mirror_zfs/module/os/freebsd/zfs/arc_os.c

261 lines
6.6 KiB
C
Raw Normal View History

/*
* 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 https://opensource.org/licenses/CDDL-1.0.
* 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
*/
#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/spa_impl.h>
#include <sys/counter.h>
#include <sys/zio_compress.h>
#include <sys/zio_checksum.h>
#include <sys/zfs_context.h>
#include <sys/arc.h>
#include <sys/arc_os.h>
#include <sys/zfs_refcount.h>
#include <sys/vdev.h>
#include <sys/vdev_trim.h>
#include <sys/vdev_impl.h>
#include <sys/dsl_pool.h>
#include <sys/zio_checksum.h>
#include <sys/multilist.h>
#include <sys/abd.h>
#include <sys/zil.h>
#include <sys/fm/fs/zfs.h>
#include <sys/eventhandler.h>
#include <sys/callb.h>
#include <sys/kstat.h>
#include <sys/zthr.h>
#include <zfs_fletcher.h>
#include <sys/arc_impl.h>
#include <sys/sdt.h>
#include <sys/aggsum.h>
#include <sys/vnode.h>
#include <cityhash.h>
#include <machine/vmparam.h>
#include <sys/vm.h>
#include <sys/vmmeter.h>
#if __FreeBSD_version >= 1300139
static struct sx arc_vnlru_lock;
static struct vnode *arc_vnlru_marker;
#endif
extern struct vfsops zfs_vfsops;
uint_t zfs_arc_free_target = 0;
static void
arc_free_target_init(void *unused __unused)
{
zfs_arc_free_target = vm_cnt.v_free_target;
}
SYSINIT(arc_free_target_init, SI_SUB_KTHREAD_PAGE, SI_ORDER_ANY,
arc_free_target_init, NULL);
/*
* We don't have a tunable for arc_free_target due to the dependency on
* pagedaemon initialisation.
*/
ZFS_MODULE_PARAM_CALL(zfs_arc, zfs_arc_, free_target,
param_set_arc_free_target, 0, CTLFLAG_RW,
"Desired number of free pages below which ARC triggers reclaim");
ZFS_MODULE_PARAM_CALL(zfs_arc, zfs_arc_, no_grow_shift,
param_set_arc_no_grow_shift, 0, ZMOD_RW,
"log2(fraction of ARC which must be free to allow growing)");
int64_t
arc_available_memory(void)
{
int64_t lowest = INT64_MAX;
int64_t n __unused;
/*
* Cooperate with pagedaemon when it's time for it to scan
* and reclaim some pages.
*/
n = PAGESIZE * ((int64_t)freemem - zfs_arc_free_target);
if (n < lowest) {
lowest = n;
}
#if defined(__i386) || !defined(UMA_MD_SMALL_ALLOC)
/*
* If we're on an i386 platform, it's possible that we'll exhaust the
* kernel heap space before we ever run out of available physical
* memory. Most checks of the size of the heap_area compare against
* tune.t_minarmem, which is the minimum available real memory that we
* can have in the system. However, this is generally fixed at 25 pages
* which is so low that it's useless. In this comparison, we seek to
* calculate the total heap-size, and reclaim if more than 3/4ths of the
* heap is allocated. (Or, in the calculation, if less than 1/4th is
* free)
*/
n = uma_avail() - (long)(uma_limit() / 4);
if (n < lowest) {
lowest = n;
}
#endif
Revise ARC shrinker algorithm The ARC shrinker callback `arc_shrinker_count/_scan()` is invoked by the kernel's shrinker mechanism when the system is running low on free pages. This happens via 2 code paths: 1. "direct reclaim": The system is attempting to allocate a page, but we are low on memory. The ARC shrinker callback is invoked from the page-allocation code path. 2. "indirect reclaim": kswapd notices that there aren't many free pages, so it invokes the ARC shrinker callback. In both cases, the kernel's shrinker code requests that the ARC shrinker callback release some of its cache, and then it measures how many pages were released. However, it's measurement of released pages does not include pages that are freed via `__free_pages()`, which is how the ARC releases memory (via `abd_free_chunks()`). Rather, the kernel shrinker code is looking for pages to be placed on the lists of reclaimable pages (which is separate from actually-free pages). Because the kernel shrinker code doesn't detect that the ARC has released pages, it may call the ARC shrinker callback many times, resulting in the ARC "collapsing" down to `arc_c_min`. This has several negative impacts: 1. ZFS doesn't use RAM to cache data effectively. 2. In the direct reclaim case, a single page allocation may wait a long time (e.g. more than a minute) while we evict the entire ARC. 3. Even with the improvements made in 67c0f0dedc5 ("ARC shrinking blocks reads/writes"), occasionally `arc_size` may stay above `arc_c` for the entire time of the ARC collapse, thus blocking ZFS read/write operations in `arc_get_data_impl()`. To address these issues, this commit limits the ways that the ARC shrinker callback can be used by the kernel shrinker code, and mitigates the impact of arc_is_overflowing() on ZFS read/write operations. With this commit: 1. We limit the amount of data that can be reclaimed from the ARC via the "direct reclaim" shrinker. This limits the amount of time it takes to allocate a single page. 2. We do not allow the ARC to shrink via kswapd (indirect reclaim). Instead we rely on `arc_evict_zthr` to monitor free memory and reduce the ARC target size to keep sufficient free memory in the system. Note that we can't simply rely on limiting the amount that we reclaim at once (as for the direct reclaim case), because kswapd's "boosted" logic can invoke the callback an unlimited number of times (see `balance_pgdat()`). 