2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
|
* 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
|
|
|
|
|
*/
|
|
|
|
|
/*
|
2010-05-28 20:45:14 +00:00
|
|
|
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
2012-12-15 00:13:40 +00:00
|
|
|
* Portions Copyright 2011 Martin Matuska
|
2014-07-18 15:08:31 +00:00
|
|
|
* Copyright (c) 2012, 2014 by Delphix. All rights reserved.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include <sys/zfs_context.h>
|
|
|
|
|
#include <sys/txg_impl.h>
|
|
|
|
|
#include <sys/dmu_impl.h>
|
2013-10-01 16:50:50 +00:00
|
|
|
#include <sys/spa_impl.h>
|
2010-05-28 20:45:14 +00:00
|
|
|
#include <sys/dmu_tx.h>
|
2008-11-20 20:01:55 +00:00
|
|
|
#include <sys/dsl_pool.h>
|
2010-05-28 20:45:14 +00:00
|
|
|
#include <sys/dsl_scan.h>
|
2008-11-20 20:01:55 +00:00
|
|
|
#include <sys/callb.h>
|
|
|
|
|
|
|
|
|
|
/*
|
2013-01-30 16:54:17 +00:00
|
|
|
* ZFS Transaction Groups
|
|
|
|
|
* ----------------------
|
|
|
|
|
*
|
|
|
|
|
* ZFS transaction groups are, as the name implies, groups of transactions
|
|
|
|
|
* that act on persistent state. ZFS asserts consistency at the granularity of
|
|
|
|
|
* these transaction groups. Each successive transaction group (txg) is
|
|
|
|
|
* assigned a 64-bit consecutive identifier. There are three active
|
|
|
|
|
* transaction group states: open, quiescing, or syncing. At any given time,
|
|
|
|
|
* there may be an active txg associated with each state; each active txg may
|
|
|
|
|
* either be processing, or blocked waiting to enter the next state. There may
|
|
|
|
|
* be up to three active txgs, and there is always a txg in the open state
|
|
|
|
|
* (though it may be blocked waiting to enter the quiescing state). In broad
|
Illumos #4045 write throttle & i/o scheduler performance work
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045
illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1913
2013-08-29 03:01:20 +00:00
|
|
|
* strokes, transactions -- operations that change in-memory structures -- are
|
2013-01-30 16:54:17 +00:00
|
|
|
* accepted into the txg in the open state, and are completed while the txg is
|
|
|
|
|
* in the open or quiescing states. The accumulated changes are written to
|
|
|
|
|
* disk in the syncing state.
|
|
|
|
|
*
|
|
|
|
|
* Open
|
|
|
|
|
*
|
|
|
|
|
* When a new txg becomes active, it first enters the open state. New
|
Illumos #4045 write throttle & i/o scheduler performance work
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045
illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1913
2013-08-29 03:01:20 +00:00
|
|
|
* transactions -- updates to in-memory structures -- are assigned to the
|
2013-01-30 16:54:17 +00:00
|
|
|
* currently open txg. There is always a txg in the open state so that ZFS can
|
|
|
|
|
* accept new changes (though the txg may refuse new changes if it has hit
|
|
|
|
|
* some limit). ZFS advances the open txg to the next state for a variety of
|
|
|
|
|
* reasons such as it hitting a time or size threshold, or the execution of an
|
|
|
|
|
* administrative action that must be completed in the syncing state.
|
|
|
|
|
*
|
|
|
|
|
* Quiescing
|
|
|
|
|
*
|
|
|
|
|
* After a txg exits the open state, it enters the quiescing state. The
|
|
|
|
|
* quiescing state is intended to provide a buffer between accepting new
|
|
|
|
|
* transactions in the open state and writing them out to stable storage in
|
|
|
|
|
* the syncing state. While quiescing, transactions can continue their
|
|
|
|
|
* operation without delaying either of the other states. Typically, a txg is
|
|
|
|
|
* in the quiescing state very briefly since the operations are bounded by
|
|
|
|
|
* software latencies rather than, say, slower I/O latencies. After all
|
|
|
|
|
* transactions complete, the txg is ready to enter the next state.
|
|
|
|
|
*
|
|
|
|
|
* Syncing
|
|
|
|
|
*
|
|
|
|
|
* In the syncing state, the in-memory state built up during the open and (to
|
|
|
|
|
* a lesser degree) the quiescing states is written to stable storage. The
|
|
|
|
|
* process of writing out modified data can, in turn modify more data. For
|
|
|
|
|
* example when we write new blocks, we need to allocate space for them; those
|
|
|
|
|
* allocations modify metadata (space maps)... which themselves must be
|
|
|
|
|
* written to stable storage. During the sync state, ZFS iterates, writing out
|
|
|
|
|
* data until it converges and all in-memory changes have been written out.
|
|
|
|
|
* The first such pass is the largest as it encompasses all the modified user
|
|
|
|
|
* data (as opposed to filesystem metadata). Subsequent passes typically have
|
|
|
|
|
* far less data to write as they consist exclusively of filesystem metadata.
|
|
|
|
|
*
|
|
|
|
|
* To ensure convergence, after a certain number of passes ZFS begins
|
|
|
|
|
* overwriting locations on stable storage that had been allocated earlier in
|
|
|
|
|
* the syncing state (and subsequently freed). ZFS usually allocates new
|
|
|
|
|
* blocks to optimize for large, continuous, writes. For the syncing state to
|
|
|
|
|
* converge however it must complete a pass where no new blocks are allocated
|
|
|
|
|
* since each allocation requires a modification of persistent metadata.
|
|
|
|
|
* Further, to hasten convergence, after a prescribed number of passes, ZFS
|
|
|
|
|
* also defers frees, and stops compressing.
