Date: Mon, 12 Aug 2019 12:05:43 +0000 (UTC) From: Andriy Gapon <avg@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-vendor@freebsd.org Subject: svn commit: r350898 - vendor-sys/illumos/dist/common/zfs vendor-sys/illumos/dist/uts/common/fs/zfs vendor-sys/illumos/dist/uts/common/fs/zfs/sys vendor-sys/illumos/dist/uts/common/sys/fs vendor/ill... Message-ID: <201908121205.x7CC5hlJ017155@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: avg Date: Mon Aug 12 12:05:40 2019 New Revision: 350898 URL: https://svnweb.freebsd.org/changeset/base/350898 Log: 8423 8199 7432 Implement large_dnode pool feature 8423 Implement large_dnode pool feature 8199 multi-threaded dmu_object_alloc() 7432 Large dnode pool feature llumos/illumos-gate@54811da5ac6b517992fdc173df5d605e4e61fdc0 https://github.com/illumos/illumos-gate/commit/54811da5ac6b517992fdc173df5d605e4e61fdc0 https://www.illumos.org/issues/8423 https://www.illumos.org/issues/8199 https://www.illumos.org/issues/7432 ZoL issues: Improved dnode allocation #6564 Clean up large dnode code #6262 Fix dnode_hold() freeing dnode behavior #8172 Fix dnode allocation race #6414, #6439 Partial: Raw sends must be able to decrease nlevels #6821, #6864 Remove unnecessary txg syncs from receive_object() Closes #7197 Author: Toomas Soome <tsoome@me.com> Modified: vendor/illumos/dist/cmd/zdb/zdb.c vendor/illumos/dist/cmd/zdb/zdb_il.c vendor/illumos/dist/cmd/zstreamdump/zstreamdump.c vendor/illumos/dist/cmd/ztest/ztest.c vendor/illumos/dist/man/man5/zpool-features.5 Changes in other areas also in this revision: Modified: vendor-sys/illumos/dist/common/zfs/zfeature_common.c vendor-sys/illumos/dist/common/zfs/zfeature_common.h vendor-sys/illumos/dist/common/zfs/zfs_prop.c vendor-sys/illumos/dist/common/zfs/zpool_prop.c vendor-sys/illumos/dist/uts/common/fs/zfs/dbuf.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu_object.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu_objset.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu_send.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu_traverse.c vendor-sys/illumos/dist/uts/common/fs/zfs/dmu_tx.c vendor-sys/illumos/dist/uts/common/fs/zfs/dnode.c vendor-sys/illumos/dist/uts/common/fs/zfs/dnode_sync.c vendor-sys/illumos/dist/uts/common/fs/zfs/dsl_scan.c vendor-sys/illumos/dist/uts/common/fs/zfs/sa.c vendor-sys/illumos/dist/uts/common/fs/zfs/spa.c vendor-sys/illumos/dist/uts/common/fs/zfs/spa_misc.c vendor-sys/illumos/dist/uts/common/fs/zfs/sys/arc.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/dmu.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/dmu_objset.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/dnode.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/dsl_dataset.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/sa_impl.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/spa.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/zap.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/zfs_ioctl.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/zfs_znode.h vendor-sys/illumos/dist/uts/common/fs/zfs/sys/zil.h vendor-sys/illumos/dist/uts/common/fs/zfs/zap.c vendor-sys/illumos/dist/uts/common/fs/zfs/zap_micro.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_acl.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_ioctl.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_log.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_replay.