mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 18:11:00 +03:00
379ca9cf2b
Add multihost=on|off pool property to control MMP. When enabled a new thread writes uberblocks to the last slot in each label, at a set frequency, to indicate to other hosts the pool is actively imported. These uberblocks are the last synced uberblock with an updated timestamp. Property defaults to off. During tryimport, find the "best" uberblock (newest txg and timestamp) repeatedly, checking for change in the found uberblock. Include the results of the activity test in the config returned by tryimport. These results are reported to user in "zpool import". Allow the user to control the period between MMP writes, and the duration of the activity test on import, via a new module parameter zfs_multihost_interval. The period is specified in milliseconds. The activity test duration is calculated from this value, and from the mmp_delay in the "best" uberblock found initially. Add a kstat interface to export statistics about Multiple Modifier Protection (MMP) updates. Include the last synced txg number, the timestamp, the delay since the last MMP update, the VDEV GUID, the VDEV label that received the last MMP update, and the VDEV path. Abbreviated output below. $ cat /proc/spl/kstat/zfs/mypool/multihost 31 0 0x01 10 880 105092382393521 105144180101111 txg timestamp mmp_delay vdev_guid vdev_label vdev_path 20468 261337 250274925 68396651780 3 /dev/sda 20468 261339 252023374 6267402363293 1 /dev/sdc 20468 261340 252000858 6698080955233 1 /dev/sdx 20468 261341 251980635 783892869810 2 /dev/sdy 20468 261342 253385953 8923255792467 3 /dev/sdd 20468 261344 253336622 042125143176 0 /dev/sdab 20468 261345 253310522 1200778101278 2 /dev/sde 20468 261346 253286429 0950576198362 2 /dev/sdt 20468 261347 253261545 96209817917 3 /dev/sds 20468 261349 253238188 8555725937673 3 /dev/sdb Add a new tunable zfs_multihost_history to specify the number of MMP updates to store history for. By default it is set to zero meaning that no MMP statistics are stored. When using ztest to generate activity, for automated tests of the MMP function, some test functions interfere with the test. For example, the pool is exported to run zdb and then imported again. Add a new ztest function, "-M", to alter ztest behavior to prevent this. Add new tests to verify the new functionality. Tests provided by Giuseppe Di Natale. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Giuseppe Di Natale <dinatale2@llnl.gov> Reviewed-by: Ned Bass <bass6@llnl.gov> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Closes #745 Closes #6279
218 lines
6.5 KiB
C
218 lines
6.5 KiB
C
/*
|
|
* CDDL HEADER SART
|
|
*
|
|
* 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 http://www.opensolaris.org/os/licensing.
|
|
* 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) 2011, 2015 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _LIBZFS_IMPL_H
|
|
#define _LIBZFS_IMPL_H
|
|
|
|
#include <sys/fs/zfs.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/nvpair.h>
|
|
#include <sys/dmu.h>
|
|
#include <sys/zfs_ioctl.h>
|
|
|
|
#include <libuutil.h>
|
|
#include <libzfs.h>
|
|
#include <libshare.h>
|
|
#include <libzfs_core.h>
|
|
|
|
#if defined(HAVE_LIBTOPO)
|
|
#include <fm/libtopo.h>
|
|
#endif /* HAVE_LIBTOPO */
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
typedef struct libzfs_fru {
|
|
char *zf_device;
|
|
char *zf_fru;
|
|
struct libzfs_fru *zf_chain;
|
|
struct libzfs_fru *zf_next;
|
|
} libzfs_fru_t;
|
|
|
|
