From owner-svn-src-head@freebsd.org Sun Aug 12 00:45:57 2018 Return-Path: Delivered-To: svn-src-head@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id F0BDE10582F6; Sun, 12 Aug 2018 00:45:56 +0000 (UTC) (envelope-from mmacy@FreeBSD.org) Received: from mxrelay.nyi.freebsd.org (mxrelay.nyi.freebsd.org [IPv6:2610:1c1:1:606c::19:3]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "mxrelay.nyi.freebsd.org", Issuer "Let's Encrypt Authority X3" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 9065497815; Sun, 12 Aug 2018 00:45:56 +0000 (UTC) (envelope-from mmacy@FreeBSD.org) Received: from repo.freebsd.org (repo.freebsd.org [IPv6:2610:1c1:1:6068::e6a:0]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mxrelay.nyi.freebsd.org (Postfix) with ESMTPS id 518351EC60; Sun, 12 Aug 2018 00:45:56 +0000 (UTC) (envelope-from mmacy@FreeBSD.org) Received: from repo.freebsd.org ([127.0.1.37]) by repo.freebsd.org (8.15.2/8.15.2) with ESMTP id w7C0junO077227; Sun, 12 Aug 2018 00:45:56 GMT (envelope-from mmacy@FreeBSD.org) Received: (from mmacy@localhost) by repo.freebsd.org (8.15.2/8.15.2/Submit) id w7C0jsYR077215; Sun, 12 Aug 2018 00:45:54 GMT (envelope-from mmacy@FreeBSD.org) Message-Id: <201808120045.w7C0jsYR077215@repo.freebsd.org> X-Authentication-Warning: repo.freebsd.org: mmacy set sender to mmacy@FreeBSD.org using -f From: Matt Macy Date: Sun, 12 Aug 2018 00:45:53 +0000 (UTC) To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r337669 - in head: cddl/contrib/opensolaris/cmd/zdb cddl/contrib/opensolaris/cmd/ztest cddl/usr.bin/ztest sys/cddl/contrib/opensolaris/common/zfs sys/cddl/contrib/opensolaris/uts/common... X-SVN-Group: head X-SVN-Commit-Author: mmacy X-SVN-Commit-Paths: in head: cddl/contrib/opensolaris/cmd/zdb cddl/contrib/opensolaris/cmd/ztest cddl/usr.bin/ztest sys/cddl/contrib/opensolaris/common/zfs sys/cddl/contrib/opensolaris/uts/common/fs/zfs sys/cddl/contrib/... X-SVN-Commit-Revision: 337669 X-SVN-Commit-Repository: base MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: svn-src-head@freebsd.org X-Mailman-Version: 2.1.27 Precedence: list List-Id: SVN commit messages for the src tree for head/-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 12 Aug 2018 00:45:57 -0000 Author: mmacy Date: Sun Aug 12 00:45:53 2018 New Revision: 337669 URL: https://svnweb.freebsd.org/changeset/base/337669 Log: MFV/ZoL: Implement large_dnode pool feature commit 50c957f702ea6d08a634e42f73e8a49931dd8055 Author: Ned Bass Date: Wed Mar 16 18:25:34 2016 -0700 Implement large_dnode pool feature Justification ------------- This feature adds support for variable length dnodes. Our motivation is to eliminate the overhead associated with using spill blocks. Spill blocks are used to store system attribute data (i.e. file metadata) that does not fit in the dnode's bonus buffer. By allowing a larger bonus buffer area the use of a spill block can be avoided. Spill blocks potentially incur an additional read I/O for every dnode in a dnode block. As a worst case example, reading 32 dnodes from a 16k dnode block and all of the spill blocks could issue 33 separate reads. Now suppose those dnodes have size 1024 and therefore don't need spill blocks. Then the worst case number of blocks read is reduced to from 33 to two--one per dnode block. In practice spill blocks may tend to be co-located on disk with the dnode blocks so the reduction in I/O would not be this drastic. In a badly fragmented pool, however, the improvement could be significant. ZFS-on-Linux systems that make heavy use of extended attributes would benefit from this feature. In particular, ZFS-on-Linux supports the xattr=sa dataset property which allows file extended attribute data to be stored in the dnode bonus buffer as an alternative to the traditional directory-based format. Workloads such as SELinux and the Lustre distributed filesystem often store enough xattr data to force spill bocks when xattr=sa is in effect. Large dnodes may therefore provide a performance benefit to such systems. Other use cases that may benefit from this feature include files with large ACLs and symbolic links with long target names. Furthermore, this feature may be desirable on other platforms in case future applications or features are developed that could make use of a larger bonus buffer area. Implementation -------------- The size of a dnode may be a multiple of 512 bytes up to the size of a dnode block (currently 16384 bytes). A dn_extra_slots field was added to the current on-disk dnode_phys_t structure to describe the size of the physical dnode on disk. The 8 bits for this field were taken from the zero filled dn_pad2 field. The field represents how many "extra" dnode_phys_t slots a dnode consumes in its dnode block. This convention results in a value of 0 for 512 byte dnodes which preserves on-disk format compatibility with older software. Similarly, the in-memory dnode_t structure has a new dn_num_slots field to represent the total number of dnode_phys_t slots consumed on disk. Thus dn->dn_num_slots is 1 greater than the corresponding dnp->dn_extra_slots. This difference in convention was adopted because, unlike on-disk structures, backward compatibility is not a concern for in-memory objects, so we used a more natural way to represent size for a dnode_t. The default size for newly created dnodes is determined by the value of a new "dnodesize" dataset property. By default the property is set to "legacy" which is compatible with older software. Setting the property to "auto" will allow the filesystem to choose the most suitable dnode size. Currently this just sets the default dnode size to 1k, but future code improvements could dynamically choose a size based on observed workload patterns. Dnodes of varying sizes can coexist within the same dataset and even within the same dnode block. For example, to enable automatically-sized dnodes, run # zfs set dnodesize=auto tank/fish The user can also specify literal values for the dnodesize property. These are currently limited to powers of two from 1k to 16k. The power-of-2 limitation is only for simplicity of the user interface. Internally