mirror_zfs/include/sys/uberblock_impl.h
Olaf Faaland 060f0226e6 MMP interval and fail_intervals in uberblock
When Multihost is enabled, and a pool is imported, uberblock writes
include ub_mmp_delay to allow an importing node to calculate the
duration of an activity test.  This value, is not enough information.

If zfs_multihost_fail_intervals > 0 on the node with the pool imported,
the safe minimum duration of the activity test is well defined, but does
not depend on ub_mmp_delay:

zfs_multihost_fail_intervals * zfs_multihost_interval

and if zfs_multihost_fail_intervals == 0 on that node, there is no such
well defined safe duration, but the importing host cannot tell whether
mmp_delay is high due to I/O delays, or due to a very large
zfs_multihost_interval setting on the host which last imported the pool.
As a result, it may use a far longer period for the activity test than
is necessary.

This patch renames ub_mmp_sequence to ub_mmp_config and uses it to
record the zfs_multihost_interval and zfs_multihost_fail_intervals
values, as well as the mmp sequence.  This allows a shorter activity
test duration to be calculated by the importing host in most situations.
These values are also added to the multihost_history kstat records.

It calculates the activity test duration differently depending on
whether the new fields are present or not; for importing pools with
only ub_mmp_delay, it uses

(zfs_multihost_interval + ub_mmp_delay) * zfs_multihost_import_intervals

Which results in an activity test duration less sensitive to the leaf
count.

In addition, it makes a few other improvements:
* It updates the "sequence" part of ub_mmp_config when MMP writes
  in between syncs occur.  This allows an importing host to detect MMP
  on the remote host sooner, when the pool is idle, as it is not limited
  to the granularity of ub_timestamp (1 second).
* It issues writes immediately when zfs_multihost_interval is changed
  so remote hosts see the updated value as soon as possible.
* It fixes a bug where setting zfs_multihost_fail_intervals = 1 results
  in immediate pool suspension.
* Update tests to verify activity check duration is based on recorded
  tunable values, not tunable values on importing host.
* Update tests to verify the expected number of uberblocks have valid
  MMP fields - fail_intervals, mmp_interval, mmp_seq (sequence number),
  that sequence number is incrementing, and that uberblock values match
  tunable settings.

Reviewed-by: Andreas Dilger <andreas.dilger@whamcloud.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Closes #7842
2019-03-21 12:47:57 -07:00

146 lines
5.1 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) 2016, 2017 by Delphix. All rights reserved.
*/
#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 */
#define MMP_MAGIC 0xa11cea11 /* all-see-all */
#define MMP_INTERVAL_VALID_BIT 0x01
#define MMP_SEQ_VALID_BIT 0x02
#define MMP_FAIL_INT_VALID_BIT 0x04
#define MMP_VALID(ubp) (ubp->ub_magic == UBERBLOCK_MAGIC && \
ubp->ub_mmp_magic == MMP_MAGIC)
#define MMP_INTERVAL_VALID(ubp) (MMP_VALID(ubp) && (ubp->ub_mmp_config & \
MMP_INTERVAL_VALID_BIT))
#define MMP_SEQ_VALID(ubp) (MMP_VALID(ubp) && (ubp->ub_mmp_config & \
MMP_SEQ_VALID_BIT))
#define MMP_FAIL_INT_VALID(ubp) (MMP_VALID(ubp) && (ubp->ub_mmp_config & \
MMP_FAIL_INT_VALID_BIT))
#define MMP_INTERVAL(ubp) ((ubp->ub_mmp_config & 0x00000000FFFFFF00) \
>> 8)
#define MMP_SEQ(ubp) ((ubp->ub_mmp_config & 0x0000FFFF00000000) \
>> 32)
#define MMP_FAIL_INT(ubp) ((ubp->ub_mmp_config & 0xFFFF000000000000) \
>> 48)
#define MMP_INTERVAL_SET(write) \
(((uint64_t)(write & 0xFFFFFF) << 8) | MMP_INTERVAL_VALID_BIT)
#define MMP_SEQ_SET(seq) \
(((uint64_t)(seq & 0xFFFF) << 32) | MMP_SEQ_VALID_BIT)
#define MMP_FAIL_INT_SET(fail) \
(((uint64_t)(fail & 0xFFFF) << 48) | MMP_FAIL_INT_VALID_BIT)
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 */
/* highest SPA_VERSION supported by software that wrote this txg */
uint64_t ub_software_version;
/* Maybe missing in uberblocks we read, but always written */
uint64_t ub_mmp_magic; /* MMP_MAGIC */
/*
* If ub_mmp_delay == 0 and ub_mmp_magic is valid, MMP is off.
* Otherwise, nanosec since last MMP write.
*/
uint64_t ub_mmp_delay;
/*
* The ub_mmp_config contains the multihost write interval, multihost
* fail intervals, sequence number for sub-second granularity, and
* valid bit mask. This layout is as follows:
*
* 64 56 48 40 32 24 16 8 0
* +-------+-------+-------+-------+-------+-------+-------+-------+
* 0 | Fail Intervals| Seq | Write Interval (ms) | VALID |
* +-------+-------+-------+-------+-------+-------+-------+-------+
*
* This allows a write_interval of (2^24/1000)s, over 4.5 hours
*
* VALID Bits:
* - 0x01 - Write Interval (ms)
* - 0x02 - Sequence number exists
* - 0x04 - Fail Intervals
* - 0xf8 - Reserved
*/
uint64_t ub_mmp_config;
/*
* 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()].
*/
uint64_t ub_checkpoint_txg;
};
#ifdef __cplusplus
}
#endif
#endif /* _SYS_UBERBLOCK_IMPL_H */