diff options
64 files changed, 1575 insertions, 224 deletions
diff --git a/cmd/zdb/zdb.c b/cmd/zdb/zdb.c index 3311a6e6f..ee5e21f10 100644 --- a/cmd/zdb/zdb.c +++ b/cmd/zdb/zdb.c @@ -1880,15 +1880,15 @@ dump_object(objset_t *os, uint64_t object, int verbosity, int *print_header) 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; 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; } @@ -1910,6 +1910,7 @@ dump_object(objset_t *os, uint64_t object, int verbosity, int *print_header) zdb_nicenum(doi.doi_max_offset, lsize); zdb_nicenum(doi.doi_physical_blocks_512 << 9, asize); zdb_nicenum(doi.doi_bonus_size, bonus_size); + zdb_nicenum(doi.doi_dnodesize, 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); @@ -1926,13 +1927,13 @@ dump_object(objset_t *os, uint64_t object, int verbosity, int *print_header) 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)); } diff --git a/cmd/zdb/zdb_il.c b/cmd/zdb/zdb_il.c index 93b905793..1501e879d 100644 --- a/cmd/zdb/zdb_il.c +++ b/cmd/zdb/zdb_il.c @@ -80,8 +80,10 @@ zil_prt_rec_create(zilog_t *zilog, int txtype, lr_create_t *lr) } (void) printf("%s%s", prefix, ctime(&crtime)); - (void) printf("%sdoid %llu, foid %llu, mode %llo\n", prefix, - (u_longlong_t)lr->lr_doid, (u_longlong_t)lr->lr_foid, + (void) printf("%sdoid %llu, foid %llu, slots %llu, mode %llo\n", 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", prefix, (u_longlong_t)lr->lr_uid, (u_longlong_t)lr->lr_gid, diff --git a/cmd/ztest/ztest.c b/cmd/ztest/ztest.c index e6d6e9803..ad15dea1d 100644 --- a/cmd/ztest/ztest.c +++ b/cmd/ztest/ztest.c @@ -221,6 +221,7 @@ 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; @@ -258,6 +259,7 @@ 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[MAXNAMELEN]; @@ -329,6 +331,7 @@ ztest_func_t ztest_split_pool; ztest_func_t ztest_reguid; ztest_func_t ztest_spa_upgrade; ztest_func_t ztest_fletcher; +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 */ @@ -375,6 +378,7 @@ ztest_info_t ztest_info[] = { ZTI_INIT(ztest_vdev_add_remove, 1, &ztest_opts.zo_vdevtime), ZTI_INIT(ztest_vdev_aux_add_remove, 1, &ztest_opts.zo_vdevtime), ZTI_INIT(ztest_fletcher, 1, &zopt_rarely), + ZTI_INIT(ztest_verify_dnode_bt, 1, &zopt_sometimes), }; #define ZTEST_FUNCS (sizeof (ztest_info) / sizeof (ztest_info_t)) @@ -1028,6 +1032,36 @@ 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 + @@ -1417,11 +1451,13 @@ ztest_pattern_match(void *buf, uint64_t size, uint64_t value) 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; @@ -1430,11 +1466,13 @@ ztest_bt_generate(ztest_block_tag_t *bt, objset_t *os, uint64_t object, 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); @@ -1456,6 +1494,52 @@ 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 */ @@ -1463,7 +1547,7 @@ 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) @@ -1578,6 +1662,7 @@ ztest_replay_create(ztest_ds_t *zd, lr_create_t *lr, boolean_t byteswap) dmu_tx_t *tx; uint64_t txg; int error = 0; + int bonuslen; if (byteswap) byteswap_uint64_array(lr, sizeof (*lr)); @@ -1600,26 +1685,27 @@ ztest_replay_create(ztest_ds_t *zd, lr_create_t *lr, boolean_t byteswap) 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); } } @@ -1639,7 +1725,9 @@ ztest_replay_create(ztest_ds_t *zd, lr_create_t *lr, boolean_t byteswap) 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, @@ -1785,7 +1873,7 @@ ztest_replay_write(ztest_ds_t *zd, lr_write_t *lr, boolean_t byteswap) 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); } } @@ -1797,7 +1885,7 @@ ztest_replay_write(ztest_ds_t *zd, lr_write_t *lr, boolean_t byteswap) * 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); } @@ -1806,7 +1894,8 @@ ztest_replay_write(ztest_ds_t *zd, lr_write_t *lr, boolean_t byteswap) * 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) { @@ -1874,7 +1963,7 @@ ztest_replay_setattr(ztest_ds_t *zd, lr_setattr_t *lr, boolean_t byteswap) 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)); @@ -1897,6 +1986,7 @@ ztest_replay_setattr(ztest_ds_t *zd, lr_setattr_t *lr, boolean_t byteswap) 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); @@ -1915,7 +2005,7 @@ ztest_replay_setattr(ztest_ds_t *zd, lr_setattr_t *lr, boolean_t byteswap) /* * 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); @@ -1925,8 +2015,9 @@ ztest_replay_setattr(ztest_ds_t *zd, lr_setattr_t *lr, boolean_t byteswap) 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); @@ -2171,7 +2262,7 @@ 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); @@ -2351,7 +2442,8 @@ ztest_io(ztest_ds_t *zd, uint64_t object, uint64_t offset) 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; @@ -2414,13 +2506,15 @@ ztest_io(ztest_ds_t *zd, uint64_t object, uint64_t offset) */ 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; @@ -3740,7 +3834,8 @@ ztest_dmu_object_alloc_free(ztest_ds_t *zd, uint64_t id) batchsize = OD_ARRAY_SIZE; for (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, @@ -3809,8 +3904,9 @@ 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, 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, 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, size, B_FALSE) != 0) { umem_free(od, size); @@ -4090,8 +4186,9 @@ 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, 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, 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, size, B_FALSE) != 0) { @@ -4299,7 +4396,7 @@ 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, ID_PARALLEL, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(od, ID_PARALLEL, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) return; @@ -4322,7 +4419,7 @@ ztest_dmu_prealloc(ztest_ds_t *zd, uint64_t id) od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0); + ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) { @@ -4375,7 +4472,7 @@ ztest_zap(ztest_ds_t *zd, uint64_t id) char *hc[2] = { "s.acl.h", ".s.open.h.hyLZlg" }; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) @@ -4512,7 +4609,7 @@ ztest_fzap(ztest_ds_t *zd, uint64_t id) int i; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(od, id, FTAG, 0, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), !ztest_random(2)) != 0) @@ -4561,7 +4658,7 @@ ztest_zap_parallel(ztest_ds_t *zd, uint64_t id) void *data; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, ID_PARALLEL, FTAG, micro, DMU_OT_ZAP_OTHER, 0, 0); + ztest_od_init(od, ID_PARALLEL, FTAG, micro, DMU_OT_ZAP_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) { umem_free(od, sizeof (ztest_od_t)); @@ -4750,7 +4847,7 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id) int i, error = 0; od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0); + ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) { umem_free(od, sizeof (ztest_od_t)); @@ -4871,6 +4968,41 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id) umem_free(od, sizeof (ztest_od_t)); } +/* + * 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) @@ -5317,7 +5449,7 @@ ztest_ddt_repair(ztest_ds_t *zd, uint64_t id) blocksize = MIN(blocksize, 2048); /* because we write so many */ od = umem_alloc(sizeof (ztest_od_t), UMEM_NOFAIL); - ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0); + ztest_od_init(od, id, FTAG, 0, DMU_OT_UINT64_OTHER, blocksize, 0, 0); if (ztest_object_init(zd, od, sizeof (ztest_od_t), B_FALSE) != 0) { umem_free(od, sizeof (ztest_od_t)); @@ -6194,7 +6326,7 @@ 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); diff --git a/configure.ac b/configure.ac index 99c25bc27..9264d6bc6 100644 --- a/configure.ac +++ b/configure.ac @@ -230,6 +230,7 @@ AC_CONFIG_FILES([ tests/zfs-tests/tests/functional/devices/Makefile tests/zfs-tests/tests/functional/exec/Makefile tests/zfs-tests/tests/functional/features/async_destroy/Makefile + tests/zfs-tests/tests/functional/features/large_dnode/Makefile tests/zfs-tests/tests/functional/features/Makefile tests/zfs-tests/tests/functional/grow_pool/Makefile tests/zfs-tests/tests/functional/grow_replicas/Makefile diff --git a/include/sys/dmu.h b/include/sys/dmu.h index 64d28334e..74001d8f3 100644 --- a/include/sys/dmu.h +++ b/include/sys/dmu.h @@ -334,10 +334,19 @@ typedef struct dmu_buf { */ uint64_t dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize, dmu_object_type_t bonus_type, int bonus_len, dmu_tx_t *tx); +uint64_t dmu_object_alloc_dnsize(objset_t *os, dmu_object_type_t ot, + int blocksize, dmu_object_type_t bonus_type, int bonus_len, + int dnodesize, dmu_tx_t *tx); int dmu_object_claim(objset_t *os, uint64_t object, dmu_object_type_t ot, int blocksize, dmu_object_type_t bonus_type, int bonus_len, dmu_tx_t *tx); +int dmu_object_claim_dnsize(objset_t *os, uint64_t object, dmu_object_type_t ot, + int blocksize, dmu_object_type_t bonus_type, int bonus_len, + int dnodesize, dmu_tx_t *tx); int dmu_object_reclaim(objset_t *os, uint64_t object, dmu_object_type_t ot, int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *txp); +int dmu_object_reclaim_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 *txp); /* * Free an object from this objset. @@ -756,6 +765,7 @@ typedef struct dmu_object_info { uint8_t doi_compress; uint8_t doi_nblkptr; uint8_t doi_pad[4]; + uint64_t doi_dnodesize; uint64_t doi_physical_blocks_512; /* data + metadata, 512b blks */ uint64_t doi_max_offset; uint64_t doi_fill_count; /* number of non-empty blocks */ @@ -797,6 +807,8 @@ void dmu_object_info_from_db(dmu_buf_t *db, dmu_object_info_t *doi); void dmu_object_size_from_db(dmu_buf_t *db, uint32_t *blksize, u_longlong_t *nblk512); +void dmu_object_dnsize_from_db(dmu_buf_t *db, int *dnsize); + typedef struct dmu_objset_stats { uint64_t dds_num_clones; /* number of clones of this */ uint64_t dds_creation_txg; @@ -854,6 +866,7 @@ extern struct dsl_dataset *dmu_objset_ds(objset_t *os); extern void dmu_objset_name(objset_t *os, char *buf); extern dmu_objset_type_t dmu_objset_type(objset_t *os); extern uint64_t dmu_objset_id(objset_t *os); +extern uint64_t dmu_objset_dnodesize(objset_t *os); extern zfs_sync_type_t dmu_objset_syncprop(objset_t *os); extern zfs_logbias_op_t dmu_objset_logbias(objset_t *os); extern int dmu_snapshot_list_next(objset_t *os, int namelen, char *name, diff --git a/include/sys/dmu_objset.h b/include/sys/dmu_objset.h index 0f03699f1..81bb89bfc 100644 --- a/include/sys/dmu_objset.h +++ b/include/sys/dmu_objset.h @@ -88,6 +88,7 @@ struct objset { list_node_t os_evicting_node; /* can change, under dsl_dir's locks: */ + uint64_t os_dnodesize; /* default dnode size for new objects */ enum zio_checksum os_checksum; enum zio_compress os_compress; uint8_t os_copies; diff --git a/include/sys/dnode.h b/include/sys/dnode.h index c5250d51a..cee4ea783 100644 --- a/include/sys/dnode.h +++ b/include/sys/dnode.h @@ -79,11 +79,18 @@ extern "C" { /* * Derived constants. */ -#define DNODE_SIZE (1 << DNODE_SHIFT) -#define DN_MAX_NBLKPTR ((DNODE_SIZE - DNODE_CORE_SIZE) >> SPA_BLKPTRSHIFT) -#define DN_MAX_BONUSLEN (DNODE_SIZE - DNODE_CORE_SIZE - (1 << SPA_BLKPTRSHIFT)) +#define DNODE_MIN_SIZE (1 << DNODE_SHIFT) +#define DNODE_MAX_SIZE (1 << DNODE_BLOCK_SHIFT) +#define DNODE_BLOCK_SIZE (1 << DNODE_BLOCK_SHIFT) +#define DNODE_MIN_SLOTS (DNODE_MIN_SIZE >> DNODE_SHIFT) +#define DNODE_MAX_SLOTS (DNODE_MAX_SIZE >> DNODE_SHIFT) +#define DN_BONUS_SIZE(dnsize) ((dnsize) - DNODE_CORE_SIZE - \ + (1 << SPA_BLKPTRSHIFT)) +#define DN_SLOTS_TO_BONUSLEN(slots) DN_BONUS_SIZE((slots) << DNODE_SHIFT) +#define DN_OLD_MAX_BONUSLEN (DN_BONUS_SIZE(DNODE_MIN_SIZE)) +#define DN_MAX_NBLKPTR ((DNODE_MIN_SIZE - DNODE_CORE_SIZE) >> SPA_BLKPTRSHIFT) #define DN_MAX_OBJECT (1ULL << DN_MAX_OBJECT_SHIFT) -#define DN_ZERO_BONUSLEN (DN_MAX_BONUSLEN + 1) +#define DN_ZERO_BONUSLEN (DN_BONUS_SIZE(DNODE_MAX_SIZE) + 1) #define DN_KILL_SPILLBLK (1) #define DNODES_PER_BLOCK_SHIFT (DNODE_BLOCK_SHIFT - DNODE_SHIFT) @@ -131,7 +138,8 @@ typedef struct dnode_phys { uint8_t dn_flags; /* DNODE_FLAG_* */ uint16_t dn_datablkszsec; /* data block size in 512b sectors */ uint16_t dn_bonuslen; /* length of dn_bonus */ - uint8_t dn_pad2[4]; + uint8_t dn_extra_slots; /* # of subsequent slots consumed */ + uint8_t dn_pad2[3]; /* accounting is protected by dn_dirty_mtx */ uint64_t dn_maxblkid; /* largest allocated block ID */ @@ -140,8 +148,11 @@ typedef struct dnode_phys { uint64_t dn_pad3[4]; /* - * The tail region