freebsd-dev/module/zfs/refcount.c

317 lines
7.2 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* 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) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
OpenZFS 7090 - zfs should throttle allocations OpenZFS 7090 - zfs should throttle allocations Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Alex Reece <alex@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Approved by: Matthew Ahrens <mahrens@delphix.com> Ported-by: Don Brady <don.brady@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> When write I/Os are issued, they are issued in block order but the ZIO pipeline will drive them asynchronously through the allocation stage which can result in blocks being allocated out-of-order. It would be nice to preserve as much of the logical order as possible. In addition, the allocations are equally scattered across all top-level VDEVs but not all top-level VDEVs are created equally. The pipeline should be able to detect devices that are more capable of handling allocations and should allocate more blocks to those devices. This allows for dynamic allocation distribution when devices are imbalanced as fuller devices will tend to be slower than empty devices. The change includes a new pool-wide allocation queue which would throttle and order allocations in the ZIO pipeline. The queue would be ordered by issued time and offset and would provide an initial amount of allocation of work to each top-level vdev. The allocation logic utilizes a reservation system to reserve allocations that will be performed by the allocator. Once an allocation is successfully completed it's scheduled on a given top-level vdev. Each top-level vdev maintains a maximum number of allocations that it can handle (mg_alloc_queue_depth). The pool-wide reserved allocations (top-levels * mg_alloc_queue_depth) are distributed across the top-level vdevs metaslab groups and round robin across all eligible metaslab groups to distribute the work. As top-levels complete their work, they receive additional work from the pool-wide allocation queue until the allocation queue is emptied. OpenZFS-issue: https://www.illumos.org/issues/7090 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/4756c3d7 Closes #5258 Porting Notes: - Maintained minimal stack in zio_done - Preserve linux-specific io sizes in zio_write_compress - Added module params and documentation - Updated to use optimize AVL cmp macros
2016-10-14 00:59:18 +00:00
* Copyright (c) 2012, 2015 by Delphix. All rights reserved.
2008-11-20 20:01:55 +00:00
*/
#include <sys/zfs_context.h>
#include <sys/refcount.h>
#ifdef _KERNEL
int reference_tracking_enable = FALSE; /* runs out of memory too easily */
#else
int reference_tracking_enable = TRUE;
#endif
int reference_history = 3; /* tunable */
2008-11-20 20:01:55 +00:00
#ifdef ZFS_DEBUG
2008-11-20 20:01:55 +00:00
static kmem_cache_t *reference_cache;
static kmem_cache_t *reference_history_cache;
void
refcount_init(void)
{
reference_cache = kmem_cache_create("reference_cache",
sizeof (reference_t), 0, NULL, NULL, NULL, NULL, NULL, 0);
reference_history_cache = kmem_cache_create("reference_history_cache",
sizeof (uint64_t), 0, NULL, NULL, NULL, NULL, NULL, 0);
}
void
refcount_fini(void)
{
kmem_cache_destroy(reference_cache);
kmem_cache_destroy(reference_history_cache);
}
void
refcount_create(refcount_t *rc)
{
mutex_init(&rc->rc_mtx, NULL, MUTEX_DEFAULT, NULL);
list_create(&rc->rc_list, sizeof (reference_t),
offsetof(reference_t, ref_link));
list_create(&rc->rc_removed, sizeof (reference_t),
offsetof(reference_t, ref_link));
rc->rc_count = 0;
rc->rc_removed_count = 0;
rc->rc_tracked = reference_tracking_enable;
}