struct libzfs_handle {
|
|
int libzfs_error;
|
|
int libzfs_fd;
|
|
FILE *libzfs_mnttab;
|
|
FILE *libzfs_sharetab;
|
|
zpool_handle_t *libzfs_pool_handles;
|
|
uu_avl_pool_t *libzfs_ns_avlpool;
|
|
uu_avl_t *libzfs_ns_avl;
|
|
uint64_t libzfs_ns_gen;
|
|
int libzfs_desc_active;
|
|
char libzfs_action[1024];
|
|
char libzfs_desc[1024];
|
|
int libzfs_printerr;
|
|
int libzfs_storeerr; /* stuff error messages into buffer */
|
|
void *libzfs_sharehdl; /* libshare handle */
|
|
uint_t libzfs_shareflags;
|
|
boolean_t libzfs_mnttab_enable;
|
|
avl_tree_t libzfs_mnttab_cache;
|
|
int libzfs_pool_iter;
|
|
#if defined(HAVE_LIBTOPO)
|
|
topo_hdl_t *libzfs_topo_hdl;
|
|
libzfs_fru_t **libzfs_fru_hash;
|
|
libzfs_fru_t *libzfs_fru_list;
|
|
#endif /* HAVE_LIBTOPO */
|
|
char libzfs_chassis_id[256];
|
|
};
|
|
|
|
#define ZFSSHARE_MISS 0x01 /* Didn't find entry in cache */
|
|
|
|
struct zfs_handle {
|
|
libzfs_handle_t *zfs_hdl;
|
|
zpool_handle_t *zpool_hdl;
|
|
char zfs_name[ZFS_MAX_DATASET_NAME_LEN];
|
|
zfs_type_t zfs_type; /* type including snapshot */
|
|
zfs_type_t zfs_head_type; /* type excluding snapshot */
|
|
dmu_objset_stats_t zfs_dmustats;
|
|
nvlist_t *zfs_props;
|
|
nvlist_t *zfs_user_props;
|
|
nvlist_t *zfs_recvd_props;
|
|
boolean_t zfs_mntcheck;
|
|
char *zfs_mntopts;
|
|
uint8_t *zfs_props_table;
|
|
};
|
|
|
|
/*
|
|
* This is different from checking zfs_type, because it will also catch
|
|
* snapshots of volumes.
|
|
*/
|
|
#define ZFS_IS_VOLUME(zhp) ((zhp)->zfs_head_type == ZFS_TYPE_VOLUME)
|
|
|
|
struct zpool_handle {
|
|
libzfs_handle_t *zpool_hdl;
|
|
zpool_handle_t *zpool_next;
|
|
char zpool_name[ZFS_MAX_DATASET_NAME_LEN];
|
|
int zpool_state;
|
|
size_t zpool_config_size;
|
|
nvlist_t *zpool_config;
|
|
nvlist_t *zpool_old_config;
|
|
nvlist_t *zpool_props;
|
|
diskaddr_t zpool_start_block;
|
|
};
|
|
|
|
typedef enum {
|
|
PROTO_NFS = 0,
|
|
PROTO_SMB = 1,
|
|
PROTO_END = 2
|
|
} zfs_share_proto_t;
|
|
|
|
/*
|
|
* The following can be used as a bitmask and any new values
|
|
* added must preserve that capability.
|
|
*/
|
|
typedef enum {
|
|
SHARED_NOT_SHARED = 0x0,
|
|
SHARED_NFS = 0x2,
|
|
SHARED_SMB = 0x4
|
|
} zfs_share_type_t;
|
|
|
|
#define CONFIG_BUF_MINSIZE 262144
|
|
|
|
int zfs_error(libzfs_handle_t *, int, const char *);
|
|
int zfs_error_fmt(libzfs_handle_t *, int, const char *, ...);
|
|
void zfs_error_aux(libzfs_handle_t *, const char *, ...);
|
|
void *zfs_alloc(libzfs_handle_t *, size_t);
|
|
void *zfs_realloc(libzfs_handle_t *, void *, size_t, size_t);
|
|
char *zfs_asprintf(libzfs_handle_t *, const char *, ...);
|
|
char *zfs_strdup(libzfs_handle_t *, const char *);
|
|
int no_memory(libzfs_handle_t *);
|
|
|
|
int zfs_standard_error(libzfs_handle_t *, int, const char *);
|
|
int zfs_standard_error_fmt(libzfs_handle_t *, int, const char *, ...);
|
|
int zpool_standard_error(libzfs_handle_t *, int, const char *);
|
|
int zpool_standard_error_fmt(libzfs_handle_t *, int, const char *, ...);
|
|
|
|
zfs_handle_t *make_dataset_handle_zc(libzfs_handle_t *, zfs_cmd_t *);
|
|
zfs_handle_t *make_dataset_simple_handle_zc(zfs_handle_t *, zfs_cmd_t *);
|
|
|
|
int zprop_parse_value(libzfs_handle_t *, nvpair_t *, int, zfs_type_t,
|
|
nvlist_t *, char **, uint64_t *, const char *);
|
|
int zprop_expand_list(libzfs_handle_t *hdl, zprop_list_t **plp,
|
|
zfs_type_t type);
|
|
|
|
/*
|
|
* Use this changelist_gather() flag to force attempting mounts
|
|
* on each change node regardless of whether or not it is currently
|
|
* mounted.