|
|
|
|
|
*
|
|
|
|
|
* In addition to writing out user data, we must also execute synctasks during
|
|
|
|
|
* the syncing context. A synctask is the mechanism by which some
|
|
|
|
|
* administrative activities work such as creating and destroying snapshots or
|
|
|
|
|
* datasets. Note that when a synctask is initiated it enters the open txg,
|
|
|
|
|
* and ZFS then pushes that txg as quickly as possible to completion of the
|
|
|
|
|
* syncing state in order to reduce the latency of the administrative
|
|
|
|
|
* activity. To complete the syncing state, ZFS writes out a new uberblock,
|
|
|
|
|
* the root of the tree of blocks that comprise all state stored on the ZFS
|
|
|
|
|
* pool. Finally, if there is a quiesced txg waiting, we signal that it can
|
|
|
|
|
* now transition to the syncing state.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
static void txg_sync_thread(dsl_pool_t *dp);
|
|
|
|
|
static void txg_quiesce_thread(dsl_pool_t *dp);
|
|
|
|
|
|
2010-08-26 21:24:34 +00:00
|
|
|
int zfs_txg_timeout = 5; /* max seconds worth of delta per txg */
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Prepare the txg subsystem.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_init(dsl_pool_t *dp, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
int c;
|
|
|
|
|
bzero(tx, sizeof (tx_state_t));
|
|
|
|
|
|
2010-08-26 18:46:09 +00:00
|
|
|
tx->tx_cpu = vmem_zalloc(max_ncpus * sizeof (tx_cpu_t), KM_SLEEP);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
for (c = 0; c < max_ncpus; c++) {
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
mutex_init(&tx->tx_cpu[c].tc_lock, NULL, MUTEX_DEFAULT, NULL);
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_init(&tx->tx_cpu[c].tc_open_lock, NULL, MUTEX_DEFAULT,
|
|
|
|
|
NULL);
|
2008-11-20 20:01:55 +00:00
|
|
|
for (i = 0; i < TXG_SIZE; i++) {
|
|
|
|
|
cv_init(&tx->tx_cpu[c].tc_cv[i], NULL, CV_DEFAULT,
|
|
|
|
|
NULL);
|
2010-05-28 20:45:14 +00:00
|
|
|
list_create(&tx->tx_cpu[c].tc_callbacks[i],
|
|
|
|
|
sizeof (dmu_tx_callback_t),
|
|
|
|
|
offsetof(dmu_tx_callback_t, dcb_node));
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
mutex_init(&tx->tx_sync_lock, NULL, MUTEX_DEFAULT, NULL);
|
|
|
|
|
|
2009-01-15 21:59:39 +00:00
|
|
|
cv_init(&tx->tx_sync_more_cv, NULL, CV_DEFAULT, NULL);
|
|
|
|
|
cv_init(&tx->tx_sync_done_cv, NULL, CV_DEFAULT, NULL);
|
|
|
|
|
cv_init(&tx->tx_quiesce_more_cv, NULL, CV_DEFAULT, NULL);
|
|
|
|
|
cv_init(&tx->tx_quiesce_done_cv, NULL, CV_DEFAULT, NULL);
|
|
|
|
|
cv_init(&tx->tx_exit_cv, NULL, CV_DEFAULT, NULL);
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
tx->tx_open_txg = txg;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Close down the txg subsystem.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_fini(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
int c;
|
|
|
|
|
|
|
|
|
|
ASSERT(tx->tx_threads == 0);
|
|
|
|
|
|
|
|
|
|
mutex_destroy(&tx->tx_sync_lock);
|
|
|
|
|
|
2009-01-15 21:59:39 +00:00
|
|
|
cv_destroy(&tx->tx_sync_more_cv);
|
|
|
|
|
cv_destroy(&tx->tx_sync_done_cv);
|
|
|
|
|
cv_destroy(&tx->tx_quiesce_more_cv);
|
|
|
|
|
cv_destroy(&tx->tx_quiesce_done_cv);
|
|
|
|
|
cv_destroy(&tx->tx_exit_cv);
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
for (c = 0; c < max_ncpus; c++) {
|
|
|
|
|
int i;
|
|
|
|
|
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_destroy(&tx->tx_cpu[c].tc_open_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
mutex_destroy(&tx->tx_cpu[c].tc_lock);
|
2010-05-28 20:45:14 +00:00
|
|
|
for (i = 0; i < TXG_SIZE; i++) {
|
2008-11-20 20:01:55 +00:00
|
|
|
cv_destroy(&tx->tx_cpu[c].tc_cv[i]);
|
2010-05-28 20:45:14 +00:00
|
|
|
list_destroy(&tx->tx_cpu[c].tc_callbacks[i]);
|
|
|
|
|
}
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
if (tx->tx_commit_cb_taskq != NULL)
|
|
|
|
|
taskq_destroy(tx->tx_commit_cb_taskq);
|
|
|
|
|
|
2010-08-26 18:46:09 +00:00
|
|
|
vmem_free(tx->tx_cpu, max_ncpus * sizeof (tx_cpu_t));
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
bzero(tx, sizeof (tx_state_t));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Start syncing transaction groups.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_sync_start(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
|
|
|
|
|
dprintf("pool %p\n", dp);
|
|
|
|
|
|
|
|
|
|
ASSERT(tx->tx_threads == 0);
|
|
|
|
|
|
|
|
|
|
tx->tx_threads = 2;
|
|
|
|
|
|
|
|
|
|
tx->tx_quiesce_thread = thread_create(NULL, 0, txg_quiesce_thread,
|
|
|
|
|
dp, 0, &p0, TS_RUN, minclsyspri);
|
|
|
|
|
|
2008-12-03 20:09:06 +00:00
|
|
|
/*
|
|
|
|
|
* The sync thread can need a larger-than-default stack size on
|
|
|
|
|
* 32-bit x86. This is due in part to nested pools and
|
|
|
|
|
* scrub_visitbp() recursion.
|
|
|
|
|
*/
|
2010-05-28 20:45:14 +00:00
|
|
|
tx->tx_sync_thread = thread_create(NULL, 32<<10, txg_sync_thread,
|
2008-11-20 20:01:55 +00:00
|
|
|
dp, 0, &p0, TS_RUN, minclsyspri);
|
|
|
|
|
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
txg_thread_enter(tx_state_t *tx, callb_cpr_t *cpr)
|
|
|
|
|
{
|
|
|
|
|
CALLB_CPR_INIT(cpr, &tx->tx_sync_lock, callb_generic_cpr, FTAG);
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
txg_thread_exit(tx_state_t *tx, callb_cpr_t *cpr, kthread_t **tpp)
|
|
|
|
|
{
|
|
|
|
|
ASSERT(*tpp != NULL);
|
|
|
|
|
*tpp = NULL;
|
|
|
|
|
tx->tx_threads--;
|
|
|
|
|
cv_broadcast(&tx->tx_exit_cv);
|
|
|
|
|
CALLB_CPR_EXIT(cpr); /* drops &tx->tx_sync_lock */
|
|
|
|
|
thread_exit();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
2013-08-28 23:05:48 +00:00
|
|
|
txg_thread_wait(tx_state_t *tx, callb_cpr_t *cpr, kcondvar_t *cv, clock_t time)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
|
CALLB_CPR_SAFE_BEGIN(cpr);
|
|
|
|
|
|
|
|
|
|
if (time)
|
2011-04-01 00:07:12 +00:00
|
|
|
(void) cv_timedwait_interruptible(cv, &tx->tx_sync_lock,
|
2010-05-28 20:45:14 +00:00
|
|
|
ddi_get_lbolt() + time);
|
2008-11-20 20:01:55 +00:00
|
|
|
else
|
2011-04-01 00:07:12 +00:00
|
|
|
cv_wait_interruptible(cv, &tx->tx_sync_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
CALLB_CPR_SAFE_END(cpr, &tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Stop syncing transaction groups.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_sync_stop(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
|
|
|
|
dprintf("pool %p\n", dp);
|
|
|
|
|
/*
|
|
|
|
|
* Finish off any work in progress.
|
|
|
|
|
*/
|
|
|
|
|
ASSERT(tx->tx_threads == 2);
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* We need to ensure that we've vacated the deferred space_maps.
|
|
|
|
|
*/
|
|
|
|
|
txg_wait_synced(dp, tx->tx_open_txg + TXG_DEFER_SIZE);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Wake all sync threads and wait for them to die.