is 448 bytes, and there are three ways to - * look at it. + * The tail region is 448 bytes for a 512 byte dnode, and + * correspondingly larger for larger dnode sizes. The spill + * block pointer, when present, is always at the end of the tail + * region. There are three ways this space may be used, using + * a 512 byte dnode for this diagram: * * 0 64 128 192 256 320 384 448 (offset) * +---------------+---------------+---------------+-------+ @@ -149,23 +160,27 @@ typedef struct dnode_phys { * +---------------+---------------+---------------+-------+ * | dn_blkptr[0] | dn_bonus[0..319] | * +---------------+-----------------------+---------------+ - * | dn_blkptr[0] | / | dn_spill | + * | dn_blkptr[0] | dn_bonus[0..191] | dn_spill | * +---------------+-----------------------+---------------+ */ union { - blkptr_t dn_blkptr[1+DN_MAX_BONUSLEN/sizeof (blkptr_t)]; + blkptr_t dn_blkptr[1+DN_OLD_MAX_BONUSLEN/sizeof (blkptr_t)]; struct { blkptr_t __dn_ignore1; - uint8_t dn_bonus[DN_MAX_BONUSLEN]; + uint8_t dn_bonus[DN_OLD_MAX_BONUSLEN]; }; struct { blkptr_t __dn_ignore2; - uint8_t __dn_ignore3[DN_MAX_BONUSLEN-sizeof (blkptr_t)]; + uint8_t __dn_ignore3[DN_OLD_MAX_BONUSLEN - + sizeof (blkptr_t)]; blkptr_t dn_spill; }; }; } dnode_phys_t; +#define DN_SPILL_BLKPTR(dnp) (blkptr_t *)((char *)(dnp) + \ + (((dnp)->dn_extra_slots + 1) << DNODE_SHIFT) - (1 << SPA_BLKPTRSHIFT)) + typedef struct dnode { /* * Protects the structure of the dnode, including the number of levels @@ -202,6 +217,7 @@ typedef struct dnode { uint32_t dn_datablksz; /* in bytes */ uint64_t dn_maxblkid; uint8_t dn_next_type[TXG_SIZE]; + uint8_t dn_num_slots; /* metadnode slots consumed on disk */ uint8_t dn_next_nblkptr[TXG_SIZE]; uint8_t dn_next_nlevels[TXG_SIZE]; uint8_t dn_next_indblkshift[TXG_SIZE]; @@ -299,7 +315,7 @@ void dnode_rm_spill(dnode_t *dn, dmu_tx_t *tx); int dnode_hold(struct objset *dd, uint64_t object, void *ref, dnode_t **dnp); -int dnode_hold_impl(struct objset *dd, uint64_t object, int flag, +int dnode_hold_impl(struct objset *dd, uint64_t object, int flag, int dn_slots, void *ref, dnode_t **dnp); boolean_t dnode_add_ref(dnode_t *dn, void *ref); void dnode_rele(dnode_t *dn, void *ref); @@ -307,9 +323,9 @@ void dnode_rele_and_unlock(dnode_t *dn, void *tag); void dnode_setdirty(dnode_t *dn, dmu_tx_t *tx); void dnode_sync(dnode_t *dn, dmu_tx_t *tx); void dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, - dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); + dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx); void dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, - dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); + dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx); void dnode_free(dnode_t *dn, dmu_tx_t *tx); void dnode_byteswap(dnode_phys_t *dnp); void dnode_buf_byteswap(void *buf, size_t size); diff --git a/include/sys/dsl_dataset.h b/include/sys/dsl_dataset.h index a596642e3..f3e64a772 100644 --- a/include/sys/dsl_dataset.h +++ b/include/sys/dsl_dataset.h @@ -92,6 +92,13 @@ struct dsl_pool; #define DS_FIELD_LARGE_BLOCKS "org.open-zfs:large_blocks" /* + * This field is present (with value=0) if this dataset may contain large + * dnodes (>512B). If it is present, then this dataset is counted in the + * refcount of the SPA_FEATURE_LARGE_DNODE feature. + */ +#define DS_FIELD_LARGE_DNODE "org.zfsonlinux:large_dnode" + +/* * DS_FLAG_CI_DATASET is set if the dataset contains a file system whose * name lookups should be performed case-insensitively. */ diff --git a/include/sys/fs/zfs.h b/include/sys/fs/zfs.h index 9de50e9a2..0935dca77 100644 --- a/include/sys/fs/zfs.h +++ b/include/sys/fs/zfs.h @@ -137,6 +137,7 @@ typedef enum { ZFS_PROP_DEDUP, ZFS_PROP_MLSLABEL, ZFS_PROP_SYNC, + ZFS_PROP_DNODESIZE, ZFS_PROP_REFRATIO, ZFS_PROP_WRITTEN, ZFS_PROP_CLONES, @@ -204,6 +205,7 @@ typedef enum { ZPOOL_PROP_LEAKED, ZPOOL_PROP_MAXBLOCKSIZE, ZPOOL_PROP_TNAME, + ZPOOL_PROP_MAXDNODESIZE, ZPOOL_NUM_PROPS } zpool_prop_t; @@ -362,6 +364,16 @@ typedef enum { } zfs_xattr_type_t; typedef enum { + ZFS_DNSIZE_LEGACY = 0, + ZFS_DNSIZE_AUTO = 1, + ZFS_DNSIZE_1K = 1024, + ZFS_DNSIZE_2K = 2048, + ZFS_DNSIZE_4K = 4096, + ZFS_DNSIZE_8K = 8192, + ZFS_DNSIZE_16K = 16384 +} zfs_dnsize_type_t; + +typedef enum { ZFS_REDUNDANT_METADATA_ALL, ZFS_REDUNDANT_METADATA_MOST } zfs_redundant_metadata_type_t; diff --git a/include/sys/sa_impl.h b/include/sys/sa_impl.h index 6f2f1db6d..b68b7610b 100644 --- a/include/sys/sa_impl.h +++ b/include/sys/sa_impl.h @@ -235,7 +235,7 @@ struct sa_handle { #define SA_BONUSTYPE_FROM_DB(db) \ (dmu_get_bonustype((dmu_buf_t *)db)) -#define SA_BLKPTR_SPACE (DN_MAX_BONUSLEN - sizeof (blkptr_t)) +#define SA_BLKPTR_SPACE (DN_OLD_MAX_BONUSLEN - sizeof (blkptr_t)) #define SA_LAYOUT_NUM(x, type) \ ((!IS_SA_BONUSTYPE(type) ? 0 : (((IS_SA_BONUSTYPE(type)) && \ diff --git a/include/sys/spa.h b/include/sys/spa.h index 7c09caf6c..17bf76de8 100644 --- a/include/sys/spa.h +++ b/include/sys/spa.h @@ -822,6 +822,7 @@ extern boolean_t spa_is_root(spa_t *spa); extern boolean_t spa_writeable(spa_t *spa); extern boolean_t spa_has_pending_synctask(spa_t *spa); extern int spa_maxblocksize(spa_t *spa); +extern int spa_maxdnodesize(spa_t *spa); extern void zfs_blkptr_verify(spa_t *spa, const blkptr_t *bp); extern int spa_mode(spa_t *spa); diff --git a/include/sys/zap.h b/include/sys/zap.h index ed60b86db..70cbaae97 100644 --- a/include/sys/zap.h +++ b/include/sys/zap.h @@ -129,16 +129,30 @@ typedef enum zap_flags { * MT_FIRST/MT_BEST matching will find entries that match without * regard to case (eg. looking for "foo" can find an entry "Foo"). * Eventually, other flags will permit unicode normalization as well. + * + * dnodesize specifies the on-disk size of the dnode for the new zapobj. + * Valid values are multiples of 512 up to DNODE_MAX_SIZE. */ uint64_t zap_create(objset_t *ds, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); +uint64_t zap_create_dnsize(objset_t *ds, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx); uint64_t zap_create_norm(objset_t *ds, int normflags, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); +uint64_t zap_create_norm_dnsize(objset_t *ds, int normflags, + dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, + int dnodesize, dmu_tx_t *tx); uint64_t zap_create_flags(objset_t *os, int normflags, zap_flags_t flags, dmu_object_type_t ot, int leaf_blockshift, int indirect_blockshift, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); +uint64_t zap_create_flags_dnsize(objset_t *os, int normflags, + zap_flags_t flags, dmu_object_type_t ot, int leaf_blockshift, + int indirect_blockshift, dmu_object_type_t bonustype, int bonuslen, + int dnodesize, dmu_tx_t *tx); uint64_t zap_create_link(objset_t *os, dmu_object_type_t ot, uint64_t parent_obj, const char *name, dmu_tx_t *tx); +uint64_t zap_create_link_dnsize(objset_t *os, dmu_object_type_t ot, + uint64_t parent_obj, const char *name, int dnodesize, dmu_tx_t *tx); /* * Initialize an already-allocated object. @@ -152,9 +166,14 @@ void mzap_create_impl(objset_t *os, uint64_t obj, int normflags, */ int zap_create_claim(objset_t *ds, uint64_t obj, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); +int zap_create_claim_dnsize(objset_t *ds, uint64_t obj, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx); int zap_create_claim_norm(objset_t *ds, uint64_t obj, int normflags, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx); +int zap_create_claim_norm_dnsize(objset_t *ds, uint64_t obj, + int normflags, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx); /* * The zapobj passed in must be a valid ZAP object for all of the diff --git a/include/sys/zfs_ioctl.h b/include/sys/zfs_ioctl.h index ac70f690e..301f83232 100644 --- a/include/sys/zfs_ioctl.h +++ b/include/sys/zfs_ioctl.h @@ -98,6 +98,7 @@ typedef enum drr_headertype { #define DMU_BACKUP_FEATURE_EMBED_DATA_LZ4 (1<<17) /* flag #18 is reserved for a Delphix feature */ #define DMU_BACKUP_FEATURE_LARGE_BLOCKS (1<<19) +#define DMU_BACKUP_FEATURE_LARGE_DNODE (1<<20) /* * Mask of all supported backup features @@ -105,7 +106,7 @@ typedef enum drr_headertype { #define DMU_BACKUP_FEATURE_MASK (DMU_BACKUP_FEATURE_DEDUP | \ DMU_BACKUP_FEATURE_DEDUPPROPS | DMU_BACKUP_FEATURE_SA_SPILL | \ DMU_BACKUP_FEATURE_EMBED_DATA | DMU_BACKUP_FEATURE_EMBED_DATA_LZ4 | \ - DMU_BACKUP_FEATURE_LARGE_BLOCKS) + DMU_BACKUP_FEATURE_LARGE_BLOCKS | DMU_BACKUP_FEATURE_LARGE_DNODE) /* Are all features in the given flag word currently supported? */ #define DMU_STREAM_SUPPORTED(x) (!((x) & ~DMU_BACKUP_FEATURE_MASK)) @@ -173,7 +174,8 @@ typedef struct dmu_replay_record { uint32_t drr_bonuslen; uint8_t drr_checksumtype; uint8_t drr_compress; - uint8_t drr_pad[6]; + uint8_t drr_dn_slots; + uint8_t drr_pad[5]; uint64_t drr_toguid; /* bonus content follows */ } drr_object; diff --git a/include/sys/zfs_znode.h b/include/sys/zfs_znode.h index 43b591915..2c09feee1 100644 --- a/include/sys/zfs_znode.h +++ b/include/sys/zfs_znode.h @@ -196,6 +196,7 @@ typedef struct znode { uint_t z_blksz; /* block size in bytes */ uint_t z_seq; /* modification sequence number */ uint64_t z_mapcnt; /* number of pages mapped to file */ + uint64_t z_dnodesize; /* dnode size */ uint64_t z_size; /* file size (cached) */ uint64_t z_links; /* file links (cached) */ uint64_t z_pflags; /* pflags (cached) */ diff --git a/include/sys/zil.h b/include/sys/zil.h index 65b14f1cd..1f04d1833 100644 --- a/include/sys/zil.h +++ b/include/sys/zil.h @@ -173,6 +173,19 @@ typedef enum zil_create { (txtype) == TX_WRITE2) /* + * The number of dnode slots consumed by the object is stored in the 8 + * unused upper bits of the object ID. We subtract 1 from the value + * stored on disk for compatibility with implementations that don't + * support large dnodes. The slot count for a single-slot dnode will + * contain 0 for those bits to preserve the log record format for + * "small" dnodes. + */ +#define LR_FOID_GET_SLOTS(oid) (BF64_GET((oid), 56, 8) + 1) +#define LR_FOID_SET_SLOTS(oid, x) BF64_SET((oid), 56, 8, (x) - 1) +#define LR_FOID_GET_OBJ(oid) BF64_GET((oid), 0, DN_MAX_OBJECT_SHIFT) +#define LR_FOID_SET_OBJ(oid, x) BF64_SET((oid), 0, DN_MAX_OBJECT_SHIFT, (x)) + +/* * Format of log records. * The fields are carefully defined to allow them to be aligned * and sized the same on sparc & intel architectures. diff --git a/include/zfeature_common.h b/include/zfeature_common.h index d481a28a8..41cfdf807 100644 --- a/include/zfeature_common.h +++ b/include/zfeature_common.h @@ -50,6 +50,7 @@ typedef enum spa_feature { SPA_FEATURE_BOOKMARKS, SPA_FEATURE_FS_SS_LIMIT, SPA_FEATURE_LARGE_BLOCKS, + SPA_FEATURE_LARGE_DNODE, SPA_FEATURES } spa_feature_t; diff --git a/lib/libzfs/libzfs_dataset.c b/lib/libzfs/libzfs_dataset.c index 87f79a532..07f2e75a6 100644 --- a/lib/libzfs/libzfs_dataset.c +++ b/lib/libzfs/libzfs_dataset.c @@ -1473,6 +1473,7 @@ zfs_setprop_error(libzfs_handle_t *hdl, zfs_prop_t prop, int err, case ERANGE: if (prop == ZFS_PROP_COMPRESSION || + prop == ZFS_PROP_DNODESIZE || prop == ZFS_PROP_RECORDSIZE) { (void) zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "property setting is not allowed on " diff --git a/man/man5/zpool-features.5 b/man/man5/zpool-features.5 index 6d74c9a78..fa04d6e81 100644 --- a/man/man5/zpool-features.5 +++ b/man/man5/zpool-features.5 @@ -432,5 +432,30 @@ set larger than 128KB, and will return to being \fBenabled\fR once all filesystems that have ever had their recordsize larger than 128KB are destroyed. .RE +.sp +.