mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-18 18:31:00 +03:00
fdc2d30371
In #13871, zfs_vdev_aggregation_limit_non_rotating and zfs_vdev_aggregation_limit being signed was pointed out as a possible reason not to eliminate an unnecessary MAX(unsigned, 0) since the unsigned value was assigned from them. There is no reason for these module parameters to be signed and upon inspection, it was found that there are a number of other module parameters that are signed, but should not be, so we make them unsigned. Making them unsigned made it clear that some other variables in the code should also be unsigned, so we also make those unsigned. This prevents users from setting negative values that could potentially cause bad behaviors. It also makes the code slightly easier to understand. Mostly module parameters that deal with timeouts, limits, bitshifts and percentages are made unsigned by this. Any that are boolean are left signed, since whether booleans should be considered signed or unsigned does not matter. Making zfs_arc_lotsfree_percent unsigned caused a `zfs_arc_lotsfree_percent >= 0` check to become redundant, so it was removed. Removing the check was also necessary to prevent a compiler error from -Werror=type-limits. Several end of line comments had to be moved to their own lines because replacing int with uint_t caused us to exceed the 80 character limit enforced by cstyle.pl. The following were kept signed because they are passed to taskq_create(), which expects signed values and modifying the OpenSolaris/Illumos DDI is out of scope of this patch: * metaslab_load_pct * zfs_sync_taskq_batch_pct * zfs_zil_clean_taskq_nthr_pct * zfs_zil_clean_taskq_minalloc * zfs_zil_clean_taskq_maxalloc * zfs_arc_prune_task_threads Also, negative values in those parameters was found to be harmless. The following were left signed because either negative values make sense, or more analysis was needed to determine whether negative values should be disallowed: * zfs_metaslab_switch_threshold * zfs_pd_bytes_max * zfs_livelist_min_percent_shared zfs_multihost_history was made static to be consistent with other parameters. A number of module parameters were marked as signed, but in reality referenced unsigned variables. upgrade_errlog_limit is one of the numerous examples. In the case of zfs_vdev_async_read_max_active, it was already uint32_t, but zdb had an extern int declaration for it. Interestingly, the documentation in zfs.4 was right for upgrade_errlog_limit despite the module parameter being wrongly marked, while the documentation for zfs_vdev_async_read_max_active (and friends) was wrong. It was also wrong for zstd_abort_size, which was unsigned, but was documented as signed. Also, the documentation in zfs.4 incorrectly described the following parameters as ulong when they were int: * zfs_arc_meta_adjust_restarts * zfs_override_estimate_recordsize They are now uint_t as of this patch and thus the man page has been updated to describe them as uint. dbuf_state_index was left alone since it does nothing and perhaps should be removed in another patch. If any module parameters were missed, they were not found by `grep -r 'ZFS_MODULE_PARAM' | grep ', INT'`. I did find a few that grep missed, but only because they were in files that had hits. This patch intentionally did not attempt to address whether some of these module parameters should be elevated to 64-bit parameters, because the length of a long on 32-bit is 32-bit. Lastly, it was pointed out during review that uint_t is a better match for these variables than uint32_t because FreeBSD kernel parameter definitions are designed for uint_t, whose bit width can change in future memory models. As a result, we change the existing parameters that are uint32_t to use uint_t. Reviewed-by: Alexander Motin <mav@FreeBSD.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Neal Gompa <ngompa@datto.com> Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu> Closes #13875
261 lines
6.6 KiB
C
261 lines
6.6 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or https://opensource.org/licenses/CDDL-1.0.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/spa_impl.h>
|
|
#include <sys/counter.h>
|
|
#include <sys/zio_compress.h>
|
|
#include <sys/zio_checksum.h>
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/arc.h>
|
|
#include <sys/arc_os.h>
|
|
#include <sys/zfs_refcount.h>
|
|
#include <sys/vdev.h>
|
|
#include <sys/vdev_trim.h>
|
|
#include <sys/vdev_impl.h>
|
|
#include <sys/dsl_pool.h>
|
|
#include <sys/zio_checksum.h>
|
|
#include <sys/multilist.h>
|
|
#include <sys/abd.h>
|
|
#include <sys/zil.h>
|
|
#include <sys/fm/fs/zfs.h>
|
|
#include <sys/eventhandler.h>
|
|
#include <sys/callb.h>
|
|
#include <sys/kstat.h>
|
|
#include <sys/zthr.h>
|
|
#include <zfs_fletcher.h>
|
|
#include <sys/arc_impl.h>
|
|
#include <sys/sdt.h>
|
|
#include <sys/aggsum.h>
|
|
#include <sys/vnode.h>
|
|
#include <cityhash.h>
|
|
#include <machine/vmparam.h>
|
|
#include <sys/vm.h>
|
|
#include <sys/vmmeter.h>
|
|
|
|
#if __FreeBSD_version >= 1300139
|
|
static struct sx arc_vnlru_lock;
|
|
static struct vnode *arc_vnlru_marker;
|
|
#endif
|
|
|
|
extern struct vfsops zfs_vfsops;
|
|
|
|
uint_t zfs_arc_free_target = 0;
|
|
|
|
static void
|
|
arc_free_target_init(void *unused __unused)
|
|
{
|
|
zfs_arc_free_target = vm_cnt.v_free_target;
|
|
}
|
|
SYSINIT(arc_free_target_init, SI_SUB_KTHREAD_PAGE, SI_ORDER_ANY,
|
|
arc_free_target_init, NULL);
|
|
|
|
/*
|
|
* We don't have a tunable for arc_free_target due to the dependency on
|
|
* pagedaemon initialisation.