OpenZFS 7090 - zfs should throttle allocations OpenZFS 7090 - zfs should throttle allocations Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Alex Reece <alex@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Approved by: Matthew Ahrens <mahrens@delphix.com> Ported-by: Don Brady <don.brady@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> When write I/Os are issued, they are issued in block order but the ZIO pipeline will drive them asynchronously through the allocation stage which can result in blocks being allocated out-of-order. It would be nice to preserve as much of the logical order as possible. In addition, the allocations are equally scattered across all top-level VDEVs but not all top-level VDEVs are created equally. The pipeline should be able to detect devices that are more capable of handling allocations and should allocate more blocks to those devices. This allows for dynamic allocation distribution when devices are imbalanced as fuller devices will tend to be slower than empty devices. The change includes a new pool-wide allocation queue which would throttle and order allocations in the ZIO pipeline. The queue would be ordered by issued time and offset and would provide an initial amount of allocation of work to each top-level vdev. The allocation logic utilizes a reservation system to reserve allocations that will be performed by the allocator. Once an allocation is successfully completed it's scheduled on a given top-level vdev. Each top-level vdev maintains a maximum number of allocations that it can handle (mg_alloc_queue_depth). The pool-wide reserved allocations (top-levels * mg_alloc_queue_depth) are distributed across the top-level vdevs metaslab groups and round robin across all eligible metaslab groups to distribute the work. As top-levels complete their work, they receive additional work from the pool-wide allocation queue until the allocation queue is emptied. OpenZFS-issue: https://www.illumos.org/issues/7090 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/4756c3d7 Closes #5258 Porting Notes: - Maintained minimal stack in zio_done - Preserve linux-specific io sizes in zio_write_compress - Added module params and documentation - Updated to use optimize AVL cmp macros
2016-10-14 00:59:18 +00:00
void
refcount_create_tracked(refcount_t *rc)
{
refcount_create(rc);
rc->rc_tracked = B_TRUE;
}
void
refcount_create_untracked(refcount_t *rc)
{
refcount_create(rc);
rc->rc_tracked = B_FALSE;
2008-11-20 20:01:55 +00:00
}
void
refcount_destroy_many(refcount_t *rc, uint64_t number)
{
reference_t *ref;
ASSERT(rc->rc_count == number);
while ((ref = list_head(&rc->rc_list))) {
2008-11-20 20:01:55 +00:00
list_remove(&rc->rc_list, ref);
kmem_cache_free(reference_cache, ref);
}
list_destroy(&rc->rc_list);
while ((ref = list_head(&rc->rc_removed))) {
2008-11-20 20:01:55 +00:00
list_remove(&rc->rc_removed, ref);
kmem_cache_free(reference_history_cache, ref->ref_removed);
kmem_cache_free(reference_cache, ref);
}
list_destroy(&rc->rc_removed);
mutex_destroy(&rc->rc_mtx);
}
void
refcount_destroy(refcount_t *rc)
{
refcount_destroy_many(rc, 0);
}
int
refcount_is_zero(refcount_t *rc)
{
return (rc->rc_count == 0);
}
int64_t
refcount_count(refcount_t *rc)
{
return (rc->rc_count);
}
int64_t
refcount_add_many(refcount_t *rc, uint64_t number, void *holder)
{
reference_t *ref = NULL;
2008-11-20 20:01:55 +00:00
int64_t count;
if (rc->rc_tracked) {
ref = kmem_cache_alloc(reference_cache, KM_SLEEP);
2008-11-20 20:01:55 +00:00
ref->ref_holder = holder;
ref->ref_number = number;
}
mutex_enter(&rc->rc_mtx);
ASSERT(rc->rc_count >= 0);
if (rc->rc_tracked)
2008-11-20 20:01:55 +00:00
list_insert_head(&rc->rc_list, ref);
rc->rc_count += number;
count = rc->rc_count;
mutex_exit(&rc->rc_mtx);
return (count);
}
int64_t
zfs_refcount_add(refcount_t *rc, void *holder)
2008-11-20 20:01:55 +00:00
{
return (refcount_add_many(rc, 1, holder));
}
int64_t
refcount_remove_many(refcount_t *rc, uint64_t number, void *holder)
{
reference_t *ref;
int64_t count;
mutex_enter(&rc->rc_mtx);
ASSERT(rc->rc_count >= number);
if (!rc->rc_tracked) {
2008-11-20 20:01:55 +00:00
rc->rc_count -= number;
count = rc->rc_count;
mutex_exit(&rc->rc_mtx);
return (count);
}
for (ref = list_head(&rc->rc_list); ref;
ref = list_next(&rc->rc_list, ref)) {
if (ref->ref_holder == holder && ref->ref_number == number) {
list_remove(&rc->rc_list, ref);
if (reference_history > 0) {