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 + .SH "SEE ALSO" \fBzpool\fR(8) diff --git a/man/man8/zfs.8 b/man/man8/zfs.8 index 4e3fa54a8..2aca58b76 100644 --- a/man/man8/zfs.8 +++ b/man/man8/zfs.8 @@ -910,6 +910,35 @@ The values \fBon\fR and \fBoff\fR are equivalent to the \fBdev\fR and \fBnodev\f .sp .ne 2 .na +\fB\fBdnodesize\fR=\fBlegacy\fR | \fBauto\fR | \fB1k\fR | \fB2k\fR | \fB4k\fR | \fB8k\fR | \fB16k\fR\fR +.ad +.sp .6 +.RS 4n +Specifies a compatibility mode or literal value for the size of dnodes +in the file system. The default value is \fBlegacy\fR. Setting this +property to a value other than \fBlegacy\fR requires the +\fBlarge_dnode\fR pool feature to be enabled. +.sp +Consider setting \fBdnodesize\fR to \fBauto\fR if the dataset uses the +\fBxattr=sa\fR property setting and the workload makes heavy use of +extended attributes. This may be applicable to SELinux-enabled systems, +Lustre servers, and Samba servers, for example. Literal values are +supported for cases where the optimal size is known in advance and for +performance testing. +.sp +Leave \fBdnodesize\fR set to \fBlegacy\fR if you need to receive +a \fBzfs send\fR stream of this dataset on a pool that doesn't enable +the \fBlarge_dnode\fR feature, or if you need to import this pool on a +system that doesn't support the \fBlarge_dnode\fR feature. +.sp +This property can also be referred to by its shortened column name, +\fBdnsize\fR. +.RE + +.sp +.ne 2 +.mk +.na \fB\fBexec\fR=\fBon\fR | \fBoff\fR\fR .ad .sp .6 diff --git a/module/zcommon/zfs_prop.c b/module/zcommon/zfs_prop.c index 76d564b43..1dbeab084 100644 --- a/module/zcommon/zfs_prop.c +++ b/module/zcommon/zfs_prop.c @@ -211,6 +211,17 @@ 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 }, @@ -271,6 +282,9 @@ zfs_prop_init(void) zprop_register_index(ZFS_PROP_XATTR, "xattr", ZFS_XATTR_DIR, PROP_INHERIT, ZFS_TYPE_FILESYSTEM | ZFS_TYPE_SNAPSHOT, "on | off | dir | sa", "XATTR", xattr_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, diff --git a/module/zcommon/zpool_prop.c b/module/zcommon/zpool_prop.c index 910c56dcc..4a5836e5b 100644 --- a/module/zcommon/zpool_prop.c +++ b/module/zcommon/zpool_prop.c @@ -135,6 +135,8 @@ 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"); } /* diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c index 126748994..4bbbd0525 100644 --- a/module/zfs/dbuf.c +++ b/module/zfs/dbuf.c @@ -478,7 +478,6 @@ 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); @@ -730,13 +729,18 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags) 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_OTHER); - 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_OTHER); + 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); @@ -962,9 +966,11 @@ 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_OTHER); - 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_OTHER); + bcopy(db->db.db_data, dr->dt.dl.dr_data, bonuslen); } else if (refcount_count(&db->db_holds) > db->db_dirtycnt) { int size = db->db.db_size; arc_buf_contents_t type = DBUF_GET_BUFC_TYPE(db); @@ -1858,8 +1864,10 @@ dbuf_clear(dmu_buf_impl_t *db) if (db->db_state == DB_CACHED) { ASSERT(db->db.db_data != NULL); if (db->db_blkid == DMU_BONUS_BLKID) { - zio_buf_free(db->db.db_data, DN_MAX_BONUSLEN); - arc_space_return(DN_MAX_BONUSLEN, ARC_SPACE_OTHER); + int slots = DB_DNODE(db)->dn_num_slots; + int bonuslen = DN_SLOTS_TO_BONUSLEN(slots); + zio_buf_free(db->db.db_data, bonuslen); + arc_space_return(bonuslen, ARC_SPACE_OTHER); } db->db.db_data = NULL; db->db_state = DB_UNCACHED; @@ -1929,7 +1937,7 @@ dbuf_findbp(dnode_t *dn, int level, uint64_t blkid, int fail_sparse, 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); @@ -2018,7 +2026,7 @@ 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; @@ -2810,7 +2818,7 @@ 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; } @@ -2950,13 +2958,16 @@ 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); + ASSERT3U(dn->dn_phys->dn_bonuslen, <=, + DN_SLOTS_TO_BONUSLEN(dn->dn_phys->dn_extra_slots + 1)); bcopy(*datap, DN_BONUS(dn->dn_phys), dn->dn_phys->dn_bonuslen); 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_OTHER); + 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_OTHER); } db->db_data_pending = NULL; drp = &db->db_last_dirty; @@ -3107,7 +3118,7 @@ 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 @@ -3119,11 +3130,16 @@ 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)) { @@ -3270,7 +3286,7 @@ 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 diff --git a/module/zfs/dmu.c b/module/zfs/dmu.c index a423264c6..e1dfb41ff 100644 --- a/module/zfs/dmu.c +++ b/module/zfs/dmu.c @@ -180,7 +180,7 @@ dmu_buf_hold(objset_t *os, uint64_t object, uint64_t offset, int dmu_bonus_max(void) { - return (DN_MAX_BONUSLEN); + return (DN_OLD_MAX_BONUSLEN); } int @@ -1853,6 +1853,7 @@ __dmu_object_info_from_dnode(dnode_t *dn, dmu_object_info_t *doi) 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; @@ -1924,9 +1925,21 @@ dmu_object_size_from_db(dmu_buf_t *db_fake, uint32_t *blksize, 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); } @@ -2020,6 +2033,7 @@ EXPORT_SYMBOL(dmu_object_info); EXPORT_SYMBOL(dmu_object_info_from_dnode); EXPORT_SYMBOL(dmu_object_info_from_db); EXPORT_SYMBOL(dmu_object_size_from_db); +EXPORT_SYMBOL(dmu_object_dnsize_from_db); EXPORT_SYMBOL(dmu_object_set_blocksize); EXPORT_SYMBOL(dmu_object_set_checksum); EXPORT_SYMBOL(dmu_object_set_compress); diff --git a/module/zfs/dmu_object.c b/module/zfs/dmu_object.c index a5a53418b..e54043fc3 100644 --- a/module/zfs/dmu_object.c +++ b/module/zfs/dmu_object.c @@ -30,28 +30,55 @@ #include <sys/dnode.h> #include <sys/zap.h> #include <sys/zfeature.h> +#include <sys/dsl_dataset.h> 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_dnsize(os, ot, blocksize, 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) +{ 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 @@ -59,9 +86,10 @@ dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize, * 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; @@ -69,13 +97,15 @@ dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize, } 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 @@ -83,16 +113,22 @@ dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize, * 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, 0, bonustype, bonuslen, tx); + dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, dn_slots, tx); dnode_rele(dn, FTAG); mutex_exit(&os->os_obj_lock); @@ -105,16 +141,33 @@ 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); + if (object == DMU_META_DNODE_OBJECT && !dmu_tx_private_ok(tx)) return (SET_ERROR(EBADF)); - err = dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, FTAG, &dn); + err = dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, dn_slots, + FTAG, &dn); if (err) return (err); - dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, tx); + + dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, dn_slots, tx); dnode_rele(dn, FTAG); dmu_tx_add_new_object(tx, os, object); @@ -125,23 +178,34 @@ int dmu_object_reclaim(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_reclaim_dnsize(os, object, ot, blocksize, bonustype, + bonuslen, 0, tx)); +} + +int +dmu_object_reclaim_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 (object == DMU_META_DNODE_OBJECT) return (SET_ERROR(EBADF)); - err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, + err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, 0, FTAG, &dn); if (err) return (err); - dnode_reallocate(dn, ot, blocksize, bonustype, bonuslen, tx); + dnode_reallocate(dn, ot, blocksize, bonustype, bonuslen, dn_slots, tx); dnode_rele(dn, FTAG); return (err); } + int dmu_object_free(objset_t *os, uint64_t object, dmu_tx_t *tx) { @@ -150,7 +214,7 @@ dmu_object_free(objset_t *os, uint64_t object, dmu_tx_t *tx) ASSERT(object != DMU_META_DNODE_OBJECT || dmu_tx_private_ok(tx)); - err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, + err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, 0, FTAG, &dn); if (err) return (err); @@ -171,9 +235,30 @@ dmu_object_free(objset_t *os, uint64_t object, dmu_tx_t *tx) int dmu_object_next(objset_t *os, uint64_t *objectp, boolean_t hole, uint64_t txg) { - uint64_t offset = (*objectp + 1) << DNODE_SHIFT; + uint64_t offset; + dmu_object_info_t doi; + struct dsl_dataset *ds = os->os_dsl_dataset; + int dnodesize; int error; + /* + * Avoid expensive dnode hold if this dataset doesn't use large dnodes. + */ + if (ds && ds->ds_feature_inuse[SPA_FEATURE_LARGE_DNODE]) { + error = dmu_object_info(os, *objectp, &doi); + if (error && !(error == EINVAL && *objectp == 0)) + return (SET_ERROR(error)); + else + dnodesize = doi.doi_dnodesize; + } else { + dnodesize = DNODE_MIN_SIZE; + } + + if (*objectp == 0) + offset = 1 << DNODE_SHIFT; + else + offset = (*objectp << DNODE_SHIFT) + dnodesize; + error = dnode_next_offset(DMU_META_DNODE(os), (hole ? DNODE_FIND_HOLE : 0), &offset, 0, DNODES_PER_BLOCK, txg); @@ -235,8 +320,11 @@ dmu_object_free_zapified(objset_t *mos, uint64_t object, dmu_tx_t *tx) #if defined(_KERNEL) && defined(HAVE_SPL) EXPORT_SYMBOL(dmu_object_alloc); +EXPORT_SYMBOL(dmu_object_alloc_dnsize); EXPORT_SYMBOL(dmu_object_claim); +EXPORT_SYMBOL(dmu_object_claim_dnsize); EXPORT_SYMBOL(dmu_object_reclaim); +EXPORT_SYMBOL(dmu_object_reclaim_dnsize); EXPORT_SYMBOL(dmu_object_free); EXPORT_SYMBOL(dmu_object_next); EXPORT_SYMBOL(dmu_object_zapify); diff --git a/module/zfs/dmu_objset.c b/module/zfs/dmu_objset.c index 03b30dd3b..cdc897726 100644 --- a/module/zfs/dmu_objset.c +++ b/module/zfs/dmu_objset.c @@ -138,6 +138,12 @@ dmu_objset_id(objset_t *os) return (ds ? ds->ds_object : 0); } +uint64_t +dmu_objset_dnodesize(objset_t *os) +{ + return (os->os_dnodesize); +} + zfs_sync_type_t dmu_objset_syncprop(objset_t *os) { @@ -268,6 +274,34 @@ redundant_metadata_changed_cb(void *arg, uint64_t newval) } static void +dnodesize_changed_cb(void *arg, uint64_t newval) +{ + objset_t *os = arg; + + switch (newval) { + case ZFS_DNSIZE_LEGACY: + os->os_dnodesize = DNODE_MIN_SIZE; + break; + case ZFS_DNSIZE_AUTO: + /* + * Choose a dnode size that will work well for most + * workloads if the user specified "auto". Future code + * improvements could dynamically select a dnode size + * based on observed workload patterns. + */ + os->os_dnodesize = DNODE_MIN_SIZE * 2; + break; + case ZFS_DNSIZE_1K: + case ZFS_DNSIZE_2K: + case ZFS_DNSIZE_4K: + case ZFS_DNSIZE_8K: + case ZFS_DNSIZE_16K: + os->os_dnodesize = newval; + break; + } +} + +static void logbias_changed_cb(void *arg, uint64_t newval) { objset_t *os = arg; @@ -421,6 +455,11 @@ dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp, zfs_prop_to_name(ZFS_PROP_RECORDSIZE), recordsize_changed_cb, os); } + if (err == 0) { + err = dsl_prop_register(ds, + zfs_prop_to_name(ZFS_PROP_DNODESIZE), + dnodesize_changed_cb, os); + } } if (err != 0) { VERIFY(arc_buf_remove_ref(os->os_phys_buf, @@ -439,6 +478,7 @@ dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp, os->os_sync = ZFS_SYNC_STANDARD; os->os_primary_cache = ZFS_CACHE_ALL; os->os_secondary_cache = ZFS_CACHE_ALL; + os->os_dnodesize = DNODE_MIN_SIZE; } if (ds == NULL || !ds->ds_is_snapshot) @@ -768,8 +808,8 @@ dmu_objset_create_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp, mdn = DMU_META_DNODE(os); - dnode_allocate(mdn, DMU_OT_DNODE, 1 << DNODE_BLOCK_SHIFT, - DN_MAX_INDBLKSHIFT, DMU_OT_NONE, 0, tx); + dnode_allocate(mdn, DMU_OT_DNODE, DNODE_BLOCK_SIZE, DN_MAX_INDBLKSHIFT, + DMU_OT_NONE, 0, DNODE_MIN_SLOTS, tx); /* * We don't want to have to increase the meta-dnode's nlevels @@ -1202,7 +1242,7 @@ do_userquota_update(objset_t *os, uint64_t used, uint64_t flags, uint64_t user, uint64_t group, boolean_t subtract, dmu_tx_t *tx) { if ((flags & DNODE_FLAG_USERUSED_ACCOUNTED)) { - int64_t delta = DNODE_SIZE + used; + int64_t delta = DNODE_MIN_SIZE + used; if (subtract) delta = -delta; VERIFY3U(0, ==, zap_increment_int(os, DMU_USERUSED_OBJECT, @@ -2023,6 +2063,7 @@ EXPORT_SYMBOL(dmu_objset_find); EXPORT_SYMBOL(dmu_objset_byteswap); EXPORT_SYMBOL(dmu_objset_evict_dbufs); EXPORT_SYMBOL(dmu_objset_snap_cmtime); +EXPORT_SYMBOL(dmu_objset_dnodesize); EXPORT_SYMBOL(dmu_objset_sync); EXPORT_SYMBOL(dmu_objset_is_dirty); diff --git a/module/zfs/dmu_send.c b/module/zfs/dmu_send.c index 896a84b50..901386a5a 100644 --- a/module/zfs/dmu_send.c +++ b/module/zfs/dmu_send.c @@ -445,6 +445,7 @@ dump_dnode(dmu_sendarg_t *dsp, uint64_t object, dnode_phys_t *dnp) drro->drr_bonustype = dnp->dn_bonustype; drro->drr_blksz = dnp->dn_datablkszsec << SPA_MINBLOCKSHIFT; drro->drr_bonuslen = dnp->dn_bonuslen; + drro->drr_dn_slots = dnp->dn_extra_slots + 1; drro->drr_checksumtype = dnp->dn_checksum; drro->drr_compress = dnp->dn_compress; drro->drr_toguid = dsp->dsa_toguid; @@ -570,7 +571,6 @@ do_dump(dmu_sendarg_t *dsa, struct send_block_record *data) spa_t *spa = ds->ds_dir->dd_pool->dp_spa; dmu_object_type_t type = bp ? BP_GET_TYPE(bp) : DMU_OT_NONE; int err = 0; - dnode_phys_t *blk; uint64_t