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

462 lines
14 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
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2018, Joyent, Inc.
* Copyright (c) 2011, 2019 by Delphix. All rights reserved.
* Copyright (c) 2014 by Saso Kiselkov. All rights reserved.
* Copyright 2017 Nexenta Systems, Inc. All rights reserved.
*/
#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/spa_impl.h>
#include <sys/zio_compress.h>
#include <sys/zio_checksum.h>
#include <sys/zfs_context.h>
#include <sys/arc.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/multilist.h>
#include <sys/abd.h>
#include <sys/zil.h>
#include <sys/fm/fs/zfs.h>
#include <sys/shrinker.h>
#include <sys/vmsystm.h>
#include <sys/zpl.h>
#include <linux/page_compat.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/version.h>
#include <sys/callb.h>
#include <sys/kstat.h>
#include <sys/zthr.h>
#include <zfs_fletcher.h>
#include <sys/arc_impl.h>
#include <sys/trace_zfs.h>
#include <sys/aggsum.h>
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
/*
* This is a limit on how many pages the ARC shrinker makes available for
* eviction in response to one page allocation attempt. Note that in
* practice, the kernel's shrinker can ask us to evict up to about 4x this
* for one allocation attempt.
*
* The default limit of 10,000 (in practice, 160MB per allocation attempt
* with 4K pages) limits the amount of time spent attempting to reclaim ARC
* memory to less than 100ms per allocation attempt, even with a small
* average compressed block size of ~8KB.
*
* See also the comment in arc_shrinker_count().
* Set to 0 to disable limit.
*/
static int zfs_arc_shrinker_limit = 10000;
/*
* Relative cost of ARC eviction, AKA number of seeks needed to restore evicted
* page. Bigger values make ARC more precious and evictions smaller comparing
* to other kernel subsystems. Value of 4 means parity with page cache,
* according to my reading of kernel's do_shrink_slab() and other code.
*/
static int zfs_arc_shrinker_seeks = DEFAULT_SEEKS;
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
#ifdef CONFIG_MEMORY_HOTPLUG
static struct notifier_block arc_hotplug_callback_mem_nb;
#endif
/*
* Return a default max arc size based on the amount of physical memory.
* This may be overridden by tuning the zfs_arc_max module parameter.
*/
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));
}
/*
* Return maximum amount of memory that we could possibly use. Reduced
* to half of all memory in user space which is primarily used for testing.
*/
uint64_t
arc_all_memory(void)
{
#ifdef CONFIG_HIGHMEM
return (ptob(zfs_totalram_pages - zfs_totalhigh_pages));
#else
return (ptob(zfs_totalram_pages));
#endif /* CONFIG_HIGHMEM */
}
/*
* Return the amount of memory that is considered free. In user space
* which is primarily used for testing we pretend that free memory ranges
* from 0-20% of all memory.
*/
uint64_t
arc_free_memory(void)
{
#ifdef CONFIG_HIGHMEM
struct sysinfo si;
si_meminfo(&si);
return (ptob(si.freeram - si.freehigh));
#else
return (ptob(nr_free_pages() +
nr_inactive_file_pages()));
#endif /* CONFIG_HIGHMEM */
}
/*
* Return the amount of memory that can be consumed before reclaim will be
* needed. Positive if there is sufficient free memory, negative indicates
* the amount of memory that needs to be freed up.
*/
int64_t
arc_available_memory(void)
{
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
return (arc_free_memory() - arc_sys_free);
}
static uint64_t
arc_evictable_memory(void)
{
int64_t asize = aggsum_value(&arc_sums.arcstat_size);
uint64_t arc_clean =
zfs_refcount_count(&arc_mru->arcs_esize[ARC_BUFC_DATA]) +
zfs_refcount_count(&arc_mru->arcs_esize[ARC_BUFC_METADATA]) +
zfs_refcount_count(&arc_mfu->arcs_esize[ARC_BUFC_DATA]) +
zfs_refcount_count(&arc_mfu->arcs_esize[ARC_BUFC_METADATA]);
uint64_t arc_dirty = MAX((int64_t)asize - (int64_t)arc_clean, 0);
/*
* Scale reported evictable memory in proportion to page cache, cap
* at specified min/max.
*/
uint64_t min = (ptob(nr_file_pages()) / 100) * zfs_arc_pc_percent;
min = MAX(arc_c_min, MIN(arc_c_max, min));
if (arc_dirty >= min)
return (arc_clean);
return (MAX((int64_t)asize - (int64_t)min, 0));
}
/*
* The _count() function returns the number of free-able objects.
* The _scan() function returns the number of objects that were freed.