the implementation can handle any multiple of 512 up to 16k, and consumers of the DMU API can specify any legal dnode value. The size of a new dnode is determined at object allocation time and stored as a new field in the znode in-memory structure. New DMU interfaces are added to allow the consumer to specify the dnode size that a newly allocated object should use. Existing interfaces are unchanged to avoid having to update every call site and to preserve compatibility with external consumers such as Lustre. The new interfaces names are given below. The versions of these functions that don't take a dnodesize parameter now just call the _dnsize() versions with a dnodesize of 0, which means use the legacy dnode size. New DMU interfaces: dmu_object_alloc_dnsize() dmu_object_claim_dnsize() dmu_object_reclaim_dnsize() New ZAP interfaces: zap_create_dnsize() zap_create_norm_dnsize() zap_create_flags_dnsize() zap_create_claim_norm_dnsize() zap_create_link_dnsize() The constant DN_MAX_BONUSLEN is renamed to DN_OLD_MAX_BONUSLEN. The spa_maxdnodesize() function should be used to determine the maximum bonus length for a pool. These are a few noteworthy changes to key functions: * The prototype for dnode_hold_impl() now takes a "slots" parameter. When the DNODE_MUST_BE_FREE flag is set, this parameter is used to ensure the hole at the specified object offset is large enough to hold the dnode being created. The slots parameter is also used to ensure a dnode does not span multiple dnode blocks. In both of these cases, if a failure occurs, ENOSPC is returned. Keep in mind, these failure cases are only possible when using DNODE_MUST_BE_FREE. If the DNODE_MUST_BE_ALLOCATED flag is set, "slots" must be 0. dnode_hold_impl() will check if the requested dnode is already consumed as an extra dnode slot by an large dnode, in which case it returns ENOENT. * The function dmu_object_alloc() advances to the next dnode block if dnode_hold_impl() returns an error for a requested object. This is because the beginning of the next dnode block is the only location it can safely assume to either be a hole or a valid starting point for a dnode. * dnode_next_offset_level() and other functions that iterate through dnode blocks may no longer use a simple array indexing scheme. These now use the current dnode's dn_num_slots field to advance to the next dnode in the block. This is to ensure we properly skip the current dnode's bonus area and don't interpret it as a valid dnode. zdb --- The zdb command was updated to display a dnode's size under the "dnsize" column when the object is dumped. For ZIL create log records, zdb will now display the slot count for the object. ztest ----- Ztest chooses a random dnodesize for every newly created object. The random distribution is more heavily weighted toward small dnodes to better simulate real-world datasets. Unused bonus buffer space is filled with non-zero values computed from the object number, dataset id, offset, and generation number. This helps ensure that the dnode traversal code properly skips the interior regions of large dnodes, and that these interior regions are not overwritten by data belonging to other dnodes. A new test visits each object in a dataset. It verifies that the actual dnode size matches what was stored in the ztest block tag when it was created. It also verifies that the unused bonus buffer space is filled with the expected data patterns. ZFS Test Suite -------------- Added six new large dnode-specific tests, and integrated the dnodesize property into existing tests for zfs allow and send/recv. Send/Receive ------------ ZFS send streams for datasets containing large dnodes cannot be received on pools that don't support the large_dnode feature. A send stream with large dnodes sets a DMU_BACKUP_FEATURE_LARGE_DNODE flag which will be unrecognized by an incompatible receiving pool so that the zfs receive will fail gracefully. While not implemented here, it may be possible to generate a backward-compatible send stream from a dataset containing large dnodes. The implementation may be tricky, however, because the send object record for a large dnode would need to be resized to a 512 byte dnode, possibly kicking in a spill block in the process. This means we would need to construct a new SA layout and possibly register it in the SA layout object. The SA layout is normally just sent as an ordinary object record. But if we are constructing new layouts while generating the send stream we'd have to build the SA layout object dynamically and send it at the end of the stream. For sending and receiving between pools that do support large dnodes, the drr_object send record type is extended with a new field to store the dnode slot count. This field was repurposed from unused padding in the structure. ZIL Replay ---------- The dnode slot count is stored in the uppermost 8 bits of the lr_foid field. The bits were unused as the object id is currently capped at 48 bits. Resizing Dnodes --------------- It should be possible to resize a dnode when it is dirtied if the current dnodesize dataset property differs from the dnode's size, but this functionality is not currently implemented. Clearly a dnode can only grow if there are sufficient contiguous unused slots in the dnode block, but it should always be possible to shrink a dnode. Growing dnodes may be useful to reduce fragmentation in a pool with many spill blocks in use. Shrinking dnodes may be useful to allow sending a dataset to a pool that doesn't support the large_dnode feature. Feature Reference Counting -------------------------- The reference count for the large_dnode pool feature tracks the number of datasets that have ever contained a dnode of size larger than 512 bytes. The first time a large dnode is created in a dataset the dataset is converted to an extensible dataset. This is a one-way operation and the only way to decrement the feature count is to destroy the dataset, even if the dataset no longer contains any large dnodes. The complexity of reference counting on a per-dnode basis was too high, so we chose to track it on a per-dataset basis similarly to the large_block feature. Signed-off-by: Ned Bass Signed-off-by: Brian Behlendorf Closes #3542 Modified: head/cddl/contrib/opensolaris/cmd/zdb/zdb.c head/cddl/contrib/opensolaris/cmd/zdb/zdb_il.c head/cddl/contrib/opensolaris/cmd/ztest/ztest.c head/cddl/usr.bin/ztest/Makefile head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.c head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.h head/sys/cddl/contrib/opensolaris/common/zfs/zfs_prop.c head/sys/cddl/contrib/opensolaris/common/zfs/zpool_prop.