|
|
|
|
|
*/
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
|
|
|
|
|
ASSERT(tx->tx_threads == 2);
|
|
|
|
|
|
|
|
|
|
tx->tx_exiting = 1;
|
|
|
|
|
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_more_cv);
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_done_cv);
|
|
|
|
|
cv_broadcast(&tx->tx_sync_more_cv);
|
|
|
|
|
|
|
|
|
|
while (tx->tx_threads != 0)
|
|
|
|
|
cv_wait(&tx->tx_exit_cv, &tx->tx_sync_lock);
|
|
|
|
|
|
|
|
|
|
tx->tx_exiting = 0;
|
|
|
|
|
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
uint64_t
|
|
|
|
|
txg_hold_open(dsl_pool_t *dp, txg_handle_t *th)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
2012-08-24 00:45:31 +00:00
|
|
|
tx_cpu_t *tc;
|
2008-11-20 20:01:55 +00:00
|
|
|
uint64_t txg;
|
|
|
|
|
|
2012-08-24 00:45:31 +00:00
|
|
|
/*
|
|
|
|
|
* It appears the processor id is simply used as a "random"
|
|
|
|
|
* number to index into the array, and there isn't any other
|
|
|
|
|
* significance to the chosen tx_cpu. Because.. Why not use
|
|
|
|
|
* the current cpu to index into the array?
|
|
|
|
|
*/
|
|
|
|
|
kpreempt_disable();
|
|
|
|
|
tc = &tx->tx_cpu[CPU_SEQID];
|
|
|
|
|
kpreempt_enable();
|
|
|
|
|
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_enter(&tc->tc_open_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
txg = tx->tx_open_txg;
|
2013-04-23 17:31:42 +00:00
|
|
|
|
|
|
|
|
mutex_enter(&tc->tc_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
tc->tc_count[txg & TXG_MASK]++;
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_exit(&tc->tc_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
th->th_cpu = tc;
|
|
|
|
|
th->th_txg = txg;
|
|
|
|
|
|
|
|
|
|
return (txg);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
txg_rele_to_quiesce(txg_handle_t *th)
|
|
|
|
|
{
|
|
|
|
|
tx_cpu_t *tc = th->th_cpu;
|
|
|
|
|
|
2013-04-23 17:31:42 +00:00
|
|
|
ASSERT(!MUTEX_HELD(&tc->tc_lock));
|
|
|
|
|
mutex_exit(&tc->tc_open_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
void
|
|
|
|
|
txg_register_callbacks(txg_handle_t *th, list_t *tx_callbacks)
|
|
|
|
|
{
|
|
|
|
|
tx_cpu_t *tc = th->th_cpu;
|
|
|
|
|
int g = th->th_txg & TXG_MASK;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tc->tc_lock);
|
|
|
|
|
list_move_tail(&tc->tc_callbacks[g], tx_callbacks);
|
|
|
|
|
mutex_exit(&tc->tc_lock);
|
|
|
|
|
}
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
void
|
|
|
|
|
txg_rele_to_sync(txg_handle_t *th)
|
|
|
|
|
{
|
|
|
|
|
tx_cpu_t *tc = th->th_cpu;
|
|
|
|
|
int g = th->th_txg & TXG_MASK;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tc->tc_lock);
|
|
|
|
|
ASSERT(tc->tc_count[g] != 0);
|
|
|
|
|
if (--tc->tc_count[g] == 0)
|
|
|
|
|
cv_broadcast(&tc->tc_cv[g]);
|
|
|
|
|
mutex_exit(&tc->tc_lock);
|
|
|
|
|
|
|
|
|
|
th->th_cpu = NULL; /* defensive */
|
|
|
|
|
}
|
|
|
|
|
|
2013-06-11 17:12:34 +00:00
|
|
|
/*
|
|
|
|
|
* Blocks until all transactions in the group are committed.
|
|
|
|
|
*
|
|
|
|
|
* On return, the transaction group has reached a stable state in which it can
|
|
|
|
|
* then be passed off to the syncing context.
|
|
|
|
|
*/
|
2008-11-20 20:01:55 +00:00
|
|
|
static void
|
|
|
|
|
txg_quiesce(dsl_pool_t *dp, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
int g = txg & TXG_MASK;
|
|
|
|
|
int c;
|
|
|
|
|
|
|
|
|
|
/*
|
2013-04-23 17:31:42 +00:00
|
|
|
* Grab all tc_open_locks so nobody else can get into this txg.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
for (c = 0; c < max_ncpus; c++)
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_enter(&tx->tx_cpu[c].tc_open_lock);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
ASSERT(txg == tx->tx_open_txg);
|
|
|
|
|
tx->tx_open_txg++;
|
Illumos #4045 write throttle & i/o scheduler performance work
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045
illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1913
2013-08-29 03:01:20 +00:00
|
|
|
tx->tx_open_time = gethrtime();
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2014-01-15 09:26:12 +00:00
|
|
|
spa_txg_history_set(dp->dp_spa, txg, TXG_STATE_OPEN, tx->tx_open_time);
|
|
|
|
|
spa_txg_history_add(dp->dp_spa, tx->tx_open_txg, tx->tx_open_time);
|
2013-10-01 16:50:50 +00:00
|
|
|
|
2013-08-28 23:05:48 +00:00
|
|
|
DTRACE_PROBE2(txg__quiescing, dsl_pool_t *, dp, uint64_t, txg);
|
|
|
|
|
DTRACE_PROBE2(txg__opened, dsl_pool_t *, dp, uint64_t, tx->tx_open_txg);
|
|
|
|
|
|
2013-04-25 23:29:22 +00:00
|
|
|
/*
|
|
|
|
|
* Now that we've incremented tx_open_txg, we can let threads
|
|
|
|
|
* enter the next transaction group.
|
|
|
|
|
*/
|
|
|
|
|
for (c = 0; c < max_ncpus; c++)
|
2013-04-23 17:31:42 +00:00
|
|
|
mutex_exit(&tx->tx_cpu[c].tc_open_lock);
|
2013-04-25 23:29:22 +00:00
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
|
* Quiesce the transaction group by waiting for everyone to txg_exit().
|
|
|
|
|
*/
|
|
|
|
|
for (c = 0; c < max_ncpus; c++) {
|
|
|
|
|
tx_cpu_t *tc = &tx->tx_cpu[c];
|
|
|
|
|
mutex_enter(&tc->tc_lock);
|
|
|
|
|
while (tc->tc_count[g] != 0)
|
|
|
|
|
cv_wait(&tc->tc_cv[g], &tc->tc_lock);
|
|
|
|
|
mutex_exit(&tc->tc_lock);
|
|
|
|
|
}
|
2013-10-01 16:50:50 +00:00
|
|
|
|
|
|
|
|
spa_txg_history_set(dp->dp_spa, txg, TXG_STATE_QUIESCED, gethrtime());
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
static void
|
|
|
|
|
txg_do_callbacks(list_t *cb_list)
|
|
|
|
|
{
|
|
|
|
|
dmu_tx_do_callbacks(cb_list, 0);
|
|
|
|
|
|
|
|
|
|
list_destroy(cb_list);
|
|
|
|
|
|
|
|
|
|
kmem_free(cb_list, sizeof (list_t));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Dispatch the commit callbacks registered on this txg to worker threads.