*/
static unsigned long
arc_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
{
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
/*
* The kernel's shrinker code may not understand how many pages the
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
* ARC's callback actually frees, so it may ask the ARC to shrink a
* lot for one page allocation. This is problematic because it may
* take a long time, thus delaying the page allocation, and because
* it may force the ARC to unnecessarily shrink very small.
*
* Therefore, we limit the amount of data that we say is evictable,
* which limits the amount that the shrinker will ask us to evict for
* one page allocation attempt.
*
* In practice, we may be asked to shrink 4x the limit to satisfy one
* page allocation, before the kernel's shrinker code gives up on us.
* When that happens, we rely on the kernel code to find the pages
* that we freed before invoking the OOM killer. This happens in
* __alloc_pages_slowpath(), which retries and finds the pages we
* freed when it calls get_page_from_freelist().
*
* See also the comment above zfs_arc_shrinker_limit.
*/
int64_t can_free = btop(arc_evictable_memory());
if (current_is_kswapd() && zfs_arc_shrinker_limit)
can_free = MIN(can_free, zfs_arc_shrinker_limit);
return (can_free);
}
static unsigned long
arc_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc)
{
/* The arc is considered warm once reclaim has occurred */
if (unlikely(arc_warm == B_FALSE))
arc_warm = B_TRUE;
/*
* We are experiencing memory pressure which the arc_evict_zthr was
* unable to keep up with. Set arc_no_grow to briefly pause ARC
* growth to avoid compounding the memory pressure.
*/
arc_no_grow = B_TRUE;
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
/*
* Evict the requested number of pages by reducing arc_c and waiting
* for the requested amount of data to be evicted. To avoid deadlock
* do not wait for eviction if we may be called from ZFS itself (see
* kmem_flags_convert() removing __GFP_FS). It may cause excessive
* eviction later if many evictions are accumulated, but just skipping
* the eviction is not good either if most of memory is used by ARC.
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
*/
uint64_t to_free = arc_reduce_target_size(ptob(sc->nr_to_scan));
if (sc->gfp_mask & __GFP_FS)
arc_wait_for_eviction(to_free, B_FALSE, B_FALSE);
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
if (current->reclaim_state != NULL)
#ifdef HAVE_RECLAIM_STATE_RECLAIMED
current->reclaim_state->reclaimed += btop(to_free);
#else
current->reclaim_state->reclaimed_slab += btop(to_free);
#endif
/*
* When direct reclaim is observed it usually indicates a rapid
* increase in memory pressure. This occurs because the kswapd
* threads were unable to asynchronously keep enough free memory
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
* available.
*/
if (current_is_kswapd()) {
ARCSTAT_BUMP(arcstat_memory_indirect_count);
} else {
ARCSTAT_BUMP(arcstat_memory_direct_count);
}
return (btop(to_free));
}
static struct shrinker *arc_shrinker = NULL;
int
arc_memory_throttle(spa_t *spa, uint64_t reserve, uint64_t txg)
{
Clean up OS-specific ARC and kmem code OS-specific code (e.g. under `module/os/linux`) does not need to share its code structure with any other operating systems. In particular, the ARC and kmem code need not be similar to the code in illumos, because we won't be syncing this OS-specific code between operating systems. For example, if/when illumos support is added to the common repo, we would add a file `module/os/illumos/zfs/arc_os.c` for the illumos versions of this code. Therefore, we can simplify the code in the OS-specific ARC and kmem routines. These changes do not impact system behavior, they are purely code cleanup. The changes are: Arenas are not used on Linux or FreeBSD (they are always `NULL`), so `heap_arena`, `zio_arena`, and `zio_alloc_arena` can be removed, along with code that uses them. In `arc_available_memory()`: * `desfree` is unused, remove it * rename `freemem` to avoid conflict with pre-existing `#define` * remove checks related to arenas * use units of bytes, rather than converting from bytes to pages and then back to bytes `SPL_KMEM_CACHE_REAP` is unused, remove it. `skc_reap` is unused, remove it. The `count` argument to `spl_kmem_cache_reap_now()` is unused, remove it. `vmem_size()` and associated type and macros are unused, remove them. In `arc_memory_throttle()`, use a less confusing variable name to store the result of `arc_free_memory()`. Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Ryan Moeller <ryan@ixsystems.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com> Closes #10499
2020-06-29 19:01:07 +03:00
uint64_t free_memory = arc_free_memory();
Clean up OS-specific ARC and kmem code OS-specific code (e.g. under `module/os/linux`) does not need to share its code structure with any other operating systems. In particular, the ARC and kmem code need not be similar to the code in illumos, because we won't be syncing this OS-specific code between operating systems. For example, if/when illumos support is added to the common repo, we would add a file `module/os/illumos/zfs/arc_os.c` for the illumos versions of this code. Therefore, we can simplify the code in the OS-specific ARC and kmem routines. These changes do not impact system behavior, they are purely code cleanup. The changes are: Arenas are not used on Linux or FreeBSD (they are always `NULL`), so `heap_arena`, `zio_arena`, and `zio_alloc_arena` can be removed, along with code that uses them. In `arc_available_memory()`: * `desfree` is unused, remove it * rename `freemem` to avoid conflict with pre-existing `#define` * remove checks related to arenas * use units of bytes, rather than converting from bytes to pages and then back to bytes `SPL_KMEM_CACHE_REAP` is unused, remove it. `skc_reap` is unused, remove it. The `count` argument to `spl_kmem_cache_reap_now()` is unused, remove it. `vmem_size()` and associated type and macros are unused, remove them. In `arc_memory_throttle()`, use a less confusing variable name to store the result of `arc_free_memory()`. Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Ryan Moeller <ryan@ixsystems.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com> Closes #10499
2020-06-29 19:01:07 +03:00
if (free_memory > arc_all_memory() * arc_lotsfree_percent / 100)
return (0);
if (txg > spa->spa_lowmem_last_txg) {
spa->spa_lowmem_last_txg = txg;
spa->spa_lowmem_page_load = 0;
}
/*
* If we are in pageout, we know that memory is already tight,
* the arc is already going to be evicting, so we just want to
* continue to let page writes occur as quickly as possible.