3. When `arc_is_overflowing()` and we want to allocate memory, `arc_get_data_impl()` will wait only for a multiple of the requested amount of data to be evicted, rather than waiting for the ARC to no longer be overflowing. This allows ZFS reads/writes to make progress even while the ARC is overflowing, while also ensuring that the eviction thread makes progress towards reducing the total amount of memory used by the ARC. 4. The amount of memory that the ARC always tries to keep free for the rest of the system, `arc_sys_free` is increased. 5. Now that the shrinker callback is able to provide feedback to the kernel's shrinker code about our progress, we can safely enable the kswapd hook. This will allow the arc to receive notifications when memory pressure is first detected by the kernel. We also re-enable the appropriate kstats to track these callbacks. Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Co-authored-by: George Wilson <george.wilson@delphix.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com> Closes #10600
2020-08-01 07:10:52 +03:00
DTRACE_PROBE1(arc__available_memory, int64_t, lowest);
return (lowest);
}
/*
* Return a default max arc size based on the amount of physical memory.
*/
uint64_t
arc_default_max(uint64_t min, uint64_t allmem)
{
uint64_t size;
if (allmem >= 1 << 30)
size = allmem - (1 << 30);
else
size = min;
return (MAX(allmem * 5 / 8, size));
}
/*
* Helper function for arc_prune_async() it is responsible for safely
* handling the execution of a registered arc_prune_func_t.
*/
static void
arc_prune_task(void *arg)
{
Cleanup: Specify unsignedness on things that should not be signed In #13871, zfs_vdev_aggregation_limit_non_rotating and zfs_vdev_aggregation_limit being signed was pointed out as a possible reason not to eliminate an unnecessary MAX(unsigned, 0) since the unsigned value was assigned from them. There is no reason for these module parameters to be signed and upon inspection, it was found that there are a number of other module parameters that are signed, but should not be, so we make them unsigned. Making them unsigned made it clear that some other variables in the code should also be unsigned, so we also make those unsigned. This prevents users from setting negative values that could potentially cause bad behaviors. It also makes the code slightly easier to understand. Mostly module parameters that deal with timeouts, limits, bitshifts and percentages are made unsigned by this. Any that are boolean are left signed, since whether booleans should be considered signed or unsigned does not matter. Making zfs_arc_lotsfree_percent unsigned caused a `zfs_arc_lotsfree_percent >= 0` check to become redundant, so it was removed. Removing the check was also necessary to prevent a compiler error from -Werror=type-limits. Several end of line comments had to be moved to their own lines because replacing int with uint_t caused us to exceed the 80 character limit enforced by cstyle.pl. The following were kept signed because they are passed to taskq_create(), which expects signed values and modifying the OpenSolaris/Illumos DDI is out of scope of this patch: * metaslab_load_pct * zfs_sync_taskq_batch_pct * zfs_zil_clean_taskq_nthr_pct * zfs_zil_clean_taskq_minalloc * zfs_zil_clean_taskq_maxalloc * zfs_arc_prune_task_threads Also, negative values in those parameters was found to be harmless. The following were left signed because either negative values make sense, or more analysis was needed to determine whether negative values should be disallowed: * zfs_metaslab_switch_threshold * zfs_pd_bytes_max * zfs_livelist_min_percent_shared zfs_multihost_history was made static to be consistent with other parameters. A number of module parameters were marked as signed, but in reality referenced unsigned variables. upgrade_errlog_limit is one of the numerous examples. In the case of zfs_vdev_async_read_max_active, it was already uint32_t, but zdb had an extern int declaration for it. Interestingly, the documentation in zfs.4 was right for upgrade_errlog_limit despite the module parameter being wrongly marked, while the documentation for