|
2013-06-11 17:12:34 +00:00
|
|
|
*
|
|
|
|
|
* If no callbacks are registered for a given TXG, nothing happens.
|
|
|
|
|
* This function creates a taskq for the associated pool, if needed.
|
2010-05-28 20:45:14 +00:00
|
|
|
*/
|
|
|
|
|
static void
|
|
|
|
|
txg_dispatch_callbacks(dsl_pool_t *dp, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int c;
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
list_t *cb_list;
|
|
|
|
|
|
|
|
|
|
for (c = 0; c < max_ncpus; c++) {
|
|
|
|
|
tx_cpu_t *tc = &tx->tx_cpu[c];
|
2013-06-11 17:12:34 +00:00
|
|
|
/*
|
|
|
|
|
* No need to lock tx_cpu_t at this point, since this can
|
|
|
|
|
* only be called once a txg has been synced.
|
|
|
|
|
*/
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
|
int g = txg & TXG_MASK;
|
|
|
|
|
|
|
|
|
|
if (list_is_empty(&tc->tc_callbacks[g]))
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
if (tx->tx_commit_cb_taskq == NULL) {
|
|
|
|
|
/*
|
|
|
|
|
* Commit callback taskq hasn't been created yet.
|
|
|
|
|
*/
|
|
|
|
|
tx->tx_commit_cb_taskq = taskq_create("tx_commit_cb",
|
2010-08-26 17:17:18 +00:00
|
|
|
100, minclsyspri, max_ncpus, INT_MAX,
|
|
|
|
|
TASKQ_THREADS_CPU_PCT | TASKQ_PREPOPULATE);
|
2010-05-28 20:45:14 +00:00
|
|
|
}
|
|
|
|
|
|
2012-05-07 17:49:51 +00:00
|
|
|
cb_list = kmem_alloc(sizeof (list_t), KM_PUSHPAGE);
|
2010-05-28 20:45:14 +00:00
|
|
|
list_create(cb_list, sizeof (dmu_tx_callback_t),
|
|
|
|
|
offsetof(dmu_tx_callback_t, dcb_node));
|
|
|
|
|
|
2010-08-26 17:17:18 +00:00
|
|
|
list_move_tail(cb_list, &tc->tc_callbacks[g]);
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
|
(void) taskq_dispatch(tx->tx_commit_cb_taskq, (task_func_t *)
|
|
|
|
|
txg_do_callbacks, cb_list, TQ_SLEEP);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2011-01-21 22:35:41 +00:00
|
|
|
/*
|
|
|
|
|
* Wait for pending commit callbacks of already-synced transactions to finish
|
|
|
|
|
* processing.
|
|
|
|
|
* Calling this function from within a commit callback will deadlock.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_wait_callbacks(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
|
|
|
|
if (tx->tx_commit_cb_taskq != NULL)
|
|
|
|
|
taskq_wait(tx->tx_commit_cb_taskq);
|
|
|
|
|
}
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
static void
|
|
|
|
|
txg_sync_thread(dsl_pool_t *dp)
|
|
|
|
|
{
|
2010-05-28 20:45:14 +00:00
|
|
|
spa_t *spa = dp->dp_spa;
|
2008-11-20 20:01:55 +00:00
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
callb_cpr_t cpr;
|
2013-10-01 16:50:50 +00:00
|
|
|
vdev_stat_t *vs1, *vs2;
|
2014-02-25 09:32:21 +00:00
|
|
|
clock_t start, delta;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2012-08-18 18:17:23 +00:00
|
|
|
#ifdef _KERNEL
|
|
|
|
|
/*
|
|
|
|
|
* Annotate this process with a flag that indicates that it is
|
|
|
|
|
* unsafe to use KM_SLEEP during memory allocations due to the
|
|
|
|
|
* potential for a deadlock. KM_PUSHPAGE should be used instead.
|
|
|
|
|
*/
|
|
|
|
|
current->flags |= PF_NOFS;
|
|
|
|
|
#endif /* _KERNEL */
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_thread_enter(tx, &cpr);
|
|
|
|
|
|
2013-11-01 19:26:11 +00:00
|
|
|
vs1 = kmem_alloc(sizeof (vdev_stat_t), KM_PUSHPAGE);
|
|
|
|
|
vs2 = kmem_alloc(sizeof (vdev_stat_t), KM_PUSHPAGE);
|
2013-10-01 16:50:50 +00:00
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
start = delta = 0;
|
|
|
|
|
for (;;) {
|
2014-02-25 09:32:21 +00:00
|
|
|
clock_t timer, timeout;
|
2008-12-03 20:09:06 +00:00
|
|
|
uint64_t txg;
|
2014-02-28 00:32:36 +00:00
|
|
|
uint64_t ndirty;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2012-10-11 20:56:32 +00:00
|
|
|
timeout = zfs_txg_timeout * hz;
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
2010-05-28 20:45:14 +00:00
|
|
|
* We sync when we're scanning, there's someone waiting
|
2008-12-03 20:09:06 +00:00
|
|
|
* on us, or the quiesce thread has handed off a txg to
|
|
|
|
|
* us, or we have reached our timeout.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
timer = (delta >= timeout ? 0 : timeout - delta);
|
2010-05-28 20:45:14 +00:00
|
|
|
while (!dsl_scan_active(dp->dp_scan) &&
|
2008-12-03 20:09:06 +00:00
|
|
|
!tx->tx_exiting && timer > 0 &&
|
2008-11-20 20:01:55 +00:00
|
|
|
tx->tx_synced_txg >= tx->tx_sync_txg_waiting &&
|
Illumos #4045 write throttle & i/o scheduler performance work
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045
illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1913
2013-08-29 03:01:20 +00:00
|
|
|
tx->tx_quiesced_txg == 0 &&
|
|
|
|
|
dp->dp_dirty_total < zfs_dirty_data_sync) {
|
2008-11-20 20:01:55 +00:00
|
|
|
dprintf("waiting; tx_synced=%llu waiting=%llu dp=%p\n",
|
|
|
|
|
tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
|
|
|
|
|
txg_thread_wait(tx, &cpr, &tx->tx_sync_more_cv, timer);
|
2010-05-28 20:45:14 +00:00
|
|
|
delta = ddi_get_lbolt() - start;
|
2008-11-20 20:01:55 +00:00
|
|
|
timer = (delta > timeout ? 0 : timeout - delta);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Wait until the quiesce thread hands off a txg to us,
|
|
|
|
|
* prompting it to do so if necessary.
