defertree[t] == NULL); ASSERT(msp->ms_defertree[t] == NULL);
@ -2387,7 +2386,6 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
vdev_space_update(vd, 0, 0, msp->ms_size); vdev_space_update(vd, 0, 0, msp->ms_size);
} }
freed_tree = &msp->ms_freetree[TXG_CLEAN(txg) & TXG_MASK];
defer_tree = &msp->ms_defertree[txg % TXG_DEFER_SIZE]; defer_tree = &msp->ms_defertree[txg % TXG_DEFER_SIZE];
free_space = metaslab_class_get_space(spa_normal_class(spa)) - free_space = metaslab_class_get_space(spa_normal_class(spa)) -
@ -2399,7 +2397,7 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
defer_delta = 0; defer_delta = 0;
alloc_delta = space_map_alloc_delta(msp->ms_sm); alloc_delta = space_map_alloc_delta(msp->ms_sm);
if (defer_allowed) { if (defer_allowed) {
defer_delta = range_tree_space(*freed_tree) - defer_delta = range_tree_space(msp->ms_freedtree) -
range_tree_space(*defer_tree); range_tree_space(*defer_tree);
} else { } else {
defer_delta -= range_tree_space(*defer_tree); defer_delta -= range_tree_space(*defer_tree);
@ -2407,9 +2405,6 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
vdev_space_update(vd, alloc_delta + defer_delta, defer_delta, 0); vdev_space_update(vd, alloc_delta + defer_delta, defer_delta, 0);
ASSERT0(range_tree_space(msp->ms_alloctree[txg & TXG_MASK]));
ASSERT0(range_tree_space(msp->ms_freetree[txg & TXG_MASK]));
/* /*
* If there's a metaslab_load() in progress, wait for it to complete * If there's a metaslab_load() in progress, wait for it to complete
* so that we have a consistent view of the in-core space map. * so that we have a consistent view of the in-core space map.
@ -2425,9 +2420,9 @@ metaslab_sync_done(metaslab_t *msp, uint64_t txg)
range_tree_vacate(*defer_tree, range_tree_vacate(*defer_tree,
msp->ms_loaded ? range_tree_add : NULL, msp->ms_tree); msp->ms_loaded ? range_tree_add : NULL, msp->ms_tree);
if (defer_allowed) { if (defer_allowed) {
range_tree_swap(freed_tree, defer_tree); range_tree_swap(&msp->ms_freedtree, defer_tree);
} else { } else {
range_tree_vacate(*freed_tree, range_tree_vacate(msp->ms_freedtree,
msp->ms_loaded ? range_tree_add : NULL, msp->ms_tree); msp->ms_loaded ? range_tree_add : NULL, msp->ms_tree);
} }
@ -3252,10 +3247,10 @@ metaslab_free_dva(spa_t *spa, const dva_t *dva, uint64_t txg, boolean_t now)
range_tree_add(msp->ms_tree, offset, size); range_tree_add(msp->ms_tree, offset, size);
msp->ms_max_size = metaslab_block_maxsize(msp); msp->ms_max_size = metaslab_block_maxsize(msp);
} else { } else {
if (range_tree_space(msp->ms_freetree[txg & TXG_MASK]) == 0) VERIFY3U(txg, ==, spa->spa_syncing_txg);
if (range_tree_space(msp->ms_freeingtree) == 0)
vdev_dirty(vd, VDD_METASLAB, msp, txg); vdev_dirty(vd, VDD_METASLAB, msp, txg);
range_tree_add(msp->ms_freetree[txg & TXG_MASK], range_tree_add(msp->ms_freeingtree, offset, size);
offset, size);
} }
mutex_exit(&msp->ms_lock); mutex_exit(&msp->ms_lock);
@ -3543,8 +3538,8 @@ metaslab_check_free(spa_t *spa, const blkptr_t *bp)
if (msp->ms_loaded) if (msp->ms_loaded)
range_tree_verify(msp->ms_tree, offset, size); range_tree_verify(msp->ms_tree, offset, size);
for (j = 0; j < TXG_SIZE; j++) range_tree_verify(msp->ms_freeingtree, offset, size);
range_tree_verify(msp->ms_freetree[j], offset, size); range_tree_verify(msp->ms_freedtree, offset, size);
for (j = 0; j < TXG_DEFER_SIZE; j++) for (j = 0; j < TXG_DEFER_SIZE; j++)
range_tree_verify(msp->ms_defertree[j], offset, size); range_tree_verify(msp->ms_defertree[j], offset, size);
} }