mirror_zfs/include/sys/txg.h

155 lines
4.7 KiB
C
Raw Normal View History

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
*/
/*
* Copyright 2010 Sun Microsystems, Inc. All rights reserved.
2008-11-20 23:01:55 +03:00
* Use is subject to license terms.
*/
/*
* Copyright (c) 2012, 2017 by Delphix. All rights reserved.
*/
2008-11-20 23:01:55 +03:00
#ifndef _SYS_TXG_H
#define _SYS_TXG_H
#include <sys/spa.h>
#include <sys/zfs_context.h>
#ifdef __cplusplus
extern "C" {
#endif
#define TXG_CONCURRENT_STATES 3 /* open, quiescing, syncing */
#define TXG_SIZE 4 /* next power of 2 */
#define TXG_MASK (TXG_SIZE - 1) /* mask for size */
#define TXG_INITIAL TXG_SIZE /* initial txg */
#define TXG_IDX (txg & TXG_MASK)
Distributed Spare (dRAID) Feature This patch adds a new top-level vdev type called dRAID, which stands for Distributed parity RAID. This pool configuration allows all dRAID vdevs to participate when rebuilding to a distributed hot spare device. This can substantially reduce the total time required to restore full parity to pool with a failed device. A dRAID pool can be created using the new top-level `draid` type. Like `raidz`, the desired redundancy is specified after the type: `draid[1,2,3]`. No additional information is required to create the pool and reasonable default values will be chosen based on the number of child vdevs in the dRAID vdev. zpool create <pool> draid[1,2,3] <vdevs...> Unlike raidz, additional optional dRAID configuration values can be provided as part of the draid type as colon separated values. This allows administrators to fully specify a layout for either performance or capacity reasons. The supported options include: zpool create <pool> \ draid[<parity>][:<data>d][:<children>c][:<spares>s] \ <vdevs...> - draid[parity] - Parity level (default 1) - draid[:<data>d] - Data devices per group (default 8) - draid[:<children>c] - Expected number of child vdevs - draid[:<spares>s] - Distributed hot spares (default 0) Abbreviated example `zpool status` output for a 68 disk dRAID pool with two distributed spares using special allocation classes. ``` pool: tank state: ONLINE config: NAME STATE READ WRITE CKSUM slag7 ONLINE 0 0 0 draid2:8d:68c:2s-0 ONLINE 0 0 0 L0 ONLINE 0 0 0 L1 ONLINE 0 0 0 ... U25 ONLINE 0 0 0 U26 ONLINE 0 0 0 spare-53 ONLINE 0 0 0 U27 ONLINE 0 0 0 draid2-0-0 ONLINE 0 0 0 U28 ONLINE 0 0 0 U29 ONLINE 0 0 0 ... U42 ONLINE 0 0 0 U43 ONLINE 0 0 0 special mirror-1 ONLINE 0 0 0 L5 ONLINE 0 0 0 U5 ONLINE 0 0 0 mirror-2 ONLINE 0 0 0 L6 ONLINE 0 0 0 U6 ONLINE 0 0 0 spares draid2-0-0 INUSE currently in use draid2-0-1 AVAIL ``` When adding test coverage for the new dRAID vdev type the following options were added to the ztest command. These options are leverages by zloop.sh to test a wide range of dRAID configurations. -K draid|raidz|random - kind of RAID to test -D <value> - dRAID data drives per group -S <value> - dRAID distributed hot spares -R <value> - RAID parity (raidz or dRAID) The zpool_create, zpool_import, redundancy, replacement and fault test groups have all been updated provide test coverage for the dRAID feature. Co-authored-by: Isaac Huang <he.huang@intel.com> Co-authored-by: Mark Maybee <mmaybee@cray.com> Co-authored-by: Don Brady <don.brady@delphix.com> Co-authored-by: Matthew Ahrens <mahrens@delphix.com> Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Mark Maybee <mmaybee@cray.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #10102
2020-11-14 00:51:51 +03:00
#define TXG_UNKNOWN 0
2008-11-20 23:01:55 +03:00
/* Number of txgs worth of frees we defer adding to in-core spacemaps */
#define TXG_DEFER_SIZE 2
2008-11-20 23:01:55 +03:00
typedef struct tx_cpu tx_cpu_t;
typedef struct txg_handle {
tx_cpu_t *th_cpu;
uint64_t th_txg;
} txg_handle_t;
typedef struct txg_node {
struct txg_node *tn_next[TXG_SIZE];
uint8_t tn_member[TXG_SIZE];
} txg_node_t;
typedef struct txg_list {
kmutex_t tl_lock;
size_t tl_offset;
spa_t *tl_spa;
2008-11-20 23:01:55 +03:00
txg_node_t *tl_head[TXG_SIZE];
} txg_list_t;
struct dsl_pool;
extern void txg_init(struct dsl_pool *dp, uint64_t txg);
extern void txg_fini(struct dsl_pool *dp);
extern void txg_sync_start(struct dsl_pool *dp);
extern void txg_sync_stop(struct dsl_pool *dp);
extern uint64_t txg_hold_open(struct dsl_pool *dp, txg_handle_t *txghp);
extern void txg_rele_to_quiesce(txg_handle_t *txghp);
extern void txg_rele_to_sync(txg_handle_t *txghp);
extern void txg_register_callbacks(txg_handle_t *txghp, list_t *tx_callbacks);
2008-11-20 23:01:55 +03:00
extern void txg_delay(struct dsl_pool *dp, uint64_t txg, hrtime_t delta,
hrtime_t resolution);
extern void txg_kick(struct dsl_pool *dp, uint64_t txg);
2008-11-20 23:01:55 +03:00
/*
* Wait until the given transaction group has finished syncing.
* Try to make this happen as soon as possible (eg. kick off any
* necessary syncs immediately). If txg==0, wait for the currently open
* txg to finish syncing.
*/
extern void txg_wait_synced(struct dsl_pool *dp, uint64_t txg);
OpenZFS 9425 - channel programs can be interrupted Problem Statement ================= ZFS Channel program scripts currently require a timeout, so that hung or long-running scripts return a timeout error instead of causing ZFS to get wedged. This limit can currently be set up to 100 million Lua instructions. Even with a limit in place, it would be desirable to have a sys admin (support engineer) be able to cancel a script that is taking a long time. Proposed Solution ================= Make it possible to abort a channel program by sending an interrupt signal.In the underlying txg_wait_sync function, switch the cv_wait to a cv_wait_sig to catch the signal. Once a signal is encountered, the dsl_sync_task function can install a Lua hook that will get called before the Lua interpreter executes a new line of code. The dsl_sync_task can resume with a standard txg_wait_sync call and wait for the txg to complete. Meanwhile, the hook will abort the script and indicate that the channel program was canceled. The kernel returns a EINTR to indicate that the channel program run was canceled. Porting notes: Added missing return value from cv_wait_sig() Authored by: Don Brady <don.brady@delphix.com> Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com> Reviewed by: Matt Ahrens <matt@delphix.com> Reviewed by: Sara Hartse <sara.hartse@delphix.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Robert Mustacchi <rm@joyent.com> Ported-by: Don Brady <don.brady@delphix.com> Signed-off-by: Don Brady <don.brady@delphix.com> OpenZFS-issue: https://www.illumos.org/issues/9425 OpenZFS-commit: https://github.com/illumos/illumos-gate/commit/d0cb1fb926 Closes #8904
2019-06-23 02:51:46 +03:00
/*
* Wait as above. Returns true if the thread was signaled while waiting.
*/
extern boolean_t txg_wait_synced_sig(struct dsl_pool *dp, uint64_t txg);
2008-11-20 23:01:55 +03:00
/*
* Wait until the given transaction group, or one after it, is
* the open transaction group. Try to make this happen as soon
Add TRIM support UNMAP/TRIM support is a frequently-requested feature to help prevent performance from degrading on SSDs and on various other SAN-like storage back-ends. By issuing UNMAP/TRIM commands for sectors which are no longer allocated the underlying device can often more efficiently manage itself. This TRIM implementation is modeled on the `zpool initialize` feature which writes a pattern to all unallocated space in the pool. The new `zpool trim` command uses the same vdev_xlate() code to calculate what sectors are unallocated, the same per- vdev TRIM thread model and locking, and the same basic CLI for a consistent user experience. The core difference is that instead of writing a pattern it will issue UNMAP/TRIM commands for those extents. The zio pipeline was updated to accommodate this by adding a new ZIO_TYPE_TRIM type and associated spa taskq. This new type makes is straight forward to add the platform specific TRIM/UNMAP calls to vdev_disk.c and vdev_file.c. These new ZIO_TYPE_TRIM zios are handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs. This makes it possible to largely avoid changing the pipieline, one exception is that TRIM zio's may exceed the 16M block size limit since they contain no data. In addition to the manual `zpool trim` command, a background automatic TRIM was added and is controlled by the 'autotrim' property. It relies on the exact same infrastructure as the manual TRIM. However, instead of relying on the extents in a metaslab's ms_allocatable range tree, a ms_trim tree is kept per metaslab. When 'autotrim=on', ranges added back to the ms_allocatable tree are also added to the ms_free tree. The ms_free tree is then periodically consumed by an autotrim thread which systematically walks a top level vdev's metaslabs. Since the automatic TRIM will skip ranges it considers too small there is value in occasionally running a full `zpool trim`. This may occur when the freed blocks are small and not enough time was allowed to aggregate them. An automatic TRIM and a manual `zpool trim` may be run concurrently, in which case the automatic TRIM will yield to the manual TRIM. Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Tim Chase <tim@chase2k.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Contributions-by: Saso Kiselkov <saso.kiselkov@nexenta.com> Contributions-by: Tim Chase <tim@chase2k.com> Contributions-by: Chunwei Chen <tuxoko@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #8419 Closes #598
2019-03-29 19:13:20 +03:00
* as possible (eg. kick off any necessary syncs immediately) when
* should_quiesce is set. If txg == 0, wait for the next open txg.
2008-11-20 23:01:55 +03:00
*/
Add TRIM support UNMAP/TRIM support is a frequently-requested feature to help prevent performance from degrading on SSDs and on various other SAN-like storage back-ends. By issuing UNMAP/TRIM commands for sectors which are no longer allocated the underlying device can often more efficiently manage itself. This TRIM implementation is modeled on the `zpool initialize` feature which writes a pattern to all unallocated space in the pool. The new `zpool trim` command uses the same vdev_xlate() code to calculate what sectors are unallocated, the same per- vdev TRIM thread model and locking, and the same basic CLI for a consistent user experience. The core difference is that instead of writing a pattern it will issue UNMAP/TRIM commands for those extents. The zio pipeline was updated to accommodate this by adding a new ZIO_TYPE_TRIM type and associated spa taskq. This new type makes is straight forward to add the platform specific TRIM/UNMAP calls to vdev_disk.c and vdev_file.c. These new ZIO_TYPE_TRIM zios are handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs. This makes it possible to largely avoid changing the pipieline, one exception is that TRIM zio's may exceed the 16M block size limit since they contain no data. In addition to the manual `zpool trim` command, a background automatic TRIM was added and is controlled by the 'autotrim' property. It relies on the exact same infrastructure as the manual TRIM. However, instead of relying on the extents in a metaslab's ms_allocatable range tree, a ms_trim tree is kept per metaslab. When 'autotrim=on', ranges added back to the ms_allocatable tree are also added to the ms_free tree. The ms_free tree is then periodically consumed by an autotrim thread which systematically walks a top level vdev's metaslabs. Since the automatic TRIM will skip ranges it considers too small there is value in occasionally running a full `zpool trim`. This may occur when the freed blocks are small and not enough time was allowed to aggregate them. An automatic TRIM and a manual `zpool trim` may be run concurrently, in which case the automatic TRIM will yield to the manual TRIM. Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Tim Chase <tim@chase2k.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Contributions-by: Saso Kiselkov <saso.kiselkov@nexenta.com> Contributions-by: Tim Chase <tim@chase2k.com> Contributions-by: Chunwei Chen <tuxoko@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #8419 Closes #598
2019-03-29 19:13:20 +03:00
extern void txg_wait_open(struct dsl_pool *dp, uint64_t txg,
boolean_t should_quiesce);
2008-11-20 23:01:55 +03:00
/*
* Returns TRUE if we are "backed up" waiting for the syncing
* transaction to complete; otherwise returns FALSE.
*/
extern boolean_t txg_stalled(struct dsl_pool *dp);
/* returns TRUE if someone is waiting for the next txg to sync */
extern boolean_t txg_sync_waiting(struct dsl_pool *dp);
2008-11-20 23:01:55 +03:00
extern void txg_verify(spa_t *spa, uint64_t txg);
/*
* Wait for pending commit callbacks of already-synced transactions to finish
* processing.
*/
extern void txg_wait_callbacks(struct dsl_pool *dp);
2008-11-20 23:01:55 +03:00
/*
* Per-txg object lists.
*/
#define TXG_CLEAN(txg) ((txg) - 1)
extern void txg_list_create(txg_list_t *tl, spa_t *spa, size_t offset);
2008-11-20 23:01:55 +03:00
extern void txg_list_destroy(txg_list_t *tl);
extern boolean_t txg_list_empty(txg_list_t *tl, uint64_t txg);
extern boolean_t txg_all_lists_empty(txg_list_t *tl);
extern boolean_t txg_list_add(txg_list_t *tl, void *p, uint64_t txg);
extern boolean_t txg_list_add_tail(txg_list_t *tl, void *p, uint64_t txg);
2008-11-20 23:01:55 +03:00
extern void *txg_list_remove(txg_list_t *tl, uint64_t txg);
extern void *txg_list_remove_this(txg_list_t *tl, void *p, uint64_t txg);
extern boolean_t txg_list_member(txg_list_t *tl, void *p, uint64_t txg);
2008-11-20 23:01:55 +03:00
extern void *txg_list_head(txg_list_t *tl, uint64_t txg);
extern void *txg_list_next(txg_list_t *tl, void *p, uint64_t txg);
/* Global tuning */
extern int zfs_txg_timeout;
#ifdef ZFS_DEBUG
#define TXG_VERIFY(spa, txg) txg_verify(spa, txg)
#else
#define TXG_VERIFY(spa, txg)
#endif
2008-11-20 23:01:55 +03:00
#ifdef __cplusplus
}
#endif
#endif /* _SYS_TXG_H */