ref->ref_removed =
kmem_cache_alloc(reference_history_cache,
KM_SLEEP);
2008-11-20 20:01:55 +00:00
list_insert_head(&rc->rc_removed, ref);
rc->rc_removed_count++;
if (rc->rc_removed_count > reference_history) {
2008-11-20 20:01:55 +00:00
ref = list_tail(&rc->rc_removed);
list_remove(&rc->rc_removed, ref);
kmem_cache_free(reference_history_cache,
ref->ref_removed);
kmem_cache_free(reference_cache, ref);
rc->rc_removed_count--;
}
} else {
kmem_cache_free(reference_cache, ref);
}
rc->rc_count -= number;
count = rc->rc_count;
mutex_exit(&rc->rc_mtx);
return (count);
}
}
panic("No such hold %p on refcount %llx", holder,
(u_longlong_t)(uintptr_t)rc);
return (-1);
}
int64_t
refcount_remove(refcount_t *rc, void *holder)
{
return (refcount_remove_many(rc, 1, holder));
}
void
refcount_transfer(refcount_t *dst, refcount_t *src)
{
int64_t count, removed_count;
list_t list, removed;
list_create(&list, sizeof (reference_t),
offsetof(reference_t, ref_link));
list_create(&removed, sizeof (reference_t),
offsetof(reference_t, ref_link));
mutex_enter(&src->rc_mtx);
count = src->rc_count;
removed_count = src->rc_removed_count;
src->rc_count = 0;
src->rc_removed_count = 0;
list_move_tail(&list, &src->rc_list);
list_move_tail(&removed, &src->rc_removed);
mutex_exit(&src->rc_mtx);
mutex_enter(&dst->rc_mtx);
dst->rc_count += count;
dst->rc_removed_count += removed_count;
list_move_tail(&dst->rc_list, &list);
list_move_tail(&dst->rc_removed, &removed);
mutex_exit(&dst->rc_mtx);
list_destroy(&list);
list_destroy(&removed);
}
OpenZFS 6950 - ARC should cache compressed data Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matt Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <pcd@delphix.com> Reviewed by: Tom Caputi <tcaputi@datto.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Ported by: David Quigley <david.quigley@intel.com> This review covers the reading and writing of compressed arc headers, sharing data between the arc_hdr_t and the arc_buf_t, and the implementation of a new dbuf cache to keep frequently access data uncompressed. I've added a new member to l1 arc hdr called b_pdata. The b_pdata always hangs off the arc_buf_hdr_t (if an L1 hdr is in use) and points to the physical block for that DVA. The physical block may or may not be compressed. If compressed arc is enabled and the block on-disk is compressed, then the b_pdata will match the block on-disk and remain compressed in memory. If the block on disk is not compressed, then neither will the b_pdata. Lastly, if compressed arc is disabled, then b_pdata will always be an uncompressed version of the on-disk block. Typically the arc will cache only the arc_buf_hdr_t and will aggressively evict any arc_buf_t's that are no longer referenced. This means that the arc will primarily have compressed blocks as the arc_buf_t's are considered overhead and are always uncompressed. When a consumer reads a block we first look to see if the arc_buf_hdr_t is cached. If the hdr is cached then we allocate a new arc_buf_t and decompress the b_pdata contents into the arc_buf_t's b_data. If the hdr already has a arc_buf_t, then we will allocate an additional arc_buf_t and bcopy the uncompressed contents from the first arc_buf_t to the new one. Writing to the compressed arc requires that we first discard the b_pdata since the physical block is about to be rewritten. The new data contents will be passed in via an arc_buf_t (uncompressed) and during the I/O pipeline stages we will copy the physical block contents to a newly allocated b_pdata. When an l2arc is inuse it will also take advantage of the b_pdata. Now the l2arc will always write the contents of b_pdata to the l2arc. This means that when compressed arc is enabled that the l2arc blocks are identical to those stored in the main data pool. This provides a significant advantage since we can leverage the bp's checksum when reading from the l2arc to determine if the contents are valid. If the compressed arc is disabled, then we must first transform the read block to look like the physical block in the main data pool before comparing the checksum and determining it's valid. OpenZFS-issue: https://www.illumos.org/issues/6950 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7fc10f0 Issue #5078
