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
195 lines
4.9 KiB
C
195 lines
4.9 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) 2016, 2018 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_ZCP_H
|
|
#define _SYS_ZCP_H
|
|
|
|
#include <sys/dmu_tx.h>
|
|
#include <sys/dsl_pool.h>
|
|
|
|
#include <sys/lua/lua.h>
|
|
#include <sys/lua/lualib.h>
|
|
#include <sys/lua/lauxlib.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define ZCP_RUN_INFO_KEY "runinfo"
|
|
|
|
extern uint64_t zfs_lua_max_instrlimit;
|
|
extern uint64_t zfs_lua_max_memlimit;
|
|
|
|
int zcp_argerror(lua_State *, int, const char *, ...);
|
|
|
|
int zcp_eval(const char *, const char *, boolean_t, uint64_t, uint64_t,
|
|
nvpair_t *, nvlist_t *);
|
|
|
|
int zcp_load_list_lib(lua_State *);
|
|
|
|
int zcp_load_synctask_lib(lua_State *, boolean_t);
|
|
|
|
typedef void (zcp_cleanup_t)(void *);
|
|
typedef struct zcp_cleanup_handler {
|
|
zcp_cleanup_t *zch_cleanup_func;
|
|
void *zch_cleanup_arg;
|
|
list_node_t zch_node;
|
|
} zcp_cleanup_handler_t;
|
|
|
|
typedef struct zcp_alloc_arg {
|
|
boolean_t aa_must_succeed;
|
|
int64_t aa_alloc_remaining;
|
|
int64_t aa_alloc_limit;
|
|
} zcp_alloc_arg_t;
|
|
|
|
typedef struct zcp_run_info {
|
|
dsl_pool_t *zri_pool;
|
|
|
|
/*
|
|
* An estimate of the total amount of space consumed by all
|
|
* synctasks we have successfully performed so far in this
|
|
* channel program. Used to generate ENOSPC errors for syncfuncs.
|
|
*/
|
|
int zri_space_used;
|
|
|
|
/*
|
|
* The credentials of the thread which originally invoked the channel
|
|
* program. Since channel programs are always invoked from the synctask
|
|
* thread they should always do permissions checks against this cred
|
|
* rather than the 'current' thread's.
|
|
*/
|
|
cred_t *zri_cred;
|
|
proc_t *zri_proc;
|
|
|
|
/*
|
|
* The tx in which this channel program is running.
|
|
*/
|
|
dmu_tx_t *zri_tx;
|
|
|
|
/*
|
|
* The maximum number of Lua instructions the channel program is allowed
|
|
* to execute. If it takes longer than this it will time out. A value
|
|
* of 0 indicates no instruction limit.
|
|
*/
|
|
uint64_t zri_maxinstrs;
|
|
|
|
/*
|
|
* The number of Lua instructions the channel program has executed.
|
|
*/
|
|
uint64_t zri_curinstrs;
|
|
|
|
/*
|
|
* Boolean indicating whether or not the channel program exited
|
|
* because it timed out.
|
|
*/
|
|
boolean_t zri_timed_out;
|
|
|
|
/*
|
|
* Channel program was canceled by user
|
|
*/
|
|
boolean_t zri_canceled;
|
|
|
|
/*
|
|
* Boolean indicating whether or not we are running in syncing
|
|
* context.
|
|
*/
|
|
boolean_t zri_sync;
|
|
|
|
/*
|
|
* List of currently registered cleanup handlers, which will be
|
|
* triggered in the event of a fatal error.
|
|
*/
|
|
list_t zri_cleanup_handlers;
|
|
|
|
/*
|
|
* The Lua state context of our channel program.
|
|
*/
|
|
lua_State *zri_state;
|
|
|
|
/*
|
|
* Lua memory allocator arguments.
|
|
*/
|
|
zcp_alloc_arg_t *zri_allocargs;
|
|
|
|
/*
|
|
* Contains output values from zcp script or error string.
|
|
*/
|
|
nvlist_t *zri_outnvl;
|
|
|
|
/*
|
|
* The keys of this nvlist are datasets which may be zvols and may need
|
|
* to have device minor nodes created. This information is passed from
|
|
* syncing context (where the zvol is created) to open context (where we
|
|
* create the minor nodes).
|
|
*/
|
|
nvlist_t *zri_new_zvols;
|
|
|
|
/*
|
|
* The errno number returned to caller of zcp_eval().
|
|
*/
|
|
int zri_result;
|
|
} zcp_run_info_t;
|
|
|
|
zcp_run_info_t *zcp_run_info(lua_State *);
|
|
zcp_cleanup_handler_t *zcp_register_cleanup(lua_State *, zcp_cleanup_t, void *);
|
|
void zcp_deregister_cleanup(lua_State *, zcp_cleanup_handler_t *);
|
|
void zcp_cleanup(lua_State *);
|
|
|
|
/*
|
|
* Argument parsing routines for channel program callback functions.
|
|
*/
|
|
typedef struct zcp_arg {
|
|
/*
|
|
* The name of this argument. For keyword arguments this is the name
|
|
* functions will use to set the argument. For positional arguments
|
|
* the name has no programmatic meaning, but will appear in error
|
|
* messages and help output.
|
|
*/
|
|
const char *za_name;
|
|
|
|
/*
|
|
* The Lua type this argument should have (e.g. LUA_TSTRING,
|
|
* LUA_TBOOLEAN) see the lua_type() function documentation for a
|
|
* complete list. Calling a function with an argument that does
|
|
* not match the expected type will result in the program terminating.
|
|
*/
|
|
const int za_lua_type;
|
|
} zcp_arg_t;
|
|
|
|
void zcp_parse_args(lua_State *, const char *, const zcp_arg_t *,
|
|
const zcp_arg_t *);
|
|
int zcp_nvlist_to_lua(lua_State *, nvlist_t *, char *, int);
|
|
int zcp_dataset_hold_error(lua_State *, dsl_pool_t *, const char *, int);
|
|
struct dsl_dataset *zcp_dataset_hold(lua_State *, dsl_pool_t *,
|
|
const char *, const void *);
|
|
|
|
typedef int (zcp_lib_func_t)(lua_State *);
|
|
typedef struct zcp_lib_info {
|
|
const char *name;
|
|
zcp_lib_func_t *func;
|
|
const zcp_arg_t pargs[4];
|
|
const zcp_arg_t kwargs[2];
|
|
} zcp_lib_info_t;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_ZCP_H */
|