mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 11:29:36 +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
184 lines
5.7 KiB
C
184 lines
5.7 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 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) 2013, 2017 by Delphix. All rights reserved.
|
|
* Copyright 2016 Nexenta Systems, Inc. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_DSL_POOL_H
|
|
#define _SYS_DSL_POOL_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/txg.h>
|
|
#include <sys/txg_impl.h>
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/dnode.h>
|
|
#include <sys/ddt.h>
|
|
#include <sys/arc.h>
|
|
#include <sys/bpobj.h>
|
|
#include <sys/bptree.h>
|
|
#include <sys/rrwlock.h>
|
|
#include <sys/mmp.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
extern int zfs_txg_synctime_ms;
|
|
|
|
struct objset;
|
|
struct dsl_dir;
|
|
struct dsl_dataset;
|
|
struct dsl_pool;
|
|
struct dmu_tx;
|
|
struct dsl_scan;
|
|
|
|
extern unsigned long zfs_dirty_data_max;
|
|
extern unsigned long zfs_dirty_data_max_max;
|
|
extern unsigned long zfs_dirty_data_sync;
|
|
extern int zfs_dirty_data_max_percent;
|
|
extern int zfs_dirty_data_max_max_percent;
|
|
extern int zfs_delay_min_dirty_percent;
|
|
extern unsigned long zfs_delay_scale;
|
|
|
|
/* These macros are for indexing into the zfs_all_blkstats_t. */
|
|
#define DMU_OT_DEFERRED DMU_OT_NONE
|
|
#define DMU_OT_OTHER DMU_OT_NUMTYPES /* place holder for DMU_OT() types */
|
|
#define DMU_OT_TOTAL (DMU_OT_NUMTYPES + 1)
|
|
|
|
typedef struct zfs_blkstat {
|
|
uint64_t zb_count;
|
|
uint64_t zb_asize;
|
|
uint64_t zb_lsize;
|
|
uint64_t zb_psize;
|
|
uint64_t zb_gangs;
|
|
uint64_t zb_ditto_2_of_2_samevdev;
|
|
uint64_t zb_ditto_2_of_3_samevdev;
|
|
uint64_t zb_ditto_3_of_3_samevdev;
|
|
} zfs_blkstat_t;
|
|
|
|
typedef struct zfs_all_blkstats {
|
|
zfs_blkstat_t zab_type[DN_MAX_LEVELS + 1][DMU_OT_TOTAL + 1];
|
|
} zfs_all_blkstats_t;
|
|
|
|
|
|
typedef struct dsl_pool {
|
|
/* Immutable */
|
|
spa_t *dp_spa;
|
|
struct objset *dp_meta_objset;
|
|
struct dsl_dir *dp_root_dir;
|
|
struct dsl_dir *dp_mos_dir;
|
|
struct dsl_dir *dp_free_dir;
|
|
struct dsl_dir *dp_leak_dir;
|
|
struct dsl_dataset *dp_origin_snap;
|
|
uint64_t dp_root_dir_obj;
|
|
struct taskq *dp_iput_taskq;
|
|
|
|
/* No lock needed - sync context only */
|
|
blkptr_t dp_meta_rootbp;
|
|
uint64_t dp_tmp_userrefs_obj;
|
|
bpobj_t dp_free_bpobj;
|
|
uint64_t dp_bptree_obj;
|
|
uint64_t dp_empty_bpobj;
|
|
|
|
struct dsl_scan *dp_scan;
|
|
|
|
/* Uses dp_lock */
|
|
kmutex_t dp_lock;
|
|
kcondvar_t dp_spaceavail_cv;
|
|
uint64_t dp_dirty_pertxg[TXG_SIZE];
|
|
uint64_t dp_dirty_total;
|
|
uint64_t dp_long_free_dirty_pertxg[TXG_SIZE];
|
|
uint64_t dp_mos_used_delta;
|
|
uint64_t dp_mos_compressed_delta;
|
|
uint64_t dp_mos_uncompressed_delta;
|
|
|
|
/*
|
|
* Time of most recently scheduled (furthest in the future)
|
|
* wakeup for delayed transactions.