*/
if (current_is_kswapd()) {
if (spa->spa_lowmem_page_load >
Clean up OS-specific ARC and kmem code OS-specific code (e.g. under `module/os/linux`) does not need to share its code structure with any other operating systems. In particular, the ARC and kmem code need not be similar to the code in illumos, because we won't be syncing this OS-specific code between operating systems. For example, if/when illumos support is added to the common repo, we would add a file `module/os/illumos/zfs/arc_os.c` for the illumos versions of this code. Therefore, we can simplify the code in the OS-specific ARC and kmem routines. These changes do not impact system behavior, they are purely code cleanup. The changes are: Arenas are not used on Linux or FreeBSD (they are always `NULL`), so `heap_arena`, `zio_arena`, and `zio_alloc_arena` can be removed, along with code that uses them. In `arc_available_memory()`: * `desfree` is unused, remove it * rename `freemem` to avoid conflict with pre-existing `#define` * remove checks related to arenas * use units of bytes, rather than converting from bytes to pages and then back to bytes `SPL_KMEM_CACHE_REAP` is unused, remove it. `skc_reap` is unused, remove it. The `count` argument to `spl_kmem_cache_reap_now()` is unused, remove it. `vmem_size()` and associated type and macros are unused, remove them. In `arc_memory_throttle()`, use a less confusing variable name to store the result of `arc_free_memory()`. Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Ryan Moeller <ryan@ixsystems.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com> Closes #10499
2020-06-29 19:01:07 +03:00
MAX(arc_sys_free / 4, free_memory) / 4) {
DMU_TX_STAT_BUMP(dmu_tx_memory_reclaim);
return (SET_ERROR(ERESTART));
}
/* Note: reserve is inflated, so we deflate */
atomic_add_64(&spa->spa_lowmem_page_load, reserve / 8);
return (0);
} else if (spa->spa_lowmem_page_load > 0 && arc_reclaim_needed()) {
/* memory is low, delay before restarting */
ARCSTAT_INCR(arcstat_memory_throttle_count, 1);
DMU_TX_STAT_BUMP(dmu_tx_memory_reclaim);
return (SET_ERROR(EAGAIN));
}
spa->spa_lowmem_page_load = 0;
return (0);
}
static void
arc_set_sys_free(uint64_t allmem)
{
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
/*
* The ARC tries to keep at least this much memory available for the
* system. This gives the ARC time to shrink in response to memory
* pressure, before running completely out of memory and invoking the
* direct-reclaim ARC shrinker.
*
* This should be more than twice high_wmark_pages(), so that
* arc_wait_for_eviction() will wait until at least the
* high_wmark_pages() are free (see arc_evict_state_impl()).
*
* Note: If concurrent allocations consume these pages, there may
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
* still be insufficient free pages, and the OOM killer takes action.
*
* By setting arc_sys_free large enough, and having
* arc_wait_for_eviction() wait until there is at least arc_sys_free/2
* free memory, it is much less likely that concurrent allocations can
* consume all the memory that was evicted before checking for
* OOM.
*
* It's hard to iterate the zones from a linux kernel module, which
* makes it difficult to determine the watermark dynamically. Instead
* we compute the maximum high watermark for this system, based
* on the amount of memory, using the same method as the kernel uses
* to calculate its internal `min_free_kbytes` variable. See
* torvalds/linux@ee8eb9a5fe86 for the change in the upper clamp value
* from 64M to 256M.
