2008-11-20 23:01:55 +03:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
*/
|
|
|
|
/*
|
2010-05-29 00:45:14 +04:00
|
|
|
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
2016-12-17 01:11:29 +03:00
|
|
|
* Copyright (c) 2016, 2017 by Delphix. All rights reserved.
|
2008-11-20 23:01:55 +03:00
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _SYS_UBERBLOCK_IMPL_H
|
|
|
|
#define _SYS_UBERBLOCK_IMPL_H
|
|
|
|
|
|
|
|
#include <sys/uberblock.h>
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The uberblock version is incremented whenever an incompatible on-disk
|
|
|
|
* format change is made to the SPA, DMU, or ZAP.
|
|
|
|
*
|
|
|
|
* Note: the first two fields should never be moved. When a storage pool
|
|
|
|
* is opened, the uberblock must be read off the disk before the version
|
|
|
|
* can be checked. If the ub_version field is moved, we may not detect
|
|
|
|
* version mismatch. If the ub_magic field is moved, applications that
|
|
|
|
* expect the magic number in the first word won't work.
|
|
|
|
*/
|
|
|
|
#define UBERBLOCK_MAGIC 0x00bab10c /* oo-ba-bloc! */
|
|
|
|
#define UBERBLOCK_SHIFT 10 /* up to 1K */
|
Multi-modifier protection (MMP)
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
2017-07-08 06:20:35 +03:00
|
|
|
#define MMP_MAGIC 0xa11cea11 /* all-see-all */
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
struct uberblock {
|
|
|
|
uint64_t ub_magic; /* UBERBLOCK_MAGIC */
|
|
|
|
uint64_t ub_version; /* SPA_VERSION */
|
|
|
|
uint64_t ub_txg; /* txg of last sync */
|
|
|
|
uint64_t ub_guid_sum; /* sum of all vdev guids */
|
|
|
|
uint64_t ub_timestamp; /* UTC time of last sync */
|
|
|
|
blkptr_t ub_rootbp; /* MOS objset_phys_t */
|
2010-05-29 00:45:14 +04:00
|
|
|
|
|
|
|
/* highest SPA_VERSION supported by software that wrote this txg */
|
|
|
|
uint64_t ub_software_version;
|
Multi-modifier protection (MMP)
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
2017-07-08 06:20:35 +03:00
|
|
|
|
|
|
|
/* Maybe missing in uberblocks we read, but always written */
|
|
|
|
uint64_t ub_mmp_magic; /* MMP_MAGIC */
|
|
|
|
uint64_t ub_mmp_delay; /* nanosec since last MMP write */
|
|
|
|
uint64_t ub_mmp_seq; /* reserved for sequence number */
|
2016-12-17 01:11:29 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* ub_checkpoint_txg indicates two things about the current uberblock:
|
|
|
|
*
|
|
|
|
* 1] If it is not zero then this uberblock is a checkpoint. If it is
|
|
|
|
* zero, then this uberblock is not a checkpoint.
|
|
|
|
*
|
|
|
|
* 2] On checkpointed uberblocks, the value of ub_checkpoint_txg is
|
|
|
|
* the ub_txg that the uberblock had at the time we moved it to
|
|
|
|
* the MOS config.
|
|
|
|
*
|
|
|
|
* The field is set when we checkpoint the uberblock and continues to
|
|
|
|
* hold that value even after we've rewound (unlike the ub_txg that
|
|
|
|
* is reset to a higher value).
|
|
|
|
*
|
|
|
|
* Besides checks used to determine whether we are reopening the
|
|
|
|
* pool from a checkpointed uberblock [see spa_ld_select_uberblock()],
|
|
|
|
* the value of the field is used to determine which ZIL blocks have
|
|
|
|
* been allocated according to the ms_sm when we are rewinding to a
|
|
|
|
* checkpoint. Specifically, if blk_birth > ub_checkpoint_txg, then
|
|
|
|
* the ZIL block is not allocated [see uses of spa_min_claim_txg()].
|
|
|
|
*/
|
2017-07-13 17:32:53 +03:00
|
|
|
uint64_t ub_checkpoint_txg;
|
2008-11-20 23:01:55 +03:00
|
|
|
};
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#endif /* _SYS_UBERBLOCK_IMPL_H */
|