aboutsummaryrefslogtreecommitdiffstats
path: root/include/sys/metaslab_impl.h
diff options
context:
space:
mode:
authorGeorge Wilson <[email protected]>2013-10-01 13:25:53 -0800
committerBrian Behlendorf <[email protected]>2014-07-22 09:39:16 -0700
commit93cf20764a1be64a603020f54b45200e37b3877e (patch)
treeb0db8d60368de34cdbd4eccc9ee98d1110beb15e /include/sys/metaslab_impl.h
parent1be627f5c28a355bcd49e4e097114c13fae7731b (diff)
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 <[email protected]> Reviewed by: Adam Leventhal <[email protected]> Reviewed by: Sebastien Roy <[email protected]> Approved by: Garrett D'Amore <[email protected]> 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 <[email protected]> Signed-off-by: Prakash Surya <[email protected]> Signed-off-by: Brian Behlendorf <[email protected]> Closes #2488
Diffstat (limited to 'include/sys/metaslab_impl.h')
-rw-r--r--include/sys/metaslab_impl.h107
1 files changed, 82 insertions, 25 deletions
diff --git a/include/sys/metaslab_impl.h b/include/sys/metaslab_impl.h
index 36aa60d4c..3e9f32e1c 100644
--- a/include/sys/metaslab_impl.h
+++ b/include/sys/metaslab_impl.h
@@ -32,6 +32,7 @@
#include <sys/metaslab.h>
#include <sys/space_map.h>
+#include <sys/range_tree.h>
#include <sys/vdev.h>
#include <sys/txg.h>
#include <sys/avl.h>
@@ -43,7 +44,7 @@ extern "C" {
struct metaslab_class {
spa_t *mc_spa;
metaslab_group_t *mc_rotor;
- space_map_ops_t *mc_ops;
+ metaslab_ops_t *mc_ops;
uint64_t mc_aliquot;
uint64_t mc_alloc_groups; /* # of allocatable groups */
uint64_t mc_alloc; /* total allocated space */
@@ -57,7 +58,6 @@ struct metaslab_group {
kmutex_t mg_lock;
avl_tree_t mg_metaslab_tree;
uint64_t mg_aliquot;
- uint64_t mg_bonus_area;
uint64_t mg_alloc_failures;
boolean_t mg_allocatable; /* can we allocate? */
uint64_t mg_free_capacity; /* percentage free */
@@ -65,45 +65,102 @@ struct metaslab_group {
int64_t mg_activation_count;
metaslab_class_t *mg_class;
vdev_t *mg_vd;
+ taskq_t *mg_taskq;
metaslab_group_t *mg_prev;
metaslab_group_t *mg_next;
};
/*
- * Each metaslab maintains an in-core free map (ms_map) that contains the
- * current list of free segments. As blocks are allocated, the allocated
- * segment is removed from the ms_map and added to a per txg allocation map.
- * As blocks are freed, they are added to the per txg free map. These per
- * txg maps allow us to process all allocations and frees in syncing context
- * where it is safe to update the on-disk space maps.
+ * This value defines the number of elements in the ms_lbas array. The value
+ * of 64 was chosen as it covers to cover all power of 2 buckets up to
+ * UINT64_MAX. This is the equivalent of highbit(UINT64_MAX).
+ */
+#define MAX_LBAS 64
+
+/*
+ * Each metaslab maintains a set of in-core trees to track metaslab operations.
+ * The in-core free tree (ms_tree) contains the current list of free segments.
+ * As blocks are allocated, the allocated segment are removed from the ms_tree
+ * and added to a per txg allocation tree (ms_alloctree). As blocks are freed,
+ * they are added to the per txg free tree (ms_freetree). These per txg
+ * trees allow us to process all allocations and frees in syncing context
+ * where it is safe to update the on-disk space maps. One additional in-core
+ * tree is maintained to track deferred frees (ms_defertree). Once a block
+ * is freed it will move from the ms_freetree to the ms_defertree. A deferred
+ * free means that a block has been freed but cannot be used by the pool
+ * until TXG_DEFER_SIZE transactions groups later. For example, a block
+ * that is freed in txg 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:
+ *
+ *
+ * ALLOCATE
+ * |
+ * V
+ * free segment (ms_tree) --------> ms_alloctree ----> (write to space map)
+ * ^
+ * |
+ * | ms_freetree <--- FREE
+ * | |
+ * | |
+ * | |
+ * +----------- ms_defertree <-------+---------> (write to space map)
*
- * Each metaslab's free space is tracked in a space map object 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,
- * we append the allocs and frees from that txg to the space map object.
- * When the txg is done syncing, metaslab_sync_done() updates ms_smo
- * to ms_smo_syncing. Everything in ms_smo is always safe to allocate.
+ * we append the allocs and frees from that txg to the space map.
+ * The pool space is only updated once all metaslabs have finished syncing.
*
- * To load the in-core free map we read the space map object from disk.
+ * To load the in-core free tree we read the space map from disk.
* This object contains a series of alloc and free records that are
* combined to make up the list of all free segments in this metaslab. These
- * segments are represented in-core by the ms_map and are stored in an
+ * segments are represented in-core by the ms_tree and are stored in an
* AVL tree.
*
- * As the space map objects grows (as a result of the appends) it will
- * eventually become space-inefficient. When the space map object is
- * zfs_condense_pct/100 times the size of the minimal on-disk representation,
- * we rewrite it in its minimized form.
+ * 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
+ * is zfs_condense_pct/100 times the size of the minimal on-disk
+ * representation, we rewrite it in its minimized form. If a metaslab
+ * needs to condense then we must set the ms_condensing flag to ensure
+ * that allocations are not performed on the metaslab that is being written.
*/
struct metaslab {
- kmutex_t ms_lock; /* metaslab lock */
- space_map_obj_t ms_smo; /* synced space map object */
- space_map_obj_t ms_smo_syncing; /* syncing space map object */
- space_map_t *ms_allocmap[TXG_SIZE]; /* allocated this txg */
- space_map_t *ms_freemap[TXG_SIZE]; /* freed this txg */
- space_map_t *ms_defermap[TXG_DEFER_SIZE]; /* deferred frees */
- space_map_t *ms_map; /* in-core free space map */
+ kmutex_t ms_lock;
+ kcondvar_t ms_load_cv;
+ space_map_t *ms_sm;
+ metaslab_ops_t *ms_ops;
+ uint64_t ms_id;
+ uint64_t ms_start;
+ uint64_t ms_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;
+
+ boolean_t ms_condensing; /* condensing? */
+ boolean_t ms_loaded;
+ boolean_t ms_loading;
+
int64_t ms_deferspace; /* sum of ms_defermap[] space */
uint64_t ms_weight; /* weight vs. others in group */
+ uint64_t ms_factor;
+ uint64_t ms_access_txg;
+
+ /*
+ * The metaslab block allocators can optionally use a size-ordered
+ * range tree and/or an array of LBAs. Not all allocators use
+ * this functionality. The ms_size_tree should always contain the
+ * same number of segments as the ms_tree. The only difference
+ * is that the ms_size_tree is ordered by segment sizes.
+ */
+ avl_tree_t ms_size_tree;
+ uint64_t ms_lbas[MAX_LBAS];
+
metaslab_group_t *ms_group; /* metaslab group */
avl_node_t ms_group_node; /* node in metaslab group tree */
txg_node_t ms_txg_node; /* per-txg dirty metaslab links */