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
*/
/*
* Base wmark_low is 4 * the square root of Kbytes of RAM.
*/
long wmark = int_sqrt(allmem / 1024 * 16) * 1024;
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
/*
* Clamp to between 128K and 256/64MB.
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
*/
wmark = MAX(wmark, 128 * 1024);
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 7, 0)
wmark = MIN(wmark, 256 * 1024 * 1024);
#else
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
wmark = MIN(wmark, 64 * 1024 * 1024);
#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
/*
* watermark_boost can increase the wmark by up to 150%.
*/
wmark += wmark * 150 / 100;
/*
* arc_sys_free needs to be more than 2x the watermark, because
* arc_wait_for_eviction() waits for half of arc_sys_free. Bump this up
* to 3x to ensure we're above it.
*/
arc_sys_free = wmark * 3 + allmem / 32;
}
void
arc_lowmem_init(void)
{
uint64_t allmem = arc_all_memory();
/*
* Register a shrinker to support synchronous (direct) memory
* reclaim from the arc. This is done to prevent kswapd from
* swapping out pages when it is preferable to shrink the arc.
*/
arc_shrinker = spl_register_shrinker("zfs-arc-shrinker",
arc_shrinker_count, arc_shrinker_scan, zfs_arc_shrinker_seeks);
VERIFY(arc_shrinker);
arc_set_sys_free(allmem);
}
void
arc_lowmem_fini(void)
{
spl_unregister_shrinker(arc_shrinker);
arc_shrinker = NULL;
}
int
Cleanup: 64-bit kernel module parameters should use fixed width types Various module parameters such as `zfs_arc_max` were originally `uint64_t` on OpenSolaris/Illumos, but were changed to `unsigned long` for Linux compatibility because Linux's kernel default module parameter implementation did not support 64-bit types on 32-bit platforms. This caused problems when porting OpenZFS to Windows because its LLP64 memory model made `unsigned long` a 32-bit type on 64-bit, which created the undesireable situation that parameters that should accept 64-bit values could not on 64-bit Windows. Upon inspection, it turns out that the Linux kernel module parameter interface is extensible, such that we are allowed to define our own types. Rather than maintaining the original type change via hacks to to continue shrinking module parameters on 32-bit Linux, we implement support for 64-bit module parameters on Linux. After doing a review of all 64-bit kernel parameters (found via the man page and also proposed changes by Andrew Innes), the kernel module parameters fell into a few groups: Parameters that were originally 64-bit on Illumos: * dbuf_cache_max_bytes * dbuf_metadata_cache_max_bytes * l2arc_feed_min_ms * l2arc_feed_secs * l2arc_headroom * l2arc_headroom_boost * l2arc_write_boost * l2arc_write_max * metaslab_aliquot * metaslab_force_ganging * zfetch_array_rd_sz * zfs_arc_max * zfs_arc_meta_limit * zfs_arc_meta_min * zfs_arc_min * zfs_async_block_max_blocks * zfs_condense_max_obsolete_bytes * zfs_condense_min_mapping_bytes * zfs_deadman_checktime_ms * zfs_deadman_synctime_ms * zfs_initialize_chunk_size * zfs_initialize_value * zfs_lua_max_instrlimit * zfs_lua_max_memlimit * zil_slog_bulk Parameters that were originally 32-bit on Illumos: * zfs_per_txg_dirty_frees_percent Parameters that were originally `ssize_t` on Illumos: * zfs_immediate_write_sz Note that `ssize_t` is `int32_t` on 32-bit and `int64_t` on 64-bit. It has been upgraded to 64-bit. Parameters that were `long`/`unsigned long` because of Linux/FreeBSD influence: * l2arc_rebuild_blocks_min_l2size * zfs_key_max_salt_uses * zfs_max_log_walking * zfs_max_logsm_summary_length * zfs_metaslab_max_size_cache_sec * zfs_min_metaslabs_to_flush * zfs_multihost_interval * zfs_unflushed_log_block_max * zfs_unflushed_log_block_min * zfs_unflushed_log_block_pct * zfs_unflushed_max_mem_amt * zfs_unflushed_max_mem_ppm New parameters that do not exist in Illumos: * l2arc_trim_ahead * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_arc_sys_free * zfs_deadman_ziotime_ms * zfs_delete_blocks * zfs_history_output_max * zfs_livelist_max_entries * zfs_max_async_dedup_frees * zfs_max_nvlist_src_size * zfs_rebuild_max_segment * zfs_rebuild_vdev_limit * zfs_unflushed_log_txg_max * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift * zfs_vnops_read_chunk_size * zvol_max_discard_blocks Rather than clutter the lists with commentary, the module parameters that need comments are repeated below. A few parameters were defined in Linux/FreeBSD specific code, where the use of ulong/long is not an issue for portability, so we