|
|
|
|
|
*/
|
|
|
|
|
while (!tx->tx_exiting && tx->tx_quiesced_txg == 0) {
|
|
|
|
|
if (tx->tx_quiesce_txg_waiting < tx->tx_open_txg+1)
|
|
|
|
|
tx->tx_quiesce_txg_waiting = tx->tx_open_txg+1;
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_more_cv);
|
|
|
|
|
txg_thread_wait(tx, &cpr, &tx->tx_quiesce_done_cv, 0);
|
|
|
|
|
}
|
|
|
|
|
|
2013-10-01 16:50:50 +00:00
|
|
|
if (tx->tx_exiting) {
|
2013-11-01 19:26:11 +00:00
|
|
|
kmem_free(vs2, sizeof (vdev_stat_t));
|
|
|
|
|
kmem_free(vs1, sizeof (vdev_stat_t));
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_thread_exit(tx, &cpr, &tx->tx_sync_thread);
|
2013-10-01 16:50:50 +00:00
|
|
|
}
|
|
|
|
|
|
2014-07-19 20:19:24 +00:00
|
|
|
spa_config_enter(spa, SCL_ALL, FTAG, RW_READER);
|
2013-10-01 16:50:50 +00:00
|
|
|
vdev_get_stats(spa->spa_root_vdev, vs1);
|
2014-07-19 20:19:24 +00:00
|
|
|
spa_config_exit(spa, SCL_ALL, FTAG);
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Consume the quiesced txg which has been handed off to
|
|
|
|
|
* us. This may cause the quiescing thread to now be
|
|
|
|
|
* able to quiesce another txg, so we must signal it.
|
|
|
|
|
*/
|
|
|
|
|
txg = tx->tx_quiesced_txg;
|
|
|
|
|
tx->tx_quiesced_txg = 0;
|
|
|
|
|
tx->tx_syncing_txg = txg;
|
2013-08-28 23:05:48 +00:00
|
|
|
DTRACE_PROBE2(txg__syncing, dsl_pool_t *, dp, uint64_t, txg);
|
2008-11-20 20:01:55 +00:00
|
|
|
cv_broadcast(&tx->tx_quiesce_more_cv);
|
|
|
|
|
|
|
|
|
|
dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
|
|
|
|
|
txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
2008-12-03 20:09:06 +00:00
|
|
|
|
2014-01-16 09:41:27 +00:00
|
|
|
spa_txg_history_set(spa, txg, TXG_STATE_WAIT_FOR_SYNC,
|
|
|
|
|
gethrtime());
|
2014-02-28 00:32:36 +00:00
|
|
|
ndirty = dp->dp_dirty_pertxg[txg & TXG_MASK];
|
2014-01-16 09:41:27 +00:00
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
start = ddi_get_lbolt();
|
|
|
|
|
spa_sync(spa, txg);
|
|
|
|
|
delta = ddi_get_lbolt() - start;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
tx->tx_synced_txg = txg;
|
|
|
|
|
tx->tx_syncing_txg = 0;
|
2013-08-28 23:05:48 +00:00
|
|
|
DTRACE_PROBE2(txg__synced, dsl_pool_t *, dp, uint64_t, txg);
|
2008-11-20 20:01:55 +00:00
|
|
|
cv_broadcast(&tx->tx_sync_done_cv);
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Dispatch commit callbacks to worker threads.
|
|
|
|
|
*/
|
|
|
|
|
txg_dispatch_callbacks(dp, txg);
|
2013-10-01 16:50:50 +00:00
|
|
|
|
2014-07-19 20:19:24 +00:00
|
|
|
spa_config_enter(spa, SCL_ALL, FTAG, RW_READER);
|
2013-10-01 16:50:50 +00:00
|
|
|
vdev_get_stats(spa->spa_root_vdev, vs2);
|
2014-07-19 20:19:24 +00:00
|
|
|
spa_config_exit(spa, SCL_ALL, FTAG);
|
2013-10-01 16:50:50 +00:00
|
|
|
spa_txg_history_set_io(spa, txg,
|
|
|
|
|
vs2->vs_bytes[ZIO_TYPE_READ]-vs1->vs_bytes[ZIO_TYPE_READ],
|
|
|
|
|
vs2->vs_bytes[ZIO_TYPE_WRITE]-vs1->vs_bytes[ZIO_TYPE_WRITE],
|
|
|
|
|
vs2->vs_ops[ZIO_TYPE_READ]-vs1->vs_ops[ZIO_TYPE_READ],
|
|
|
|
|
vs2->vs_ops[ZIO_TYPE_WRITE]-vs1->vs_ops[ZIO_TYPE_WRITE],
|
2014-02-28 00:32:36 +00:00
|
|
|
ndirty);
|
2013-10-01 16:50:50 +00:00
|
|
|
spa_txg_history_set(spa, txg, TXG_STATE_SYNCED, gethrtime());
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void
|
|
|
|
|
txg_quiesce_thread(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
callb_cpr_t cpr;
|
|
|
|
|
|
|
|
|
|
txg_thread_enter(tx, &cpr);
|
|
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
|
uint64_t txg;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* We quiesce when there's someone waiting on us.
|
|
|
|
|
* However, we can only have one txg in "quiescing" or
|
|
|
|
|
* "quiesced, waiting to sync" state. So we wait until
|
|
|
|
|
* the "quiesced, waiting to sync" txg has been consumed
|
|
|
|
|
* by the sync thread.
|
|
|
|
|
*/
|
|
|
|
|
while (!tx->tx_exiting &&
|
|
|
|
|
(tx->tx_open_txg >= tx->tx_quiesce_txg_waiting ||
|
|
|
|
|
tx->tx_quiesced_txg != 0))
|
|
|
|
|
txg_thread_wait(tx, &cpr, &tx->tx_quiesce_more_cv, 0);
|
|
|
|
|
|
|
|
|
|
if (tx->tx_exiting)
|
|
|
|
|
txg_thread_exit(tx, &cpr, &tx->tx_quiesce_thread);
|
|
|
|
|
|
|
|
|
|
txg = tx->tx_open_txg;
|
|
|
|
|
dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
|
|
|
|
|
txg, tx->tx_quiesce_txg_waiting,
|
|
|
|
|
tx->tx_sync_txg_waiting);
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
txg_quiesce(dp, txg);
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Hand this txg off to the sync thread.
|
|
|
|
|
*/
|
|
|
|
|
dprintf("quiesce done, handing off txg %llu\n", txg);
|
|
|
|
|
tx->tx_quiesced_txg = txg;
|
2013-08-28 23:05:48 +00:00
|
|
|
DTRACE_PROBE2(txg__quiesced, dsl_pool_t *, dp, uint64_t, txg);
|
2008-11-20 20:01:55 +00:00
|
|
|
cv_broadcast(&tx->tx_sync_more_cv);
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_done_cv);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2013-08-28 23:05:48 +00:00
|
|
|
* Delay this thread by delay nanoseconds if we are still in the open
|
|
|
|
|
* transaction group and there is already a waiting txg quiesing or quiesced.