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_objset.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_send.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_traverse.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_tx.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dnode.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dnode_sync.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dsl_scan.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sa.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/spa.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/spa_misc.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/dmu.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/dmu_objset.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/dnode.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/dsl_dataset.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/sa_impl.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/spa.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/zap.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/zfs_ioctl.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/zfs_znode.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/zil.h head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zap.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zap_micro.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_acl.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_ioctl.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_log.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_replay.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_sa.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zfs_znode.c head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zil.c head/sys/cddl/contrib/opensolaris/uts/common/sys/fs/zfs.h Modified: head/cddl/contrib/opensolaris/cmd/zdb/zdb.c ============================================================================== --- head/cddl/contrib/opensolaris/cmd/zdb/zdb.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/cddl/contrib/opensolaris/cmd/zdb/zdb.c Sun Aug 12 00:45:53 2018 (r337669) @@ -2096,7 +2096,7 @@ dump_object(objset_t *os, uint64_t object, int verbosi dnode_t *dn; void *bonus = NULL; size_t bsize = 0; - char iblk[32], dblk[32], lsize[32], asize[32], fill[32]; + char iblk[32], dblk[32], lsize[32], asize[32], fill[32], dnsize[32]; char bonus_size[32]; char aux[50]; int error; @@ -2109,9 +2109,9 @@ dump_object(objset_t *os, uint64_t object, int verbosi CTASSERT(sizeof (bonus_size) >= NN_NUMBUF_SZ); if (*print_header) { - (void) printf("\n%10s %3s %5s %5s %5s %5s %6s %s\n", - "Object", "lvl", "iblk", "dblk", "dsize", "lsize", - "%full", "type"); + (void) printf("\n%10s %3s %5s %5s %5s %6s %5s %6s %s\n", + "Object", "lvl", "iblk", "dblk", "dsize", "dnsize", + "lsize", "%full", "type"); *print_header = 0; } @@ -2133,6 +2133,7 @@ dump_object(objset_t *os, uint64_t object, int verbosi zdb_nicenum(doi.doi_max_offset, lsize, sizeof (lsize)); zdb_nicenum(doi.doi_physical_blocks_512 << 9, asize, sizeof (asize)); zdb_nicenum(doi.doi_bonus_size, bonus_size, sizeof (bonus_size)); + zdb_nicenum(doi.doi_dnodesize, dnsize, sizeof (dnsize)); (void) sprintf(fill, "%6.2f", 100.0 * doi.doi_fill_count * doi.doi_data_block_size / (object == 0 ? DNODES_PER_BLOCK : 1) / doi.doi_max_offset); @@ -2149,13 +2150,13 @@ dump_object(objset_t *os, uint64_t object, int verbosi ZDB_COMPRESS_NAME(doi.doi_compress)); } - (void) printf("%10lld %3u %5s %5s %5s %5s %6s %s%s\n", + (void) printf("%10lld %3u %5s %5s %5s %6s %5s %6s %s%s\n", (u_longlong_t)object, doi.doi_indirection, iblk, dblk, - asize, lsize, fill, ZDB_OT_NAME(doi.doi_type), aux); + asize, dnsize, lsize, fill, ZDB_OT_NAME(doi.doi_type), aux); if (doi.doi_bonus_type != DMU_OT_NONE && verbosity > 3) { - (void) printf("%10s %3s %5s %5s %5s %5s %6s %s\n", - "", "", "", "", "", bonus_size, "bonus", + (void) printf("%10s %3s %5s %5s %5s %5s %5s %6s %s\n", + "", "", "", "", "", "", bonus_size, "bonus", ZDB_OT_NAME(doi.doi_bonus_type)); } Modified: head/cddl/contrib/opensolaris/cmd/zdb/zdb_il.c ============================================================================== --- head/cddl/contrib/opensolaris/cmd/zdb/zdb_il.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/cddl/contrib/opensolaris/cmd/zdb/zdb_il.c Sun Aug 12 00:45:53 2018 (r337669) @@ -84,8 +84,10 @@ zil_prt_rec_create(zilog_t *zilog, int txtype, void *a } (void) printf("%s%s", tab_prefix, ctime(&crtime)); - (void) printf("%sdoid %llu, foid %llu, mode %llo\n", tab_prefix, - (u_longlong_t)lr->lr_doid, (u_longlong_t)lr->lr_foid, + (void) printf("%sdoid %llu, foid %llu, slots %llu, mode %llo\n", tab_prefix, + (u_longlong_t)lr->lr_doid, + (u_longlong_t)LR_FOID_GET_OBJ(lr->lr_foid), + (u_longlong_t)LR_FOID_GET_SLOTS(lr->lr_foid), (longlong_t)lr->lr_mode); (void) printf("%suid %llu, gid %llu, gen %llu, rdev 0x%llx\n", tab_prefix, Modified: head/cddl/contrib/opensolaris/cmd/ztest/ztest.c ============================================================================== --- head/cddl/contrib/opensolaris/cmd/ztest/ztest.