d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

MFV r337171:

Browse Source 
9464 txg_kick() fails to see that we are quiescing, forcing transactions
to their next stages without leaving them accumulate changes

Ideally we would like txg_kick() to get triggered only when we are sure
that we are not syncing AND not quiescing any txg. This way we can kick
an open TXG to the quiescing state when we are sure that there is nothing
going on and we would benefit from the different states running
concurrently.

illumos/illumos-gate@fa41d87de9

Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Andriy Gapon <avg@FreeBSD.org>
Approved by: Dan McDonald <danmcd@joyent.com>
Author:     Serapheim Dimitropoulos <serapheim@delphix.com>
This commit is contained in:
Alexander Motin 2018-08-02 20:18:49 +00:00
commit 0485d5cba8
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=337172
3 changed files with 41 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_tx.c
View File

@ -1091,7 +1091,12 @@ dmu_tx_wait(dmu_tx_t *tx)
mutex_exit(&dn->dn_mtx);
tx->tx_needassign_txh = NULL;
} else {
txg_wait_open(tx->tx_pool, tx->tx_lasttried_txg + 1);
/*
* If we have a lot of dirty data just wait until we sync
* out a TXG at which point we'll hopefully have synced
* a portion of the changes.
*/
txg_wait_synced(dp, spa_last_synced_txg(spa) + 1);
}
}

3
sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/txg_impl.h
View File

@ -25,7 +25,7 @@
*/
/*
* Copyright (c) 2013 by Delphix. All rights reserved.
* Copyright (c) 2013, 2017 by Delphix. All rights reserved.
*/
#ifndef _SYS_TXG_IMPL_H
@ -92,6 +92,7 @@ typedef struct tx_state {
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 */

37
sys/cddl/contrib/opensolaris/uts/common/fs/zfs/txg.c
View File

@ -450,6 +450,30 @@ txg_dispatch_callbacks(dsl_pool_t *dp, uint64_t txg)
}
}
static boolean_t
txg_is_syncing(dsl_pool_t *dp)
{
tx_state_t *tx = &dp->dp_tx;
ASSERT(MUTEX_HELD(&tx->tx_sync_lock));
return (tx->tx_syncing_txg != 0);
}
static boolean_t
txg_is_quiescing(dsl_pool_t *dp)
{
tx_state_t *tx = &dp->dp_tx;
ASSERT(MUTEX_HELD(&tx->tx_sync_lock));
return (tx->tx_quiescing_txg != 0);
}
static boolean_t
txg_has_quiesced_to_sync(dsl_pool_t *dp)
{
tx_state_t *tx = &dp->dp_tx;
ASSERT(MUTEX_HELD(&tx->tx_sync_lock));
return (tx->tx_quiesced_txg != 0);
}
static void
txg_sync_thread(void *arg)
{
@ -476,7 +500,7 @@ txg_sync_thread(void *arg)
while (!dsl_scan_active(dp->dp_scan) &&
!tx->tx_exiting && timer > 0 &&
tx->tx_synced_txg >= tx->tx_sync_txg_waiting &&
tx->tx_quiesced_txg == 0 &&
!txg_has_quiesced_to_sync(dp) &&
dp->dp_dirty_total < zfs_dirty_data_sync) {
dprintf("waiting; tx_synced=%llu waiting=%llu dp=%p\n",
tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
@ -489,7 +513,7 @@ txg_sync_thread(void *arg)
* 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) {
while (!tx->tx_exiting && !txg_has_quiesced_to_sync(dp)) {
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);
@ -504,6 +528,7 @@ txg_sync_thread(void *arg)
* us. This may cause the quiescing thread to now be
* able to quiesce another txg, so we must signal it.
*/
ASSERT(tx->tx_quiesced_txg != 0);
txg = tx->tx_quiesced_txg;
tx->tx_quiesced_txg = 0;
tx->tx_syncing_txg = txg;
@ -552,7 +577,7 @@ txg_quiesce_thread(void *arg)
*/
while (!tx->tx_exiting &&
(tx->tx_open_txg >= tx->tx_quiesce_txg_waiting ||
tx->tx_quiesced_txg != 0))
txg_has_quiesced_to_sync(dp)))
txg_thread_wait(tx, &cpr, &tx->tx_quiesce_more_cv, 0);
if (tx->tx_exiting)
@ -562,6 +587,8 @@ txg_quiesce_thread(void *arg)
dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
txg, tx->tx_quiesce_txg_waiting,
tx->tx_sync_txg_waiting);
tx->tx_quiescing_txg = txg;
mutex_exit(&tx->tx_sync_lock);
txg_quiesce(dp, txg);
mutex_enter(&tx->tx_sync_lock);
@ -570,6 +597,7 @@ txg_quiesce_thread(void *arg)
* Hand this txg off to the sync thread.
*/
dprintf("quiesce done, handing off txg %llu\n", txg);
tx->tx_quiescing_txg = 0;
tx->tx_quiesced_txg = txg;
DTRACE_PROBE2(txg__quiesced, dsl_pool_t *, dp, uint64_t, txg);
cv_broadcast(&tx->tx_sync_more_cv);
@ -667,7 +695,8 @@ txg_kick(dsl_pool_t *dp)
ASSERT(!dsl_pool_config_held(dp));
mutex_enter(&tx->tx_sync_lock);
if (tx->tx_syncing_txg == 0 &&
if (!txg_is_syncing(dp) &&
!txg_is_quiescing(dp) &&
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) {