c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2024-12-26 19:19:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix txg_quiesce thread deadlock

Browse Source 
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 <behlendorf1@llnl.gov>
Issue #1274
This commit is contained in:
Brian Behlendorf 2013-04-25 16:29:22 -07:00
parent 0c15bf16f1
commit 57f5a2008e
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
module/zfs/dsl_pool.c
View File

@ -143,7 +143,7 @@ dsl_pool_txg_history_add(dsl_pool_t *dp, uint64_t txg)
{ {
txg_history_t *th, *rm; 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); mutex_init(&th->th_lock, NULL, MUTEX_DEFAULT, NULL);
th->th_kstat.txg = txg; th->th_kstat.txg = txg;
th->th_kstat.state = TXG_STATE_OPEN; th->th_kstat.state = TXG_STATE_OPEN;

14
module/zfs/txg.c
View File

@ -366,6 +366,13 @@ txg_quiesce(dsl_pool_t *dp, uint64_t txg)
ASSERT(txg == tx->tx_open_txg); ASSERT(txg == tx->tx_open_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. * 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_put(th);
dsl_pool_txg_history_add(dp, tx->tx_open_txg); 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(). * Quiesce the transaction group by waiting for everyone to txg_exit().
*/ */