diff options
| author | lidongyang <[email protected]> | 2017-12-23 05:19:51 +1100 |
|---|---|---|
| committer | Tony Hutter <[email protected]> | 2018-01-30 10:27:31 -0600 |
| commit | 8d82a19def540bba43c8c7597142ff53f7a0b7e5 (patch) | |
| tree | 7e8c14ea864a460cb3ac84e3639b332b5d124120 /include/sys | |
| parent | c2aacf20872856559972a27f7c3f9b4a6fe10cd2 (diff) | |
Call commit callbacks from the tail of the list
Our zfs backed Lustre MDT had soft lockups while under heavy metadata
workloads while handling transaction callbacks from osd_zfs.
The problem is zfs is not taking advantage of the fast path in
Lustre's trans callback handling, where Lustre will skip the calls
to ptlrpc_commit_replies() when it already saw a higher transaction
number.
This patch corrects this, it also has a positive impact on metadata
performance on Lustre with osd_zfs, plus some cleanup in the headers.
A similar issue for ext4/ldiskfs is described on:
https://jira.hpdd.intel.com/browse/LU-6527
Reviewed-by: Olaf Faaland <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Li Dongyang <[email protected]>
Closes #6986
Diffstat (limited to 'include/sys')
| -rw-r--r-- | include/sys/dmu.h | 5 | ||||
| -rw-r--r-- | include/sys/dmu_tx.h | 4 |
2 files changed, 5 insertions, 4 deletions
diff --git a/include/sys/dmu.h b/include/sys/dmu.h index d24615262..bcdf7d646 100644 --- a/include/sys/dmu.h +++ b/include/sys/dmu.h @@ -713,11 +713,16 @@ void dmu_tx_mark_netfree(dmu_tx_t *tx); * to stable storage and will also be called if the dmu_tx is aborted. * If there is any error which prevents the transaction from being committed to * disk, the callback will be called with a value of error != 0. + * + * When multiple callbacks are registered to the transaction, the callbacks + * will be called in reverse order to let Lustre, the only user of commit + * callback currently, take the fast path of its commit callback handling. */ typedef void dmu_tx_callback_func_t(void *dcb_data, int error); void dmu_tx_callback_register(dmu_tx_t *tx, dmu_tx_callback_func_t *dcb_func, void *dcb_data); +void dmu_tx_do_callbacks(list_t *cb_list, int error); /* * Free up the data blocks for a defined range of a file. If size is diff --git a/include/sys/dmu_tx.h b/include/sys/dmu_tx.h index f16e1e858..d82a79310 100644 --- a/include/sys/dmu_tx.h +++ b/include/sys/dmu_tx.h @@ -145,10 +145,6 @@ uint64_t dmu_tx_get_txg(dmu_tx_t *tx); struct dsl_pool *dmu_tx_pool(dmu_tx_t *tx); void dmu_tx_wait(dmu_tx_t *tx); -void dmu_tx_callback_register(dmu_tx_t *tx, dmu_tx_callback_func_t *dcb_func, - void *dcb_data); -void dmu_tx_do_callbacks(list_t *cb_list, int error); - /* * These routines are defined in dmu_spa.h, and are called by the SPA. */ |