|
|
|
|
|
* Abort the delay if this txg stalls or enters the quiesing state.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
|
|
|
|
void
|
2013-08-28 23:05:48 +00:00
|
|
|
txg_delay(dsl_pool_t *dp, uint64_t txg, hrtime_t delay, hrtime_t resolution)
|
2008-11-20 20:01:55 +00:00
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
2013-08-28 23:05:48 +00:00
|
|
|
hrtime_t start = gethrtime();
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2013-06-11 17:12:34 +00:00
|
|
|
/* don't delay if this txg could transition to quiescing immediately */
|
2008-11-20 20:01:55 +00:00
|
|
|
if (tx->tx_open_txg > txg ||
|
|
|
|
|
tx->tx_syncing_txg == txg-1 || tx->tx_synced_txg == txg-1)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
if (tx->tx_open_txg > txg || tx->tx_synced_txg == txg-1) {
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
2013-08-28 23:05:48 +00:00
|
|
|
while (gethrtime() - start < delay &&
|
|
|
|
|
tx->tx_syncing_txg < txg-1 && !txg_stalled(dp)) {
|
|
|
|
|
(void) cv_timedwait_hires(&tx->tx_quiesce_more_cv,
|
|
|
|
|
&tx->tx_sync_lock, delay, resolution, 0);
|
|
|
|
|
}
|
2008-11-20 20:01:55 +00:00
|
|
|
|
2012-01-20 18:58:57 +00:00
|
|
|
DMU_TX_STAT_BUMP(dmu_tx_delay);
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
txg_wait_synced(dsl_pool_t *dp, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
ASSERT(!dsl_pool_config_held(dp));
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
ASSERT(tx->tx_threads == 2);
|
|
|
|
|
if (txg == 0)
|
2010-05-28 20:45:14 +00:00
|
|
|
txg = tx->tx_open_txg + TXG_DEFER_SIZE;
|
2008-11-20 20:01:55 +00:00
|
|
|
if (tx->tx_sync_txg_waiting < txg)
|
|
|
|
|
tx->tx_sync_txg_waiting = txg;
|
|
|
|
|
dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
|
|
|
|
|
txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
|
|
|
|
|
while (tx->tx_synced_txg < txg) {
|
|
|
|
|
dprintf("broadcasting sync more "
|
|
|
|
|
"tx_synced=%llu waiting=%llu dp=%p\n",
|
|
|
|
|
tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
|
|
|
|
|
cv_broadcast(&tx->tx_sync_more_cv);
|
|
|
|
|
cv_wait(&tx->tx_sync_done_cv, &tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
txg_wait_open(dsl_pool_t *dp, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
ASSERT(!dsl_pool_config_held(dp));
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
ASSERT(tx->tx_threads == 2);
|
|
|
|
|
if (txg == 0)
|
|
|
|
|
txg = tx->tx_open_txg + 1;
|
|
|
|
|
if (tx->tx_quiesce_txg_waiting < txg)
|
|
|
|
|
tx->tx_quiesce_txg_waiting = txg;
|
|
|
|
|
dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
|
|
|
|
|
txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
|
|
|
|
|
while (tx->tx_open_txg < txg) {
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_more_cv);
|
|
|
|
|
cv_wait(&tx->tx_quiesce_done_cv, &tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
Illumos #4045 write throttle & i/o scheduler performance work
4045 zfs write throttle & i/o scheduler performance work
1. The ZFS i/o scheduler (vdev_queue.c) now divides i/os into 5 classes: sync
read, sync write, async read, async write, and scrub/resilver. The scheduler
issues a number of concurrent i/os from each class to the device. Once a class
has been selected, an i/o is selected from this class using either an elevator
algorithem (async, scrub classes) or FIFO (sync classes). The number of
concurrent async write i/os is tuned dynamically based on i/o load, to achieve
good sync i/o latency when there is not a high load of writes, and good write
throughput when there is. See the block comment in vdev_queue.c (reproduced
below) for more details.
2. The write throttle (dsl_pool_tempreserve_space() and
txg_constrain_throughput()) is rewritten to produce much more consistent delays
when under constant load. The new write throttle is based on the amount of
dirty data, rather than guesses about future performance of the system. When
there is a lot of dirty data, each transaction (e.g. write() syscall) will be
delayed by the same small amount. This eliminates the "brick wall of wait"
that the old write throttle could hit, causing all transactions to wait several
seconds until the next txg opens. One of the keys to the new write throttle is
decrementing the amount of dirty data as i/o completes, rather than at the end
of spa_sync(). Note that the write throttle is only applied once the i/o
scheduler is issuing the maximum number of outstanding async writes. See the
block comments in dsl_pool.c and above dmu_tx_delay() (reproduced below) for
more details.
This diff has several other effects, including:
* the commonly-tuned global variable zfs_vdev_max_pending has been removed;
use per-class zfs_vdev_*_max_active values or zfs_vdev_max_active instead.
* the size of each txg (meaning the amount of dirty data written, and thus the
time it takes to write out) is now controlled differently. There is no longer
an explicit time goal; the primary determinant is amount of dirty data.
Systems that are under light or medium load will now often see that a txg is
always syncing, but the impact to performance (e.g. read latency) is minimal.
Tune zfs_dirty_data_max and zfs_dirty_data_sync to control this.
* zio_taskq_batch_pct = 75 -- Only use 75% of all CPUs for compression,
checksum, etc. This improves latency by not allowing these CPU-intensive tasks
to consume all CPU (on machines with at least 4 CPU's; the percentage is
rounded up).
--matt
APPENDIX: problems with the current i/o scheduler
The current ZFS i/o scheduler (vdev_queue.c) is deadline based. The problem
with this is that if there are always i/os pending, then certain classes of
i/os can see very long delays.
For example, if there are always synchronous reads outstanding, then no async
writes will be serviced until they become "past due". One symptom of this
situation is that each pass of the txg sync takes at least several seconds
(typically 3 seconds).
If many i/os become "past due" (their deadline is in the past), then we must
service all of these overdue i/os before any new i/os. This happens when we
enqueue a batch of async writes for the txg sync, with deadlines 2.5 seconds in
the future. If we can't complete all the i/os in 2.5 seconds (e.g. because
there were always reads pending), then these i/os will become past due. Now we
must service all the "async" writes (which could be hundreds of megabytes)
before we service any reads, introducing considerable latency to synchronous
i/os (reads or ZIL writes).
Notes on porting to ZFS on Linux:
- zio_t gained new members io_physdone and io_phys_children. Because
object caches in the Linux port call the constructor only once at
allocation time, objects may contain residual data when retrieved
from the cache. Therefore zio_create() was updated to zero out the two
new fields.
- vdev_mirror_pending() relied on the depth of the per-vdev pending queue
(vq->vq_pending_tree) to select the least-busy leaf vdev to read from.
This tree has been replaced by vq->vq_active_tree which is now used
for the same purpose.
- vdev_queue_init() used the value of zfs_vdev_max_pending to determine
the number of vdev I/O buffers to pre-allocate. That global no longer
exists, so we instead use the sum of the *_max_active values for each of
the five I/O classes described above.
- The Illumos implementation of dmu_tx_delay() delays a transaction by
sleeping in condition variable embedded in the thread
(curthread->t_delay_cv). We do not have an equivalent CV to use in
Linux, so this change replaced the delay logic with a wrapper called
zfs_sleep_until(). This wrapper could be adopted upstream and in other
downstream ports to abstract away operating system-specific delay logic.