|
|
*/
|
|
#define CL_GATHER_MOUNT_ALWAYS 1
|
|
|
|
typedef struct prop_changelist prop_changelist_t;
|
|
|
|
int zcmd_alloc_dst_nvlist(libzfs_handle_t *, zfs_cmd_t *, size_t);
|
|
int zcmd_write_src_nvlist(libzfs_handle_t *, zfs_cmd_t *, nvlist_t *);
|
|
int zcmd_write_conf_nvlist(libzfs_handle_t *, zfs_cmd_t *, nvlist_t *);
|
|
int zcmd_expand_dst_nvlist(libzfs_handle_t *, zfs_cmd_t *);
|
|
int zcmd_read_dst_nvlist(libzfs_handle_t *, zfs_cmd_t *, nvlist_t **);
|
|
void zcmd_free_nvlists(zfs_cmd_t *);
|
|
|
|
int changelist_prefix(prop_changelist_t *);
|
|
int changelist_postfix(prop_changelist_t *);
|
|
void changelist_rename(prop_changelist_t *, const char *, const char *);
|
|
void changelist_remove(prop_changelist_t *, const char *);
|
|
void changelist_free(prop_changelist_t *);
|
|
prop_changelist_t *changelist_gather(zfs_handle_t *, zfs_prop_t, int, int);
|
|
int changelist_unshare(prop_changelist_t *, zfs_share_proto_t *);
|
|
int changelist_haszonedchild(prop_changelist_t *);
|
|
|
|
void remove_mountpoint(zfs_handle_t *);
|
|
int create_parents(libzfs_handle_t *, char *, int);
|
|
boolean_t isa_child_of(const char *dataset, const char *parent);
|
|
|
|
zfs_handle_t *make_dataset_handle(libzfs_handle_t *, const char *);
|
|
zfs_handle_t *make_bookmark_handle(zfs_handle_t *, const char *,
|
|
nvlist_t *props);
|
|
|
|
int zpool_open_silent(libzfs_handle_t *, const char *, zpool_handle_t **);
|
|
|
|
boolean_t zpool_name_valid(libzfs_handle_t *, boolean_t, const char *);
|
|
|
|
int zfs_validate_name(libzfs_handle_t *hdl, const char *path, int type,
|
|
boolean_t modifying);
|
|
|
|
void namespace_clear(libzfs_handle_t *);
|
|
|
|
/*
|
|
* libshare (sharemgr) interfaces used internally.
|
|
*/
|
|
|
|
extern int zfs_init_libshare(libzfs_handle_t *, int);
|
|
extern void zfs_uninit_libshare(libzfs_handle_t *);
|
|
extern int zfs_parse_options(char *, zfs_share_proto_t);
|
|
|
|
extern int zfs_unshare_proto(zfs_handle_t *,
|
|
const char *, zfs_share_proto_t *);
|
|
|
|
extern void libzfs_fru_clear(libzfs_handle_t *, boolean_t);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _LIBZFS_IMPL_H */
|