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/cddl/contrib/opensolaris/cmd/ztest/ztest.c Sun Aug 12 00:45:53 2018 (r337669) @@ -226,6 +226,7 @@ typedef struct ztest_block_tag { uint64_t bt_magic; uint64_t bt_objset; uint64_t bt_object; + uint64_t bt_dnodesize; uint64_t bt_offset; uint64_t bt_gen; uint64_t bt_txg; @@ -274,6 +275,7 @@ typedef struct ztest_od { dmu_object_type_t od_crtype; uint64_t od_blocksize; uint64_t od_crblocksize; + uint64_t od_crdnodesize; uint64_t od_gen; uint64_t od_crgen; char od_name[ZFS_MAX_DATASET_NAME_LEN]; @@ -350,6 +352,7 @@ ztest_func_t ztest_device_removal; ztest_func_t ztest_remap_blocks; ztest_func_t ztest_spa_checkpoint_create_discard; ztest_func_t ztest_initialize; +ztest_func_t ztest_verify_dnode_bt; uint64_t zopt_always = 0ULL * NANOSEC; /* all the time */ uint64_t zopt_incessant = 1ULL * NANOSEC / 10; /* every 1/10 second */ @@ -394,7 +397,8 @@ ztest_info_t ztest_info[] = { { ztest_device_removal, 1, &zopt_sometimes }, { ztest_remap_blocks, 1, &zopt_sometimes }, { ztest_spa_checkpoint_create_discard, 1, &zopt_rarely }, - { ztest_initialize, 1, &zopt_sometimes } + { ztest_initialize, 1, &zopt_sometimes }, + { ztest_verify_dnode_bt, 1, &zopt_sometimes } }; #define ZTEST_FUNCS (sizeof (ztest_info) / sizeof (ztest_info_t)) @@ -440,8 +444,8 @@ static spa_t *ztest_spa = NULL; static ztest_ds_t *ztest_ds; static kmutex_t ztest_vdev_lock; -static kmutex_t ztest_checkpoint_lock; static boolean_t ztest_device_removal_active = B_FALSE; +static kmutex_t ztest_checkpoint_lock; /* * The ztest_name_lock protects the pool and dataset namespace used by @@ -1011,6 +1015,36 @@ ztest_random_blocksize(void) } static int +ztest_random_dnodesize(void) +{ + int slots; + int max_slots = spa_maxdnodesize(ztest_spa) >> DNODE_SHIFT; + + if (max_slots == DNODE_MIN_SLOTS) + return (DNODE_MIN_SIZE); + + /* + * Weight the random distribution more heavily toward smaller + * dnode sizes since that is more likely to reflect real-world + * usage. + */ + ASSERT3U(max_slots, >, 4); + switch (ztest_random(10)) { + case 0: + slots = 5 + ztest_random(max_slots - 4); + break; + case 1 ... 4: + slots = 2 + ztest_random(3); + break; + default: + slots = 1; + break; + } + + return (slots << DNODE_SHIFT); +} + +static int ztest_random_ibshift(void) { return (DN_MIN_INDBLKSHIFT + @@ -1287,11 +1321,13 @@ ztest_pattern_match(void *buf, uint64_t size, uint64_t static void ztest_bt_generate(ztest_block_tag_t *bt, objset_t *os, uint64_t object, - uint64_t offset, uint64_t gen, uint64_t txg, uint64_t crtxg) + uint64_t dnodesize, uint64_t offset, uint64_t gen, uint64_t txg, + uint64_t crtxg) { bt->bt_magic = BT_MAGIC; bt->bt_objset = dmu_objset_id(os); bt->bt_object = object; + bt->bt_dnodesize = dnodesize; bt->bt_offset = offset; bt->bt_gen = gen; bt->bt_txg = txg; @@ -1300,11 +1336,13 @@ ztest_bt_generate(ztest_block_tag_t *bt, objset_t *os, static void ztest_bt_verify(ztest_block_tag_t *bt, objset_t *os, uint64_t object, - uint64_t offset, uint64_t gen, uint64_t txg, uint64_t crtxg) + uint64_t dnodesize, uint64_t offset, uint64_t gen, uint64_t txg, + uint64_t crtxg) { ASSERT3U(bt->bt_magic, ==, BT_MAGIC); ASSERT3U(bt->bt_objset, ==, dmu_objset_id(os)); ASSERT3U(bt->bt_object, ==, object); + ASSERT3U(bt->bt_dnodesize, ==, dnodesize); ASSERT3U(bt->bt_offset, ==, offset); ASSERT3U(bt->bt_gen, <=, gen); ASSERT3U(bt->bt_txg, <=, txg); @@ -1326,6 +1364,52 @@ ztest_bt_bonus(dmu_buf_t *db) } /* + * Generate a token to fill up unused bonus buffer space. Try to make + * it unique to the object, generation, and offset to verify that data + * is not getting overwritten by data from other dnodes. + */ +#define ZTEST_BONUS_FILL_TOKEN(obj, ds, gen, offset) \ + (((ds) << 48) | ((gen) << 32) | ((obj) << 8) | (offset)) + +/* + * Fill up the unused bonus buffer region before the block tag with a + * verifiable pattern. Filling the whole bonus area with non-zero data + * helps ensure that all dnode traversal code properly skips the + * interior regions of large dnodes. + */ +void +ztest_fill_unused_bonus(dmu_buf_t *db, void *end, uint64_t obj, + objset_t *os, uint64_t gen) +{ + uint64_t *bonusp; + + ASSERT(IS_P2ALIGNED((char *)end - (char *)db->db_data, 8)); + + for (bonusp = db->db_data; bonusp < (uint64_t *)end; bonusp++) { + uint64_t token = ZTEST_BONUS_FILL_TOKEN(obj, dmu_objset_id(os), + gen, bonusp - (uint64_t *)db->db_data); + *bonusp = token; + } +} + +/* + * Verify that the unused area of a bonus buffer is filled with the + * expected tokens. + */ +void +ztest_verify_unused_bonus(dmu_buf_t *db, void *end, uint64_t obj, + objset_t *os, uint64_t gen) +{ + uint64_t *bonusp; + + for (bonusp = db->db_data; bonusp < (uint64_t *)end; bonusp++) { + uint64_t token = ZTEST_BONUS_FILL_TOKEN(obj, dmu_objset_id(os), + gen, bonusp - (uint64_t *)db->db_data); + VERIFY3U(*bonusp, ==, token); + } +} + +/* * ZIL logging ops */ @@ -1333,7 +1417,7 @@ ztest_bt_bonus(dmu_buf_t *db) #define lrz_blocksize lr_uid #define lrz_ibshift lr_gid #define lrz_bonustype lr_rdev -#define lrz_bonuslen lr_crtime[1] +#define lrz_dnodesize lr_crtime[1] static void ztest_log_create(ztest_ds_t *zd, dmu_tx_t *tx, lr_create_t *lr) @@ -1449,6 +1533,7 @@ ztest_replay_create(void *arg1, void *arg2, boolean_t dmu_tx_t *tx; uint64_t txg; int error = 0; + int bonuslen; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -1471,26 +1556,27 @@ ztest_replay_create(void *arg1, void *arg2, boolean_t return (ENOSPC); ASSERT(dmu_objset_zil(os)->zl_replay == !!lr->lr_foid); + bonuslen = DN_BONUS_SIZE(lr->lrz_dnodesize); if (lr->lrz_type == DMU_OT_ZAP_OTHER) { if (lr->lr_foid == 0) { - lr->lr_foid = zap_create(os, + lr->lr_foid = zap_create_dnsize(os, lr->lrz_type, lr->lrz_bonustype, - lr->lrz_bonuslen, tx); + bonuslen, lr->lrz_dnodesize, tx); } else { - error = zap_create_claim(os, lr->lr_foid, + error = zap_create_claim_dnsize(os, lr->lr_foid, lr->lrz_type, lr->lrz_bonustype, - lr->lrz_bonuslen, tx); + bonuslen, lr->lrz_dnodesize, tx); } } else { if (lr->lr_foid == 0) { - lr->lr_foid = dmu_object_alloc(os, + lr->lr_foid = dmu_object_alloc_dnsize(os, lr->lrz_type, 0, lr->lrz_bonustype, - lr->lrz_bonuslen, tx); + bonuslen, lr->lrz_dnodesize, tx); } else { - error = dmu_object_claim(os, lr->lr_foid, + error = dmu_object_claim_dnsize(os, lr->lr_foid, lr->lrz_type, 0, lr->lrz_bonustype, - lr->lrz_bonuslen, tx); + bonuslen, lr->lrz_dnodesize, tx); } } @@ -1510,7 +1596,9 @@ ztest_replay_create(void *arg1, void *arg2, boolean_t VERIFY3U(0, ==, dmu_bonus_hold(os, lr->lr_foid, FTAG, &db)); bbt = ztest_bt_bonus(db); dmu_buf_will_dirty(db, tx); - ztest_bt_generate(bbt, os, lr->lr_foid, -1ULL, lr->lr_gen, txg, txg); + ztest_bt_generate(bbt, os, lr->lr_foid, lr->lrz_dnodesize, -1ULL, + lr->lr_gen, txg, txg); + ztest_fill_unused_bonus(db, bbt, lr->lr_foid, os, lr->lr_gen); dmu_buf_rele(db, FTAG); VERIFY3U(0, ==, zap_add(os, lr->lr_doid, name, sizeof (uint64_t), 1, @@ -1660,7 +1748,7 @@ ztest_replay_write(void *arg1, void *arg2, boolean_t b VERIFY(dmu_read(os, lr->lr_foid, offset, sizeof (rbt), &rbt, prefetch) == 0); if (rbt.bt_magic == BT_MAGIC) { - ztest_bt_verify(&rbt, os, lr->lr_foid, + ztest_bt_verify(&rbt, os, lr->lr_foid, 0, offset, gen, txg, crtxg); } } @@ -1672,7 +1760,7 @@ ztest_replay_write(void *arg1, void *arg2, boolean_t b * as it was when the write was generated. */ if (zd->zd_zilog->zl_replay) { - ztest_bt_verify(bt, os, lr->lr_foid, offset, + ztest_bt_verify(bt, os, lr->lr_foid, 0, offset, MAX(gen, bt->bt_gen), MAX(txg, lrtxg), bt->bt_crtxg); } @@ -1681,7 +1769,8 @@ ztest_replay_write(void *arg1, void *arg2, boolean_t b * Set the bt's gen/txg to the bonus buffer's gen/txg * so that all of the usual ASSERTs will work. */ - ztest_bt_generate(bt, os, lr->lr_foid, offset, gen, txg, crtxg); + ztest_bt_generate(bt, os, lr->lr_foid, 0, offset, gen, txg, + crtxg); } if (abuf == NULL) { @@ -1753,7 +1842,7 @@ ztest_replay_setattr(void *arg1, void *arg2, boolean_t dmu_tx_t *tx; dmu_buf_t *db; ztest_block_tag_t *bbt; - uint64_t txg, lrtxg, crtxg; + uint64_t txg, lrtxg, crtxg, dnodesize; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -1776,6 +1865,7 @@ ztest_replay_setattr(void *arg1, void *arg2, boolean_t ASSERT3U(bbt->bt_magic, ==, BT_MAGIC); crtxg = bbt->bt_crtxg; lrtxg = lr->lr_common.lrc_txg; + dnodesize = bbt->bt_dnodesize; if (zd->zd_zilog->zl_replay) { ASSERT(lr->lr_size != 0); @@ -1794,7 +1884,7 @@ ztest_replay_setattr(void *arg1, void *arg2, boolean_t /* * Verify that the current bonus buffer is not newer than our txg. */ - ztest_bt_verify(bbt, os, lr->lr_foid, -1ULL, lr->lr_mode, + ztest_bt_verify(bbt, os, lr->lr_foid, dnodesize, -1ULL, lr->lr_mode, MAX(txg, lrtxg), crtxg); dmu_buf_will_dirty(db, tx); @@ -1804,8 +1894,9 @@ ztest_replay_setattr(void *arg1, void *arg2, boolean_t VERIFY0(dmu_set_bonus(db, lr->lr_size, tx)); bbt = ztest_bt_bonus(db); - ztest_bt_generate(bbt, os, lr->lr_foid, -1ULL, lr->lr_mode, txg, crtxg); - + ztest_bt_generate(bbt, os, lr->lr_foid, dnodesize, -1ULL, lr->lr_mode, + txg, crtxg); + ztest_fill_unused_bonus(db, bbt, lr->lr_foid, os, bbt->bt_gen); dmu_buf_rele(db, FTAG); (void) ztest_log_setattr(zd, tx, lr); @@ -2037,7 +2128,7 @@ ztest_create(ztest_ds_t *zd, ztest_od_t *od, int count lr->lrz_blocksize = od->od_crblocksize; lr->lrz_ibshift = ztest_random_ibshift(); lr->lrz_bonustype = DMU_OT_UINT64_OTHER; - lr->lrz_bonuslen = dmu_bonus_max(); + lr->lrz_dnodesize = od->od_crdnodesize; lr->lr_gen = od->od_crgen; lr->lr_crtime[0] = time(NULL); @@ -2216,7 +2307,8 @@ ztest_io(ztest_ds_t *zd, uint64_t object, uint64_t off switch (io_type) { case ZTEST_IO_WRITE_TAG: - ztest_bt_generate(&wbt, zd->zd_os, object, offset, 0, 0, 0); + ztest_bt_generate(&wbt, zd->zd_os, object, doi.doi_dnodesize, + offset, 0, 0, 0); (void) ztest_write(zd, object, offset, sizeof (wbt), &wbt); break; @@ -2277,13 +2369,15 @@ ztest_io(ztest_ds_t *zd, uint64_t object, uint64_t off */ static void ztest_od_init(ztest_od_t *od, uint64_t id, char *tag, uint64_t index, - dmu_object_type_t type, uint64_t blocksize, uint64_t gen) + dmu_object_type_t type, uint64_t blocksize, uint64_t dnodesize, + uint64_t gen) { od->od_dir = ZTEST_DIROBJ; od->od_object = 0; od->od_crtype = type; od->od_crblocksize = blocksize ? blocksize : ztest_random_blocksize(); + od->od_crdnodesize = dnodesize ? dnodesize : ztest_random_dnodesize(); od->od_crgen = gen; od->od_type = DMU_OT_NONE; @@ -3726,7 +3820,7 @@ ztest_dmu_object_alloc_free(ztest_ds_t *zd, uint64_t i int batchsize = sizeof (od) / sizeof (od[0]); for (int b = 0; b < batchsize; b++) - ztest_od_init(&od[b], id, FTAG, b, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(&od[b], id, FTAG, b, DMU_OT_UINT64_OTHER, 0, 0, 0); /* * Destroy the previous batch of objects, create a new batch, @@ -3786,8 +3880,8 @@ ztest_dmu_read_write(ztest_ds_t *zd, uint64_t id) /* * Read the directory info. If it's the first time, set things up. */ - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, chunksize); - ztest_od_init(&od[1], id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, chunksize); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, chunksize); + ztest_od_init(&od[1], id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, 0, chunksize); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -4056,8 +4150,8 @@ ztest_dmu_read_write_zcopy(ztest_ds_t *zd, uint64_t id /* * Read the directory info. If it's the first time, set things up. */ - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0); - ztest_od_init(&od[1], id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, chunksize); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); + ztest_od_init(&od[1], id, FTAG, 1, DMU_OT_UINT64_OTHER, 0, 0, chunksize); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -4257,7 +4351,7 @@ ztest_dmu_write_parallel(ztest_ds_t *zd, uint64_t id) * to verify that parallel writes to an object -- even to the * same blocks within the object -- doesn't cause any trouble. */ - ztest_od_init(&od[0], ID_PARALLEL, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(&od[0], ID_PARALLEL, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -4276,7 +4370,7 @@ ztest_dmu_prealloc(ztest_ds_t *zd, uint64_t id) uint64_t blocksize = ztest_random_blocksize(); void *data; - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); if (ztest_object_init(zd, od, sizeof (od), !ztest_random(2)) != 0) return; @@ -4322,7 +4416,7 @@ ztest_zap(ztest_ds_t *zd, uint64_t id) int error; char *hc[2] = { "s.acl.h", ".s.open.h.hyLZlg" }; - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (od), !ztest_random(2)) != 0) return; @@ -4454,7 +4548,7 @@ ztest_fzap(ztest_ds_t *zd, uint64_t id) ztest_od_t od[1]; uint64_t object, txg; - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (od), !ztest_random(2)) != 