From: Serge Petrenko via Tarantool-patches <tarantool-patches@dev.tarantool.org> To: v.shpilevoy@tarantool.org, gorcunov@gmail.com Cc: tarantool-patches@dev.tarantool.org Subject: [Tarantool-patches] [PATCH 4/9] box: make clear_synchro_queue() write a PROMOTE entry instead of CONFIRM + ROLLBACK Date: Sun, 11 Apr 2021 20:55:59 +0300 [thread overview] Message-ID: <c0ffbb0e57170fc7aa326150ed6796d2dcccda82.1618163409.git.sergepetrenko@tarantool.org> (raw) In-Reply-To: <cover.1618163409.git.sergepetrenko@tarantool.org> A successful box_clear_synchro_queue() call results in writing CONFIRM(N) ROLLBACK(N+1) pair, where N is the confirmed lsn. Let's write a single PROMOTE(N) entry instead. It'll have the same meaning as CONFIRM + ROLLBACK and it will give followers some additional information regarding leader state change later. Part of #5445 --- src/box/applier.cc | 4 +- src/box/box.cc | 14 ++++++- src/box/iproto_constants.h | 5 +++ src/box/txn_limbo.c | 79 +++++++++++++++++++++----------------- src/box/txn_limbo.h | 10 ++++- 5 files changed, 72 insertions(+), 40 deletions(-) diff --git a/src/box/applier.cc b/src/box/applier.cc index 971b2e64c..e8cbbe27a 100644 --- a/src/box/applier.cc +++ b/src/box/applier.cc @@ -763,7 +763,7 @@ applier_txn_wal_write_cb(struct trigger *trigger, void *event) struct synchro_entry { /** Encoded form of a synchro record. */ - struct synchro_body_bin body_bin; + struct promote_body_bin body_bin; /** xrow to write, used by the journal engine. */ struct xrow_header row; @@ -822,7 +822,7 @@ synchro_entry_new(struct xrow_header *applier_row, } struct journal_entry *journal_entry = &entry->journal_entry; - struct synchro_body_bin *body_bin = &entry->body_bin; + struct synchro_body_bin *body_bin = &entry->body_bin.base; struct xrow_header *row = &entry->row; journal_entry->rows[0] = row; diff --git a/src/box/box.cc b/src/box/box.cc index b846ba8f5..8aba051a2 100644 --- a/src/box/box.cc +++ b/src/box/box.cc @@ -1556,7 +1556,19 @@ box_clear_synchro_queue(bool try_wait) "new synchronous transactions appeared"); rc = -1; } else { - txn_limbo_force_empty(&txn_limbo, wait_lsn); + /* + * Term parameter is unused now, We'll pass + * box_raft()->term there later. + */ + txn_limbo_write_promote(&txn_limbo, wait_lsn, 0); + struct synchro_request req = { + .type = 0, /* unused */ + .replica_id = 0, /* unused */ + .origin_id = instance_id, + .lsn = wait_lsn, + .term = 0, /* unused */ + }; + txn_limbo_read_promote(&txn_limbo, &req); assert(txn_limbo_is_empty(&txn_limbo)); } } diff --git a/src/box/iproto_constants.h b/src/box/iproto_constants.h index 816a308d8..da78ac4d4 100644 --- a/src/box/iproto_constants.h +++ b/src/box/iproto_constants.h @@ -362,6 +362,11 @@ iproto_type_is_synchro_request(uint32_t type) type == IPROTO_PROMOTE; } +static inline bool +iproto_type_is_promote_request(uint32_t type) +{ + return type == IPROTO_PROMOTE; +} static inline bool iproto_type_is_raft_request(uint32_t type) { diff --git a/src/box/txn_limbo.c b/src/box/txn_limbo.c index cf0ad9350..664f9d369 100644 --- a/src/box/txn_limbo.c +++ b/src/box/txn_limbo.c @@ -314,21 +314,25 @@ txn_limbo_write_cb(struct journal_entry *entry) } static void -txn_limbo_write_synchro(struct txn_limbo *limbo, uint32_t type, int64_t lsn) +txn_limbo_write_synchro(struct txn_limbo *limbo, uint32_t type, int64_t lsn, + uint64_t term) { - assert(lsn > 0); + assert(lsn >= 0); struct synchro_request req = { .type = type, .replica_id = limbo->owner_id, .lsn = lsn, + .term = term, }; /* - * This is a synchronous commit so we can - * allocate everything on a stack. + * This is a synchronous commit so we can allocate everything on a + * stack. Promote body includes synchro body. */ - struct synchro_body_bin body; + struct promote_body_bin body; + struct synchro_body_bin *base = &body.base; + struct xrow_header row; char buf[sizeof(struct journal_entry) + sizeof(struct xrow_header *)]; @@ -336,7 +340,7 @@ txn_limbo_write_synchro(struct txn_limbo *limbo, uint32_t type, int64_t lsn) struct journal_entry *entry = (struct journal_entry *)buf; entry->rows[0] = &row; - xrow_encode_synchro(&row, &body, &req); + xrow_encode_synchro(&row, base, &req); journal_entry_create(entry, 1, xrow_approx_len(&row), txn_limbo_write_cb, fiber()); @@ -368,14 +372,14 @@ txn_limbo_write_confirm(struct txn_limbo *limbo, int64_t lsn) assert(lsn > limbo->confirmed_lsn); assert(!limbo->is_in_rollback); limbo->confirmed_lsn = lsn; - txn_limbo_write_synchro(limbo, IPROTO_CONFIRM, lsn); + txn_limbo_write_synchro(limbo, IPROTO_CONFIRM, lsn, 0); } /** Confirm all the entries <= @a lsn. */ static void txn_limbo_read_confirm(struct txn_limbo *limbo, int64_t lsn) { - assert(limbo->owner_id != REPLICA_ID_NIL); + assert(limbo->owner_id != REPLICA_ID_NIL || txn_limbo_is_empty(limbo)); assert(limbo == &txn_limbo); struct txn_limbo_entry *e, *tmp; rlist_foreach_entry_safe(e, &limbo->queue, in_queue, tmp) { @@ -431,7 +435,7 @@ txn_limbo_write_rollback(struct txn_limbo *limbo, int64_t lsn) assert(lsn > limbo->confirmed_lsn); assert(!limbo->is_in_rollback); limbo->is_in_rollback = true; - txn_limbo_write_synchro(limbo, IPROTO_ROLLBACK, lsn); + txn_limbo_write_synchro(limbo, IPROTO_ROLLBACK, lsn, 0); limbo->is_in_rollback = false; } @@ -439,7 +443,7 @@ txn_limbo_write_rollback(struct txn_limbo *limbo, int64_t lsn) static void txn_limbo_read_rollback(struct txn_limbo *limbo, int64_t lsn) { - assert(limbo->owner_id != REPLICA_ID_NIL); + assert(limbo->owner_id != REPLICA_ID_NIL || txn_limbo_is_empty(limbo)); assert(limbo == &txn_limbo); struct txn_limbo_entry *e, *tmp; struct txn_limbo_entry *last_rollback = NULL; @@ -487,6 +491,32 @@ txn_limbo_read_rollback(struct txn_limbo *limbo, int64_t lsn) box_update_ro_summary(); } +void +txn_limbo_write_promote(struct txn_limbo *limbo, int64_t lsn, uint64_t term) +{ + limbo->confirmed_lsn = lsn; + /* + * We make sure that promote is only written once everything this + * instance has may be confirmed. + */ + struct txn_limbo_entry *e = txn_limbo_last_synchro_entry(limbo); + assert(e == NULL || e->lsn <= lsn); + (void) e; + txn_limbo_write_synchro(limbo, IPROTO_PROMOTE, lsn, term); + limbo->is_in_rollback = false; +} + +void +txn_limbo_read_promote(struct txn_limbo *limbo, + const struct synchro_request *req) +{ + txn_limbo_read_confirm(limbo, req->lsn); + txn_limbo_read_rollback(limbo, req->lsn + 1); + assert(txn_limbo_is_empty(&txn_limbo)); + limbo->owner_id = req->origin_id; + limbo->confirmed_lsn = 0; +} + void txn_limbo_ack(struct txn_limbo *limbo, uint32_t replica_id, int64_t lsn) { @@ -649,38 +679,15 @@ txn_limbo_process(struct txn_limbo *limbo, const struct synchro_request *req) case IPROTO_ROLLBACK: txn_limbo_read_rollback(limbo, req->lsn); break; + case IPROTO_PROMOTE: + txn_limbo_read_promote(limbo, req); + break; default: unreachable(); } return; } -void -txn_limbo_force_empty(struct txn_limbo *limbo, int64_t confirm_lsn) -{ - struct txn_limbo_entry *e, *last_quorum = NULL; - struct txn_limbo_entry *rollback = NULL; - rlist_foreach_entry(e, &limbo->queue, in_queue) { - if (txn_has_flag(e->txn, TXN_WAIT_ACK)) { - if (e->lsn <= confirm_lsn) { - last_quorum = e; - } else { - rollback = e; - break; - } - } - } - - if (last_quorum != NULL) { - txn_limbo_write_confirm(limbo, last_quorum->lsn); - txn_limbo_read_confirm(limbo, last_quorum->lsn); - } - if (rollback != NULL) { - txn_limbo_write_rollback(limbo, rollback->lsn); - txn_limbo_read_rollback(limbo, rollback->lsn); - } -} - void txn_limbo_on_parameters_change(struct txn_limbo *limbo) { diff --git a/src/box/txn_limbo.h b/src/box/txn_limbo.h index af0addf8d..ec317ed20 100644 --- a/src/box/txn_limbo.h +++ b/src/box/txn_limbo.h @@ -275,7 +275,15 @@ txn_limbo_wait_confirm(struct txn_limbo *limbo); * immediately. */ void -txn_limbo_force_empty(struct txn_limbo *limbo, int64_t last_confirm); +txn_limbo_write_promote(struct txn_limbo *limbo, int64_t lsn, uint64_t term); + +/** + * Process a PROMOTE request, i.e. confirm all entries <= @lsn and rollback all + * entries > @lsn. + */ +void +txn_limbo_read_promote(struct txn_limbo *limbo, + const struct synchro_request *req); /** * Update qsync parameters dynamically. -- 2.24.3 (Apple Git-128)
next prev parent reply other threads:[~2021-04-11 17:58 UTC|newest] Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-04-11 17:55 [Tarantool-patches] [PATCH 0/9] raft: introduce manual elections and fix a bug with re-applying rolled back transactions Serge Petrenko via Tarantool-patches 2021-04-11 17:55 ` [Tarantool-patches] [PATCH 1/9] wal: enrich row's meta information with sync replication flags Serge Petrenko via Tarantool-patches 2021-04-12 13:06 ` Cyrill Gorcunov via Tarantool-patches 2021-04-13 13:26 ` Serge Petrenko via Tarantool-patches 2021-04-12 19:21 ` Serge Petrenko via Tarantool-patches 2021-04-11 17:55 ` [Tarantool-patches] [PATCH 2/9] xrow: introduce a PROMOTE entry Serge Petrenko via Tarantool-patches 2021-04-11 17:55 ` [Tarantool-patches] [PATCH 3/9] box: actualise iproto_key_type array Serge Petrenko via Tarantool-patches 2021-04-11 17:55 ` Serge Petrenko via Tarantool-patches [this message] 2021-04-11 17:56 ` [Tarantool-patches] [PATCH 5/9] box: write PROMOTE even for empty limbo Serge Petrenko via Tarantool-patches 2021-04-11 17:56 ` [Tarantool-patches] [PATCH 6/9] raft: keep track of greatest known term and filter replication sources based on that Serge Petrenko via Tarantool-patches 2021-04-12 19:23 ` Serge Petrenko via Tarantool-patches 2021-04-11 17:56 ` [Tarantool-patches] [PATCH 7/9] replication: introduce a new election mode: "manual" Serge Petrenko via Tarantool-patches 2021-04-11 17:56 ` [Tarantool-patches] [PATCH 8/9] Support manual elections in `box.ctl.clear_synchro_queue()` Serge Petrenko via Tarantool-patches 2021-04-12 19:23 ` Serge Petrenko via Tarantool-patches 2021-04-11 17:56 ` [Tarantool-patches] [PATCH 9/9] box.ctl: rename clear_synchro_queue to promote Serge Petrenko via Tarantool-patches 2021-04-12 19:24 ` Serge Petrenko via Tarantool-patches
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=c0ffbb0e57170fc7aa326150ed6796d2dcccda82.1618163409.git.sergepetrenko@tarantool.org \ --to=tarantool-patches@dev.tarantool.org \ --cc=gorcunov@gmail.com \ --cc=sergepetrenko@tarantool.org \ --cc=v.shpilevoy@tarantool.org \ --subject='Re: [Tarantool-patches] [PATCH 4/9] box: make clear_synchro_queue() write a PROMOTE entry instead of CONFIRM + ROLLBACK' \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox