[mirror_zfs.git] / include / sys / txg_impl.h

/*
 * 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 https://opensource.org/licenses/CDDL-1.0.
 * 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 2009 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */

/*
 * Copyright (c) 2013, 2017 by Delphix. All rights reserved.
 */

#ifndef _SYS_TXG_IMPL_H
#define	_SYS_TXG_IMPL_H

#include <sys/spa.h>
#include <sys/txg.h>

#ifdef	__cplusplus
extern "C" {
#endif

/*
 * The tx_cpu structure is a per-cpu structure that is used to track
 * the number of active transaction holds (tc_count). As transactions
 * are assigned into a transaction group the appropriate tc_count is
 * incremented to indicate that there are pending changes that have yet
 * to quiesce. Consumers eventually call txg_rele_to_sync() to decrement
 * the tc_count. A transaction group is not considered quiesced until all
 * tx_cpu structures have reached a tc_count of zero.
 *
 * This structure is a per-cpu structure by design. Updates to this structure
 * are frequent and concurrent. Having a single structure would result in
 * heavy lock contention so a per-cpu design was implemented. With the fanned
 * out mutex design, consumers only need to lock the mutex associated with
 * thread's cpu.
 *
 * The tx_cpu contains two locks, the tc_lock and tc_open_lock.
 * The tc_lock is used to protect all members of the tx_cpu structure with
 * the exception of the tc_open_lock. This lock should only be held for a
 * short period of time, typically when updating the value of tc_count.
 *
 * The tc_open_lock protects the tx_open_txg member of the tx_state structure.
 * This lock is used to ensure that transactions are only assigned into
 * the current open transaction group. In order to move the current open
 * transaction group to the quiesce phase, the txg_quiesce thread must
 * grab all tc_open_locks, increment the tx_open_txg, and drop the locks.
 * The tc_open_lock is held until the transaction is assigned into the
 * transaction group. Typically, this is a short operation but if throttling
 * is occurring it may be held for longer periods of time.
 */
struct tx_cpu {
	kmutex_t	tc_open_lock;	/* protects tx_open_txg */
	kmutex_t	tc_lock;	/* protects the rest of this struct */
	kcondvar_t	tc_cv[TXG_SIZE];
	uint64_t	tc_count[TXG_SIZE];	/* tx hold count on each txg */
	list_t		tc_callbacks[TXG_SIZE]; /* commit cb list */
} ____cacheline_aligned;

/*
 * The tx_state structure maintains the state information about the different
 * stages of the pool's transaction groups. A per pool tx_state structure
 * is used to track this information. The tx_state structure also points to
 * an array of tx_cpu structures (described above). Although the tx_sync_lock
 * is used to protect the members of this structure, it is not used to
 * protect the tx_open_txg. Instead a special lock in the tx_cpu structure
 * is used. Readers of tx_open_txg must grab the per-cpu tc_open_lock.
 * Any thread wishing to update tx_open_txg must grab the tc_open_lock on
 * every cpu (see txg_quiesce()).
 */
typedef struct tx_state {
	tx_cpu_t	*tx_cpu;	/* protects access to tx_open_txg */
	kmutex_t	tx_sync_lock;	/* protects the rest of this struct */

	uint64_t	tx_open_txg;	/* currently open txg id */
	uint64_t	tx_quiescing_txg; /* currently quiescing txg id */
	uint64_t	tx_quiesced_txg; /* quiesced txg waiting for sync */
	uint64_t	tx_syncing_txg;	/* currently syncing txg id */
	uint64_t	tx_synced_txg;	/* last synced txg id */

	hrtime_t	tx_open_time;	/* start time of tx_open_txg */

	uint64_t	tx_sync_txg_waiting; /* txg we're waiting to sync */
	uint64_t	tx_quiesce_txg_waiting; /* txg we're waiting to open */

	kcondvar_t	tx_sync_more_cv;
	kcondvar_t	tx_sync_done_cv;
	kcondvar_t	tx_quiesce_more_cv;
	kcondvar_t	tx_quiesce_done_cv;
	kcondvar_t	tx_timeout_cv;
	kcondvar_t	tx_exit_cv;	/* wait for all threads to exit */

	uint8_t		tx_threads;	/* number of threads */
	uint8_t		tx_exiting;	/* set when we're exiting */

	kthread_t	*tx_sync_thread;
	kthread_t	*tx_quiesce_thread;

	taskq_t		*tx_commit_cb_taskq; /* commit callback taskq */
} tx_state_t;

#ifdef	__cplusplus
}
#endif

#endif	/* _SYS_TXG_IMPL_H */
Commit	Line	Data
	1	/*
	2	* CDDL HEADER START
	3	*
	4	* The contents of this file are subject to the terms of the
	5	* Common Development and Distribution License (the "License").
	6	* You may not use this file except in compliance with the License.
	7	*
	8	* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
	9	* or https://opensource.org/licenses/CDDL-1.0.
	10	* See the License for the specific language governing permissions
	11	* and limitations under the License.
	12	*
	13	* When distributing Covered Code, include this CDDL HEADER in each
	14	* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
	15	* If applicable, add the following below this CDDL HEADER, with the
	16	* fields enclosed by brackets "[]" replaced with your own identifying
	17	* information: Portions Copyright [yyyy] [name of copyright owner]
	18	*
	19	* CDDL HEADER END
	20	*/
	21
	22	/*
	23	* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
	24	* Use is subject to license terms.
	25	*/
	26
	27	/*
	28	* Copyright (c) 2013, 2017 by Delphix. All rights reserved.
	29	*/
	30
	31	#ifndef _SYS_TXG_IMPL_H
	32	#define _SYS_TXG_IMPL_H
	33
	34	#include <sys/spa.h>
	35	#include <sys/txg.h>
	36
	37	#ifdef __cplusplus
	38	extern "C" {
	39	#endif
	40
	41	/*
	42	* The tx_cpu structure is a per-cpu structure that is used to track
	43	* the number of active transaction holds (tc_count). As transactions
	44	* are assigned into a transaction group the appropriate tc_count is
	45	* incremented to indicate that there are pending changes that have yet
	46	* to quiesce. Consumers eventually call txg_rele_to_sync() to decrement
	47	* the tc_count. A transaction group is not considered quiesced until all
	48	* tx_cpu structures have reached a tc_count of zero.
	49	*
	50	* This structure is a per-cpu structure by design. Updates to this structure
	51	* are frequent and concurrent. Having a single structure would result in
	52	* heavy lock contention so a per-cpu design was implemented. With the fanned
	53	* out mutex design, consumers only need to lock the mutex associated with
	54	* thread's cpu.
	55	*
	56	* The tx_cpu contains two locks, the tc_lock and tc_open_lock.
	57	* The tc_lock is used to protect all members of the tx_cpu structure with
	58	* the exception of the tc_open_lock. This lock should only be held for a
	59	* short period of time, typically when updating the value of tc_count.
	60	*
	61	* The tc_open_lock protects the tx_open_txg member of the tx_state structure.
	62	* This lock is used to ensure that transactions are only assigned into
	63	* the current open transaction group. In order to move the current open
	64	* transaction group to the quiesce phase, the txg_quiesce thread must
	65	* grab all tc_open_locks, increment the tx_open_txg, and drop the locks.
	66	* The tc_open_lock is held until the transaction is assigned into the
	67	* transaction group. Typically, this is a short operation but if throttling
	68	* is occurring it may be held for longer periods of time.
	69	*/
	70	struct tx_cpu {
	71	kmutex_t tc_open_lock; /* protects tx_open_txg */
	72	kmutex_t tc_lock; /* protects the rest of this struct */
	73	kcondvar_t tc_cv[TXG_SIZE];
	74	uint64_t tc_count[TXG_SIZE]; /* tx hold count on each txg */
	75	list_t tc_callbacks[TXG_SIZE]; /* commit cb list */
	76	} ____cacheline_aligned;
	77
	78	/*
	79	* The tx_state structure maintains the state information about the different
	80	* stages of the pool's transaction groups. A per pool tx_state structure
	81	* is used to track this information. The tx_state structure also points to
	82	* an array of tx_cpu structures (described above). Although the tx_sync_lock
	83	* is used to protect the members of this structure, it is not used to
	84	* protect the tx_open_txg. Instead a special lock in the tx_cpu structure
	85	* is used. Readers of tx_open_txg must grab the per-cpu tc_open_lock.
	86	* Any thread wishing to update tx_open_txg must grab the tc_open_lock on
	87	* every cpu (see txg_quiesce()).
	88	*/
	89	typedef struct tx_state {
	90	tx_cpu_t tx_cpu; / protects access to tx_open_txg */
	91	kmutex_t tx_sync_lock; /* protects the rest of this struct */
	92
	93	uint64_t tx_open_txg; /* currently open txg id */
	94	uint64_t tx_quiescing_txg; /* currently quiescing txg id */
	95	uint64_t tx_quiesced_txg; /* quiesced txg waiting for sync */
	96	uint64_t tx_syncing_txg; /* currently syncing txg id */
	97	uint64_t tx_synced_txg; /* last synced txg id */
	98
	99	hrtime_t tx_open_time; /* start time of tx_open_txg */
	100
	101	uint64_t tx_sync_txg_waiting; /* txg we're waiting to sync */
	102	uint64_t tx_quiesce_txg_waiting; /* txg we're waiting to open */
	103
	104	kcondvar_t tx_sync_more_cv;
	105	kcondvar_t tx_sync_done_cv;
	106	kcondvar_t tx_quiesce_more_cv;
	107	kcondvar_t tx_quiesce_done_cv;
	108	kcondvar_t tx_timeout_cv;
	109	kcondvar_t tx_exit_cv; /* wait for all threads to exit */
	110
	111	uint8_t tx_threads; /* number of threads */
	112	uint8_t tx_exiting; /* set when we're exiting */
	113
	114	kthread_t *tx_sync_thread;
	115	kthread_t *tx_quiesce_thread;
	116
	117	taskq_t tx_commit_cb_taskq; / commit callback taskq */
	118	} tx_state_t;
	119
	120	#ifdef __cplusplus
	121	}
	122	#endif
	123
	124	#endif /* _SYS_TXG_IMPL_H */