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_sa.c vendor-sys/illumos/dist/uts/common/fs/zfs/zfs_znode.c vendor-sys/illumos/dist/uts/common/fs/zfs/zil.c vendor-sys/illumos/dist/uts/common/sys/fs/zfs.h Modified: vendor/illumos/dist/cmd/zdb/zdb.c ============================================================================== --- vendor/illumos/dist/cmd/zdb/zdb.c Mon Aug 12 11:42:16 2019 (r350897) +++ vendor/illumos/dist/cmd/zdb/zdb.c Mon Aug 12 12:05:40 2019 (r350898) @@ -2108,14 +2108,15 @@ static object_viewer_t *object_viewer[DMU_OT_NUMTYPES }; static void -dump_object(objset_t *os, uint64_t object, int verbosity, int *print_header) +dump_object(objset_t *os, uint64_t object, int verbosity, int *print_header, + uint64_t *dnode_slots_used) { dmu_buf_t *db = NULL; dmu_object_info_t doi; 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; @@ -2128,9 +2129,9 @@ 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; } @@ -2147,11 +2148,15 @@ dump_object(objset_t *os, uint64_t object, int verbosi } dmu_object_info_from_dnode(dn, &doi); + if (dnode_slots_used != NULL) + *dnode_slots_used = doi.doi_dnodesize / DNODE_MIN_SIZE; + zdb_nicenum(doi.doi_metadata_block_size, iblk, sizeof (iblk)); zdb_nicenum(doi.doi_data_block_size, dblk, sizeof (dblk)); 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); @@ -2168,13 +2173,14 @@ 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", - (u_longlong_t)object, doi.doi_indirection, iblk, dblk, - asize, lsize, fill, ZDB_OT_NAME(doi.doi_type), aux); + (void) printf("%10" PRIu64 + " %3u %5s %5s %5s %5s %5s %6s %s%s\n", + object, doi.doi_indirection, iblk, dblk, + 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)); } @@ -2278,6 +2284,9 @@ dump_dir(objset_t *os) int print_header = 1; unsigned i; int error; + uint64_t total_slots_used = 0; + uint64_t max_slot_used = 0; + uint64_t dnode_slots; /* make sure nicenum has enough space */ CTASSERT(sizeof (numbuf) >= NN_NUMBUF_SZ); @@ -2322,7 +2331,7 @@ dump_dir(objset_t *os) if (zopt_objects != 0) { for (i = 0; i < zopt_objects; i++) dump_object(os, zopt_object[i], verbosity, - &print_header); + &print_header, NULL); (void) printf("\n"); return; } @@ -2347,24 +2356,39 @@ dump_dir(objset_t *os) if (BP_IS_HOLE(os->os_rootbp)) return; - dump_object(os, 0, verbosity, &print_header); + dump_object(os, 0, verbosity, &print_header, NULL); object_count = 0; if (DMU_USERUSED_DNODE(os) != NULL && DMU_USERUSED_DNODE(os)->dn_type != 0) { - dump_object(os, DMU_USERUSED_OBJECT, verbosity, &print_header); - dump_object(os, DMU_GROUPUSED_OBJECT, verbosity, &print_header); + dump_object(os, DMU_USERUSED_OBJECT, verbosity, &print_header, + NULL); + dump_object(os, DMU_GROUPUSED_OBJECT, verbosity, &print_header, + NULL); } object = 0; while ((error = dmu_object_next(os, &object, B_FALSE, 0)) == 0) { - dump_object(os, object, verbosity, &print_header); + dump_object(os, object, verbosity, &print_header, &dnode_slots); object_count++; + total_slots_used += dnode_slots; + max_slot_used = object + dnode_slots - 1; } ASSERT3U(object_count, ==, usedobjs); (void) printf("\n"); + (void) printf(" Dnode slots:\n"); + (void) printf("\tTotal used: %10llu\n", + (u_longlong_t)total_slots_used); + (void) printf("\tMax used: %10llu\n", + (u_longlong_t)max_slot_used); + (void) printf("\tPercent empty: %10lf\n", + (double)(max_slot_used - total_slots_used)*100 / + (double)max_slot_used); + + (void) printf("\n"); + if (error != ESRCH) { (void) fprintf(stderr, "dmu_object_next() = %d\n", error); abort(); @@ -2553,7 +2577,7 @@ dump_path_impl(objset_t *os, uint64_t obj, char *name) return (dump_path_impl(os, child_obj, s + 1)); /*FALLTHROUGH*/ case DMU_OT_PLAIN_FILE_CONTENTS: - dump_object(os, child_obj, dump_opt['v'], &header); + dump_object(os, child_obj, dump_opt['v'], &header, NULL); return (0); default: (void) fprintf(stderr, "object %llu has non-file/directory " Modified: vendor/illumos/dist/cmd/zdb/zdb_il.c ============================================================================== --- vendor/illumos/dist/cmd/zdb/zdb_il.c Mon Aug 12 11:42:16 2019 (r350897) +++ vendor/illumos/dist/cmd/zdb/zdb_il.c Mon Aug 12 12:05:40 2019 (r350898) @@ -84,13 +84,15 @@ 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, - (longlong_t)lr->lr_mode); - (void) printf("%suid %llu, gid %llu, gen %llu, rdev 0x%llx\n", - tab_prefix, - (u_longlong_t)lr->lr_uid, (u_longlong_t)lr->lr_gid, - (u_longlong_t)lr->lr_gen, (u_longlong_t)lr->lr_rdev); + (void) printf("%sdoid %" PRIu64 ", foid %" PRIu64 ", slots %" PRIu64 + ", mode %" PRIo64 "\n", + tab_prefix, lr->lr_doid, + LR_FOID_GET_OBJ(lr->lr_foid), + LR_FOID_GET_SLOTS(lr->lr_foid), + lr->lr_mode); + (void) printf("%suid %" PRIu64 ", gid %" PRIu64 ", gen %" PRIu64 + ", rdev %#" PRIx64 "\n", + tab_prefix, lr->lr_uid, lr->lr_gid, lr->lr_gen, lr->lr_rdev); } /* ARGSUSED */ Modified: vendor/illumos/dist/cmd/zstreamdump/zstreamdump.c ============================================================================== --- vendor/illumos/dist/cmd/zstreamdump/zstreamdump.c Mon Aug 12 11:42:16 2019 (r350897) +++ vendor/illumos/dist/cmd/zstreamdump/zstreamdump.c Mon Aug 12 12:05:40 2019 (r350898) @@ -416,13 +416,15 @@ main(int argc, char *argv[]) drro->drr_toguid = BSWAP_64(drro->drr_toguid); } if (verbose) { - (void) printf("OBJECT object = %llu type = %u " - "bonustype = %u blksz = %u bonuslen = %u\n", - (u_longlong_t)drro->drr_object, + (void) printf("OBJECT object = %" PRIu64 + " type = %u bonustype = %u blksz = %u" + " bonuslen = %u dn_slots = %u\n", + drro->drr_object, drro->drr_type, drro->drr_bonustype, drro->drr_blksz, - drro->drr_bonuslen); + drro->drr_bonuslen, + drro->drr_dn_slots); } if (drro->drr_bonuslen > 0) { (void) ssread(buf, Modified: vendor/illumos/dist/cmd/ztest/ztest.c ============================================================================== --- vendor/illumos/dist/cmd/ztest/ztest.c Mon Aug 12 11:42:16 2019 (r350897) +++ vendor/illumos/dist/cmd/ztest/ztest.c Mon Aug 12 12:05:40 2019 (r350898) @@ -194,6 +194,7 @@ extern uint64_t zfs_deadman_synctime_ms; extern int metaslab_preload_limit; extern boolean_t zfs_compressed_arc_enabled; extern boolean_t zfs_abd_scatter_enabled; +extern int dmu_object_alloc_chunk_shift; extern boolean_t zfs_force_some_double_word_sm_entries; static ztest_shared_opts_t *ztest_shared_opts; @@ -224,6 +225,7 @@ 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 +276,7 @@ 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]; @@ -320,6 +323,7 @@ static ztest_shared_callstate_t *ztest_shared_callstat ztest_func_t ztest_dmu_read_write; ztest_func_t ztest_dmu_write_parallel; ztest_func_t ztest_dmu_object_alloc_free; +ztest_func_t ztest_dmu_object_next_chunk; ztest_func_t ztest_dmu_commit_callbacks; ztest_func_t ztest_zap; ztest_func_t ztest_zap_parallel; @@ -349,6 +353,7 @@ 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 */ @@ -360,6 +365,7 @@ ztest_info_t ztest_info[] = { { ztest_dmu_read_write, 1, &zopt_always }, { ztest_dmu_write_parallel, 10, &zopt_always }, { ztest_dmu_object_alloc_free, 1, &zopt_always }, + { ztest_dmu_object_next_chunk, 1, &zopt_sometimes }, { ztest_dmu_commit_callbacks, 1, &zopt_always }, { ztest_zap, 30, &zopt_always }, { ztest_zap_parallel, 100, &zopt_always }, @@ -392,7 +398,8 @@ 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)) @@ -438,8 +445,8 @@ 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 @@ -1009,6 +1016,36 @@ 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 + @@ -1285,11 +1322,13 @@ 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; @@ -1298,11 +1337,13 @@ 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); @@ -1324,6 +1365,52 @@ 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 */ @@ -1331,7 +1418,7 @@ 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) @@ -1447,6 +1534,7 @@ 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)); @@ -1469,26 +1557,27 @@ 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); } } @@ -1508,7 +1597,9 @@ 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, @@ -1658,7 +1749,7 @@ 