dnobj; ASSERT3U(zb->zb_level, >=, 0); @@ -590,7 +590,8 @@ do_dump(dmu_sendarg_t *dsa, struct send_block_record *data) } else if (zb->zb_level > 0 || type == DMU_OT_OBJSET) { return (0); } else if (type == DMU_OT_DNODE) { - int blksz = BP_GET_LSIZE(bp); + dnode_phys_t *blk; + int epb = BP_GET_LSIZE(bp) >> DNODE_SHIFT; arc_flags_t aflags = ARC_FLAG_WAIT; arc_buf_t *abuf; int i; @@ -603,8 +604,8 @@ do_dump(dmu_sendarg_t *dsa, struct send_block_record *data) return (SET_ERROR(EIO)); blk = abuf->b_data; - dnobj = zb->zb_blkid * (blksz >> DNODE_SHIFT); - for (i = 0; i < blksz >> DNODE_SHIFT; i++) { + dnobj = zb->zb_blkid * epb; + for (i = 0; i < epb; i += blk[i].dn_extra_slots + 1) { err = dump_dnode(dsa, dnobj + i, blk + i); if (err != 0) break; @@ -736,6 +737,8 @@ dmu_send_impl(void *tag, dsl_pool_t *dp, dsl_dataset_t *to_ds, if (large_block_ok && to_ds->ds_feature_inuse[SPA_FEATURE_LARGE_BLOCKS]) featureflags |= DMU_BACKUP_FEATURE_LARGE_BLOCKS; + if (to_ds->ds_feature_inuse[SPA_FEATURE_LARGE_DNODE]) + featureflags |= DMU_BACKUP_FEATURE_LARGE_DNODE; if (embedok && spa_feature_is_active(dp->dp_spa, SPA_FEATURE_EMBEDDED_DATA)) { featureflags |= DMU_BACKUP_FEATURE_EMBED_DATA; @@ -1252,6 +1255,15 @@ dmu_recv_begin_check(void *arg, dmu_tx_t *tx) !spa_feature_is_enabled(dp->dp_spa, SPA_FEATURE_LARGE_BLOCKS)) return (SET_ERROR(ENOTSUP)); + /* + * The receiving code doesn't know how to translate large dnodes + * to smaller ones, so the pool must have the LARGE_DNODE + * feature enabled if the stream has LARGE_DNODE. + */ + if ((featureflags & DMU_BACKUP_FEATURE_LARGE_DNODE) && + !spa_feature_is_enabled(dp->dp_spa, SPA_FEATURE_LARGE_DNODE)) + return (SET_ERROR(ENOTSUP)); + error = dsl_dataset_hold(dp, tofs, FTAG, &ds); if (error == 0) { /* target fs already exists; recv into temp clone */ @@ -1658,7 +1670,8 @@ deduce_nblkptr(dmu_object_type_t bonus_type, uint64_t bonus_size) return (1); } else { return (1 + - ((DN_MAX_BONUSLEN - bonus_size) >> SPA_BLKPTRSHIFT)); + ((DN_OLD_MAX_BONUSLEN - + MIN(DN_OLD_MAX_BONUSLEN, bonus_size)) >> SPA_BLKPTRSHIFT)); } } @@ -1679,7 +1692,8 @@ receive_object(struct receive_writer_arg *rwa, struct drr_object *drro, P2PHASE(drro->drr_blksz, SPA_MINBLOCKSIZE) || drro->drr_blksz < SPA_MINBLOCKSIZE || drro->drr_blksz > spa_maxblocksize(dmu_objset_spa(rwa->os)) || - drro->drr_bonuslen > DN_MAX_BONUSLEN) { + drro->drr_bonuslen > + DN_BONUS_SIZE(spa_maxdnodesize(dmu_objset_spa(rwa->os)))) { return (SET_ERROR(EINVAL)); } @@ -1719,9 +1733,10 @@ receive_object(struct receive_writer_arg *rwa, struct drr_object *drro, if (object == DMU_NEW_OBJECT) { /* currently free, want to be allocated */ - err = dmu_object_claim(rwa->os, drro->drr_object, + err = dmu_object_claim_dnsize(rwa->os, drro->drr_object, drro->drr_type, drro->drr_blksz, - drro->drr_bonustype, drro->drr_bonuslen, tx); + drro->drr_bonustype, drro->drr_bonuslen, + drro->drr_dn_slots << DNODE_SHIFT, tx); } else if (drro->drr_type != doi.doi_type || drro->drr_blksz != doi.doi_data_block_size || drro->drr_bonustype != doi.doi_bonus_type || @@ -1771,18 +1786,25 @@ receive_freeobjects(struct receive_writer_arg *rwa, if (drrfo->drr_firstobj + drrfo->drr_numobjs < drrfo->drr_firstobj) return (SET_ERROR(EINVAL)); - for (obj = drrfo->drr_firstobj; + for (obj = drrfo->drr_firstobj == 0 ? 1 : drrfo->drr_firstobj; obj < drrfo->drr_firstobj + drrfo->drr_numobjs; (void) dmu_object_next(rwa->os, &obj, FALSE, 0)) { + dmu_object_info_t doi; int err; - if (dmu_object_info(rwa->os, obj, NULL) != 0) + err = dmu_object_info(rwa->os, obj, &doi); + if (err == ENOENT) { + obj++; continue; + } else if (err != 0) { + return (err); + } err = dmu_free_long_object(rwa->os, obj); if (err != 0) return (err); } + return (0); } diff --git a/module/zfs/dmu_traverse.c b/module/zfs/dmu_traverse.c index bba9efe14..44ba74181 100644 --- a/module/zfs/dmu_traverse.c +++ b/module/zfs/dmu_traverse.c @@ -331,13 +331,13 @@ traverse_visitbp(traverse_data_t *td, const dnode_phys_t *dnp, goto post; cdnp = buf->b_data; - for (i = 0; i < epb; i++) { + for (i = 0; i < epb; i += cdnp[i].dn_extra_slots + 1) { prefetch_dnode_metadata(td, &cdnp[i], zb->zb_objset, zb->zb_blkid * epb + i); } /* recursively visitbp() blocks below this */ - for (i = 0; i < epb; i++) { + for (i = 0; i < epb; i += cdnp[i].dn_extra_slots + 1) { err = traverse_dnode(td, &cdnp[i], zb->zb_objset, zb->zb_blkid * epb + i); if (err != 0) @@ -439,7 +439,7 @@ prefetch_dnode_metadata(traverse_data_t *td, const dnode_phys_t *dnp, if (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR) { SET_BOOKMARK(&czb, objset, object, 0, DMU_SPILL_BLKID); - traverse_prefetch_metadata(td, &dnp->dn_spill, &czb); + traverse_prefetch_metadata(td, DN_SPILL_BLKPTR(dnp), &czb); } } @@ -470,7 +470,7 @@ traverse_dnode(traverse_data_t *td, const dnode_phys_t *dnp, if (err == 0 && (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR)) { SET_BOOKMARK(&czb, objset, object, 0, DMU_SPILL_BLKID); - err = traverse_visitbp(td, dnp, &dnp->dn_spill, &czb); + err = traverse_visitbp(td, dnp, DN_SPILL_BLKPTR(dnp), &czb); } if (err == 0 && (td->td_flags & TRAVERSE_POST)) { diff --git a/module/zfs/dmu_tx.c b/module/zfs/dmu_tx.c index 74e323dbd..ed29bfbc6 100644 --- a/module/zfs/dmu_tx.c +++ b/module/zfs/dmu_tx.c @@ -1586,7 +1586,7 @@ dmu_tx_hold_spill(dmu_tx_t *tx, uint64_t object) } else { blkptr_t *bp; - bp = &dn->dn_phys->dn_spill; + bp = DN_SPILL_BLKPTR(dn->dn_phys); if (dsl_dataset_block_freeable(dn->dn_objset->os_dsl_dataset, bp, bp->blk_birth)) txh->txh_space_tooverwrite += SPA_OLD_MAXBLOCKSIZE; @@ -1618,7 +1618,7 @@ dmu_tx_hold_sa_create(dmu_tx_t *tx, int attrsize) dmu_tx_sa_registration_hold(sa, tx); - if (attrsize <= DN_MAX_BONUSLEN && !sa->sa_force_spill) + if (attrsize <= DN_OLD_MAX_BONUSLEN && !sa->sa_force_spill) return; (void) dmu_tx_hold_object_impl(tx, tx->tx_objset, DMU_NEW_OBJECT, diff --git a/module/zfs/dnode.c b/module/zfs/dnode.c index 38bcecd46..975bd5fb8 100644 --- a/module/zfs/dnode.c +++ b/module/zfs/dnode.c @@ -248,6 +248,7 @@ dnode_verify(dnode_t *dn) } if (dn->dn_phys->dn_type != DMU_OT_NONE || dn->dn_allocated_txg != 0) { int i; + int max_bonuslen = DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots); ASSERT3U(dn->dn_indblkshift, <=, SPA_MAXBLOCKSHIFT); if (dn->dn_datablkshift) { ASSERT3U(dn->dn_datablkshift, >=, SPA_MINBLOCKSHIFT); @@ -258,12 +259,12 @@ dnode_verify(dnode_t *dn) ASSERT(DMU_OT_IS_VALID(dn->dn_type)); ASSERT3U(dn->dn_nblkptr, >=, 1); ASSERT3U(dn->dn_nblkptr, <=, DN_MAX_NBLKPTR); - ASSERT3U(dn->dn_bonuslen, <=, DN_MAX_BONUSLEN); + ASSERT3U(dn->dn_bonuslen, <=, max_bonuslen); ASSERT3U(dn->dn_datablksz, ==, dn->dn_datablkszsec << SPA_MINBLOCKSHIFT); ASSERT3U(ISP2(dn->dn_datablksz), ==, dn->dn_datablkshift != 0); ASSERT3U((dn->dn_nblkptr - 1) * sizeof (blkptr_t) + - dn->dn_bonuslen, <=, DN_MAX_BONUSLEN); + dn->dn_bonuslen, <=, max_bonuslen); for (i = 0; i < TXG_SIZE; i++) { ASSERT3U(dn->dn_next_nlevels[i], <=, dn->dn_nlevels); } @@ -294,6 +295,7 @@ dnode_byteswap(dnode_phys_t *dnp) dnp->dn_datablkszsec = BSWAP_16(dnp->dn_datablkszsec); dnp->dn_bonuslen = BSWAP_16(dnp->dn_bonuslen); + dnp->dn_extra_slots = BSWAP_8(dnp->dn_extra_slots); dnp->dn_maxblkid = BSWAP_64(dnp->dn_maxblkid); dnp->dn_used = BSWAP_64(dnp->dn_used); @@ -320,7 +322,8 @@ dnode_byteswap(dnode_phys_t *dnp) * dnode buffer). */ int off = (dnp->dn_nblkptr-1) * sizeof (blkptr_t); - size_t len = DN_MAX_BONUSLEN - off; + int slots = dnp->dn_extra_slots + 1; + size_t len = DN_SLOTS_TO_BONUSLEN(slots) - off; dmu_object_byteswap_t byteswap; ASSERT(DMU_OT_IS_VALID(dnp->dn_bonustype)); byteswap = DMU_OT_BYTESWAP(dnp->dn_bonustype); @@ -329,23 +332,24 @@ dnode_byteswap(dnode_phys_t *dnp) /* Swap SPILL block if we have one */ if (dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR) - byteswap_uint64_array(&dnp->dn_spill, sizeof (blkptr_t)); - + byteswap_uint64_array(DN_SPILL_BLKPTR(dnp), sizeof (blkptr_t)); } void dnode_buf_byteswap(void *vbuf, size_t size) { - dnode_phys_t *buf = vbuf; - int i; + int i = 0; ASSERT3U(sizeof (dnode_phys_t), ==, (1<<DNODE_SHIFT)); ASSERT((size & (sizeof (dnode_phys_t)-1)) == 0); - size >>= DNODE_SHIFT; - for (i = 0; i < size; i++) { - dnode_byteswap(buf); - buf++; + while (i < size) { + dnode_phys_t *dnp = vbuf + i; + dnode_byteswap(dnp); + + i += DNODE_MIN_SIZE; + if (dnp->dn_type != DMU_OT_NONE) + i += dnp->dn_extra_slots * DNODE_MIN_SIZE; } } @@ -356,7 +360,7 @@ dnode_setbonuslen(dnode_t *dn, int newsize, dmu_tx_t *tx) dnode_setdirty(dn, tx); rw_enter(&dn->dn_struct_rwlock, RW_WRITER); - ASSERT3U(newsize, <=, DN_MAX_BONUSLEN - + ASSERT3U(newsize, <=, DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots) - (dn->dn_nblkptr-1) * sizeof (blkptr_t)); dn->dn_bonuslen = newsize; if (newsize == 0) @@ -434,6 +438,7 @@ dnode_create(objset_t *os, dnode_phys_t *dnp, dmu_buf_impl_t *db, dn->dn_compress = dnp->dn_compress; dn->dn_bonustype = dnp->dn_bonustype; dn->dn_bonuslen = dnp->dn_bonuslen; + dn->dn_num_slots = dnp->dn_extra_slots + 1; dn->dn_maxblkid = dnp->dn_maxblkid; dn->dn_have_spill = ((dnp->dn_flags & DNODE_FLAG_SPILL_BLKPTR) != 0); dn->dn_id_flags = 0; @@ -534,10 +539,13 @@ dnode_destroy(dnode_t *dn) void dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, - dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) + dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx) { int i; + ASSERT3U(dn_slots, >, 0); + ASSERT3U(dn_slots << DNODE_SHIFT, <=, + spa_maxdnodesize(dmu_objset_spa(dn->dn_objset))); ASSERT3U(blocksize, <=, spa_maxblocksize(dmu_objset_spa(dn->dn_objset))); if (blocksize == 0) @@ -550,8 +558,8 @@ dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, ibs = MIN(MAX(ibs, DN_MIN_INDBLKSHIFT), DN_MAX_INDBLKSHIFT); - dprintf("os=%p obj=%llu txg=%llu blocksize=%d ibs=%d\n", dn->dn_objset, - dn->dn_object, tx->tx_txg, blocksize, ibs); + dprintf("os=%p obj=%llu txg=%llu blocksize=%d ibs=%d dn_slots=%d\n", + dn->dn_objset, dn->dn_object, tx->tx_txg, blocksize, ibs, dn_slots); ASSERT(dn->dn_type == DMU_OT_NONE); ASSERT(bcmp(dn->dn_phys, &dnode_phys_zero, sizeof (dnode_phys_t)) == 0); @@ -562,7 +570,7 @@ dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, (bonustype == DMU_OT_SA && bonuslen == 0) || (bonustype != DMU_OT_NONE && bonuslen != 0)); ASSERT(DMU_OT_IS_VALID(bonustype)); - ASSERT3U(bonuslen, <=, DN_MAX_BONUSLEN); + ASSERT3U(bonuslen, <=, DN_SLOTS_TO_BONUSLEN(dn_slots)); ASSERT(dn->dn_type == DMU_OT_NONE); ASSERT0(dn->dn_maxblkid); ASSERT0(dn->dn_allocated_txg); @@ -588,11 +596,15 @@ dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, dnode_setdblksz(dn, blocksize); dn->dn_indblkshift = ibs; dn->dn_nlevels = 1; + dn->dn_num_slots = dn_slots; if (bonustype == DMU_OT_SA) /* Maximize bonus space for SA */ dn->dn_nblkptr = 1; - else - dn->dn_nblkptr = 1 + - ((DN_MAX_BONUSLEN - bonuslen) >> SPA_BLKPTRSHIFT); + else { + dn->dn_nblkptr = MIN(DN_MAX_NBLKPTR, + 1 + ((DN_SLOTS_TO_BONUSLEN(dn_slots) - bonuslen) >> + SPA_BLKPTRSHIFT)); + } + dn->dn_bonustype = bonustype; dn->dn_bonuslen = bonuslen; dn->dn_checksum = ZIO_CHECKSUM_INHERIT; @@ -617,7 +629,7 @@ dnode_allocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, int ibs, void dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, - dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) + dmu_object_type_t bonustype, int bonuslen, int dn_slots, dmu_tx_t *tx) { int nblkptr; @@ -631,7 +643,10 @@ dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, (bonustype != DMU_OT_NONE && bonuslen != 0) || (bonustype == DMU_OT_SA && bonuslen == 0)); ASSERT(DMU_OT_IS_VALID(bonustype)); - ASSERT3U(bonuslen, <=, DN_MAX_BONUSLEN); + ASSERT3U(bonuslen, <=, + DN_BONUS_SIZE(spa_maxdnodesize(dmu_objset_spa(dn->dn_objset)))); + + dn_slots = dn_slots > 0 ? dn_slots : DNODE_MIN_SLOTS; /* clean up any unreferenced dbufs */ dnode_evict_dbufs(dn); @@ -654,7 +669,9 @@ dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, if (bonustype == DMU_OT_SA) /* Maximize bonus space for SA */ nblkptr = 1; else - nblkptr = 1 + ((DN_MAX_BONUSLEN - bonuslen) >> SPA_BLKPTRSHIFT); + nblkptr = MIN(DN_MAX_NBLKPTR, + 1 + ((DN_SLOTS_TO_BONUSLEN(dn_slots) - bonuslen) >> + SPA_BLKPTRSHIFT)); if (dn->dn_bonustype != bonustype) dn->dn_next_bonustype[tx->tx_txg&TXG_MASK] = bonustype; if (dn->dn_nblkptr != nblkptr) @@ -672,6 +689,7 @@ dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, mutex_enter(&dn->dn_mtx); dn->dn_bonustype = bonustype; dn->dn_bonuslen = bonuslen; + dn->dn_num_slots = dn_slots; dn->dn_nblkptr = nblkptr; dn->dn_checksum = ZIO_CHECKSUM_INHERIT; dn->dn_compress = ZIO_COMPRESS_INHERIT; @@ -680,7 +698,8 @@ dnode_reallocate(dnode_t *dn, dmu_object_type_t ot, int blocksize, /* fix up the bonus db_size */ if (dn->dn_bonus) { dn->dn_bonus->db.db_size = - DN_MAX_BONUSLEN - (dn->dn_nblkptr-1) * sizeof (blkptr_t); + DN_SLOTS_TO_BONUSLEN(dn->dn_num_slots) - + (dn->dn_nblkptr-1) * sizeof (blkptr_t); ASSERT(dn->dn_bonuslen <= dn->dn_bonus->db.db_size); } @@ -1053,24 +1072,150 @@ dnode_buf_pageout(void *dbu) } /* + * Return true if the given index is interior to a dnode already + * allocated in the block. That is, the index is neither free nor + * allocated, but is consumed by a large dnode. + * + * The dnode_phys_t buffer may not be in sync with the in-core dnode + * structure, so we try to check the dnode structure first and fall back + * to the dnode_phys_t buffer it doesn't exist. + */ +static boolean_t +dnode_is_consumed(dmu_buf_impl_t *db, int idx) +{ + dnode_handle_t *dnh; + dmu_object_type_t ot; + dnode_children_t *children_dnodes; + dnode_phys_t *dn_block; + int skip; + int i; + + children_dnodes = dmu_buf_get_user(&db->db); + dn_block = (dnode_phys_t *)db->db.db_data; + + for (i = 0; i < idx; i += skip) { + dnh = &children_dnodes->dnc_children[i]; + + zrl_add(&dnh->dnh_zrlock); + if (dnh->dnh_dnode != NULL) { + ot = dnh->dnh_dnode->dn_type; + skip = dnh->dnh_dnode->dn_num_slots; + } else { + ot = dn_block[i].dn_type; + skip = dn_block[i].dn_extra_slots + 1; + } + zrl_remove(&dnh->dnh_zrlock); + + if (ot == DMU_OT_NONE) + skip = 1; + } + + return (i > idx); +} + +/* + * Return true if the given index in the dnode block is a valid + * allocated dnode. That is, the index is not consumed by a large + * dnode and is not free. + * + * The dnode_phys_t buffer may not be in sync with the in-core dnode + * structure, so we try to check the dnode structure first and fall back + * to the dnode_phys_t buffer it doesn't exist. + */ +static boolean_t +dnode_is_allocated(dmu_buf_impl_t *db, int idx) +{ + dnode_handle_t *dnh; + dmu_object_type_t ot; + dnode_children_t *children_dnodes; + dnode_phys_t *dn_block; + + if (dnode_is_consumed(db, idx)) + return (B_FALSE); + + children_dnodes = dmu_buf_get_user(&db->db); + dn_block = (dnode_phys_t *)db->db.db_data; + + dnh = &children_dnodes->dnc_children[idx]; + + zrl_add(&dnh->dnh_zrlock); + if (dnh->dnh_dnode != NULL) + ot = dnh->dnh_dnode->dn_type; + else + ot = dn_block[idx].dn_type; + zrl_remove(&dnh->dnh_zrlock); + + return (ot != DMU_OT_NONE); +} + +/* + * Return true if the given range of indices in the dnode block are + * free. That is, the starting index is not consumed by a large dnode + * and none of the indices are allocated. + * + * The dnode_phys_t buffer may not be in sync with the in-core dnode + * structure, so we try to check the dnode structure first and fall back + * to the dnode_phys_t buffer it doesn't exist. + */ +static boolean_t +dnode_is_free(dmu_buf_impl_t *db, int idx, int slots) +{ + dnode_handle_t *dnh; + dmu_object_type_t ot; + dnode_children_t *children_dnodes; + dnode_phys_t *dn_block; + int i; + + if (idx + slots > DNODES_PER_BLOCK) + return (B_FALSE); + + children_dnodes = dmu_buf_get_user(&db->db); + dn_block = (dnode_phys_t *)db->db.db_data; + + if (dnode_is_consumed(db, idx)) + return (B_FALSE); + + for (i = idx; i < idx + slots; i++) { + dnh = &children_dnodes->dnc_children[i]; + + zrl_add(&dnh->dnh_zrlock); + if (dnh->dnh_dnode != NULL) + ot = dnh->dnh_dnode->dn_type; + else + ot = dn_block[i].dn_type; + zrl_remove(&dnh->dnh_zrlock); + + if (ot != DMU_OT_NONE) + return (B_FALSE); + } + + return (B_TRUE); +} + +/* * errors: * EINVAL - invalid object number. + * ENOSPC - hole too small to fulfill "slots" request * EIO - i/o error. * succeeds even for free dnodes. */ int -dnode_hold_impl(objset_t *os, uint64_t object, int flag, +dnode_hold_impl(objset_t *os, uint64_t object, int flag, int slots, void *tag, dnode_t **dnp) { - int epb, idx, err; + int epb, idx, err, i; int drop_struct_lock = FALSE; int type; uint64_t blk; dnode_t *mdn, *dn; dmu_buf_impl_t *db; dnode_children_t *children_dnodes; + dnode_phys_t *dn_block_begin; dnode_handle_t *dnh; + ASSERT(!(flag & DNODE_MUST_BE_ALLOCATED) || (slots == 0)); + ASSERT(!(flag & DNODE_MUST_BE_FREE) || (slots > 0)); + /* * If you are holding the spa config lock as writer, you shouldn't * be asking the DMU to do *anything* unless it's the root pool @@ -1126,12 +1271,9 @@ dnode_hold_impl(objset_t *os, uint64_t object, int flag, ASSERT3U(db->db.db_size, >=, 1<<DNODE_SHIFT); epb = db->db.db_size >> DNODE_SHIFT; - idx = object & (epb-1); - ASSERT(DB_DNODE(db)->dn_type == DMU_OT_DNODE); children_dnodes = dmu_buf_get_user(&db->db); if (children_dnodes == NULL) { - int i; dnode_children_t *winner; children_dnodes = kmem_zalloc(sizeof (dnode_children_t) + epb * sizeof (dnode_handle_t), KM_SLEEP); @@ -1156,21 +1298,28 @@ dnode_hold_impl(objset_t *os, uint64_t object, int flag, } ASSERT(children_dnodes->dnc_count == epb); + idx = object & (epb - 1); + dn_block_begin = (dnode_phys_t *)db->db.db_data; + + if ((flag & DNODE_MUST_BE_FREE) && !dnode_is_free(db, idx, slots)) { + dbuf_rele(db, FTAG); + return (ENOSPC); + } else if ((flag & DNODE_MUST_BE_ALLOCATED) && + !dnode_is_allocated(db, idx)) { + dbuf_rele(db, FTAG); + return (ENOENT); + } + dnh = &children_dnodes->dnc_children[idx]; zrl_add(&dnh->dnh_zrlock); dn = dnh->dnh_dnode; - if (dn == NULL) { - dnode_phys_t *phys = (dnode_phys_t *)db->db.db_data+idx; - - dn = dnode_create(os, phys, db, object, dnh); - } + if (dn == NULL) + dn = dnode_create(os, dn_block_begin + idx, db, object, dnh); mutex_enter(&dn->dn_mtx); type = dn->dn_type; if (dn->dn_free_txg || - ((flag & DNODE_MUST_BE_ALLOCATED) && type == DMU_OT_NONE) || - ((flag & DNODE_MUST_BE_FREE) && - (type != DMU_OT_NONE || !refcount_is_zero(&dn->dn_holds)))) { + ((flag & DNODE_MUST_BE_FREE) && !refcount_is_zero(&dn->dn_holds))) { mutex_exit(&dn->dn_mtx); zrl_remove(&dnh->dnh_zrlock); dbuf_rele(db, FTAG); @@ -1198,7 +1347,8 @@ dnode_hold_impl(objset_t *os, uint64_t object, int flag, int dnode_hold(objset_t *os, uint64_t object, void *tag, dnode_t **dnp) { - return (dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, tag, dnp)); + return (dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED, 0, tag, + dnp)); } /* @@ -1908,17 +2058,21 @@ dnode_next_offset_level(dnode_t *dn, int flags, uint64_t *offset, error = SET_ERROR(ESRCH); } else if (lvl == 0) { dnode_phys_t *dnp = data; - span = DNODE_SHIFT; + ASSERT(dn->dn_type == DMU_OT_DNODE); + ASSERT(!(flags & DNODE_FIND_BACKWARDS)); - for (i = (*offset >> span) & (blkfill - 1); - i >= 0 && i < blkfill; i += inc) { + for (i = (*offset >> DNODE_SHIFT) & (blkfill - 1); + i < blkfill; i += dnp[i].dn_extra_slots + 1) { if ((dnp[i].dn_type == DMU_OT_NONE) == hole) break; - *offset += (1ULL << span) * inc; } - if (i < 0 || i == blkfill) + + if (i == blkfill) error = SET_ERROR(ESRCH); + + *offset = (*offset & ~(DNODE_BLOCK_SIZE - 1)) + + (i << DNODE_SHIFT); } else { blkptr_t *bp = data; uint64_t start = *offset; diff --git a/module/zfs/dnode_sync.c b/module/zfs/dnode_sync.c index bea7be186..54066e2e3 100644 --- a/module/zfs/dnode_sync.c +++ b/module/zfs/dnode_sync.c @@ -524,7 +524,7 @@ dnode_sync_free(dnode_t *dn, dmu_tx_t *tx) ASSERT(dn->dn_free_txg > 0); if (dn->dn_allocated_txg != dn->dn_free_txg) dmu_buf_will_dirty(&dn->dn_dbuf->db, tx); - bzero(dn->dn_phys, sizeof (dnode_phys_t)); + bzero(dn->dn_phys, sizeof (dnode_phys_t) * dn->dn_num_slots); mutex_enter(&dn->dn_mtx); dn->dn_type = DMU_OT_NONE; @@ -559,7 +559,7 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx) ASSERT(dmu_tx_is_syncing(tx)); ASSERT(dnp->dn_type != DMU_OT_NONE || dn->dn_allocated_txg); ASSERT(dnp->dn_type != DMU_OT_NONE || - bcmp(dnp, &zerodn, DNODE_SIZE) == 0); + bcmp(dnp, &zerodn, DNODE_MIN_SIZE) == 0); DNODE_VERIFY(dn); ASSERT(dn->dn_dbuf == NULL || arc_released(dn->dn_dbuf->db_buf)); @@ -591,6 +591,9 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx) dnp->dn_bonustype = dn->dn_bonustype; dnp->dn_bonuslen = dn->dn_bonuslen; } + + dnp->dn_extra_slots = dn->dn_num_slots - 1; + ASSERT(dnp->dn_nlevels > 1 || BP_IS_HOLE(&dnp->dn_blkptr[0]) || BP_IS_EMBEDDED(&dnp->dn_blkptr[0]) || @@ -623,7 +626,8 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx) dnp->dn_bonuslen = 0; else dnp->dn_bonuslen = dn->dn_next_bonuslen[txgoff]; - ASSERT(dnp->dn_bonuslen <= DN_MAX_BONUSLEN); + ASSERT(dnp->dn_bonuslen <= + DN_SLOTS_TO_BONUSLEN(dnp->dn_extra_slots + 1)); dn->dn_next_bonuslen[txgoff] = 0; } @@ -662,7 +666,7 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx) mutex_exit(&dn->dn_mtx); if (kill_spill) { - free_blocks(dn, &dn->dn_phys->dn_spill, 1, tx); + free_blocks(dn, DN_SPILL_BLKPTR(dn->dn_phys), 1, tx); mutex_enter(&dn->dn_mtx); dnp->dn_flags &= ~DNODE_FLAG_SPILL_BLKPTR; mutex_exit(&dn->dn_mtx); @@ -687,6 +691,14 @@ dnode_sync(dnode_t *dn, dmu_tx_t *tx) return; } + if (dn->dn_num_slots > DNODE_MIN_SLOTS) { + dsl_dataset_t *ds = dn->dn_objset->os_dsl_dataset; + mutex_enter(&ds->ds_lock); + ds->ds_feature_activation_needed[SPA_FEATURE_LARGE_DNODE] = + B_TRUE; + mutex_exit(&ds->ds_lock); + } + if (dn->dn_next_nlevels[txgoff]) { dnode_increase_indirection(dn, tx); dn->dn_next_nlevels[txgoff] = 0; diff --git a/module/zfs/dsl_scan.c b/module/zfs/dsl_scan.c index b5e272fb9..72163521e 100644 --- a/module/zfs/dsl_scan.c +++ b/module/zfs/dsl_scan.c @@ -709,14 +709,18 @@ dsl_scan_recurse(dsl_scan_t *scn, dsl_dataset_t *ds, dmu_objset_type_t ostype, scn->scn_phys.scn_errors++; return (err); } - for (i = 0, cdnp = buf->b_data; i < epb; i++, cdnp++) { + for (i = 0, cdnp = buf->b_data; i < epb; + i += cdnp->dn_extra_slots + 1, + cdnp += cdnp->dn_extra_slots + 1) { for (j = 0; j < cdnp->dn_nblkptr; j++) { blkptr_t *cbp = &cdnp->dn_blkptr[j]; dsl_scan_prefetch(scn, buf, cbp, zb->zb_objset, zb->zb_blkid * epb + i, j); } } - for (i = 0, cdnp = buf->b_data; i < epb; i++, cdnp++) { + for (i = 0, cdnp = buf->b_data; i < epb; + i += cdnp->dn_extra_slots + 1, + cdnp += cdnp->dn_extra_slots + 1) { dsl_scan_visitdnode(scn, ds, ostype, cdnp, zb->zb_blkid * epb + i, tx); } @@ -779,7 +783,7 @@ dsl_scan_visitdnode(dsl_scan_t *scn, dsl_dataset_t *ds, zbookmark_phys_t czb; SET_BOOKMARK(&czb, ds ? ds->ds_object : 0, object, 0, DMU_SPILL_BLKID); - dsl_scan_visitbp(&dnp->dn_spill, + dsl_scan_visitbp(DN_SPILL_BLKPTR(dnp), &czb, dnp, ds, scn, ostype, tx); } } diff --git a/module/zfs/sa.c b/module/zfs/sa.c index d6ac5fcc7..adc301512 100644 --- a/module/zfs/sa.c +++ b/module/zfs/sa.c @@ -33,6 +33,7 @@ #include <sys/dmu.h> #include <sys/dmu_impl.h> #include <sys/dmu_objset.h> +#include <sys/dmu_tx.h> #include <sys/dbuf.h> #include <sys/dnode.h> #include <sys/zap.h> @@ -553,12 +554,11 @@ sa_copy_data(sa_data_locator_t *func, void *datastart, void *target, int buflen) */ static int sa_find_sizes(sa_os_t *sa, sa_bulk_attr_t *attr_desc, int attr_count, - dmu_buf_t *db, sa_buf_type_t buftype, int *index, int *total, - boolean_t *will_spill) + dmu_buf_t *db, sa_buf_type_t buftype, int full_space, int *index, + int *total, boolean_t *will_spill) { int var_size_count = 0; int i; - int full_space; int hdrsize; int extra_hdrsize; @@ -577,7 +577,6 @@ sa_find_sizes(sa_os_t *sa, sa_bulk_attr_t *attr_desc, int attr_count, hdrsize = (SA_BONUSTYPE_FROM_DB(db) == DMU_OT_ZNODE) ? 