- These tunables are added as module parameters, and descriptions added
to the zfs-module-parameters.5 man page.
spa_asize_inflation
zfs_deadman_synctime_ms
zfs_vdev_max_active
zfs_vdev_async_write_active_min_dirty_percent
zfs_vdev_async_write_active_max_dirty_percent
zfs_vdev_async_read_max_active
zfs_vdev_async_read_min_active
zfs_vdev_async_write_max_active
zfs_vdev_async_write_min_active
zfs_vdev_scrub_max_active
zfs_vdev_scrub_min_active
zfs_vdev_sync_read_max_active
zfs_vdev_sync_read_min_active
zfs_vdev_sync_write_max_active
zfs_vdev_sync_write_min_active
zfs_dirty_data_max_percent
zfs_delay_min_dirty_percent
zfs_dirty_data_max_max_percent
zfs_dirty_data_max
zfs_dirty_data_max_max
zfs_dirty_data_sync
zfs_delay_scale
The latter four have type unsigned long, whereas they are uint64_t in
Illumos. This accommodates Linux's module_param() supported types, but
means they may overflow on 32-bit architectures.
The values zfs_dirty_data_max and zfs_dirty_data_max_max are the most
likely to overflow on 32-bit systems, since they express physical RAM
sizes in bytes. In fact, Illumos initializes zfs_dirty_data_max_max to
2^32 which does overflow. To resolve that, this port instead initializes
it in arc_init() to 25% of physical RAM, and adds the tunable
zfs_dirty_data_max_max_percent to override that percentage. While this
solution doesn't completely avoid the overflow issue, it should be a
reasonable default for most systems, and the minority of affected
systems can work around the issue by overriding the defaults.
- Fixed reversed logic in comment above zfs_delay_scale declaration.
- Clarified comments in vdev_queue.c regarding when per-queue minimums take
effect.
- Replaced dmu_tx_write_limit in the dmu_tx kstat file
with dmu_tx_dirty_delay and dmu_tx_dirty_over_max. The first counts
how many times a transaction has been delayed because the pool dirty
data has exceeded zfs_delay_min_dirty_percent. The latter counts how
many times the pool dirty data has exceeded zfs_dirty_data_max (which
we expect to never happen).
- The original patch would have regressed the bug fixed in
zfsonlinux/zfs@c418410, which prevented users from setting the
zfs_vdev_aggregation_limit tuning larger than SPA_MAXBLOCKSIZE.
A similar fix is added to vdev_queue_aggregate().
- In vdev_queue_io_to_issue(), dynamically allocate 'zio_t search' on the
heap instead of the stack. In Linux we can't afford such large
structures on the stack.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brendan Gregg <brendan.gregg@joyent.com>
Approved by: Robert Mustacchi <rm@joyent.com>
References:
http://www.illumos.org/issues/4045
illumos/illumos-gate@69962b5647e4a8b9b14998733b765925381b727e
Ported-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #1913
2013-08-29 03:01:20 +00:00
|
|
|
/*
|
|
|
|
|
* If there isn't a txg syncing or in the pipeline, push another txg through
|
|
|
|
|
* the pipeline by queiscing the open txg.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_kick(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
|
|
|
|
ASSERT(!dsl_pool_config_held(dp));
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tx->tx_sync_lock);
|
|
|
|
|
if (tx->tx_syncing_txg == 0 &&
|
|
|
|
|
tx->tx_quiesce_txg_waiting <= tx->tx_open_txg &&
|
|
|
|
|
tx->tx_sync_txg_waiting <= tx->tx_synced_txg &&
|
|
|
|
|
tx->tx_quiesced_txg <= tx->tx_synced_txg) {
|
|
|
|
|
tx->tx_quiesce_txg_waiting = tx->tx_open_txg + 1;
|
|
|
|
|
cv_broadcast(&tx->tx_quiesce_more_cv);
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tx->tx_sync_lock);
|
|
|
|
|
}
|
|
|
|
|
|
2008-12-03 20:09:06 +00:00
|
|
|
boolean_t
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_stalled(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
return (tx->tx_quiesce_txg_waiting > tx->tx_open_txg);
|
|
|
|
|
}
|
|
|
|
|
|
2008-12-03 20:09:06 +00:00
|
|
|
boolean_t
|
|
|
|
|
txg_sync_waiting(dsl_pool_t *dp)
|
|
|
|
|
{
|
|
|
|
|
tx_state_t *tx = &dp->dp_tx;
|
|
|
|
|
|
|
|
|
|
return (tx->tx_syncing_txg <= tx->tx_sync_txg_waiting ||
|
|
|
|
|
tx->tx_quiesced_txg != 0);
|
|
|
|
|
}
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
|
* Per-txg object lists.
|
|
|
|
|
*/
|
|
|
|
|
void
|
|
|
|
|
txg_list_create(txg_list_t *tl, size_t offset)
|
|
|
|
|
{
|
|
|
|
|
int t;
|
|
|
|
|
|
|
|
|
|
mutex_init(&tl->tl_lock, NULL, MUTEX_DEFAULT, NULL);
|
|
|
|
|
|
|
|
|
|
tl->tl_offset = offset;
|
|
|
|
|
|
|
|
|
|
for (t = 0; t < TXG_SIZE; t++)
|
|
|
|
|
tl->tl_head[t] = NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
txg_list_destroy(txg_list_t *tl)
|
|
|
|
|
{
|
|
|
|
|
int t;
|
|
|
|
|
|
|
|
|
|
for (t = 0; t < TXG_SIZE; t++)
|
|
|
|
|
ASSERT(txg_list_empty(tl, t));
|
|
|
|
|
|
|
|
|
|
mutex_destroy(&tl->tl_lock);
|
|
|
|
|
}
|
|
|
|
|
|
2012-12-15 00:13:40 +00:00
|
|
|
boolean_t
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_list_empty(txg_list_t *tl, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
return (tl->tl_head[txg & TXG_MASK] == NULL);
|
|
|
|
|
}
|
|
|
|
|
|
2014-07-18 15:08:31 +00:00
|
|
|
/*
|
|
|
|
|
* Returns true if all txg lists are empty.
|
|
|
|
|
*
|
|
|
|
|
* Warning: this is inherently racy (an item could be added immediately
|
|
|
|
|
* after this function returns). We don't bother with the lock because
|
|
|
|
|
* it wouldn't change the semantics.
|
|
|
|
|
*/
|
|
|
|
|
boolean_t
|
|
|
|
|
txg_all_lists_empty(txg_list_t *tl)
|
|
|
|
|
{
|
|
|
|
|
int i;
|
|
|
|
|
|
|
|
|
|
for (i = 0; i < TXG_SIZE; i++) {
|
|
|
|
|
if (!txg_list_empty(tl, i)) {
|
|
|
|
|
return (B_FALSE);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return (B_TRUE);
|
|
|
|
|
}
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
2013-09-04 12:00:57 +00:00
|
|
|
* Add an entry to the list (unless it's already on the list).
|
|
|
|
|
* Returns B_TRUE if it was actually added.