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); } } @@ -1670,7 +1761,7 @@ 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); } @@ -1679,7 +1770,8 @@ 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) { @@ -1751,7 +1843,7 @@ 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)); @@ -1774,6 +1866,7 @@ 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); @@ -1792,7 +1885,7 @@ 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); @@ -1802,7 +1895,9 @@ 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); @@ -2033,7 +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); @@ -2212,7 +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; @@ -2273,13 +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; @@ -3721,8 +3819,10 @@ ztest_dmu_object_alloc_free(ztest_ds_t *zd, uint64_t i ztest_od_t od[4]; 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); + for (int b = 0; b < batchsize; b++) { + 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, @@ -3737,6 +3837,26 @@ ztest_dmu_object_alloc_free(ztest_ds_t *zd, uint64_t i } /* + * Rewind the global allocator to verify object allocation backfilling. + */ +void +ztest_dmu_object_next_chunk(ztest_ds_t *zd, uint64_t id) +{ + objset_t *os = zd->zd_os; + int dnodes_per_chunk = 1 << dmu_object_alloc_chunk_shift; + uint64_t object; + + /* + * Rewind the global allocator randomly back to a lower object number + * to force backfilling and reclamation of recently freed dnodes. + */ + mutex_enter(&os->os_obj_lock); + object = ztest_random(os->os_obj_next_chunk); + os->os_obj_next_chunk = P2ALIGN(object, dnodes_per_chunk); + mutex_exit(&os->os_obj_lock); +} + +/* * Verify that dmu_{read,write} work as expected. */ void @@ -3782,8 +3902,10 @@ 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; @@ -4052,8 +4174,10 @@ 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; @@ -4254,7 +4378,8 @@ 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; @@ -4273,7 +4398,8 @@ 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; @@ -4319,7 +4445,7 @@ 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; @@ -4451,7 +4577,7 @@ 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; @@ -4497,7 +4623,8 @@ 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; @@ -4685,7 +4812,7 @@ 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; @@ -4799,6 +4926,41 @@ 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) @@ -5283,7 +5445,8 @@ 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; @@ -6155,7 +6318,7 @@ 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: vendor/illumos/dist/man/man5/zpool-features.5 ============================================================================== --- vendor/illumos/dist/man/man5/zpool-features.5 Mon Aug 12 11:42:16 2019 (r350897) +++ vendor/illumos/dist/man/man5/zpool-features.5 Mon Aug 12 12:05:40 2019 (r350898) @@ -533,6 +533,30 @@ set larger than 128KB, and will return to being \fBena filesystems that have ever had their recordsize larger than 128KB are destroyed. .RE +.ne 2 +.na +\fB\fBlarge_dnode\fR\fR +.ad +.RS 4n +.TS +l l . +GUID org.zfsonlinux:large_dnode +READ\-ONLY COMPATIBLE no +DEPENDENCIES extensible_dataset +.TE + +The \fBlarge_dnode\fR feature allows the size of dnodes in a dataset to be +set larger than 512B. + +This feature becomes \fBactive\fR once a dataset contains an object with a +dnode larger than 512B, which occurs as a result of setting the \fBdnodesize\fR +dataset property to a value other than \fBlegacy\fR. The feature will return to +being \fBenabled\fR once all filesystems that have ever contained a dnode larger +than 512B are destroyed. Large dnodes allow more data to be stored in the +bonus buffer, thus potentially improving performance by avoiding the use of +spill blocks. +.RE + .sp .ne 2 .na
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201908121205.x7CC5hlJ017155>