0 : sizeof (sa_hdr_phys_t); - full_space = (buftype == SA_BONUS) ? DN_MAX_BONUSLEN : db->db_size; ASSERT(IS_P2ALIGNED(full_space, 8)); for (i = 0; i != attr_count; i++) { @@ -668,6 +667,7 @@ sa_build_layouts(sa_handle_t *hdl, sa_bulk_attr_t *attr_desc, int attr_count, void *data_start; sa_attr_type_t *attrs, *attrs_start; int i, lot_count; + int dnodesize; int spill_idx; int hdrsize; int spillhdrsize = 0; @@ -676,20 +676,23 @@ sa_build_layouts(sa_handle_t *hdl, sa_bulk_attr_t *attr_desc, int attr_count, sa_lot_t *lot; int len_idx; int spill_used; + int bonuslen; boolean_t spilling; dmu_buf_will_dirty(hdl->sa_bonus, tx); bonustype = SA_BONUSTYPE_FROM_DB(hdl->sa_bonus); + dmu_object_dnsize_from_db(hdl->sa_bonus, &dnodesize); + bonuslen = DN_BONUS_SIZE(dnodesize); /* first determine bonus header size and sum of all attributes */ hdrsize = sa_find_sizes(sa, attr_desc, attr_count, hdl->sa_bonus, - SA_BONUS, &spill_idx, &used, &spilling); + SA_BONUS, bonuslen, &spill_idx, &used, &spilling); if (used > SPA_OLD_MAXBLOCKSIZE) return (SET_ERROR(EFBIG)); - VERIFY(0 == dmu_set_bonus(hdl->sa_bonus, spilling ? - MIN(DN_MAX_BONUSLEN - sizeof (blkptr_t), used + hdrsize) : + VERIFY0(dmu_set_bonus(hdl->sa_bonus, spilling ? + MIN(bonuslen - sizeof (blkptr_t), used + hdrsize) : used + hdrsize, tx)); ASSERT((bonustype == DMU_OT_ZNODE && spilling == 0) || @@ -706,8 +709,8 @@ sa_build_layouts(sa_handle_t *hdl, sa_bulk_attr_t *attr_desc, int attr_count, dmu_buf_will_dirty(hdl->sa_spill, tx); spillhdrsize = sa_find_sizes(sa, &attr_desc[spill_idx], - attr_count - spill_idx, hdl->sa_spill, SA_SPILL, &i, - &spill_used, &dummy); + attr_count - spill_idx, hdl->sa_spill, SA_SPILL, + hdl->sa_spill->db_size, &i, &spill_used, &dummy); if (spill_used > SPA_OLD_MAXBLOCKSIZE) return (SET_ERROR(EFBIG)); diff --git a/module/zfs/spa.c b/module/zfs/spa.c index c23fd7a3a..d1aefe585 100644 --- a/module/zfs/spa.c +++ b/module/zfs/spa.c @@ -281,6 +281,14 @@ spa_prop_get_config(spa_t *spa, nvlist_t **nvp) SPA_OLD_MAXBLOCKSIZE, ZPROP_SRC_NONE); } + if (spa_feature_is_enabled(spa, SPA_FEATURE_LARGE_DNODE)) { + spa_prop_add_list(*nvp, ZPOOL_PROP_MAXDNODESIZE, NULL, + DNODE_MAX_SIZE, ZPROP_SRC_NONE); + } else { + spa_prop_add_list(*nvp, ZPOOL_PROP_MAXDNODESIZE, NULL, + DNODE_MIN_SIZE, ZPROP_SRC_NONE); + } + if ((dp = list_head(&spa->spa_config_list)) != NULL) { if (dp->scd_path == NULL) { spa_prop_add_list(*nvp, ZPOOL_PROP_CACHEFILE, @@ -512,7 +520,8 @@ spa_prop_validate(spa_t *spa, nvlist_t *props) /* * Must be ZPL, and its property settings * must be supported by GRUB (compression - * is not gzip, and large blocks are not used). + * is not gzip, and large blocks or large + * dnodes are not used). */ if (dmu_objset_type(os) != DMU_OST_ZFS) { @@ -529,6 +538,12 @@ spa_prop_validate(spa_t *spa, nvlist_t *props) &propval)) == 0 && propval > SPA_OLD_MAXBLOCKSIZE) { error = SET_ERROR(ENOTSUP); + } else if ((error = + dsl_prop_get_int_ds(dmu_objset_ds(os), + zfs_prop_to_name(ZFS_PROP_DNODESIZE), + &propval)) == 0 && + propval != ZFS_DNSIZE_LEGACY) { + error = SET_ERROR(ENOTSUP); } else { objnum = dmu_objset_id(os); } diff --git a/module/zfs/spa_misc.c b/module/zfs/spa_misc.c index e3e7e36fe..d1303b5c2 100644 --- a/module/zfs/spa_misc.c +++ b/module/zfs/spa_misc.c @@ -2000,6 +2000,15 @@ spa_maxblocksize(spa_t *spa) return (SPA_OLD_MAXBLOCKSIZE); } +int +spa_maxdnodesize(spa_t *spa) +{ + if (spa_feature_is_enabled(spa, SPA_FEATURE_LARGE_DNODE)) + return (DNODE_MAX_SIZE); + else + return (DNODE_MIN_SIZE); +} + #if defined(_KERNEL) && defined(HAVE_SPL) /* Namespace manipulation */ EXPORT_SYMBOL(spa_lookup); @@ -2056,6 +2065,7 @@ EXPORT_SYMBOL(spa_bootfs); EXPORT_SYMBOL(spa_delegation); EXPORT_SYMBOL(spa_meta_objset); EXPORT_SYMBOL(spa_maxblocksize); +EXPORT_SYMBOL(spa_maxdnodesize); /* Miscellaneous support routines */ EXPORT_SYMBOL(spa_rename); diff --git a/module/zfs/zap.c b/module/zfs/zap.c index 454b4be62..9e4f05049 100644 --- a/module/zfs/zap.c +++ b/module/zfs/zap.c @@ -968,9 +968,17 @@ uint64_t zap_create_link(objset_t *os, dmu_object_type_t ot, uint64_t parent_obj, const char *name, dmu_tx_t *tx) { + return (zap_create_link_dnsize(os, ot, parent_obj, name, 0, tx)); +} + +uint64_t +zap_create_link_dnsize(objset_t *os, dmu_object_type_t ot, uint64_t parent_obj, + const char *name, int dnodesize, dmu_tx_t *tx) +{ uint64_t new_obj; - VERIFY((new_obj = zap_create(os, ot, DMU_OT_NONE, 0, tx)) > 0); + VERIFY((new_obj = zap_create_dnsize(os, ot, DMU_OT_NONE, 0, + dnodesize, tx)) > 0); VERIFY0(zap_add(os, parent_obj, name, sizeof (uint64_t), 1, &new_obj, tx)); diff --git a/module/zfs/zap_micro.c b/module/zfs/zap_micro.c index 3faf27ce3..f3153cc18 100644 --- a/module/zfs/zap_micro.c +++ b/module/zfs/zap_micro.c @@ -630,8 +630,16 @@ int zap_create_claim(objset_t *os, uint64_t obj, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { - return (zap_create_claim_norm(os, obj, - 0, ot, bonustype, bonuslen, tx)); + return (zap_create_claim_dnsize(os, obj, ot, bonustype, bonuslen, + 0, tx)); +} + +int +zap_create_claim_dnsize(objset_t *os, uint64_t obj, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx) +{ + return (zap_create_claim_norm_dnsize(os, obj, + 0, ot, bonustype, bonuslen, dnodesize, tx)); } int @@ -639,9 +647,19 @@ zap_create_claim_norm(objset_t *os, uint64_t obj, int normflags, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { + return (zap_create_claim_norm_dnsize(os, obj, normflags, ot, bonustype, + bonuslen, 0, tx)); +} + +int +zap_create_claim_norm_dnsize(objset_t *os, uint64_t obj, int normflags, + dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, + int dnodesize, dmu_tx_t *tx) +{ int err; - err = dmu_object_claim(os, obj, ot, 0, bonustype, bonuslen, tx); + err = dmu_object_claim_dnsize(os, obj, ot, 0, bonustype, bonuslen, + dnodesize, tx); if (err != 0) return (err); mzap_create_impl(os, obj, normflags, 0, tx); @@ -656,10 +674,27 @@ zap_create(objset_t *os, dmu_object_type_t ot, } uint64_t +zap_create_dnsize(objset_t *os, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx) +{ + return (zap_create_norm_dnsize(os, 0, ot, bonustype, bonuslen, + dnodesize, tx)); +} + +uint64_t zap_create_norm(objset_t *os, int normflags, dmu_object_type_t ot, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { - uint64_t obj = dmu_object_alloc(os, ot, 0, bonustype, bonuslen, tx); + return (zap_create_norm_dnsize(os, normflags, ot, bonustype, bonuslen, + 0, tx)); +} + +uint64_t +zap_create_norm_dnsize(objset_t *os, int normflags, dmu_object_type_t ot, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx) +{ + uint64_t obj = dmu_object_alloc_dnsize(os, ot, 0, bonustype, bonuslen, + dnodesize, tx); mzap_create_impl(os, obj, normflags, 0, tx); return (obj); @@ -670,7 +705,17 @@ zap_create_flags(objset_t *os, int normflags, zap_flags_t flags, dmu_object_type_t ot, int leaf_blockshift, int indirect_blockshift, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx) { - uint64_t obj = dmu_object_alloc(os, ot, 0, bonustype, bonuslen, tx); + return (zap_create_flags_dnsize(os, normflags, flags, ot, + leaf_blockshift, indirect_blockshift, bonustype, bonuslen, 0, tx)); +} + +uint64_t +zap_create_flags_dnsize(objset_t *os, int normflags, zap_flags_t flags, + dmu_object_type_t ot, int leaf_blockshift, int indirect_blockshift, + dmu_object_type_t bonustype, int bonuslen, int dnodesize, dmu_tx_t *tx) +{ + uint64_t obj = dmu_object_alloc_dnsize(os, ot, 0, bonustype, bonuslen, + dnodesize, tx); ASSERT(leaf_blockshift >= SPA_MINBLOCKSHIFT && leaf_blockshift <= SPA_OLD_MAXBLOCKSHIFT && @@ -1458,10 +1503,14 @@ zap_count_write(objset_t *os, uint64_t zapobj, const char *name, int add, #if defined(_KERNEL) && defined(HAVE_SPL) EXPORT_SYMBOL(zap_create); +EXPORT_SYMBOL(zap_create_dnsize); EXPORT_SYMBOL(zap_create_norm); +EXPORT_SYMBOL(zap_create_norm_dnsize); EXPORT_SYMBOL(zap_create_flags); +EXPORT_SYMBOL(zap_create_flags_dnsize); EXPORT_SYMBOL(zap_create_claim); EXPORT_SYMBOL(zap_create_claim_norm); +EXPORT_SYMBOL(zap_create_claim_norm_dnsize); EXPORT_SYMBOL(zap_destroy); EXPORT_SYMBOL(zap_lookup); EXPORT_SYMBOL(zap_lookup_norm); diff --git a/module/zfs/zfeature_common.c b/module/zfs/zfeature_common.c index f57e5489c..3264f6235 100644 --- a/module/zfs/zfeature_common.c +++ b/module/zfs/zfeature_common.c @@ -242,4 +242,15 @@ zpool_feature_init(void) "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); + } } diff --git a/module/zfs/zfs_acl.c b/module/zfs/zfs_acl.c index 961083d4a..f820cdfd6 100644 --- a/module/zfs/zfs_acl.c +++ b/module/zfs/zfs_acl.c @@ -1394,7 +1394,7 @@ zfs_aclset_common(znode_t *zp, zfs_acl_t *aclp, cred_t *cr, dmu_tx_t *tx) otype == DMU_OT_ACL ? DMU_OT_SYSACL : DMU_OT_NONE, otype == DMU_OT_ACL ? - DN_MAX_BONUSLEN : 0, tx); + DN_OLD_MAX_BONUSLEN : 0, tx); } else { (void) dmu_object_set_blocksize(zsb->z_os, aoid, aclp->z_acl_bytes, 0, tx); diff --git a/module/zfs/zfs_ioctl.c b/module/zfs/zfs_ioctl.c index c63af167a..30338ac14 100644 --- a/module/zfs/zfs_ioctl.c +++ b/module/zfs/zfs_ioctl.c @@ -3785,7 +3785,7 @@ zfs_check_settable(const char *dsname, nvpair_t *pair, cred_t *cr) /* * If this is a bootable dataset then - * the we don't allow large (>128K) blocks, + * we don't allow large (>128K) blocks, * because GRUB doesn't support them. */ if (zfs_is_bootfs(dsname) && @@ -3813,6 +3813,34 @@ zfs_check_settable(const char *dsname, nvpair_t *pair, cred_t *cr) } break; + case ZFS_PROP_DNODESIZE: + /* Dnode sizes above 512 need the feature to be enabled */ + if (nvpair_value_uint64(pair, &intval) == 0 && + intval != ZFS_DNSIZE_LEGACY) { + spa_t *spa; + + /* + * If this is a bootable dataset then + * we don't allow large (>512B) dnodes, + * because GRUB doesn't support them. + */ + if (zfs_is_bootfs(dsname) && + intval != ZFS_DNSIZE_LEGACY) { + return (SET_ERROR(EDOM)); + } + + if ((err = spa_open(dsname, &spa, FTAG)) != 0) + return (err); + + if (!spa_feature_is_enabled(spa, + SPA_FEATURE_LARGE_DNODE)) { + spa_close(spa, FTAG); + return (SET_ERROR(ENOTSUP)); + } + spa_close(spa, FTAG); + } + break; + case ZFS_PROP_SHARESMB: if (zpl_earlier_version(dsname, ZPL_VERSION_FUID)) return (SET_ERROR(ENOTSUP)); diff --git a/module/zfs/zfs_log.c b/module/zfs/zfs_log.c index 38d8de0eb..4d89cb04b 100644 --- a/module/zfs/zfs_log.c +++ b/module/zfs/zfs_log.c @@ -279,6 +279,8 @@ zfs_log_create(zilog_t *zilog, dmu_tx_t *tx, uint64_t txtype, lr = (lr_create_t *)&itx->itx_lr; lr->lr_doid = dzp->z_id; lr->lr_foid = zp->z_id; + /* Store dnode slot count in 8 bits above object id. */ + LR_FOID_SET_SLOTS(lr->lr_foid, zp->z_dnodesize >> DNODE_SHIFT); lr->lr_mode = zp->z_mode; if (!IS_EPHEMERAL(zp->z_uid)) { lr->lr_uid = (uint64_t)zp->z_uid; diff --git a/module/zfs/zfs_replay.c b/module/zfs/zfs_replay.c index b97a60ed8..54c175437 100644 --- a/module/zfs/zfs_replay.c +++ b/module/zfs/zfs_replay.c @@ -279,6 +279,8 @@ zfs_replay_create_acl(zfs_sb_t *zsb, lr_acl_create_t *lracl, boolean_t byteswap) void *fuidstart; size_t xvatlen = 0; uint64_t txtype; + uint64_t objid; + uint64_t dnodesize; int error; txtype = (lr->lr_common.lrc_txtype & ~TX_CI); @@ -304,19 +306,24 @@ zfs_replay_create_acl(zfs_sb_t *zsb, lr_acl_create_t *lracl, boolean_t byteswap) if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0) return (error); + objid = LR_FOID_GET_OBJ(lr->lr_foid); + dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT; + xva_init(&xva); zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID, - lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid); + lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid); /* * All forms of zfs create (create, mkdir, mkxattrdir, symlink) * eventually end up in zfs_mknode(), which assigns the object's - * creation time and generation number. The generic zfs_create() - * doesn't have either concept, so we smuggle the values inside - * the vattr's otherwise unused va_ctime and va_nblocks fields. + * creation time, generation number, and dnode size. The generic + * zfs_create() has no concept of these attributes, so we smuggle + * the values inside the vattr's otherwise unused va_ctime, + * va_nblocks, and va_fsid fields. */ ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime); xva.xva_vattr.va_nblocks = lr->lr_gen; + xva.xva_vattr.va_fsid = dnodesize; error = dmu_object_info(zsb->z_os, lr->lr_foid, NULL); if (error != ENOENT) @@ -418,6 +425,8 @@ zfs_replay_create(zfs_sb_t *zsb, lr_create_t *lr, boolean_t byteswap) void *start; size_t xvatlen; uint64_t txtype; + uint64_t objid; + uint64_t dnodesize; int error; txtype = (lr->lr_common.lrc_txtype & ~TX_CI); @@ -431,21 +440,26 @@ zfs_replay_create(zfs_sb_t *zsb, lr_create_t *lr, boolean_t byteswap) if ((error = zfs_zget(zsb, lr->lr_doid, &dzp)) != 0) return (error); + objid = LR_FOID_GET_OBJ(lr->lr_foid); + dnodesize = LR_FOID_GET_SLOTS(lr->lr_foid) << DNODE_SHIFT; + xva_init(&xva); zfs_init_vattr(&xva.xva_vattr, ATTR_MODE | ATTR_UID | ATTR_GID, - lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, lr->lr_foid); + lr->lr_mode, lr->lr_uid, lr->lr_gid, lr->lr_rdev, objid); /* * All forms of zfs create (create, mkdir, mkxattrdir, symlink) * eventually end up in zfs_mknode(), which assigns the object's - * creation time and generation number. The generic zfs_create() - * doesn't have either concept, so we smuggle the values inside - * the vattr's otherwise unused va_ctime and va_nblocks fields. + * creation time, generation number, and dnode slot count. The + * generic zfs_create() has no concept of these attributes, so + * we smuggle the values inside * the vattr's otherwise unused + * va_ctime, va_nblocks, and va_nlink fields. */ ZFS_TIME_DECODE(&xva.xva_vattr.va_ctime, lr->lr_crtime); xva.xva_vattr.va_nblocks = lr->lr_gen; + xva.xva_vattr.va_fsid = dnodesize; - error = dmu_object_info(zsb->z_os, lr->lr_foid, NULL); + error = dmu_object_info(zsb->z_os, objid, NULL); if (error != ENOENT) goto out; diff --git a/module/zfs/zfs_sa.c b/module/zfs/zfs_sa.c index f4841435b..f3eac51f8 100644 --- a/module/zfs/zfs_sa.c +++ b/module/zfs/zfs_sa.c @@ -97,8 +97,7 @@ zfs_sa_symlink(znode_t *zp, char *link, int len, dmu_tx_t *tx) dmu_buf_t *db = sa_get_db(zp->z_sa_hdl); if (ZFS_OLD_ZNODE_PHYS_SIZE + len <= dmu_bonus_max()) { - VERIFY(dmu_set_bonus(db, - len + ZFS_OLD_ZNODE_PHYS_SIZE, tx) == 0); + VERIFY0(dmu_set_bonus(db, len + ZFS_OLD_ZNODE_PHYS_SIZE, tx)); if (len) { bcopy(link, (caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE, len); @@ -107,8 +106,8 @@ zfs_sa_symlink(znode_t *zp, char *link, int len, dmu_tx_t *tx) dmu_buf_t *dbp; zfs_grow_blocksize(zp, len, tx); - VERIFY(0 == dmu_buf_hold(ZTOZSB(zp)->z_os, - zp->z_id, 0, FTAG, &dbp, DMU_READ_NO_PREFETCH)); + VERIFY0(dmu_buf_hold(ZTOZSB(zp)->z_os, zp->z_id, 0, FTAG, &dbp, + DMU_READ_NO_PREFETCH)); dmu_buf_will_dirty(dbp, tx); diff --git a/module/zfs/zfs_znode.c b/module/zfs/zfs_znode.c index 19cb414a9..310d4827b 100644 --- a/module/zfs/zfs_znode.c +++ b/module/zfs/zfs_znode.c @@ -62,6 +62,7 @@ #include <sys/dmu.h> #include <sys/dmu_objset.h> +#include <sys/dmu_tx.h> #include <sys/refcount.h> #include <sys/stat.h> #include <sys/zap.h> @@ -728,6 +729,7 @@ zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr, timestruc_t now; uint64_t gen, obj; int bonuslen; + int dnodesize; sa_handle_t *sa_hdl; dmu_object_type_t obj_type; sa_bulk_attr_t *sa_attrs; @@ -739,15 +741,21 @@ zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr, obj = vap->va_nodeid; now = vap->va_ctime; /* see zfs_replay_create() */ gen = vap->va_nblocks; /* ditto */ + dnodesize = vap->va_fsid; /* ditto */ } else { obj = 0; gethrestime(&now); gen = dmu_tx_get_txg(tx); + dnodesize = dmu_objset_dnodesize(zsb->z_os); } + if (dnodesize == 0) + dnodesize = DNODE_MIN_SIZE; + obj_type = zsb->z_use_sa ? DMU_OT_SA : DMU_OT_ZNODE; + bonuslen = (obj_type == DMU_OT_SA) ? - DN_MAX_BONUSLEN : ZFS_OLD_ZNODE_PHYS_SIZE; + DN_BONUS_SIZE(dnodesize) : ZFS_OLD_ZNODE_PHYS_SIZE; /* * Create a new DMU object. @@ -760,23 +768,23 @@ zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr, */ if (S_ISDIR(vap->va_mode)) { if (zsb->z_replay) { - VERIFY0(zap_create_claim_norm(zsb->z_os, obj, + VERIFY0(zap_create_claim_norm_dnsize(zsb->z_os, obj, zsb->z_norm, DMU_OT_DIRECTORY_CONTENTS, - obj_type, bonuslen, tx)); + obj_type, bonuslen, dnodesize, tx)); } else { - obj = zap_create_norm(zsb->z_os, + obj = zap_create_norm_dnsize(zsb->z_os, zsb->z_norm, DMU_OT_DIRECTORY_CONTENTS, - obj_type, bonuslen, tx); + obj_type, bonuslen, dnodesize, tx); } } else { if (zsb->z_replay) { - VERIFY0(dmu_object_claim(zsb->z_os, obj, + VERIFY0(dmu_object_claim_dnsize(zsb->z_os, obj, DMU_OT_PLAIN_FILE_CONTENTS, 0, - obj_type, bonuslen, tx)); + obj_type, bonuslen, dnodesize, tx)); } else { - obj = dmu_object_alloc(zsb->z_os, + obj = dmu_object_alloc_dnsize(zsb->z_os, DMU_OT_PLAIN_FILE_CONTENTS, 0, - obj_type, bonuslen, tx); + obj_type, bonuslen, dnodesize, tx); } } @@ -948,6 +956,7 @@ zfs_mknode(znode_t *dzp, vattr_t *vap, dmu_tx_t *tx, cred_t *cr, (*zpp)->z_pflags = pflags; (*zpp)->z_mode = mode; + (*zpp)->z_dnodesize = dnodesize; if (obj_type == DMU_OT_ZNODE || acl_ids->z_aclp->z_version < ZFS_ACL_VERSION_FUID) { @@ -1767,6 +1776,14 @@ zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *zplprops, dmu_tx_t *tx) ASSERT(error == 0); /* + * Give dmu_object_alloc() a hint about where to start + * allocating new objects. Otherwise, since the metadnode's + * dnode_phys_t structure isn't initialized yet, dmu_object_next() + * would fail and we'd have to skip to the next dnode block. + */ + os->os_obj_next = moid + 1; + + /* * Set starting attributes. */ version = zfs_zpl_version_map(spa_version(dmu_objset_spa(os))); diff --git a/module/zfs/zil.c b/module/zfs/zil.c index 289b23c7f..988ffec29 100644 --- a/module/zfs/zil.c +++ b/module/zfs/zil.c @@ -1372,7 +1372,8 @@ zil_itx_assign(zilog_t *zilog, itx_t *itx, dmu_tx_t *tx) itxg->itxg_sod += itx->itx_sod; } else { avl_tree_t *t = &itxs->i_async_tree; - uint64_t foid = ((lr_ooo_t *)&itx->itx_lr)->lr_foid; + uint64_t foid = + LR_FOID_GET_OBJ(((lr_ooo_t *)&itx->itx_lr)->lr_foid); itx_async_node_t *ian; avl_index_t where; @@ -1918,7 +1919,8 @@ zil_close(zilog_t *zilog) mutex_exit(&zilog->zl_lock); if (txg) txg_wait_synced(zilog->zl_dmu_pool, txg); - ASSERT(!zilog_is_dirty(zilog)); + if (txg < spa_freeze_txg(zilog->zl_spa)) + ASSERT(!zilog_is_dirty(zilog)); taskq_destroy(zilog->zl_clean_taskq); zilog->zl_clean_taskq = NULL; @@ -2122,7 +2124,7 @@ zil_replay_log_record(zilog_t *zilog, lr_t *lr, void *zra, uint64_t claim_txg) */ if (TX_OOO(txtype)) { error = dmu_object_info(zilog->zl_os, - ((lr_ooo_t *)lr)->lr_foid, NULL); + LR_FOID_GET_OBJ(((lr_ooo_t *)lr)->lr_foid), NULL); if (error == ENOENT || error == EEXIST) return (0); } diff --git a/tests/runfiles/linux.run b/tests/runfiles/linux.run index 1f52d2815..003c513dd 100644 --- a/tests/runfiles/linux.run +++ b/tests/runfiles/linux.run @@ -411,6 +411,11 @@ tests = ['exec_001_pos'] [tests/functional/features/async_destroy] tests = ['async_destroy_001_pos'] +[tests/functional/features/large_dnode] +tests = ['large_dnode_001_pos', 'large_dnode_002_pos', 'large_dnode_003_pos', + 'large_dnode_004_neg', 'large_dnode_005_pos', 'large_dnode_006_pos', + 'large_dnode_007_neg'] + # DISABLED: needs investigation #[tests/functional/grow_pool] #tests = ['grow_pool_001_pos'] diff --git a/tests/zfs-tests/include/default.cfg.in b/tests/zfs-tests/include/default.cfg.in index 9474c489e..13317ea87 100644 --- a/tests/zfs-tests/include/default.cfg.in +++ b/tests/zfs-tests/include/default.cfg.in @@ -80,7 +80,7 @@ export READMMAP=${READMMAP:-${helperdir}/readmmap} export RENAME_DIR=${RENAME_DIR:-${helperdir}/rename_dir} export RM_LNKCNT_ZERO_FILE=${RM_LNKCNT_ZERO_FILE:-${helperdir}/rm_lnkcnt_zero_file} export THREADSAPPEND=${THREADSAPPEND:-${helperdir}/threadsappend} -export XATTRTEST=${XATTRTEST:-${helpdir}/xattrtest} +export XATTRTEST=${XATTRTEST:-${helperdir}/xattrtest} # ensure we're running in the C locale, since # localised messages may result in test failures diff --git a/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg b/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg index d1d89f1af..f7a1d9cb1 100644 --- a/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg +++ b/tests/zfs-tests/tests/functional/cli_root/zpool_get/zpool_get.cfg @@ -35,7 +35,7 @@ typeset -a properties=("size" "capacity" "altroot" "health" "guid" "version" "free" "allocated" "readonly" "comment" "expandsize" "freeing" "failmode" "listsnapshots" "autoexpand" "fragmentation" "leaked" "ashift" "feature@async_destroy" "feature@empty_bpobj" "feature@lz4_compress" - "feature@large_blocks" "feature@filesystem_limits" + "feature@large_blocks" "feature@large_dnode" "feature@filesystem_limits" "feature@spacemap_histogram" "feature@enabled_txg" "feature@hole_birth" "feature@extensible_dataset" "feature@bookmarks" "feature@embedded_data") else diff --git a/tests/zfs-tests/tests/functional/delegate/delegate_common.kshlib b/tests/zfs-tests/tests/functional/delegate/delegate_common.kshlib index c90329ce1..796cda929 100644 --- a/tests/zfs-tests/tests/functional/delegate/delegate_common.kshlib +++ b/tests/zfs-tests/tests/functional/delegate/delegate_common.kshlib @@ -250,6 +250,10 @@ function check_fs_perm verify_fs_canmount $user $perm $fs ret=$? ;; + dnodesize) + verify_fs_dnodesize $user $perm $fs + ret=$? + ;; recordsize) verify_fs_recordsize $user $perm $fs ret=$? @@ -1112,6 +1116,21 @@ function verify_fs_recordsize return 0 } +function verify_fs_dnodesize +{ + typeset user=$1 + typeset perm=$2 + typeset fs=$3 + value="2k" + + user_run $user $ZFS set dnodesize=$value $fs + if [[ $value != $(get_prop dnodesize $fs) ]]; then + return 1 + fi + + return 0 +} + function verify_fs_quota { typeset user=$1 diff --git a/tests/zfs-tests/tests/functional/delegate/zfs_allow_010_pos.ksh b/tests/zfs-tests/tests/functional/delegate/zfs_allow_010_pos.ksh index 28b2b1dec..2e3be0cf5 100755 --- a/tests/zfs-tests/tests/functional/delegate/zfs_allow_010_pos.ksh +++ b/tests/zfs-tests/tests/functional/delegate/zfs_allow_010_pos.ksh @@ -70,6 +70,7 @@ set -A perms create true false \ allow true true \ quota true false \ reservation true true \ + dnodesize true false \ recordsize true false \ checksum true true \ compression true true \ @@ -95,6 +96,7 @@ set -A perms create true false \ allow true true \ quota true false \ reservation true true \ + dnodesize true false \ recordsize true false \ mountpoint true false \ checksum true true \ diff --git a/tests/zfs-tests/tests/functional/delegate/zfs_allow_012_neg.ksh b/tests/zfs-tests/tests/functional/delegate/zfs_allow_012_neg.ksh index a64561b69..723fb9292 100755 --- a/tests/zfs-tests/tests/functional/delegate/zfs_allow_012_neg.ksh +++ b/tests/zfs-tests/tests/functional/delegate/zfs_allow_012_neg.ksh @@ -59,13 +59,13 @@ if is_linux; then set -A perms create snapshot mount send allow quota reservation \ recordsize mountpoint checksum compression canmount atime \ devices exec volsize setuid readonly snapdir userprop \ - rollback clone rename promote \ + rollback clone rename promote dnodesize \ zoned xattr receive destroy else set -A perms create snapshot mount send allow quota reservation \ recordsize mountpoint checksum compression canmount atime \ devices exec volsize setuid readonly snapdir userprop \ - aclmode aclinherit rollback clone rename promote \ + aclmode aclinherit rollback clone rename promote dnodesize \ zoned xattr receive destroy sharenfs share fi diff --git a/tests/zfs-tests/tests/functional/features/Makefile.am b/tests/zfs-tests/tests/functional/features/Makefile.am index 4c6142a2f..3657461e6 100644 --- a/tests/zfs-tests/tests/functional/features/Makefile.am +++ b/tests/zfs-tests/tests/functional/features/Makefile.am @@ -1 +1,3 @@ -SUBDIRS = async_destroy +SUBDIRS = \ + async_destroy \ + large_dnode diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/Makefile.am b/tests/zfs-tests/tests/functional/features/large_dnode/Makefile.am new file mode 100644 index 000000000..6afda5362 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/Makefile.am @@ -0,0 +1,11 @@ +pkgdatadir = $(datadir)/@PACKAGE@/zfs-tests/tests/functional/features/large_dnode +dist_pkgdata_SCRIPTS = \ + cleanup.ksh \ + setup.ksh \ + large_dnode_001_pos.ksh \ + large_dnode_002_pos.ksh \ + large_dnode_003_pos.ksh \ + large_dnode_004_neg.ksh \ + large_dnode_005_pos.ksh \ + large_dnode_006_pos.ksh \ + large_dnode_007_neg.ksh diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/cleanup.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/cleanup.ksh new file mode 100755 index 000000000..61caf3910 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/cleanup.ksh @@ -0,0 +1,25 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +default_cleanup diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_001_pos.