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 2/9] xrow: introduce a PROMOTE entry Date: Sun, 11 Apr 2021 20:55:57 +0300 [thread overview] Message-ID: <45386860deded154a47c6a07b0537b88e362aa51.1618163409.git.sergepetrenko@tarantool.org> (raw) In-Reply-To: <cover.1618163409.git.sergepetrenko@tarantool.org> A PROMOTE entry combines effect of CONFIRM, ROLLBACK and RAFT_TERM entries with some additional semantics on top. PROMOTE carries the following arguments: 1) former_leader_id - the id of previous limbo owner whose entries we want to confirm. 2) confirm_lsn - the lsn of the last former leader's transaction to be confirmed. In this sense PROMOTE(confirm_lsn) replaces CONFIRM(confirm_lsn) + ROLLBACK(confirm_lsn + 1). 3) replica_id - id of the instance issuing `box.ctl.clear_synchro_queue()` 4) term - the new term the instance issuing `box.ctl.clear_synchro_queue()` has just entered. This entry will be written to WAL instead of the usual CONFIRM + ROLLBACK pair on a successful `box.ctl.clear_synchro_queue()` call. Note, the ususal CONFIRM and ROLLBACK occurrences (after a confirmed or rolled back synchronous transaction) are here to stay. Part of #5445 --- src/box/iproto_constants.h | 17 ++++++++++++++++- src/box/xrow.c | 30 +++++++++++++++++++++++++----- src/box/xrow.h | 24 +++++++++++++++++++++++- 3 files changed, 64 insertions(+), 7 deletions(-) diff --git a/src/box/iproto_constants.h b/src/box/iproto_constants.h index f7f46088f..816a308d8 100644 --- a/src/box/iproto_constants.h +++ b/src/box/iproto_constants.h @@ -132,6 +132,18 @@ enum iproto_key { IPROTO_REPLICA_ANON = 0x50, IPROTO_ID_FILTER = 0x51, IPROTO_ERROR = 0x52, + /** + * Term. Has the same meaning as IPROTO_RAFT_TERM, but is an iproto + * key, rather than a raft key. Used for PROMOTE request, which needs + * both iproto (e.g. REPLICA_ID) and raft (RAFT_TERM) keys. + */ + IPROTO_TERM = 0x53, + /* + * Be careful to not extend iproto_key values over 0x7f. + * iproto_keys are encoded in msgpack as positive fixnum, which ends at + * 0x7f, and we rely on this in some places by allocating a uint8_t to + * hold a msgpack-encoded key value. + */ IPROTO_KEY_MAX }; @@ -226,6 +238,8 @@ enum iproto_type { IPROTO_TYPE_STAT_MAX, IPROTO_RAFT = 30, + /** PROMOTE request. */ + IPROTO_PROMOTE = 31, /** A confirmation message for synchronous transactions. */ IPROTO_CONFIRM = 40, @@ -344,7 +358,8 @@ dml_request_key_map(uint32_t type) static inline bool iproto_type_is_synchro_request(uint32_t type) { - return type == IPROTO_CONFIRM || type == IPROTO_ROLLBACK; + return type == IPROTO_CONFIRM || type == IPROTO_ROLLBACK || + type == IPROTO_PROMOTE; } static inline bool diff --git a/src/box/xrow.c b/src/box/xrow.c index cc8e43ed4..70ba075f8 100644 --- a/src/box/xrow.c +++ b/src/box/xrow.c @@ -890,11 +890,11 @@ xrow_encode_synchro(struct xrow_header *row, const struct synchro_request *req) { /* - * A map with two elements. We don't compress + * A map with two or three elements. We don't compress * numbers to have this structure constant in size, * which allows us to preallocate it on stack. */ - body->m_body = 0x80 | 2; + body->m_body = 0x80 | (req->type == IPROTO_PROMOTE ? 3 : 2); body->k_replica_id = IPROTO_REPLICA_ID; body->m_replica_id = 0xce; body->v_replica_id = mp_bswap_u32(req->replica_id); @@ -903,10 +903,24 @@ xrow_encode_synchro(struct xrow_header *row, body->v_lsn = mp_bswap_u64(req->lsn); memset(row, 0, sizeof(*row)); - row->type = req->type; - row->body[0].iov_base = (void *)body; - row->body[0].iov_len = sizeof(*body); + + /* Promote body is longer. It has an additional IPROTO_TERM field. */ + if (req->type == IPROTO_PROMOTE) { + struct promote_body_bin *promote_body = + (struct promote_body_bin *)body; + + promote_body->k_term = IPROTO_TERM; + promote_body->m_term = 0xcf; + promote_body->v_term = mp_bswap_u64(req->term); + + row->body[0].iov_base = (void *)promote_body; + row->body[0].iov_len = sizeof(*promote_body); + } else { + row->body[0].iov_base = (void *)body; + row->body[0].iov_len = sizeof(*body); + } + row->bodycnt = 1; } @@ -952,11 +966,17 @@ xrow_decode_synchro(const struct xrow_header *row, struct synchro_request *req) case IPROTO_LSN: req->lsn = mp_decode_uint(&d); break; + case IPROTO_TERM: + req->term = mp_decode_uint(&d); + break; default: mp_next(&d); } } + req->type = row->type; + req->origin_id = row->replica_id; + return 0; } diff --git a/src/box/xrow.h b/src/box/xrow.h index 2a18733c0..af4ad0d12 100644 --- a/src/box/xrow.h +++ b/src/box/xrow.h @@ -226,7 +226,10 @@ xrow_encode_dml(const struct request *request, struct region *region, * pending synchronous transactions. */ struct synchro_request { - /** Operation type - IPROTO_ROLLBACK or IPROTO_CONFIRM. */ + /** + * Operation type - either IPROTO_ROLLBACK or IPROTO_CONFIRM or + * IPROTO_PROMOTE + */ uint32_t type; /** * ID of the instance owning the pending transactions. @@ -236,14 +239,25 @@ struct synchro_request { * finish transactions of an old master. */ uint32_t replica_id; + /** + * Id of the instance which has issued this request. Only filled on + * decoding, and left blank when encoding a request. + */ + uint32_t origin_id; /** * Operation LSN. * In case of CONFIRM it means 'confirm all * transactions with lsn <= this value'. * In case of ROLLBACK it means 'rollback all transactions * with lsn >= this value'. + * In case of PROMOTE it means CONFIRM(lsn) + ROLLBACK(lsn+1) */ int64_t lsn; + /** + * The new term the instance issuing this request is in. Only used for + * PROMOTE request. + */ + uint64_t term; }; /** Synchro request xrow's body in MsgPack format. */ @@ -257,6 +271,14 @@ struct PACKED synchro_body_bin { uint64_t v_lsn; }; +/** PROMOTE request's xrow body in MsgPack format. */ +struct PACKED promote_body_bin { + struct synchro_body_bin base; + uint8_t k_term; + uint8_t m_term; + uint64_t v_term; +}; + /** * Encode synchronous replication request. * @param row xrow header. -- 2.24.3 (Apple Git-128)
next prev parent reply other threads:[~2021-04-11 17:57 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 ` Serge Petrenko via Tarantool-patches [this message] 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 ` [Tarantool-patches] [PATCH 4/9] box: make clear_synchro_queue() write a PROMOTE entry instead of CONFIRM + ROLLBACK Serge Petrenko via Tarantool-patches 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=45386860deded154a47c6a07b0537b88e362aa51.1618163409.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 2/9] xrow: introduce a PROMOTE entry' \ /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