0) return; @@ -4500,7 +4594,7 @@ ztest_zap_parallel(ztest_ds_t *zd, uint64_t id) char name[20], string_value[20]; void *data; - ztest_od_init(&od[0], ID_PARALLEL, FTAG, micro, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(&od[0], ID_PARALLEL, FTAG, micro, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -4688,7 +4782,7 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id uint64_t old_txg, txg; int i, error; - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -4802,6 +4896,41 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id dmu_tx_commit(tx); } +/* + * Visit each object in the dataset. Verify that its properties + * are consistent what was stored in the block tag when it was created, + * and that its unused bonus buffer space has not been overwritten. + */ +void +ztest_verify_dnode_bt(ztest_ds_t *zd, uint64_t id) +{ + objset_t *os = zd->zd_os; + uint64_t obj; + int err = 0; + + for (obj = 0; err == 0; err = dmu_object_next(os, &obj, FALSE, 0)) { + ztest_block_tag_t *bt = NULL; + dmu_object_info_t doi; + dmu_buf_t *db; + + if (dmu_bonus_hold(os, obj, FTAG, &db) != 0) + continue; + + dmu_object_info_from_db(db, &doi); + if (doi.doi_bonus_size >= sizeof (*bt)) + bt = ztest_bt_bonus(db); + + if (bt && bt->bt_magic == BT_MAGIC) { + ztest_bt_verify(bt, os, obj, doi.doi_dnodesize, + bt->bt_offset, bt->bt_gen, bt->bt_txg, + bt->bt_crtxg); + ztest_verify_unused_bonus(db, bt, obj, os, bt->bt_gen); + } + + dmu_buf_rele(db, FTAG); + } +} + /* ARGSUSED */ void ztest_dsl_prop_get_set(ztest_ds_t *zd, uint64_t id) @@ -5286,7 +5415,7 @@ ztest_ddt_repair(ztest_ds_t *zd, uint64_t id) blocksize = ztest_random_blocksize(); blocksize = MIN(blocksize, 2048); /* because we write so many */ - ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0); + ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); if (ztest_object_init(zd, od, sizeof (od), B_FALSE) != 0) return; @@ -6212,7 +6341,7 @@ ztest_freeze(void) numloops++ < ztest_opts.zo_maxloops && metaslab_class_get_alloc(spa_normal_class(spa)) < capacity) { ztest_od_t od; - ztest_od_init(&od, 0, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(&od, 0, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); VERIFY0(ztest_object_init(zd, &od, sizeof (od), B_FALSE)); ztest_io(zd, od.od_object, ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT); Modified: head/cddl/usr.bin/ztest/Makefile ============================================================================== --- head/cddl/usr.bin/ztest/Makefile Sun Aug 12 00:33:24 2018 (r337668) +++ head/cddl/usr.bin/ztest/Makefile Sun Aug 12 00:45:53 2018 (r337669) @@ -23,6 +23,6 @@ CSTD= c99 # Since there are many asserts in this program, it makes no sense to compile # it without debugging. -CFLAGS+= -g -DDEBUG=1 +CFLAGS+= -g -DDEBUG=1 -Wno-format .include Modified: head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.c Sun Aug 12 00:45:53 2018 (r337669) @@ -243,6 +243,18 @@ zpool_feature_init(void) "org.open-zfs:large_blocks", "large_blocks", "Support for blocks larger than 128KB.", ZFEATURE_FLAG_PER_DATASET, large_blocks_deps); + + { + static const spa_feature_t large_dnode_deps[] = { + SPA_FEATURE_EXTENSIBLE_DATASET, + SPA_FEATURE_NONE + }; + zfeature_register(SPA_FEATURE_LARGE_DNODE, + "org.zfsonlinux:large_dnode", "large_dnode", + "Variable on-disk size of dnodes.", + ZFEATURE_FLAG_PER_DATASET, large_dnode_deps); + } + zfeature_register(SPA_FEATURE_SHA512, "org.illumos:sha512", "sha512", "SHA-512/256 hash algorithm.", Modified: head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.h ============================================================================== --- head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.h Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/common/zfs/zfeature_common.h Sun Aug 12 00:45:53 2018 (r337669) @@ -52,6 +52,7 @@ typedef enum spa_feature { SPA_FEATURE_BOOKMARKS, SPA_FEATURE_FS_SS_LIMIT, SPA_FEATURE_LARGE_BLOCKS, + SPA_FEATURE_LARGE_DNODE, SPA_FEATURE_SHA512, SPA_FEATURE_SKEIN, #ifdef illumos Modified: head/sys/cddl/contrib/opensolaris/common/zfs/zfs_prop.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/common/zfs/zfs_prop.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/common/zfs/zfs_prop.c Sun Aug 12 00:45:53 2018 (r337669) @@ -222,6 +222,17 @@ zfs_prop_init(void) { NULL } }; + static zprop_index_t dnsize_table[] = { + { "legacy", ZFS_DNSIZE_LEGACY }, + { "auto", ZFS_DNSIZE_AUTO }, + { "1k", ZFS_DNSIZE_1K }, + { "2k", ZFS_DNSIZE_2K }, + { "4k", ZFS_DNSIZE_4K }, + { "8k", ZFS_DNSIZE_8K }, + { "16k", ZFS_DNSIZE_16K }, + { NULL } + }; + static zprop_index_t redundant_metadata_table[] = { { "all", ZFS_REDUNDANT_METADATA_ALL }, { "most", ZFS_REDUNDANT_METADATA_MOST }, @@ -281,7 +292,10 @@ zfs_prop_init(void) ZFS_VOLMODE_DEFAULT, PROP_INHERIT, ZFS_TYPE_FILESYSTEM | ZFS_TYPE_SNAPSHOT | ZFS_TYPE_VOLUME, "default | geom | dev | none", "VOLMODE", volmode_table); - + zprop_register_index(ZFS_PROP_DNODESIZE, "dnodesize", + ZFS_DNSIZE_LEGACY, PROP_INHERIT, ZFS_TYPE_FILESYSTEM, + "legacy | auto | 1k | 2k | 4k | 8k | 16k", "DNSIZE", dnsize_table); + /* inherit index (boolean) properties */ zprop_register_index(ZFS_PROP_ATIME, "atime", 1, PROP_INHERIT, ZFS_TYPE_FILESYSTEM, "on | off", "ATIME", boolean_table); Modified: head/sys/cddl/contrib/opensolaris/common/zfs/zpool_prop.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/common/zfs/zpool_prop.