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_001_pos.ksh new file mode 100755 index 000000000..a05acb97e --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_001_pos.ksh @@ -0,0 +1,77 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +# +# DESCRIPTION: +# Verify that the dnode sizes of newly created files are consistent +# with the dnodesize dataset property. +# +# STRATEGY: +# 1. Create a file system +# 2. Set dnodesize to a legal literal value +# 3. Create a file +# 4. Repeat 2-3 for all legal literal values of dnodesize values +# 5. Unmount the file system +# 6. Use zdb to check expected dnode sizes +# + +TEST_FS=$TESTPOOL/large_dnode + +verify_runnable "both" + +function cleanup +{ + datasetexists $TEST_FS && log_must $ZFS destroy $TEST_FS +} + +log_onexit cleanup +log_assert "dnode sizes are consistent with dnodesize dataset property" + +log_must $ZFS create $TEST_FS + +set -A dnsizes "512" "1k" "2k" "4k" "8k" "16k" +set -A inodes + +for ((i=0; i < ${#dnsizes[*]}; i++)) ; do + size=${dnsizes[$i]} + if [[ $size == "512" ]] ; then + size="legacy" + fi + file=/$TEST_FS/file.$size + log_must $ZFS set dnsize=$size $TEST_FS + touch $file + inodes[$i]=$(ls -li $file | awk '{print $1}') +done + +log_must $ZFS umount $TEST_FS + +for ((i=0; i < ${#dnsizes[*]}; i++)) ; do + dnsize=$($ZDB -dddd $TEST_FS ${inodes[$i]} | + awk '/ZFS plain file/ {print $6}' | tr K k) + if [[ "$dnsize" != "${dnsizes[$i]}" ]]; then + log_fail "dnode size is $dnsize (expected ${dnsizes[$i]})" + fi +done + +log_pass "dnode sizes are consistent with dnodesize dataset property" diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_002_pos.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_002_pos.ksh new file mode 100755 index 000000000..788e33a13 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_002_pos.ksh @@ -0,0 +1,78 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +# +# DESCRIPTION: +# Verify that extended attributes can use extra bonus space of a large +# dnode without kicking in a spill block. +# +# STRATEGY: +# 1. Create a file system with xattr=sa +# 2. Set dnodesize to a legal literal value +# 3. Create a file +# 4 Store an xattr that fits within the dnode size +# 4. Repeat 2-3 for all legal literal values of dnodesize values +# 5. Unmount the file system +# 6. Use zdb to check for missing SPILL_BLKPTR flag +# + +TEST_FS=$TESTPOOL/large_dnode + +verify_runnable "both" + +function cleanup +{ + datasetexists $TEST_FS && log_must $ZFS destroy $TEST_FS +} + +log_onexit cleanup +log_assert "extended attributes use extra bonus space of a large dnode" + +log_must $ZFS create -o xattr=sa $TEST_FS + +# Store dnode size minus 512 in an xattr +set -A xattr_sizes "512" "1536" "3584" "7680" "15872" +set -A prop_values "1k" "2k" "4k" "8k" "16k" +set -A inodes + +for ((i=0; i < ${#prop_values[*]}; i++)) ; do + prop_val=${prop_values[$i]} + file=/$TEST_FS/file.$prop_val + log_must $ZFS set dnsize=$prop_val $TEST_FS + touch $file + xattr_size=${xattr_sizes[$i]} + xattr_name=user.foo + xattr_val=$(dd if=/dev/urandom bs=1 count=$xattr_size | + openssl enc -a -A) + log_must setfattr -n $xattr_name -v 0s$xattr_val $file + inodes[$i]=$(ls -li $file | awk '{print $1}') +done + +log_must $ZFS umount $TEST_FS + +for ((i=0; i < ${#inodes[*]}; i++)) ; do + log_mustnot eval "$ZDB -dddd $TEST_FS ${inodes[$i]} | grep SPILL_BLKPTR" +done + +log_pass "extended attributes use extra bonus space of a large dnode" diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_003_pos.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_003_pos.ksh new file mode 100755 index 000000000..3f5779ded --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_003_pos.ksh @@ -0,0 +1,65 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +verify_runnable "both" + +function cleanup +{ + if datasetexists $LDNPOOL ; then + log_must $ZPOOL destroy -f $LDNPOOL + fi +} + +log_onexit cleanup + +log_assert "feature correctly switches between enabled and active" + +LDNPOOL=ldnpool +LDNFS=$LDNPOOL/large_dnode +log_must $MKFILE 64M $TESTDIR/$LDNPOOL +log_must $ZPOOL create $LDNPOOL $TESTDIR/$LDNPOOL + + +state=$($ZPOOL list -Ho feature@large_dnode $LDNPOOL) +if [[ "$state" != "enabled" ]]; then + log_fail "large_dnode has state $state (expected enabled)" +fi + +log_must $ZFS create -o dnodesize=1k $LDNFS +log_must touch /$LDNFS/foo +log_must $ZFS unmount $LDNFS + +state=$($ZPOOL list -Ho feature@large_dnode $LDNPOOL) +if [[ "$state" != "active" ]]; then + log_fail "large_dnode has state $state (expected active)" +fi + +log_must $ZFS destroy $LDNFS + +state=$($ZPOOL list -Ho feature@large_dnode $LDNPOOL) +if [[ "$state" != "enabled" ]]; then + log_fail "large_dnode has state $state (expected enabled)" +fi + +log_pass diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_004_neg.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_004_neg.ksh new file mode 100755 index 000000000..26ed66994 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_004_neg.ksh @@ -0,0 +1,59 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +verify_runnable "both" + +TEST_FS=$TESTPOOL/large_dnode +TEST_SNAP=$TESTPOOL/large_dnode@ldnsnap +TEST_STREAM=$TESTDIR/ldnsnap + +function cleanup +{ + if datasetexists $TEST_FS ; then + log_must $ZFS destroy -r $TEST_FS + fi + + if datasetexists $LGCYPOOL ; then + log_must $ZPOOL destroy -f $LGCYPOOL + fi + + rm -f $TEST_STREAM +} + +log_onexit cleanup +log_assert "zfs send stream with large dnodes not accepted by legacy pool" + +log_must $ZFS create -o dnodesize=1k $TEST_FS +log_must touch /$TEST_FS/foo +log_must $ZFS umount $TEST_FS +log_must $ZFS snap $TEST_SNAP +log_must eval "$ZFS send $TEST_SNAP > $TEST_STREAM" + +LGCYPOOL=ldnpool +LGCYFS=$LGCYPOOL/legacy +log_must $MKFILE 64M $TESTDIR/$LGCYPOOL +log_must $ZPOOL create -d $LGCYPOOL $TESTDIR/$LGCYPOOL +log_mustnot eval "$ZFS recv $LGCYFS < $TEST_STREAM" + +log_pass diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_005_pos.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_005_pos.ksh new file mode 100755 index 000000000..e03d1274f --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_005_pos.ksh @@ -0,0 +1,64 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +verify_runnable "both" + +TEST_SEND_FS=$TESTPOOL/send_large_dnode +TEST_RECV_FS=$TESTPOOL/recv_large_dnode +TEST_SNAP=$TEST_SEND_FS@ldnsnap +TEST_STREAM=$TESTDIR/ldnsnap +TEST_FILE=foo + + +function cleanup +{ + if datasetexists $TEST_SEND_FS ; then + log_must $ZFS destroy -r $TEST_SEND_FS + fi + + if datasetexists $TEST_RECV_FS ; then + log_must $ZFS destroy -r $TEST_RECV_FS + fi + + rm -f $TEST_STREAM +} + +log_onexit cleanup + +log_assert "zfs send stream with large dnodes accepted by new pool" + +log_must $ZFS create -o dnodesize=1k $TEST_SEND_FS +log_must touch /$TEST_SEND_FS/$TEST_FILE +log_must $ZFS umount $TEST_SEND_FS +log_must $ZFS snap $TEST_SNAP +log_must $ZFS send $TEST_SNAP > $TEST_STREAM + +log_must eval "$ZFS recv $TEST_RECV_FS < $TEST_STREAM" +inode=$(ls -li /$TEST_RECV_FS/$TEST_FILE | awk '{print $1}') +dnsize=$($ZDB -dddd $TEST_RECV_FS $inode | awk '/ZFS plain file/ {print $6}') +if [[ "$dnsize" != "1K" ]]; then + log_fail "dnode size is $dnsize (expected 1K)" +fi + +log_pass diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_006_pos.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_006_pos.ksh new file mode 100755 index 000000000..198b69bf7 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_006_pos.ksh @@ -0,0 +1,58 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +# +# DESCRIPTION: +# Run xattrtest on a dataset with large dnodes and xattr=sa +# to stress xattr usage of the extra bonus space and verify +# contents +# + +TEST_FS=$TESTPOOL/large_dnode + +verify_runnable "both" + +function cleanup +{ + datasetexists $TEST_FS && log_must $ZFS destroy $TEST_FS +} + +log_onexit cleanup +log_assert "xattrtest runs cleanly on dataset with large dnodes" + +log_must $ZFS create $TEST_FS + +set -A xattr_sizes "512" "1536" "3584" "7680" "15872" +set -A prop_values "1k" "2k" "4k" "8k" "16k" + +for ((i=0; i < ${#prop_values[*]}; i++)) ; do + prop_val=${prop_values[$i]} + dir=/$TEST_FS/$prop_val + xattr_size=${xattr_sizes[$i]} + log_must $ZFS set dnsize=$prop_val $TEST_FS + log_must mkdir $dir + log_must $XATTRTEST -R -y -s $xattr_size -f 1024 -p $dir +done + +log_pass diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_007_neg.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_007_neg.ksh new file mode 100755 index 000000000..d6cc17e0b --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_007_neg.ksh @@ -0,0 +1,56 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +# +# DESCRIPTION: +# Verify that the dnodesize dataset property won't accept a value +# other than "legacy" if the large_dnode feature is not enabled. +# + +verify_runnable "both" + +function cleanup +{ + if datasetexists $LGCYPOOL ; then + log_must $ZPOOL destroy -f $LGCYPOOL + fi +} + +log_onexit cleanup + +log_assert "values other than dnodesize=legacy rejected by legacy pool" + +set -A prop_vals "auto" "1k" "2k" "4k" "8k" "16k" + +LGCYPOOL=lgcypool +LGCYFS=$LGCYPOOL/legacy +log_must $MKFILE 64M $TESTDIR/$LGCYPOOL +log_must $ZPOOL create -d $LGCYPOOL $TESTDIR/$LGCYPOOL +log_must $ZFS create $LGCYFS + +for val in ${prop_vals[@]} ; do + log_mustnot $ZFS set dnodesize=$val $LGCYFS +done + +log_pass diff --git a/tests/zfs-tests/tests/functional/features/large_dnode/setup.ksh b/tests/zfs-tests/tests/functional/features/large_dnode/setup.ksh new file mode 100755 index 000000000..d9b1a6ee8 --- /dev/null +++ b/tests/zfs-tests/tests/functional/features/large_dnode/setup.ksh @@ -0,0 +1,27 @@ +#!/bin/ksh -p +# +# CDDL HEADER START +# +# The contents of this file are subject to the terms of the +# Common Development and Distribution License (the "License"). +# You may not use this file except in compliance with the License. +# +# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE +# or http://www.opensolaris.org/os/licensing. +# See the License for the specific language governing permissions +# and limitations under the License. +# +# When distributing Covered Code, include this CDDL HEADER in each +# file and include the License file at usr/src/OPENSOLARIS.LICENSE. +# If applicable, add the following below this CDDL HEADER, with the +# fields enclosed by brackets "[]" replaced with your own identifying +# information: Portions Copyright [yyyy] [name of copyright owner] +# +# CDDL HEADER END +# + +. $STF_SUITE/include/libtest.shlib + +DISK=${DISKS%% *} + +default_setup $DISK diff --git a/tests/zfs-tests/tests/functional/rsend/rsend.kshlib b/tests/zfs-tests/tests/functional/rsend/rsend.kshlib index 46f96fa61..91779cc78 100644 --- a/tests/zfs-tests/tests/functional/rsend/rsend.kshlib +++ b/tests/zfs-tests/tests/functional/rsend/rsend.kshlib @@ -201,8 +201,8 @@ function cmp_ds_prop for item in "type" "origin" "volblocksize" "aclinherit" "aclmode" \ "atime" "canmount" "checksum" "compression" "copies" "devices" \ - "exec" "quota" "readonly" "recordsize" "reservation" "setuid" \ - "sharenfs" "snapdir" "version" "volsize" "xattr" "zoned" \ + "dnodesize" "exec" "quota" "readonly" "recordsize" "reservation" \ + "setuid" "sharenfs" "snapdir" "version" "volsize" "xattr" "zoned" \ "mountpoint"; do $ZFS get -H -o property,value,source $item $dtst1 >> \ diff --git a/tests/zfs-tests/tests/functional/rsend/rsend_012_pos.ksh b/tests/zfs-tests/tests/functional/rsend/rsend_012_pos.ksh index 4a590fab4..91cdd6e34 100755 --- a/tests/zfs-tests/tests/functional/rsend/rsend_012_pos.ksh +++ b/tests/zfs-tests/tests/functional/rsend/rsend_012_pos.ksh @@ -142,6 +142,7 @@ for fs in "$POOL" "$POOL/pclone" "$POOL/$FS" "$POOL/$FS/fs1" \ rand_set_prop $fs exec "on" "off" rand_set_prop $fs quota "512M" "1024M" rand_set_prop $fs recordsize "512" "2K" "8K" "32K" "128K" + rand_set_prop $fs dnodesize "legacy" "auto" "1k" "2k" "4k" "8k" "16k" rand_set_prop $fs setuid "on" "off" rand_set_prop $fs snapdir "hidden" "visible" rand_set_prop $fs xattr "on" "off" diff --git a/zfs-script-config.sh.in b/zfs-script-config.sh.in index 2470c554a..e22cfd595 100644 --- a/zfs-script-config.sh.in +++ b/zfs-script-config.sh.in @@ -59,7 +59,7 @@ export READMMAP=${TESTSDIR}/zfs-tests/cmd/readmmap/readmmap export RENAME_DIR=${TESTSDIR}/zfs-tests/cmd/rename_dir/rename_dir export RM_LNKCNT_ZERO_FILE=${TESTSDIR}/zfs-tests/cmd/rm_lnkcnt_zero_file/rm_lnkcnt_zero_file export THREADSAPPEND=${TESTSDIR}/zfs-tests/cmd/threadsappend/threadsappend -export XATTRTEST=${TESTDIR}/zfs-tests/cmd/xattrtest +export XATTRTEST=${TESTSDIR}/zfs-tests/cmd/xattrtest/xattrtest export INTREE=1 export LDMOD=/sbin/insmod |