zfs_vdev_async_read_max_active (and friends) was wrong. It was also wrong for zstd_abort_size, which was unsigned, but was documented as signed. Also, the documentation in zfs.4 incorrectly described the following parameters as ulong when they were int: * zfs_arc_meta_adjust_restarts * zfs_override_estimate_recordsize They are now uint_t as of this patch and thus the man page has been updated to describe them as uint. dbuf_state_index was left alone since it does nothing and perhaps should be removed in another patch. If any module parameters were missed, they were not found by `grep -r 'ZFS_MODULE_PARAM' | grep ', INT'`. I did find a few that grep missed, but only because they were in files that had hits. This patch intentionally did not attempt to address whether some of these module parameters should be elevated to 64-bit parameters, because the length of a long on 32-bit is 32-bit. Lastly, it was pointed out during review that uint_t is a better match for these variables than uint32_t because FreeBSD kernel parameter definitions are designed for uint_t, whose bit width can change in future memory models. As a result, we change the existing parameters that are uint32_t to use uint_t. Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Neal Gompa <ngompa@datto.com> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13875
2022-09-28 02:42:41 +03:00
uint64_t nr_scan = (uintptr_t)arg;
arc_reduce_target_size(ptob(nr_scan));
#ifndef __ILP32__
if (nr_scan > INT_MAX)
nr_scan = INT_MAX;
#endif
#if __FreeBSD_version >= 1300139
sx_xlock(&arc_vnlru_lock);
vnlru_free_vfsops(nr_scan, &zfs_vfsops, arc_vnlru_marker);
sx_xunlock(&arc_vnlru_lock);
#else
vnlru_free(nr_scan, &zfs_vfsops);
#endif
}
/*
* Notify registered consumers they must drop holds on a portion of the ARC
* buffered they reference. This provides a mechanism to ensure the ARC can
More adaptive ARC eviction Traditionally ARC adaptation was limited to MRU/MFU distribution. But for years people with metadata-centric workload demanded mechanisms to also manage data/metadata distribution, that in original ZFS was just a FIFO. As result ZFS effectively got separate states for data and metadata, minimum and maximum metadata limits etc, but it all required manual tuning, was not adaptive and in its heart remained a bad FIFO. This change removes most of existing eviction logic, rewriting it from scratch. This makes MRU/MFU adaptation individual for data and meta- data, same as the distribution between data and metadata themselves. Since most of required states separation was already done, it only required to make arcs_size state field specific per data/metadata. The adaptation logic is still based on previous concept of ghost hits, just now it balances ARC capacity between 4 states: MRU data, MRU metadata, MFU data and MFU metadata. To simplify arc_c changes instead of arc_p measured in bytes, this code uses 3 variable arc_meta, arc_pd and arc_pm, representing ARC balance between metadata and data, MRU and MFU for data, and MRU and MFU for metadata respectively as 32-bit fixed point fractions. Since we care about the math result only when need to evict, this moves all the logic from arc_adapt() to arc_evict(), that reduces per-block overhead, since per-block operations are limited to stats collection, now moved from arc_adapt() to arc_access() and using cheaper wmsums. This also allows to remove ugly ARC_HDR_DO_ADAPT flag from many places. This change also removes number of metadata specific tunables, part of which were actually not functioning correctly, since not all metadata are equal and some (like L2ARC headers) are not really evictable. Instead it introduced single opaque knob zfs_arc_meta_balance, tuning ARC's reaction on ghost hits, allowing administrator give more or less preference to metadata without setting strict limits. Some of old code parts like arc_evict_meta() are just removed, because since introduction of ABD ARC they really make no sense: only headers referenced by small number of buffers are not evictable, and they are really not evictable no matter what this code do. Instead just call arc_prune_async() if too much metadata appear not evictable. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes #14359
2023-03-08 22:17:23 +03:00
* honor the metadata limit and reclaim otherwise pinned ARC buffers. This
* is analogous to dnlc_reduce_cache() but more generic.
*
* This operation is performed asynchronously so it may be safely called
* in the context of the arc_reclaim_thread(). A reference is taken here
* for each registered arc_prune_t and the arc_prune_task() is responsible
* for releasing it once the registered arc_prune_func_t has completed.