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/common/zfs/zpool_prop.c Sun Aug 12 00:45:53 2018 (r337669) @@ -138,6 +138,8 @@ zpool_prop_init(void) PROP_TYPE_NUMBER, PROP_READONLY, ZFS_TYPE_POOL, "MAXBLOCKSIZE"); zprop_register_hidden(ZPOOL_PROP_TNAME, "tname", PROP_TYPE_STRING, PROP_ONETIME, ZFS_TYPE_POOL, "TNAME"); + zprop_register_hidden(ZPOOL_PROP_MAXDNODESIZE, "maxdnodesize", + PROP_TYPE_NUMBER, PROP_READONLY, ZFS_TYPE_POOL, "MAXDNODESIZE"); } /* Modified: head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dbuf.c Sun Aug 12 00:45:53 2018 (r337669) @@ -752,7 +752,6 @@ dbuf_verify(dmu_buf_impl_t *db) ASSERT3U(db->db.db_offset, ==, DMU_BONUS_BLKID); } else if (db->db_blkid == DMU_SPILL_BLKID) { ASSERT(dn != NULL); - ASSERT3U(db->db.db_size, >=, dn->dn_bonuslen); ASSERT0(db->db.db_offset); } else { ASSERT3U(db->db.db_offset, ==, db->db_blkid * db->db.db_size); @@ -1010,13 +1009,18 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_ ASSERT(db->db_buf == NULL); if (db->db_blkid == DMU_BONUS_BLKID) { + /* + * The bonus length stored in the dnode may be less than + * the maximum available space in the bonus buffer. + */ int bonuslen = MIN(dn->dn_bonuslen, dn->dn_phys->dn_bonuslen); + int max_bonuslen = DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots); ASSERT3U(bonuslen, <=, db->db.db_size); - db->db.db_data = zio_buf_alloc(DN_MAX_BONUSLEN); - arc_space_consume(DN_MAX_BONUSLEN, ARC_SPACE_BONUS); - if (bonuslen < DN_MAX_BONUSLEN) - bzero(db->db.db_data, DN_MAX_BONUSLEN); + db->db.db_data = zio_buf_alloc(max_bonuslen); + arc_space_consume(max_bonuslen, ARC_SPACE_BONUS); + if (bonuslen < max_bonuslen) + bzero(db->db.db_data, max_bonuslen); if (bonuslen) bcopy(DN_BONUS(dn->dn_phys), db->db.db_data, bonuslen); DB_DNODE_EXIT(db); @@ -1123,9 +1127,11 @@ dbuf_fix_old_data(dmu_buf_impl_t *db, uint64_t txg) ASSERT(dr->dr_txg >= txg - 2); if (db->db_blkid == DMU_BONUS_BLKID) { /* Note that the data bufs here are zio_bufs */ - dr->dt.dl.dr_data = zio_buf_alloc(DN_MAX_BONUSLEN); - arc_space_consume(DN_MAX_BONUSLEN, ARC_SPACE_BONUS); - bcopy(db->db.db_data, dr->dt.dl.dr_data, DN_MAX_BONUSLEN); + dnode_t *dn = DB_DNODE(db); + int bonuslen = DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots); + dr->dt.dl.dr_data = zio_buf_alloc(bonuslen); + arc_space_consume(bonuslen, ARC_SPACE_BONUS); + bcopy(db->db.db_data, dr->dt.dl.dr_data, bonuslen); } else if (refcount_count(&db->db_holds) > db->db_dirtycnt) { int size = arc_buf_size(db->db_buf); arc_buf_contents_t type = DBUF_GET_BUFC_TYPE(db); @@ -2096,10 +2102,13 @@ dbuf_destroy(dmu_buf_impl_t *db) } if (db->db_blkid == DMU_BONUS_BLKID) { - ASSERT(db->db.db_data != NULL); - zio_buf_free(db->db.db_data, DN_MAX_BONUSLEN); - arc_space_return(DN_MAX_BONUSLEN, ARC_SPACE_BONUS); - db->db_state = DB_UNCACHED; + int slots = DB_DNODE(db)->dn_num_slots; + int bonuslen = DN_SLOTS_TO_BONUSLEN(slots); + if (db->db.db_data != NULL) { + zio_buf_free(db->db.db_data, bonuslen); + arc_space_return(bonuslen, ARC_SPACE_BONUS); + db->db_state = DB_UNCACHED; + } } dbuf_clear_data(db); @@ -2203,7 +2212,7 @@ dbuf_findbp(dnode_t *dn, int level, uint64_t blkid, in mutex_enter(&dn->dn_mtx); if (dn->dn_have_spill && (dn->dn_phys->dn_flags & DNODE_FLAG_SPILL_BLKPTR)) - *bpp = &dn->dn_phys->dn_spill; + *bpp = DN_SPILL_BLKPTR(dn->dn_phys); else *bpp = NULL; dbuf_add_ref(dn->dn_dbuf, NULL); @@ -2304,7 +2313,7 @@ dbuf_create(dnode_t *dn, uint8_t level, uint64_t blkid if (blkid == DMU_BONUS_BLKID) { ASSERT3P(parent, ==, dn->dn_dbuf); - db->db.db_size = DN_MAX_BONUSLEN - + db->db.db_size = DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots) - (dn->dn_nblkptr-1) * sizeof (blkptr_t); ASSERT3U(db->db.db_size, >=, dn->dn_bonuslen); db->db.db_offset = DMU_BONUS_BLKID; @@ -3054,7 +3063,7 @@ dbuf_check_blkptr(dnode_t *dn, dmu_buf_impl_t *db) return; if (db->db_blkid == DMU_SPILL_BLKID) { - db->db_blkptr = &dn->dn_phys->dn_spill; + db->db_blkptr = DN_SPILL_BLKPTR(dn->dn_phys); BP_ZERO(db->db_blkptr); return; } @@ -3185,13 +3194,17 @@ dbuf_sync_leaf(dbuf_dirty_record_t *dr, dmu_tx_t *tx) ASSERT(*datap != NULL); ASSERT0(db->db_level); - ASSERT3U(dn->dn_phys->dn_bonuslen, <=, DN_MAX_BONUSLEN); - bcopy(*datap, DN_BONUS(dn->dn_phys), dn->dn_phys->dn_bonuslen); + ASSERT3U(DN_MAX_BONUS_LEN(dn->dn_phys), <=, + DN_SLOTS_TO_BONUSLEN(dn->dn_phys->dn_extra_slots + 1)); + bcopy(*datap, DN_BONUS(dn->dn_phys), + DN_MAX_BONUS_LEN(dn->dn_phys)); DB_DNODE_EXIT(db); if (*datap != db->db.db_data) { - zio_buf_free(*datap, DN_MAX_BONUSLEN); - arc_space_return(DN_MAX_BONUSLEN, ARC_SPACE_BONUS); + int slots = DB_DNODE(db)->dn_num_slots; + int bonuslen = DN_SLOTS_TO_BONUSLEN(slots); + zio_buf_free(*datap, bonuslen); + arc_space_return(bonuslen, ARC_SPACE_BONUS); } db->db_data_pending = NULL; drp = &db->db_last_dirty; @@ -3201,8 +3214,8 @@ dbuf_sync_leaf(dbuf_dirty_record_t *dr, dmu_tx_t *tx) ASSERT(dr->dr_dbuf == db); *drp = dr->dr_next; if (dr->dr_dbuf->db_level != 0) { - list_destroy(&dr->dt.di.dr_children); mutex_destroy(&dr->dt.di.dr_mtx); + list_destroy(&dr->dt.di.dr_children); } kmem_free(dr, sizeof (dbuf_dirty_record_t)); ASSERT(db->db_dirtycnt > 0); @@ -3351,7 +3364,7 @@ dbuf_write_ready(zio_t *zio, arc_buf_t *buf, void *vdb if (db->db_blkid == DMU_SPILL_BLKID) { ASSERT(dn->dn_phys->dn_flags & DNODE_FLAG_SPILL_BLKPTR); ASSERT(!(BP_IS_HOLE(bp)) && - db->db_blkptr == &dn->dn_phys->dn_spill); + db->db_blkptr == DN_SPILL_BLKPTR(dn->dn_phys)); } #endif @@ -3363,11 +3376,16 @@ dbuf_write_ready(zio_t *zio, arc_buf_t *buf, void *vdb mutex_exit(&dn->dn_mtx); if (dn->dn_type == DMU_OT_DNODE) { - dnode_phys_t *dnp = db->db.db_data; - for (i = db->db.db_size >> DNODE_SHIFT; i > 0; - i--, dnp++) { - if (dnp->dn_type != DMU_OT_NONE) + i = 0; + while (i < db->db.db_size) { + dnode_phys_t *dnp = db->db.db_data + i; + + i += DNODE_MIN_SIZE; + if (dnp->dn_type != DMU_OT_NONE) { fill++; + i += dnp->dn_extra_slots * + DNODE_MIN_SIZE; + } } } else { if (BP_IS_HOLE(bp)) { @@ -3520,7 +3538,7 @@ dbuf_write_done(zio_t *zio, arc_buf_t *buf, void *vdb) dn = DB_DNODE(db); ASSERT(dn->dn_phys->dn_flags & DNODE_FLAG_SPILL_BLKPTR); ASSERT(!