|
|
*/
|
|
ZFS_MODULE_PARAM_CALL(zfs_arc, zfs_arc_, free_target,
|
|
param_set_arc_free_target, 0, CTLFLAG_RW,
|
|
"Desired number of free pages below which ARC triggers reclaim");
|
|
ZFS_MODULE_PARAM_CALL(zfs_arc, zfs_arc_, no_grow_shift,
|
|
param_set_arc_no_grow_shift, 0, ZMOD_RW,
|
|
"log2(fraction of ARC which must be free to allow growing)");
|
|
|
|
int64_t
|
|
arc_available_memory(void)
|
|
{
|
|
int64_t lowest = INT64_MAX;
|
|
int64_t n __unused;
|
|
|
|
/*
|
|
* Cooperate with pagedaemon when it's time for it to scan
|
|
* and reclaim some pages.
|
|
*/
|
|
n = PAGESIZE * ((int64_t)freemem - zfs_arc_free_target);
|
|
if (n < lowest) {
|
|
lowest = n;
|
|
}
|
|
#if defined(__i386) || !defined(UMA_MD_SMALL_ALLOC)
|
|
/*
|
|
* If we're on an i386 platform, it's possible that we'll exhaust the
|
|
* kernel heap space before we ever run out of available physical
|
|
* memory. Most checks of the size of the heap_area compare against
|
|
* tune.t_minarmem, which is the minimum available real memory that we
|
|
* can have in the system. However, this is generally fixed at 25 pages
|
|
* which is so low that it's useless. In this comparison, we seek to
|
|
* calculate the total heap-size, and reclaim if more than 3/4ths of the
|
|
* heap is allocated. (Or, in the calculation, if less than 1/4th is
|
|
* free)
|
|
*/
|
|
n = uma_avail() - (long)(uma_limit() / 4);
|
|
if (n < lowest) {
|
|
lowest = n;
|
|
}
|
|
#endif
|
|
|
|
DTRACE_PROBE1(arc__available_memory, int64_t, lowest);
|
|
return (lowest);
|
|
}
|
|
|
|
/*
|
|
* Return a default max arc size based on the amount of physical memory.
|
|
*/
|
|
uint64_t
|
|
arc_default_max(uint64_t min, uint64_t allmem)
|
|
{
|
|
uint64_t size;
|
|
|
|
if (allmem >= 1 << 30)
|
|
size = allmem - (1 << 30);
|
|
else
|
|
size = min;
|
|
return (MAX(allmem * 5 / 8, size));
|
|
}
|
|
|
|
/*
|
|
* Helper function for arc_prune_async() it is responsible for safely
|
|
* handling the execution of a registered arc_prune_func_t.
