From 1b310dfb1d5aa90db7d8c4ec8d6a92b4430b0496 Mon Sep 17 00:00:00 2001 From: Alexander Motin Date: Wed, 11 Oct 2023 19:37:21 -0400 Subject: [PATCH] DMU: Do not pre-read holes during write dmu_tx_check_ioerr() pre-reads blocks that are going to be dirtied as part of transaction to both prefetch them and check for errors. But it makes no sense to do it for holes, since there are no disk reads to prefetch and there can be no errors. On the other side those blocks are anonymous, and they are freed immediately by the dbuf_rele() without even being put into dbuf cache, so we just burn CPU time on decompression and overheads and get absolutely no result at the end. Use of dbuf_hold_impl() with fail_sparse parameter allows to skip the extra work, and on my tests with sequential 8KB writes to empty ZVOL with 32KB blocks shows throughput increase from 1.7 to 2GB/s. Reviewed-by: Brian Atkinson Reviewed-by: Brian Behlendorf Signed-off-by: Alexander Motin Sponsored by: iXsystems, Inc. Closes #15371 --- module/zfs/dmu_tx.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/module/zfs/dmu_tx.c b/module/zfs/dmu_tx.c index 0eb8c17e33..8451b5082e 100644 --- a/module/zfs/dmu_tx.c +++ b/module/zfs/dmu_tx.c @@ -210,10 +210,12 @@ dmu_tx_check_ioerr(zio_t *zio, dnode_t *dn, int level, uint64_t blkid) dmu_buf_impl_t *db; rw_enter(&dn->dn_struct_rwlock, RW_READER); - db = dbuf_hold_level(dn, level, blkid, FTAG); + err = dbuf_hold_impl(dn, level, blkid, TRUE, FALSE, FTAG, &db); rw_exit(&dn->dn_struct_rwlock); - if (db == NULL) - return (SET_ERROR(EIO)); + if (err == ENOENT) + return (0); + if (err != 0) + return (err); /* * PARTIAL_FIRST allows caching for uncacheable blocks. It will * be cleared after dmu_buf_will_dirty() call dbuf_read() again.