(BP_IS_HOLE(db->db_blkptr)) && - db->db_blkptr == &dn->dn_phys->dn_spill); + db->db_blkptr == DN_SPILL_BLKPTR(dn->dn_phys)); DB_DNODE_EXIT(db); } #endif Modified: head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu.c Sun Aug 12 00:45:53 2018 (r337669) @@ -244,7 +244,7 @@ dmu_buf_hold(objset_t *os, uint64_t object, uint64_t o int dmu_bonus_max(void) { - return (DN_MAX_BONUSLEN); + return (DN_OLD_MAX_BONUSLEN); } int @@ -2524,6 +2524,7 @@ dmu_object_info_from_dnode(dnode_t *dn, dmu_object_inf doi->doi_type = dn->dn_type; doi->doi_bonus_type = dn->dn_bonustype; doi->doi_bonus_size = dn->dn_bonuslen; + doi->doi_dnodesize = dn->dn_num_slots << DNODE_SHIFT; doi->doi_indirection = dn->dn_nlevels; doi->doi_checksum = dn->dn_checksum; doi->doi_compress = dn->dn_compress; @@ -2586,9 +2587,21 @@ dmu_object_size_from_db(dmu_buf_t *db_fake, uint32_t * dn = DB_DNODE(db); *blksize = dn->dn_datablksz; - /* add 1 for dnode space */ + /* add in number of slots used for the dnode itself */ *nblk512 = ((DN_USED_BYTES(dn->dn_phys) + SPA_MINBLOCKSIZE/2) >> - SPA_MINBLOCKSHIFT) + 1; + SPA_MINBLOCKSHIFT) + dn->dn_num_slots; + DB_DNODE_EXIT(db); +} + +void +dmu_object_dnsize_from_db(dmu_buf_t *db_fake, int *dnsize) +{ + dmu_buf_impl_t *db = (dmu_buf_impl_t *)db_fake; + dnode_t *dn; + + DB_DNODE_ENTER(db); + dn = DB_DNODE(db); + *dnsize = dn->dn_num_slots << DNODE_SHIFT; DB_DNODE_EXIT(db); } Modified: head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c ============================================================================== --- head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c Sun Aug 12 00:33:24 2018 (r337668) +++ head/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_object.c Sun Aug 12 00:45:53 2018 (r337669) @@ -30,29 +30,49 @@ #include #include #include +#include -uint64_t -dmu_object_alloc_ibs(objset_t *os, dmu_object_type_t ot, int blocksize, - int indirect_blockshift, - dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) + +static uint64_t +dmu_object_alloc_impl(objset_t *os, dmu_object_type_t ot, int blocksize, + int indirect_blockshift, dmu_object_type_t bonustype, int bonuslen, + int dnodesize, dmu_tx_t *tx) { uint64_t object; uint64_t L1_dnode_count = DNODES_PER_BLOCK << (DMU_META_DNODE(os)->dn_indblkshift - SPA_BLKPTRSHIFT); dnode_t *dn = NULL; + int dn_slots = dnodesize >> DNODE_SHIFT; + boolean_t restarted = B_FALSE; + if (dn_slots == 0) { + dn_slots = DNODE_MIN_SLOTS; + } else { + ASSERT3S(dn_slots, >=, DNODE_MIN_SLOTS); + ASSERT3S(dn_slots, <=, DNODE_MAX_SLOTS); + } + mutex_enter(&os->os_obj_lock); for (;;) { object = os->os_obj_next; /* * Each time we polish off a L1 bp worth of dnodes (2^12 - * objects), move to another L1 bp that's still reasonably - * sparse (at most 1/4 full). Look from the beginning at most - * once per txg, but after that keep looking from here. + * objects), move to another L1 bp that's still + * reasonably sparse (at most 1/4 full). Look from the + * beginning at most once per txg. If we still can't + * allocate from that L1 block, search for an empty L0 + * block, which will quickly skip to the end of the + * metadnode if the no nearby L0 blocks are empty. This + * fallback avoids a pathology where full dnode blocks + * containing large dnodes appear sparse because they + * have a low blk_fill, leading to many failed + * allocation attempts. In the long term a better + * mechanism to search for sparse metadnode regions, + * such as spacemaps, could be implemented. + * * os_scan_dnodes is set during txg sync if enough objects * have been freed since the previous rescan to justify - * backfilling again. If we can't find a suitable block, just - * keep going from here. + * backfilling again. * * Note that dmu_traverse depends on the behavior that we use * multiple blocks of the dnode object before going back to @@ -60,9 +80,10 @@ dmu_object_alloc_ibs(objset_t *os, dmu_object_type_t o * that property or find another solution to the issues * described in traverse_visitbp. */ - if (P2PHASE(object, L1_dnode_count) == 0) { uint64_t offset; + uint64_t blkfill; + int minlvl; int error; if (os->os_rescan_dnodes) { offset = 0; @@ -70,13 +91,15 @@ dmu_object_alloc_ibs(objset_t *os, dmu_object_type_t o } else { offset = object << DNODE_SHIFT; } + blkfill = restarted ? 1 : DNODES_PER_BLOCK >> 2; + minlvl = restarted ? 1 : 2; + restarted = B_TRUE; error = dnode_next_offset(DMU_META_DNODE(os), - DNODE_FIND_HOLE, - &offset, 2, DNODES_PER_BLOCK >> 2, 0); + DNODE_FIND_HOLE, &offset, minlvl, blkfill, 0); if (error == 0) object = offset >> DNODE_SHIFT; } - os->os_obj_next = ++object; + os->os_obj_next = object + dn_slots; /* * XXX We should check for an i/o error here and return @@ -84,17 +107,23 @@ dmu_object_alloc_ibs(objset_t *os, dmu_object_type_t o * dmu_tx_assign(), but there is currently no mechanism * to do so. */ - (void) dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, + (void) dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, dn_slots, FTAG, &dn); if (dn) break; if (dmu_object_next(os, &object, B_TRUE, 0) == 0) - os->os_obj_next = object - 1; + os->os_obj_next = object; + else + /* + * Skip to next known valid starting point for a dnode. + */ + os->os_obj_next = P2ROUNDUP(object + 1, + DNODES_PER_BLOCK); } dnode_allocate(dn, ot, blocksize, indirect_blockshift, - bonustype, bonuslen, tx); + bonustype, bonuslen, dn_slots, tx); mutex_exit(&os->os_obj_lock); dmu_tx_add_new_object(tx, dn); @@ -107,24 +136,57 @@ uint64_t dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { - return (dmu_object_alloc_ibs(os, ot, blocksize, 0, - bonustype, bonuslen, tx)); + return dmu_object_alloc_impl(os, ot, blocksize, 0, bonustype, + bonuslen, 0, tx); } +uint64_t +dmu_object_alloc_ibs(objset_t *os, dmu_object_type_t ot, int blocksize, + int indirect_blockshift, dmu_object_type_t bonustype, int bonuslen, + dmu_tx_t *tx) +{ + return dmu_object_alloc_impl(os, ot, blocksize, indirect_blockshift, + bonustype, bonuslen, 0, tx); +} + +uint64_t +dmu_object_alloc_dnsize(objset_t *os, dmu_object_type_t ot, int blocksize, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx) +{ + return (dmu_object_alloc_impl(os, ot, blocksize, 0, bonustype, + bonuslen, dnodesize, tx)); +} + int dmu_object_claim(objset_t *os, uint64_t object, dmu_object_type_t ot, int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { + return (dmu_object_claim_dnsize(os, object, ot, blocksize, bonustype, + bonuslen, 0, tx)); +} + +int +dmu_object_claim_dnsize(objset_t *os, uint64_t object, dmu_object_type_t ot, + int blocksize, dmu_object_type_t bonustype, int bonuslen, + int dnodesize, dmu_tx_t *tx) +{ dnode_t *dn; + int dn_slots = dnodesize >> DNODE_SHIFT; int err; + if (dn_slots == 0) + dn_slots = DNODE_MIN_SLOTS; + ASSERT3S(dn_slots, >=, DNODE_MIN_SLOTS); + ASSERT3S(dn_slots, <=, DNODE_MAX_SLOTS); *** DIFF OUTPUT TRUNCATED AT 1000 LINES ***