2016-06-02 04:04:53 +00:00
void
refcount_transfer_ownership(refcount_t *rc, void *current_holder,
void *new_holder)
{
reference_t *ref;
boolean_t found = B_FALSE;
mutex_enter(&rc->rc_mtx);
if (!rc->rc_tracked) {
mutex_exit(&rc->rc_mtx);
return;
}
for (ref = list_head(&rc->rc_list); ref;
ref = list_next(&rc->rc_list, ref)) {
if (ref->ref_holder == current_holder) {
ref->ref_holder = new_holder;
found = B_TRUE;
break;
}
}
ASSERT(found);
mutex_exit(&rc->rc_mtx);
}
OpenZFS 7090 - zfs should throttle allocations OpenZFS 7090 - zfs should throttle allocations Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Alex Reece <alex@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Approved by: Matthew Ahrens <mahrens@delphix.com> Ported-by: Don Brady <don.brady@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> When write I/Os are issued, they are issued in block order but the ZIO pipeline will drive them asynchronously through the allocation stage which can result in blocks being allocated out-of-order. It would be nice to preserve as much of the logical order as possible. In addition, the allocations are equally scattered across all top-level VDEVs but not all top-level VDEVs are created equally. The pipeline should be able to detect devices that are more capable of handling allocations and should allocate more blocks to those devices. This allows for dynamic allocation distribution when devices are imbalanced as fuller devices will tend to be slower than empty devices. The change includes a new pool-wide allocation queue which would throttle and order allocations in the ZIO pipeline. The queue would be ordered by issued time and offset and would provide an initial amount of allocation of work to each top-level vdev. The allocation logic utilizes a reservation system to reserve allocations that will be performed by the allocator. Once an allocation is successfully completed it's scheduled on a given top-level vdev. Each top-level vdev maintains a maximum number of allocations that it can handle (mg_alloc_queue_depth). The pool-wide reserved allocations (top-levels * mg_alloc_queue_depth) are distributed across the top-level vdevs metaslab groups and round robin across all eligible metaslab groups to distribute the work. As top-levels complete their work, they receive additional work from the pool-wide allocation queue until the allocation queue is emptied. OpenZFS-issue: https://www.illumos.org/issues/7090 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/4756c3d7 Closes #5258 Porting Notes: - Maintained minimal stack in zio_done - Preserve linux-specific io sizes in zio_write_compress - Added module params and documentation - Updated to use optimize AVL cmp macros
2016-10-14 00:59:18 +00:00
/*
* If tracking is enabled, return true if a reference exists that matches
* the "holder" tag. If tracking is disabled, then return true if a reference
* might be held.
*/
boolean_t
refcount_held(refcount_t *rc, void *holder)
{
reference_t *ref;
mutex_enter(&rc->rc_mtx);
if (!rc->rc_tracked) {
mutex_exit(&rc->rc_mtx);
return (rc->rc_count > 0);
}
for (ref = list_head(&rc->rc_list); ref;
ref = list_next(&rc->rc_list, ref)) {
if (ref->ref_holder == holder) {
mutex_exit(&rc->rc_mtx);
return (B_TRUE);
}
}
mutex_exit(&rc->rc_mtx);
return (B_FALSE);
}
/*
* If tracking is enabled, return true if a reference does not exist that
* matches the "holder" tag. If tracking is disabled, always return true
* since the reference might not be held.
*/
boolean_t
refcount_not_held(refcount_t *rc, void *holder)
{
reference_t *ref;
mutex_enter(&rc->rc_mtx);
if (!rc->rc_tracked) {
mutex_exit(&rc->rc_mtx);
return (B_TRUE);
}
for (ref = list_head(&rc->rc_list); ref;
ref = list_next(&rc->rc_list, ref)) {
if (ref->ref_holder == holder) {
mutex_exit(&rc->rc_mtx);
return (B_FALSE);
}
}
mutex_exit(&rc->rc_mtx);
return (B_TRUE);
}
#endif /* ZFS_DEBUG */