leave them alone: * zfs_delete_blocks * zfs_key_max_salt_uses * zvol_max_discard_blocks The documentation for a few parameters was found to be incorrect: * zfs_deadman_checktime_ms - incorrectly documented as int * zfs_delete_blocks - not documented as Linux only * zfs_history_output_max - incorrectly documented as int * zfs_vnops_read_chunk_size - incorrectly documented as long * zvol_max_discard_blocks - incorrectly documented as ulong The documentation for these has been fixed, alongside the changes to document the switch to fixed width types. In addition, several kernel module parameters were percentages or held ashift values, so being 64-bit never made sense for them. They have been downgraded to 32-bit: * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_per_txg_dirty_frees_percent * zfs_unflushed_log_block_pct * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift Of special note are `zfs_vdev_max_auto_ashift` and `zfs_vdev_min_auto_ashift`, which were already defined as `uint64_t`, and passed to the kernel as `ulong`. This is inherently buggy on big endian 32-bit Linux, since the values would not be written to the correct locations. 32-bit FreeBSD was unaffected because its sysctl code correctly treated this as a `uint64_t`. Lastly, a code comment suggests that `zfs_arc_sys_free` is Linux-specific, but there is nothing to indicate to me that it is Linux-specific. Nothing was done about that. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Reviewed-by: Alexander Motin <mav@FreeBSD.org> Original-patch-by: Andrew Innes <andrew.c12@gmail.com> Original-patch-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13984 Closes #14004
2022-10-03 22:06:54 +03:00
param_set_arc_u64(const char *buf, zfs_kernel_param_t *kp)
{
int error;
Cleanup: 64-bit kernel module parameters should use fixed width types Various module parameters such as `zfs_arc_max` were originally `uint64_t` on OpenSolaris/Illumos, but were changed to `unsigned long` for Linux compatibility because Linux's kernel default module parameter implementation did not support 64-bit types on 32-bit platforms. This caused problems when porting OpenZFS to Windows because its LLP64 memory model made `unsigned long` a 32-bit type on 64-bit, which created the undesireable situation that parameters that should accept 64-bit values could not on 64-bit Windows. Upon inspection, it turns out that the Linux kernel module parameter interface is extensible, such that we are allowed to define our own types. Rather than maintaining the original type change via hacks to to continue shrinking module parameters on 32-bit Linux, we implement support for 64-bit module parameters on Linux. After doing a review of all 64-bit kernel parameters (found via the man page and also proposed changes by Andrew Innes), the kernel module parameters fell into a few groups: Parameters that were originally 64-bit on Illumos: * dbuf_cache_max_bytes * dbuf_metadata_cache_max_bytes * l2arc_feed_min_ms * l2arc_feed_secs * l2arc_headroom * l2arc_headroom_boost * l2arc_write_boost * l2arc_write_max * metaslab_aliquot * metaslab_force_ganging * zfetch_array_rd_sz * zfs_arc_max * zfs_arc_meta_limit * zfs_arc_meta_min * zfs_arc_min * zfs_async_block_max_blocks * zfs_condense_max_obsolete_bytes * zfs_condense_min_mapping_bytes * zfs_deadman_checktime_ms * zfs_deadman_synctime_ms * zfs_initialize_chunk_size * zfs_initialize_value * zfs_lua_max_instrlimit * zfs_lua_max_memlimit * zil_slog_bulk Parameters that were originally 32-bit on Illumos: * zfs_per_txg_dirty_frees_percent Parameters that were originally `ssize_t` on Illumos: * zfs_immediate_write_sz Note that `ssize_t` is `int32_t` on 32-bit and `int64_t` on 64-bit. It has been upgraded to 64-bit. Parameters that were `long`/`unsigned long` because of Linux/FreeBSD influence: * l2arc_rebuild_blocks_min_l2size * zfs_key_max_salt_uses * zfs_max_log_walking * zfs_max_logsm_summary_length * zfs_metaslab_max_size_cache_sec * zfs_min_metaslabs_to_flush * zfs_multihost_interval * zfs_unflushed_log_block_max * zfs_unflushed_log_block_min * zfs_unflushed_log_block_pct * zfs_unflushed_max_mem_amt * zfs_unflushed_max_mem_ppm New parameters that do not exist in Illumos: * l2arc_trim_ahead * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_arc_sys_free * zfs_deadman_ziotime_ms * zfs_delete_blocks * zfs_history_output_max * zfs_livelist_max_entries * zfs_max_async_dedup_frees * zfs_max_nvlist_src_size * zfs_rebuild_max_segment * zfs_rebuild_vdev_limit * zfs_unflushed_log_txg_max * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift * zfs_vnops_read_chunk_size * zvol_max_discard_blocks Rather than clutter the lists with commentary, the module parameters that need comments are repeated below. A few parameters were defined in Linux/FreeBSD specific code, where the use of ulong/long is not an issue for portability, so we leave them alone: * zfs_delete_blocks * zfs_key_max_salt_uses * zvol_max_discard_blocks The documentation for a few parameters was found to be incorrect: * zfs_deadman_checktime_ms - incorrectly documented as int * zfs_delete_blocks - not documented as Linux only * zfs_history_output_max - incorrectly documented as int * zfs_vnops_read_chunk_size - incorrectly documented as long * zvol_max_discard_blocks - incorrectly documented as ulong The documentation for these has been fixed, alongside the changes to document the switch to fixed width types. In addition, several kernel module parameters were percentages or held ashift values, so being 64-bit never made sense for them. They have been downgraded to 32-bit: * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_per_txg_dirty_frees_percent * zfs_unflushed_log_block_pct * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift Of special note are `zfs_vdev_max_auto_ashift` and `zfs_vdev_min_auto_ashift`, which were already defined as `uint64_t`, and passed to the kernel as `ulong`. This is inherently buggy on big endian 32-bit Linux, since the values would not be written to the correct locations. 32-bit FreeBSD was unaffected because its sysctl code correctly treated this as a `uint64_t`. Lastly, a code comment suggests that `zfs_arc_sys_free` is Linux-specific, but there is nothing to indicate to me that it is Linux-specific. Nothing was done about that. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Reviewed-by: Alexander Motin <mav@FreeBSD.org> Original-patch-by: Andrew Innes <andrew.c12@gmail.com> Original-patch-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13984 Closes #14004
2022-10-03 22:06:54 +03:00
error = spl_param_set_u64(buf, kp);
if (error < 0)
return (SET_ERROR(error));
arc_tuning_update(B_TRUE);
return (0);
}
int
param_set_arc_min(const char *buf, zfs_kernel_param_t *kp)
{
Cleanup: 64-bit kernel module parameters should use fixed width types Various module parameters such as `zfs_arc_max` were originally `uint64_t` on OpenSolaris/Illumos, but were changed to `unsigned long` for Linux compatibility because Linux's kernel default module parameter implementation did not support 64-bit types on 32-bit platforms. This caused problems when porting OpenZFS to Windows because its LLP64 memory model made `unsigned long` a 32-bit type on 64-bit, which created the undesireable situation that parameters that should accept 64-bit values could not on 64-bit Windows. Upon inspection, it turns out that the Linux kernel module parameter interface is extensible, such that we are allowed to define our own types. Rather than maintaining the original type change via hacks to to continue shrinking module parameters on 32-bit Linux, we implement support for 64-bit module parameters on Linux. After doing a review of all 64-bit kernel parameters (found via the man page and also proposed changes by Andrew Innes), the kernel module parameters fell into a few groups: Parameters that were originally 64-bit on Illumos: * dbuf_cache_max_bytes * dbuf_metadata_cache_max_bytes * l2arc_feed_min_ms * l2arc_feed_secs * l2arc_headroom * l2arc_headroom_boost * l2arc_write_boost * l2arc_write_max * metaslab_aliquot * metaslab_force_ganging * zfetch_array_rd_sz * zfs_arc_max * zfs_arc_meta_limit * zfs_arc_meta_min * zfs_arc_min * zfs_async_block_max_blocks * zfs_condense_max_obsolete_bytes * zfs_condense_min_mapping_bytes * zfs_deadman_checktime_ms * zfs_deadman_synctime_ms * zfs_initialize_chunk_size * zfs_initialize_value * zfs_lua_max_instrlimit * zfs_lua_max_memlimit * zil_slog_bulk Parameters that were originally 32-bit on Illumos: * zfs_per_txg_dirty_frees_percent Parameters that were originally `ssize_t` on Illumos: * zfs_immediate_write_sz Note that `ssize_t` is `int32_t` on 32-bit and `int64_t` on 64-bit. It has been upgraded to 64-bit. Parameters that were `long`/`unsigned long` because of Linux/FreeBSD influence: * l2arc_rebuild_blocks_min_l2size * zfs_key_max_salt_uses * zfs_max_log_walking * zfs_max_logsm_summary_length * zfs_metaslab_max_size_cache_sec * zfs_min_metaslabs_to_flush * zfs_multihost_interval * zfs_unflushed_log_block_max * zfs_unflushed_log_block_min * zfs_unflushed_log_block_pct * zfs_unflushed_max_mem_amt * zfs_unflushed_max_mem_ppm New parameters that do not exist in Illumos: * l2arc_trim_ahead * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_arc_sys_free * zfs_deadman_ziotime_ms * zfs_delete_blocks * zfs_history_output_max * zfs_livelist_max_entries * zfs_max_async_dedup_frees * zfs_max_nvlist_src_size * zfs_rebuild_max_segment * zfs_rebuild_vdev_limit * zfs_unflushed_log_txg_max * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift * zfs_vnops_read_chunk_size * zvol_max_discard_blocks Rather than clutter the lists with commentary, the module parameters that need comments are repeated below. A few parameters were defined in Linux/FreeBSD specific code, where the use of ulong/long is not an issue for portability, so we leave them alone: * zfs_delete_blocks * zfs_key_max_salt_uses * zvol_max_discard_blocks The documentation for a few parameters was found to be incorrect: * zfs_deadman_checktime_ms - incorrectly documented as int * zfs_delete_blocks - not documented as Linux only * zfs_history_output_max - incorrectly documented as int * zfs_vnops_read_chunk_size - incorrectly documented as long * zvol_max_discard_blocks - incorrectly documented as ulong The documentation for these has been fixed, alongside the changes to document the switch to fixed width types. In addition, several kernel module parameters were percentages or held ashift values, so being 64-bit never made sense for them. They have been downgraded to 32-bit: * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_per_txg_dirty_frees_percent * zfs_unflushed_log_block_pct * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift Of special note are `zfs_vdev_max_auto_ashift` and `zfs_vdev_min_auto_ashift`, which were already defined as `uint64_t`, and passed to the kernel as `ulong`. This is inherently buggy on big endian 32-bit Linux, since the values would not be written to the correct locations. 32-bit FreeBSD was unaffected because its sysctl code correctly treated this as a `uint64_t`. Lastly, a code comment suggests that `zfs_arc_sys_free` is Linux-specific, but there is nothing to indicate to me that it is Linux-specific. Nothing was done about that. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Reviewed-by: Alexander Motin <mav@FreeBSD.org> Original-patch-by: Andrew Innes <andrew.c12@gmail.com> Original-patch-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13984 Closes #14004
2022-10-03 22:06:54 +03:00
return (param_set_arc_u64(buf, kp));
}
int
param_set_arc_max(const char *buf, zfs_kernel_param_t *kp)
{
Cleanup: 64-bit kernel module parameters should use fixed width types Various module parameters such as `zfs_arc_max` were originally `uint64_t` on OpenSolaris/Illumos, but were changed to `unsigned long` for Linux compatibility because Linux's kernel default module parameter implementation did not support 64-bit types on 32-bit platforms. This caused problems when porting OpenZFS to Windows because its LLP64 memory model made `unsigned long` a 32-bit type on 64-bit, which created the undesireable situation that parameters that should accept 64-bit values could not on 64-bit Windows. Upon inspection, it turns out that the Linux kernel module parameter interface is extensible, such that we are allowed to define our own types. Rather than maintaining the original type change via hacks to to continue shrinking module parameters on 32-bit Linux, we implement support for 64-bit module parameters on Linux. After doing a review of all 64-bit kernel parameters (found via the man page and also proposed changes by Andrew Innes), the kernel module parameters fell into a few groups: Parameters that were originally 64-bit on Illumos: * dbuf_cache_max_bytes * dbuf_metadata_cache_max_bytes * l2arc_feed_min_ms * l2arc_feed_secs * l2arc_headroom * l2arc_headroom_boost * l2arc_write_boost * l2arc_write_max * metaslab_aliquot * metaslab_force_ganging * zfetch_array_rd_sz * zfs_arc_max * zfs_arc_meta_limit * zfs_arc_meta_min * zfs_arc_min * zfs_async_block_max_blocks * zfs_condense_max_obsolete_bytes * zfs_condense_min_mapping_bytes * zfs_deadman_checktime_ms * zfs_deadman_synctime_ms * zfs_initialize_chunk_size * zfs_initialize_value * zfs_lua_max_instrlimit * zfs_lua_max_memlimit * zil_slog_bulk Parameters that were originally 32-bit on Illumos: * zfs_per_txg_dirty_frees_percent Parameters that were originally `ssize_t` on Illumos: * zfs_immediate_write_sz Note that `ssize_t` is `int32_t` on 32-bit and `int64_t` on 64-bit. It has been upgraded