metaslab_impl.h revision 8363e80ae72609660f6090766ca8c2c18aa53f0c
/*
* 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
* 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 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
/*
* Copyright (c) 2011, 2015 by Delphix. All rights reserved.
*/
#ifndef _SYS_METASLAB_IMPL_H
#define _SYS_METASLAB_IMPL_H
#include <sys/metaslab.h>
#include <sys/space_map.h>
#include <sys/range_tree.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Metaslab allocation tracing record.
*/
typedef struct metaslab_alloc_trace {
/*
* Used by the metaslab allocation tracing facility to indicate
* error conditions. These errors are stored to the offset member
* of the metaslab_alloc_trace_t record and displayed by mdb.
*/
typedef enum trace_alloc_type {
TRACE_ALLOC_FAILURE = -1ULL,
TRACE_TOO_SMALL = -2ULL,
TRACE_FORCE_GANG = -3ULL,
TRACE_NOT_ALLOCATABLE = -4ULL,
TRACE_GROUP_FAILURE = -5ULL,
TRACE_ENOSPC = -6ULL,
TRACE_CONDENSING = -7ULL,
TRACE_VDEV_ERROR = -8ULL
#define METASLAB_ACTIVE_MASK \
/*
* The metaslab weight is used to encode the amount of free space in a
* metaslab, such that the "best" metaslab appears first when sorting the
* metaslabs by weight. The weight (and therefore the "best" metaslab) can
* be determined in two different ways: by computing a weighted sum of all
* the free space in the metaslab (a space based weight) or by counting only
* the free segments of the largest size (a segment based weight). We prefer
* the segment based weight because it reflects how the free space is
* comprised, but we cannot always use it -- legacy pools do not have the
* space map histogram information necessary to determine the largest
* contiguous regions. Pools that have the space map histogram determine
* the segment weight by looking at each bucket in the histogram and
* determining the free space whose size in bytes is in the range:
* [2^i, 2^(i+1))
* We then encode the largest index, i, that contains regions into the
* segment-weighted value.
*
* Space-based weight:
*
* 64 56 48 40 32 24 16 8 0
* +-------+-------+-------+-------+-------+-------+-------+-------+
* |PS1| weighted-free space |
* +-------+-------+-------+-------+-------+-------+-------+-------+
*
* PS - indicates primary and secondary activation
* space - the fragmentation-weighted space
*
* Segment-based weight:
*
* 64 56 48 40 32 24 16 8 0
* +-------+-------+-------+-------+-------+-------+-------+-------+
* |PS0| idx| count of segments in region |
* +-------+-------+-------+-------+-------+-------+-------+-------+
*
* PS - indicates primary and secondary activation
* idx - index for the highest bucket in the histogram
* count - number of segments in the specified bucket
*/
#define WEIGHT_IS_SPACEBASED(weight) \
/*
* These macros are only applicable to segment-based weighting.
*/
/*
* A metaslab class encompasses a category of allocatable top-level vdevs.
* Each top-level vdev is associated with a metaslab group which defines
* the allocatable region for that vdev. Examples of these categories include
* "normal" for data block allocations (i.e. main pool allocations) or "log"
* for allocations designated for intent log devices (i.e. slog devices).
* When a block allocation is requested from the SPA it is associated with a
* metaslab_class_t, and only top-level vdevs (i.e. metaslab groups) belonging
* to the class can be used to satisfy that request. Allocations are done
* by traversing the metaslab groups that are linked off of the mc_rotor field.
* This rotor points to the next metaslab group where allocations will be
* attempted. Allocating a block is a 3 step process -- select the metaslab
* group, select the metaslab, and then allocate the block. The metaslab
* class defines the low-level block allocator that will be used as the
* final step in allocation. These allocators are pluggable allowing each class
* to use a block allocator that best suits that class.
*/
struct metaslab_class {
/*
* Track the number of metaslab groups that have been initialized
* and can accept allocations. An initialized metaslab group is
* one has been completely added to the config (i.e. we have
* updated the MOS config and the space has been added to the pool).
*/
/*
*/
/*
* The allocation throttle works on a reservation system. Whenever
* an asynchronous zio wants to perform an allocation it must
* first reserve the number of blocks that it wants to allocate.
* If there aren't sufficient slots available for the pending zio
* then that I/O is throttled until more slots free up. The current
* number of reserved allocations is maintained by the mc_alloc_slots
* refcount. The mc_alloc_max_slots value determines the maximum
* number of allocations that the system allows. Gang blocks are
* allowed to reserve slots even if we've reached the maximum
* number of allocations allowed.
*/
};
/*
* Metaslab groups encapsulate all the allocatable regions (i.e. metaslabs)
* of a top-level vdev. They are linked togther to form a circular linked
* list and can belong to only one metaslab class. Metaslab groups may become
* ineligible for allocations for a number of reasons such as limited free
* space, fragmentation, or going offline. When this happens the allocator will
* simply find the next metaslab group in the linked list and attempt
* to allocate from that group instead.
*/
struct metaslab_group {
/*
* A metaslab group is considered to be initialized only after
* we have updated the MOS config and added the space to the pool.
* We only allow allocation attempts to a metaslab group if it
* has been initialized.
*/
/*
* Each metaslab group can handle mg_max_alloc_queue_depth allocations
* which are tracked by mg_alloc_queue_depth. It's possible for a
* metaslab group to handle more allocations than its max. This
* can occur when gang blocks are required or when other groups
* are unable to handle their share of allocations.
*/
/*
* A metalab group that can no longer allocate the minimum block
* size will set mg_no_free_space. Once a metaslab group is out
* of space then its share of work must be distributed to other
* groups.
*/
};
/*
* This value defines the number of elements in the ms_lbas array. The value
* of 64 was chosen as it covers 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 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.
* The 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.
* 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_tree and are stored in an
* AVL tree.
*
* 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 {
/*
* We must hold both ms_lock and ms_group->mg_lock in order to
* modify ms_loaded.
*/
/*
* Track of whenever a metaslab is selected for loading or allocation.
* We use this value to determine how long the metaslab should
* stay cached.
*/
/*
* The metaslab block allocators can optionally use a size-ordered
* 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.
*/
};
#ifdef __cplusplus
}
#endif
#endif /* _SYS_METASLAB_IMPL_H */