Date: Tue, 4 May 2010 12:42:47 +0200 (CEST) From: Martin Matuska <mm@FreeBSD.org> To: FreeBSD-gnats-submit@FreeBSD.org Cc: pjd@FreeBSD.org Subject: kern/146296: [zfs] [patch] fix deadlock during zfs receive (onnv 9299) Message-ID: <20100504104247.198038F567@mail.vx.sk> Resent-Message-ID: <201005041050.o44Ao2v0041139@freefall.freebsd.org>
next in thread | raw e-mail | index | archive | help
>Number: 146296 >Category: kern >Synopsis: [zfs] [patch] fix deadlock during zfs receive (onnv 9299) >Confidential: no >Severity: serious >Priority: medium >Responsible: freebsd-bugs >State: open >Quarter: >Keywords: >Date-Required: >Class: sw-bug >Submitter-Id: current-users >Arrival-Date: Tue May 04 10:50:01 UTC 2010 >Closed-Date: >Last-Modified: >Originator: Martin Matuska >Release: FreeBSD 8.0-STABLE amd64 >Organization: >Environment: >Description: I have encountered a hanging zfs receive during receiving many incremental streams. This problem has been described in OpenSolaris mailing lists, it matches my symptoms and affects our ZFS port. OpenSolaris Bug IDs: 6783818 Incremental stream receive panics system 6826836 Deadlock possible in dmu_object_reclaim() Mailing list discussion: http://mail.opensolaris.org/pipermail/storage-discuss/2009-June/006171.html Fixed in onnv revision: 9299:8809e849f63e >How-To-Repeat: >Fix: Index: sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c =================================================================== --- sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c (revision 207608) +++ sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c (working copy) @@ -128,15 +128,6 @@ return (0); } - tx = dmu_tx_create(os); - dmu_tx_hold_bonus(tx, object); - err = dmu_tx_assign(tx, TXG_WAIT); - if (err) { - dmu_tx_abort(tx); - dnode_rele(dn, FTAG); - return (err); - } - nblkptr = 1 + ((DN_MAX_BONUSLEN - bonuslen) >> SPA_BLKPTRSHIFT); /* @@ -144,16 +135,27 @@ * be a new file instance. We must clear out the previous file * contents before we can change this type of metadata in the dnode. */ - if (dn->dn_nblkptr > nblkptr || dn->dn_datablksz != blocksize) - dmu_free_long_range(os, object, 0, DMU_OBJECT_END); + if (dn->dn_nblkptr > nblkptr || dn->dn_datablksz != blocksize) { + err = dmu_free_long_range(os, object, 0, DMU_OBJECT_END); + if (err) + goto out; + } + tx = dmu_tx_create(os); + dmu_tx_hold_bonus(tx, object); + err = dmu_tx_assign(tx, TXG_WAIT); + if (err) { + dmu_tx_abort(tx); + goto out; + } + dnode_reallocate(dn, ot, blocksize, bonustype, bonuslen, tx); dmu_tx_commit(tx); - +out: dnode_rele(dn, FTAG); - return (0); + return (err); } int Index: sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c =================================================================== --- sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c (revision 207608) +++ sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c (working copy) @@ -464,15 +464,15 @@ ASSERT(db->db_buf == NULL); if (db->db_blkid == DB_BONUS_BLKID) { - int bonuslen = dn->dn_bonuslen; + int bonuslen = MIN(dn->dn_bonuslen, dn->dn_phys->dn_bonuslen); ASSERT3U(bonuslen, <=, db->db.db_size); db->db.db_data = zio_buf_alloc(DN_MAX_BONUSLEN); arc_space_consume(DN_MAX_BONUSLEN); if (bonuslen < DN_MAX_BONUSLEN) bzero(db->db.db_data, DN_MAX_BONUSLEN); - bcopy(DN_BONUS(dn->dn_phys), db->db.db_data, - bonuslen); + if (bonuslen) + bcopy(DN_BONUS(dn->dn_phys), db->db.db_data, bonuslen); dbuf_update_data(db); db->db_state = DB_CACHED; mutex_exit(&db->db_mtx); >Release-Note: >Audit-Trail: >Unformatted:
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20100504104247.198038F567>