|
|
*/
|
|
hrtime_t dp_last_wakeup;
|
|
|
|
/* Has its own locking */
|
|
tx_state_t dp_tx;
|
|
txg_list_t dp_dirty_datasets;
|
|
txg_list_t dp_dirty_zilogs;
|
|
txg_list_t dp_dirty_dirs;
|
|
txg_list_t dp_sync_tasks;
|
|
taskq_t *dp_sync_taskq;
|
|
|
|
/*
|
|
* Protects administrative changes (properties, namespace)
|
|
*
|
|
* It is only held for write in syncing context. Therefore
|
|
* syncing context does not need to ever have it for read, since
|
|
* nobody else could possibly have it for write.
|
|
*/
|
|
rrwlock_t dp_config_rwlock;
|
|
|
|
zfs_all_blkstats_t *dp_blkstats;
|
|
} dsl_pool_t;
|
|
|
|
int dsl_pool_init(spa_t *spa, uint64_t txg, dsl_pool_t **dpp);
|
|
int dsl_pool_open(dsl_pool_t *dp);
|
|
void dsl_pool_close(dsl_pool_t *dp);
|
|
dsl_pool_t *dsl_pool_create(spa_t *spa, nvlist_t *zplprops, uint64_t txg);
|
|
void dsl_pool_sync(dsl_pool_t *dp, uint64_t txg);
|
|
void dsl_pool_sync_done(dsl_pool_t *dp, uint64_t txg);
|
|
int dsl_pool_sync_context(dsl_pool_t *dp);
|
|
uint64_t dsl_pool_adjustedsize(dsl_pool_t *dp, boolean_t netfree);
|
|
uint64_t dsl_pool_adjustedfree(dsl_pool_t *dp, boolean_t netfree);
|
|
void dsl_pool_dirty_space(dsl_pool_t *dp, int64_t space, dmu_tx_t *tx);
|
|
void dsl_pool_undirty_space(dsl_pool_t *dp, int64_t space, uint64_t txg);
|
|
void dsl_free(dsl_pool_t *dp, uint64_t txg, const blkptr_t *bpp);
|
|
void dsl_free_sync(zio_t *pio, dsl_pool_t *dp, uint64_t txg,
|
|
const blkptr_t *bpp);
|
|
void dsl_pool_create_origin(dsl_pool_t *dp, dmu_tx_t *tx);
|
|
void dsl_pool_upgrade_clones(dsl_pool_t *dp, dmu_tx_t *tx);
|
|
void dsl_pool_upgrade_dir_clones(dsl_pool_t *dp, dmu_tx_t *tx);
|
|
void dsl_pool_mos_diduse_space(dsl_pool_t *dp,
|
|
int64_t used, int64_t comp, int64_t uncomp);
|
|
boolean_t dsl_pool_need_dirty_delay(dsl_pool_t *dp);
|
|
void dsl_pool_config_enter(dsl_pool_t *dp, void *tag);
|
|
void dsl_pool_config_enter_prio(dsl_pool_t *dp, void *tag);
|
|
void dsl_pool_config_exit(dsl_pool_t *dp, void *tag);
|
|
boolean_t dsl_pool_config_held(dsl_pool_t *dp);
|
|
boolean_t dsl_pool_config_held_writer(dsl_pool_t *dp);
|
|
|
|
taskq_t *dsl_pool_iput_taskq(dsl_pool_t *dp);
|
|
|
|
int dsl_pool_user_hold(dsl_pool_t *dp, uint64_t dsobj,
|
|
const char *tag, uint64_t now, dmu_tx_t *tx);
|
|
int dsl_pool_user_release(dsl_pool_t *dp, uint64_t dsobj,
|
|
const char *tag, dmu_tx_t *tx);
|
|
void dsl_pool_clean_tmp_userrefs(dsl_pool_t *dp);
|
|
int dsl_pool_open_special_dir(dsl_pool_t *dp, const char *name, dsl_dir_t **);
|
|
int dsl_pool_hold(const char *name, void *tag, dsl_pool_t **dp);
|
|
void dsl_pool_rele(dsl_pool_t *dp, void *tag);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_DSL_POOL_H */
|