From 57f5a2008e2e6acf58934cf43c5fdca0faffa73e Mon Sep 17 00:00:00 2001 From: Brian Behlendorf Date: Thu, 25 Apr 2013 16:29:22 -0700 Subject: Fix txg_quiesce thread deadlock A deadlock was accidentally introduced by commit e95853a which can occur when the system is under memory pressure. What happens is that while the txg_quiesce thread is holding the tx->tx_cpu locks it enters memory reclaim. In the context of this memory reclaim it then issues synchronous I/O to a ZVOL swap device. Because the txg_quiesce thread is holding the tx->tx_cpu locks a new txg cannot be opened to handle the I/O. Deadlock. The fix is straight forward. Move the memory allocation outside the critical region where the tx->tx_cpu locks are held. And for good measure change the offending allocation to KM_PUSHPAGE to ensure it never attempts to issue I/O during reclaim. Signed-off-by: Brian Behlendorf Issue #1274 --- module/zfs/dsl_pool.c | 2 +- module/zfs/txg.c | 14 +++++++------- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'module') diff --git a/module/zfs/dsl_pool.c b/module/zfs/dsl_pool.c index 704f034e9..771b265c2 100644 --- a/module/zfs/dsl_pool.c +++ b/module/zfs/dsl_pool.c @@ -143,7 +143,7 @@ dsl_pool_txg_history_add(dsl_pool_t *dp, uint64_t txg) { txg_history_t *th, *rm; - th = kmem_zalloc(sizeof(txg_history_t), KM_SLEEP); + th = kmem_zalloc(sizeof(txg_history_t), KM_PUSHPAGE); mutex_init(&th->th_lock, NULL, MUTEX_DEFAULT, NULL); th->th_kstat.txg = txg; th->th_kstat.state = TXG_STATE_OPEN; diff --git a/module/zfs/txg.c b/module/zfs/txg.c index c7c3df3f8..7c820af4f 100644 --- a/module/zfs/txg.c +++ b/module/zfs/txg.c @@ -366,6 +366,13 @@ txg_quiesce(dsl_pool_t *dp, uint64_t txg) ASSERT(txg == tx->tx_open_txg); tx->tx_open_txg++; + /* + * Now that we've incremented tx_open_txg, we can let threads + * enter the next transaction group. + */ + for (c = 0; c < max_ncpus; c++) + mutex_exit(&tx->tx_cpu[c].tc_lock); + /* * Measure how long the txg was open and replace the kstat. */ @@ -375,13 +382,6 @@ txg_quiesce(dsl_pool_t *dp, uint64_t txg) dsl_pool_txg_history_put(th); dsl_pool_txg_history_add(dp, tx->tx_open_txg); - /* - * Now that we've incremented tx_open_txg, we can let threads - * enter the next transaction group. - */ - for (c = 0; c < max_ncpus; c++) - mutex_exit(&tx->tx_cpu[c].tc_lock); - /* * Quiesce the transaction group by waiting for everyone to txg_exit(). */ -- cgit v1.2.3