mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 19:39:35 +03:00
ab8d9c1783
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
76 lines
2.4 KiB
C
76 lines
2.4 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* This file and its contents are supplied under the terms of the
|
|
* Common Development and Distribution License ("CDDL"), version 1.0.
|
|
* You may only use this file in accordance with the terms of version
|
|
* 1.0 of the CDDL.
|
|
*
|
|
* A full copy of the text of the CDDL should have accompanied this
|
|
* source. A copy of the CDDL is also available via the Internet at
|
|
* http://www.illumos.org/license/CDDL.
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright (C) 2017 by Lawrence Livermore National Security, LLC.
|
|
*/
|
|
|
|
#ifndef _SYS_MMP_H
|
|
#define _SYS_MMP_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/uberblock_impl.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define MMP_MIN_INTERVAL 100 /* ms */
|
|
#define MMP_DEFAULT_INTERVAL 1000 /* ms */
|
|
#define MMP_DEFAULT_IMPORT_INTERVALS 20
|
|
#define MMP_DEFAULT_FAIL_INTERVALS 10
|
|
#define MMP_MIN_FAIL_INTERVALS 2 /* min if != 0 */
|
|
#define MMP_IMPORT_SAFETY_FACTOR 200 /* pct */
|
|
#define MMP_INTERVAL_OK(interval) MAX(interval, MMP_MIN_INTERVAL)
|
|
#define MMP_FAIL_INTVS_OK(fails) (fails == 0 ? 0 : MAX(fails, \
|
|
MMP_MIN_FAIL_INTERVALS))
|
|
|
|
typedef struct mmp_thread {
|
|
kmutex_t mmp_thread_lock; /* protect thread mgmt fields */
|
|
kcondvar_t mmp_thread_cv;
|
|
kthread_t *mmp_thread;
|
|
uint8_t mmp_thread_exiting;
|
|
kmutex_t mmp_io_lock; /* protect below */
|
|
hrtime_t mmp_last_write; /* last successful MMP write */
|
|
uint64_t mmp_delay; /* decaying avg ns between MMP writes */
|
|
uberblock_t mmp_ub; /* last ub written by sync */
|
|
zio_t *mmp_zio_root; /* root of mmp write zios */
|
|
uint64_t mmp_kstat_id; /* unique id for next MMP write kstat */
|
|
int mmp_skip_error; /* reason for last skipped write */
|
|
vdev_t *mmp_last_leaf; /* last mmp write sent here */
|
|
uint64_t mmp_leaf_last_gen; /* last mmp write sent here */
|
|
uint32_t mmp_seq; /* intra-second update counter */
|
|
} mmp_thread_t;
|
|
|
|
|
|
extern void mmp_init(struct spa *spa);
|
|
extern void mmp_fini(struct spa *spa);
|
|
extern void mmp_thread_start(struct spa *spa);
|
|
extern void mmp_thread_stop(struct spa *spa);
|
|
extern void mmp_update_uberblock(struct spa *spa, struct uberblock *ub);
|
|
extern void mmp_signal_all_threads(void);
|
|
|
|
/* Global tuning */
|
|
extern int param_set_multihost_interval(ZFS_MODULE_PARAM_ARGS);
|
|
extern uint64_t zfs_multihost_interval;
|
|
extern uint_t zfs_multihost_fail_intervals;
|
|
extern uint_t zfs_multihost_import_intervals;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_MMP_H */
|