*/
void
Cleanup: Specify unsignedness on things that should not be signed In #13871, zfs_vdev_aggregation_limit_non_rotating and zfs_vdev_aggregation_limit being signed was pointed out as a possible reason not to eliminate an unnecessary MAX(unsigned, 0) since the unsigned value was assigned from them. There is no reason for these module parameters to be signed and upon inspection, it was found that there are a number of other module parameters that are signed, but should not be, so we make them unsigned. Making them unsigned made it clear that some other variables in the code should also be unsigned, so we also make those unsigned. This prevents users from setting negative values that could potentially cause bad behaviors. It also makes the code slightly easier to understand. Mostly module parameters that deal with timeouts, limits, bitshifts and percentages are made unsigned by this. Any that are boolean are left signed, since whether booleans should be considered signed or unsigned does not matter. Making zfs_arc_lotsfree_percent unsigned caused a `zfs_arc_lotsfree_percent >= 0` check to become redundant, so it was removed. Removing the check was also necessary to prevent a compiler error from -Werror=type-limits. Several end of line comments had to be moved to their own lines because replacing int with uint_t caused us to exceed the 80 character limit enforced by cstyle.pl. The following were kept signed because they are passed to taskq_create(), which expects signed values and modifying the OpenSolaris/Illumos DDI is out of scope of this patch: * metaslab_load_pct * zfs_sync_taskq_batch_pct * zfs_zil_clean_taskq_nthr_pct * zfs_zil_clean_taskq_minalloc * zfs_zil_clean_taskq_maxalloc * zfs_arc_prune_task_threads Also, negative values in those parameters was found to be harmless. The following were left signed because either negative values make sense, or more analysis was needed to determine whether negative values should be disallowed: * zfs_metaslab_switch_threshold * zfs_pd_bytes_max * zfs_livelist_min_percent_shared zfs_multihost_history was made static to be consistent with other parameters. A number of module parameters were marked as signed, but in reality referenced unsigned variables. upgrade_errlog_limit is one of the numerous examples. In the case of zfs_vdev_async_read_max_active, it was already uint32_t, but zdb had an extern int declaration for it. Interestingly, the documentation in zfs.4 was right for upgrade_errlog_limit despite the module parameter being wrongly marked, while the documentation for zfs_vdev_async_read_max_active (and friends) was wrong. It was also wrong for zstd_abort_size, which was unsigned, but was documented as signed. Also, the documentation in zfs.4 incorrectly described the following parameters as ulong when they were int: * zfs_arc_meta_adjust_restarts * zfs_override_estimate_recordsize They are now uint_t as of this patch and thus the man page has been updated to describe them as uint. dbuf_state_index was left alone since it does nothing and perhaps should be removed in another patch. If any module parameters were missed, they were not found by `grep -r 'ZFS_MODULE_PARAM' | grep ', INT'`. I did find a few that grep missed, but only because they were in files that had hits. This patch intentionally did not attempt to address whether some of these module parameters should be elevated to 64-bit parameters, because the length of a long on 32-bit is 32-bit. Lastly, it was pointed out during review that uint_t is a better match for these variables than uint32_t because FreeBSD kernel parameter definitions are designed for uint_t, whose bit width can change in future memory models. As a result, we change the existing parameters that are uint32_t to use uint_t. Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Neal Gompa <ngompa@datto.com> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13875
2022-09-28 02:42:41 +03:00
arc_prune_async(uint64_t adjust)
{
#ifndef __LP64__
Cleanup: Specify unsignedness on things that should not be signed In #13871, zfs_vdev_aggregation_limit_non_rotating and zfs_vdev_aggregation_limit being signed was pointed out as a possible reason not to eliminate an unnecessary MAX(unsigned, 0) since the unsigned value was assigned from them. There is no reason for these module parameters to be signed and upon inspection, it was found that there are a number of other module parameters that are signed, but should not be, so we make them unsigned. Making them unsigned made it clear that some other variables in the code should also be unsigned, so we also make those unsigned. This prevents users from setting negative values that could potentially cause bad behaviors. It also makes the code slightly easier to understand. Mostly module parameters that deal with