|
|
*/
|
|
static void
|
|
arc_prune_task(void *arg)
|
|
{
|
|
uint64_t nr_scan = (uintptr_t)arg;
|
|
|
|
arc_reduce_target_size(ptob(nr_scan));
|
|
|
|
#ifndef __ILP32__
|
|
if (nr_scan > INT_MAX)
|
|
nr_scan = INT_MAX;
|
|
#endif
|
|
|
|
#if __FreeBSD_version >= 1300139
|
|
sx_xlock(&arc_vnlru_lock);
|
|
vnlru_free_vfsops(nr_scan, &zfs_vfsops, arc_vnlru_marker);
|
|
sx_xunlock(&arc_vnlru_lock);
|
|
#else
|
|
vnlru_free(nr_scan, &zfs_vfsops);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Notify registered consumers they must drop holds on a portion of the ARC
|
|
* buffered they reference. This provides a mechanism to ensure the ARC can
|
|
* honor the arc_meta_limit and reclaim otherwise pinned ARC buffers. This
|
|
* is analogous to dnlc_reduce_cache() but more generic.
|
|
*
|
|
* This operation is performed asynchronously so it may be safely called
|
|
* in the context of the arc_reclaim_thread(). A reference is taken here
|
|
* for each registered arc_prune_t and the arc_prune_task() is responsible
|
|
* for releasing it once the registered arc_prune_func_t has completed.
|
|
*/
|
|
void
|
|
arc_prune_async(uint64_t adjust)
|
|
{
|
|
|
|
#ifndef __LP64__
|
|
if (adjust > UINTPTR_MAX)
|
|
adjust = UINTPTR_MAX;
|
|
#endif
|
|
taskq_dispatch(arc_prune_taskq, arc_prune_task,
|
|
(void *)(intptr_t)adjust, TQ_SLEEP);
|
|
ARCSTAT_BUMP(arcstat_prune);
|
|
}
|
|
|
|
uint64_t
|
|
arc_all_memory(void)
|
|
{
|
|
return (ptob(physmem));
|
|
}
|
|
|
|
int
|
|
arc_memory_throttle(spa_t *spa, uint64_t reserve, uint64_t txg)
|
|
{
|
|
return (0);
|
|
}
|
|
|
|
uint64_t
|
|
arc_free_memory(void)
|
|
{
|
|
return (ptob(freemem));
|
|
}
|
|
|
|
static eventhandler_tag arc_event_lowmem = NULL;
|
|
|
|
static void
|
|
arc_lowmem(void *arg __unused, int howto __unused)
|
|
{
|
|
int64_t free_memory, to_free;
|
|
|
|
arc_no_grow = B_TRUE;
|
|
arc_warm = B_TRUE;
|
|
arc_growtime = gethrtime() + SEC2NSEC(arc_grow_retry);
|
|
free_memory = arc_available_memory();
|
|
int64_t can_free = arc_c - arc_c_min;
|
|
if (can_free <= 0)
|
|
return;
|
|
to_free = (can_free >> arc_shrink_shift) - MIN(free_memory, 0);
|
|
DTRACE_PROBE2(arc__needfree, int64_t, free_memory, int64_t, to_free);
|
|
arc_reduce_target_size(to_free);
|
|
|
|
/*
|
|
* It is unsafe to block here in arbitrary threads, because we can come
|
|
* here from ARC itself and may hold ARC locks and thus risk a deadlock
|
|
* with ARC reclaim thread.
|
|
*/
|
|
if (curproc == pageproc)
|
|
arc_wait_for_eviction(to_free, B_FALSE);
|
|
}
|
|
|
|
void
|
|
arc_lowmem_init(void)
|
|
{
|
|
arc_event_lowmem = EVENTHANDLER_REGISTER(vm_lowmem, arc_lowmem, NULL,
|
|
EVENTHANDLER_PRI_FIRST);
|
|
#if __FreeBSD_version >= 1300139
|
|
arc_vnlru_marker = vnlru_alloc_marker();
|
|
sx_init(&arc_vnlru_lock, "arc vnlru lock");
|
|
#endif
|
|
}
|
|
|
|
void
|
|
arc_lowmem_fini(void)
|
|
{
|
|
if (arc_event_lowmem != NULL)
|
|
EVENTHANDLER_DEREGISTER(vm_lowmem, arc_event_lowmem);
|
|
#if __FreeBSD_version >= 1300139
|
|
if (arc_vnlru_marker != NULL) {
|
|
vnlru_free_marker(arc_vnlru_marker);
|
|
sx_destroy(&arc_vnlru_lock);
|
|
}
|
|
#endif
|
|
}
|
|
|
|
void
|
|
arc_register_hotplug(void)
|
|
{
|
|
}
|
|
|
|
void
|
|
arc_unregister_hotplug(void)
|
|
{
|
|
}
|