From 823d48bfb182137c53b9432498f1f0564eaa8bfc Mon Sep 17 00:00:00 2001 From: lidongyang Date: Sat, 23 Dec 2017 05:19:51 +1100 Subject: [PATCH] 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 Reviewed-by: Brian Behlendorf Signed-off-by: Li Dongyang Closes #6986 --- include/sys/dmu.h | 5 +++++ include/sys/dmu_tx.h | 4 ---- module/zfs/dmu_tx.c | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/sys/dmu.h b/include/sys/dmu.h index f252a9cb6..61c02e8a7 100644 --- a/include/sys/dmu.h +++ b/include/sys/dmu.h @@ -748,11 +748,16 @@ 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. */ diff --git a/module/zfs/dmu_tx.c b/module/zfs/dmu_tx.c index 2bb202647..6408837d2 100644 --- a/module/zfs/dmu_tx.c +++ b/module/zfs/dmu_tx.c @@ -1197,7 +1197,7 @@ dmu_tx_do_callbacks(list_t *cb_list, int error) { dmu_tx_callback_t *dcb; - while ((dcb = list_head(cb_list)) != NULL) { + while ((dcb = list_tail(cb_list)) != NULL) { list_remove(cb_list, dcb); dcb->dcb_func(dcb->dcb_data, error); kmem_free(dcb, sizeof (dmu_tx_callback_t)); -- 2.40.0