to 64-bit. Parameters that were `long`/`unsigned long` because of Linux/FreeBSD influence: * l2arc_rebuild_blocks_min_l2size * zfs_key_max_salt_uses * zfs_max_log_walking * zfs_max_logsm_summary_length * zfs_metaslab_max_size_cache_sec * zfs_min_metaslabs_to_flush * zfs_multihost_interval * zfs_unflushed_log_block_max * zfs_unflushed_log_block_min * zfs_unflushed_log_block_pct * zfs_unflushed_max_mem_amt * zfs_unflushed_max_mem_ppm New parameters that do not exist in Illumos: * l2arc_trim_ahead * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_arc_sys_free * zfs_deadman_ziotime_ms * zfs_delete_blocks * zfs_history_output_max * zfs_livelist_max_entries * zfs_max_async_dedup_frees * zfs_max_nvlist_src_size * zfs_rebuild_max_segment * zfs_rebuild_vdev_limit * zfs_unflushed_log_txg_max * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift * zfs_vnops_read_chunk_size * zvol_max_discard_blocks Rather than clutter the lists with commentary, the module parameters that need comments are repeated below. A few parameters were defined in Linux/FreeBSD specific code, where the use of ulong/long is not an issue for portability, so we leave them alone: * zfs_delete_blocks * zfs_key_max_salt_uses * zvol_max_discard_blocks The documentation for a few parameters was found to be incorrect: * zfs_deadman_checktime_ms - incorrectly documented as int * zfs_delete_blocks - not documented as Linux only * zfs_history_output_max - incorrectly documented as int * zfs_vnops_read_chunk_size - incorrectly documented as long * zvol_max_discard_blocks - incorrectly documented as ulong The documentation for these has been fixed, alongside the changes to document the switch to fixed width types. In addition, several kernel module parameters were percentages or held ashift values, so being 64-bit never made sense for them. They have been downgraded to 32-bit: * vdev_file_logical_ashift * vdev_file_physical_ashift * zfs_arc_dnode_limit_percent * zfs_arc_dnode_reduce_percent * zfs_arc_meta_limit_percent * zfs_per_txg_dirty_frees_percent * zfs_unflushed_log_block_pct * zfs_vdev_max_auto_ashift * zfs_vdev_min_auto_ashift Of special note are `zfs_vdev_max_auto_ashift` and `zfs_vdev_min_auto_ashift`, which were already defined as `uint64_t`, and passed to the kernel as `ulong`. This is inherently buggy on big endian 32-bit Linux, since the values would not be written to the correct locations. 32-bit FreeBSD was unaffected because its sysctl code correctly treated this as a `uint64_t`. Lastly, a code comment suggests that `zfs_arc_sys_free` is Linux-specific, but there is nothing to indicate to me that it is Linux-specific. Nothing was done about that. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Ryan Moeller <ryan@iXsystems.com> Reviewed-by: Alexander Motin <mav@FreeBSD.org> Original-patch-by: Andrew Innes <andrew.c12@gmail.com> Original-patch-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13984 Closes #14004
2022-10-03 22:06:54 +03:00
return (param_set_arc_u64(buf, kp));
}
int
param_set_arc_int(const char *buf, zfs_kernel_param_t *kp)
{
int error;
error = param_set_int(buf, kp);
if (error < 0)
return (SET_ERROR(error));
arc_tuning_update(B_TRUE);
return (0);
}
#ifdef CONFIG_MEMORY_HOTPLUG
static int
arc_hotplug_callback(struct notifier_block *self, unsigned long action,
void *arg)
{
(void) self, (void) arg;
uint64_t allmem = arc_all_memory();
if (action != MEM_ONLINE)
return (NOTIFY_OK);
arc_set_limits(allmem);
#ifdef __LP64__
if (zfs_dirty_data_max_max == 0)
zfs_dirty_data_max_max = MIN(4ULL * 1024 * 1024 * 1024,
allmem * zfs_dirty_data_max_max_percent / 100);
#else
if (zfs_dirty_data_max_max == 0)
zfs_dirty_data_max_max = MIN(1ULL * 1024 * 1024 * 1024,
allmem * zfs_dirty_data_max_max_percent / 100);
#endif
arc_set_sys_free(allmem);
return (NOTIFY_OK);
}
#endif
void
arc_register_hotplug(void)
{
#ifdef CONFIG_MEMORY_HOTPLUG
arc_hotplug_callback_mem_nb.notifier_call = arc_hotplug_callback;
/* There is no significance to the value 100 */
arc_hotplug_callback_mem_nb.priority = 100;
register_memory_notifier(&arc_hotplug_callback_mem_nb);
#endif
}
void
arc_unregister_hotplug(void)
{
#ifdef CONFIG_MEMORY_HOTPLUG
unregister_memory_notifier(&arc_hotplug_callback_mem_nb);
#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
ZFS_MODULE_PARAM(zfs_arc, zfs_arc_, shrinker_limit, INT, ZMOD_RW,
"Limit on number of pages that ARC shrinker can reclaim at once");
ZFS_MODULE_PARAM(zfs_arc, zfs_arc_, shrinker_seeks, INT, ZMOD_RD,
"Relative cost of ARC eviction vs other kernel subsystems");