|
2008-11-20 20:01:55 +00:00
|
|
|
*/
|
2013-09-04 12:00:57 +00:00
|
|
|
boolean_t
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_list_add(txg_list_t *tl, void *p, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);
|
2013-09-04 12:00:57 +00:00
|
|
|
boolean_t add;
|
2008-11-20 20:01:55 +00:00
|
|
|
|
|
|
|
|
mutex_enter(&tl->tl_lock);
|
2013-09-04 12:00:57 +00:00
|
|
|
add = (tn->tn_member[t] == 0);
|
|
|
|
|
if (add) {
|
2008-11-20 20:01:55 +00:00
|
|
|
tn->tn_member[t] = 1;
|
|
|
|
|
tn->tn_next[t] = tl->tl_head[t];
|
|
|
|
|
tl->tl_head[t] = tn;
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tl->tl_lock);
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
return (add);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
2010-05-28 20:45:14 +00:00
|
|
|
/*
|
2013-09-04 12:00:57 +00:00
|
|
|
* Add an entry to the end of the list, unless it's already on the list.
|
|
|
|
|
* (walks list to find end)
|
|
|
|
|
* Returns B_TRUE if it was actually added.
|
2010-05-28 20:45:14 +00:00
|
|
|
*/
|
2013-09-04 12:00:57 +00:00
|
|
|
boolean_t
|
2010-05-28 20:45:14 +00:00
|
|
|
txg_list_add_tail(txg_list_t *tl, void *p, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);
|
2013-09-04 12:00:57 +00:00
|
|
|
boolean_t add;
|
2010-05-28 20:45:14 +00:00
|
|
|
|
|
|
|
|
mutex_enter(&tl->tl_lock);
|
2013-09-04 12:00:57 +00:00
|
|
|
add = (tn->tn_member[t] == 0);
|
|
|
|
|
if (add) {
|
2010-05-28 20:45:14 +00:00
|
|
|
txg_node_t **tp;
|
|
|
|
|
|
|
|
|
|
for (tp = &tl->tl_head[t]; *tp != NULL; tp = &(*tp)->tn_next[t])
|
|
|
|
|
continue;
|
|
|
|
|
|
|
|
|
|
tn->tn_member[t] = 1;
|
|
|
|
|
tn->tn_next[t] = NULL;
|
|
|
|
|
*tp = tn;
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tl->tl_lock);
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
return (add);
|
2010-05-28 20:45:14 +00:00
|
|
|
}
|
|
|
|
|
|
2008-11-20 20:01:55 +00:00
|
|
|
/*
|
|
|
|
|
* Remove the head of the list and return it.
|
|
|
|
|
*/
|
|
|
|
|
void *
|
|
|
|
|
txg_list_remove(txg_list_t *tl, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn;
|
|
|
|
|
void *p = NULL;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tl->tl_lock);
|
|
|
|
|
if ((tn = tl->tl_head[t]) != NULL) {
|
|
|
|
|
p = (char *)tn - tl->tl_offset;
|
|
|
|
|
tl->tl_head[t] = tn->tn_next[t];
|
|
|
|
|
tn->tn_next[t] = NULL;
|
|
|
|
|
tn->tn_member[t] = 0;
|
|
|
|
|
}
|
|
|
|
|
mutex_exit(&tl->tl_lock);
|
|
|
|
|
|
|
|
|
|
return (p);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Remove a specific item from the list and return it.
|
|
|
|
|
*/
|
|
|
|
|
void *
|
|
|
|
|
txg_list_remove_this(txg_list_t *tl, void *p, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn, **tp;
|
|
|
|
|
|
|
|
|
|
mutex_enter(&tl->tl_lock);
|
|
|
|
|
|
|
|
|
|
for (tp = &tl->tl_head[t]; (tn = *tp) != NULL; tp = &tn->tn_next[t]) {
|
|
|
|
|
if ((char *)tn - tl->tl_offset == p) {
|
|
|
|
|
*tp = tn->tn_next[t];
|
|
|
|
|
tn->tn_next[t] = NULL;
|
|
|
|
|
tn->tn_member[t] = 0;
|
|
|
|
|
mutex_exit(&tl->tl_lock);
|
|
|
|
|
return (p);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
mutex_exit(&tl->tl_lock);
|
|
|
|
|
|
|
|
|
|
return (NULL);
|
|
|
|
|
}
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
boolean_t
|
2008-11-20 20:01:55 +00:00
|
|
|
txg_list_member(txg_list_t *tl, void *p, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);
|
|
|
|
|
|
2013-09-04 12:00:57 +00:00
|
|
|
return (tn->tn_member[t] != 0);
|
2008-11-20 20:01:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Walk a txg list -- only safe if you know it's not changing.
|
|
|
|
|
*/
|
|
|
|
|
void *
|
|
|
|
|
txg_list_head(txg_list_t *tl, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn = tl->tl_head[t];
|
|
|
|
|
|
|
|
|
|
return (tn == NULL ? NULL : (char *)tn - tl->tl_offset);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void *
|
|
|
|
|
txg_list_next(txg_list_t *tl, void *p, uint64_t txg)
|
|
|
|
|
{
|
|
|
|
|
int t = txg & TXG_MASK;
|
|
|
|
|
txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);
|
|
|
|
|
|
|
|
|
|
tn = tn->tn_next[t];
|
|
|
|
|
|
|
|
|
|
return (tn == NULL ? NULL : (char *)tn - tl->tl_offset);
|
|
|
|
|
}
|
2010-08-26 18:49:16 +00:00
|
|
|
|
|
|
|
|
#if defined(_KERNEL) && defined(HAVE_SPL)
|
|
|
|
|
EXPORT_SYMBOL(txg_init);
|
|
|
|
|
EXPORT_SYMBOL(txg_fini);
|
|
|
|
|
EXPORT_SYMBOL(txg_sync_start);
|
|
|
|
|
EXPORT_SYMBOL(txg_sync_stop);
|
|
|
|
|
EXPORT_SYMBOL(txg_hold_open);
|
|
|
|
|
EXPORT_SYMBOL(txg_rele_to_quiesce);
|
|
|
|
|
EXPORT_SYMBOL(txg_rele_to_sync);
|
|
|
|
|
EXPORT_SYMBOL(txg_register_callbacks);
|
|
|
|
|
EXPORT_SYMBOL(txg_delay);
|
|
|
|
|
EXPORT_SYMBOL(txg_wait_synced);
|
|
|
|
|
EXPORT_SYMBOL(txg_wait_open);
|
2011-01-21 22:35:41 +00:00
|
|
|
EXPORT_SYMBOL(txg_wait_callbacks);
|
2010-08-26 18:49:16 +00:00
|
|
|
EXPORT_SYMBOL(txg_stalled);
|
|
|
|
|
EXPORT_SYMBOL(txg_sync_waiting);
|
2012-10-11 20:56:32 +00:00
|
|
|
|
|
|
|
|
module_param(zfs_txg_timeout, int, 0644);
|
|
|
|
|
MODULE_PARM_DESC(zfs_txg_timeout, "Max seconds worth of delta per txg");
|
2010-08-26 18:49:16 +00:00
|
|
|
#endif
|