timeouts, limits, bitshifts and percentages are made unsigned by this. Any that are boolean are left signed, since whether booleans should be considered signed or unsigned does not matter. Making zfs_arc_lotsfree_percent unsigned caused a `zfs_arc_lotsfree_percent >= 0` check to become redundant, so it was removed. Removing the check was also necessary to prevent a compiler error from -Werror=type-limits. Several end of line comments had to be moved to their own lines because replacing int with uint_t caused us to exceed the 80 character limit enforced by cstyle.pl. The following were kept signed because they are passed to taskq_create(), which expects signed values and modifying the OpenSolaris/Illumos DDI is out of scope of this patch: * metaslab_load_pct * zfs_sync_taskq_batch_pct * zfs_zil_clean_taskq_nthr_pct * zfs_zil_clean_taskq_minalloc * zfs_zil_clean_taskq_maxalloc * zfs_arc_prune_task_threads Also, negative values in those parameters was found to be harmless. The following were left signed because either negative values make sense, or more analysis was needed to determine whether negative values should be disallowed: * zfs_metaslab_switch_threshold * zfs_pd_bytes_max * zfs_livelist_min_percent_shared zfs_multihost_history was made static to be consistent with other parameters. A number of module parameters were marked as signed, but in reality referenced unsigned variables. upgrade_errlog_limit is one of the numerous examples. In the case of zfs_vdev_async_read_max_active, it was already uint32_t, but zdb had an extern int declaration for it. Interestingly, the documentation in zfs.4 was right for upgrade_errlog_limit despite the module parameter being wrongly marked, while the documentation for zfs_vdev_async_read_max_active (and friends) was wrong. It was also wrong for zstd_abort_size, which was unsigned, but was documented as signed. Also, the documentation in zfs.4 incorrectly described the following parameters as ulong when they were int: * zfs_arc_meta_adjust_restarts * zfs_override_estimate_recordsize They are now uint_t as of this patch and thus the man page has been updated to describe them as uint. dbuf_state_index was left alone since it does nothing and perhaps should be removed in another patch. If any module parameters were missed, they were not found by `grep -r 'ZFS_MODULE_PARAM' | grep ', INT'`. I did find a few that grep missed, but only because they were in files that had hits. This patch intentionally did not attempt to address whether some of these module parameters should be elevated to 64-bit parameters, because the length of a long on 32-bit is 32-bit. Lastly, it was pointed out during review that uint_t is a better match for these variables than uint32_t because FreeBSD kernel parameter definitions are designed for uint_t, whose bit width can change in future memory models. As a result, we change the existing parameters that are uint32_t to use uint_t. Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Neal Gompa <ngompa@datto.com> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13875
2022-09-28 02:42:41 +03:00
if (adjust > UINTPTR_MAX)
adjust = UINTPTR_MAX;
#endif
taskq_dispatch(arc_prune_taskq, arc_prune_task,
(void *)(intptr_t)adjust, TQ_SLEEP);
ARCSTAT_BUMP(arcstat_prune);
}
uint64_t
arc_all_memory(void)
{
return (ptob(physmem));
}
int
arc_memory_throttle(spa_t *spa, uint64_t reserve, uint64_t txg)
{
return (0);
}
uint64_t
arc_free_memory(void)
{
return (ptob(freemem));
}
static eventhandler_tag arc_event_lowmem = NULL;
static void
arc_lowmem(void *arg __unused, int howto __unused)
{
int64_t free_memory, to_free;
arc_no_grow = B_TRUE;
arc_warm = B_TRUE;
arc_growtime = gethrtime() + SEC2NSEC(arc_grow_retry);
free_memory = arc_available_memory();
int64_t can_free = arc_c - arc_c_min;
if (can_free <= 0)
return;
to_free = (can_free >> arc_shrink_shift) - MIN(free_memory, 0);
DTRACE_PROBE2(arc__needfree, int64_t, free_memory, int64_t, to_free);
arc_reduce_target_size(to_free);
/*
* It is unsafe to block here in arbitrary threads, because we can come
* here from ARC itself and may hold ARC locks and thus risk a deadlock
* with ARC reclaim thread.
*/
if (curproc == pageproc)
arc_wait_for_eviction(to_free, B_FALSE);
}
void
arc_lowmem_init(void)
{
arc_event_lowmem = EVENTHANDLER_REGISTER(vm_lowmem, arc_lowmem, NULL,
EVENTHANDLER_PRI_FIRST);
#if __FreeBSD_version >= 1300139
arc_vnlru_marker = vnlru_alloc_marker();
sx_init(&arc_vnlru_lock, "arc vnlru lock");
#endif
}
void
arc_lowmem_fini(void)
{
if (arc_event_lowmem != NULL)
EVENTHANDLER_DEREGISTER(vm_lowmem, arc_event_lowmem);
#if __FreeBSD_version >= 1300139
if (arc_vnlru_marker != NULL) {
vnlru_free_marker(arc_vnlru_marker);
sx_destroy(&arc_vnlru_lock);
}
#endif
}
void
arc_register_hotplug(void)
{
}
void
arc_unregister_hotplug(void)
{
}