From: Vladimir Davydov <vdavydov.dev@gmail.com> To: Konstantin Osipov <kostja@tarantool.org> Cc: tarantool-patches@freelists.org Subject: Re: [PATCH v2 5/7] Introduce _vinyl_deferred_delete system space Date: Wed, 22 Aug 2018 20:04:59 +0300 [thread overview] Message-ID: <20180822170459.o5mqviz2e3n43q37@esperanza> (raw) In-Reply-To: <20180821154252.GE28159@chai> On Tue, Aug 21, 2018 at 06:42:52PM +0300, Konstantin Osipov wrote: > * Vladimir Davydov <vdavydov.dev@gmail.com> [18/08/21 15:19]: > > + /* > > + * _vinyl_deferred_delete - blackhole that is needed > > + * for writing deferred DELETE statements generated by > > + * vinyl compaction tasks to WAL. > > + */ > > Please expand this comment to explain why we can't create this > space purely from Lua or upgrade script: > > There is an intricate ordering dependency between creating of this > system space, recovery, and engine initialization, when we set an > on_replace trigger on the space. To resolve this dependency, we > create a space stub at schema_init(), then set a trigger in > engine_init(), which is called next, and then "alter" the space to > its final form in recovery(), which is called next. Done: diff --git a/src/box/schema.cc b/src/box/schema.cc index 32669c69..dd5896c5 100644 --- a/src/box/schema.cc +++ b/src/box/schema.cc @@ -357,6 +357,15 @@ schema_init() * _vinyl_deferred_delete - blackhole that is needed * for writing deferred DELETE statements generated by * vinyl compaction tasks to WAL. + * + * There is an intricate ordering dependency between + * recovery of this system space and initialization of + * the vinyl engine, when we set an on_replace trigger + * on the space. To resolve this dependency, we create + * a space stub in schema_init(), then set a trigger in + * engine_begin_initial_recovery(), which is called next, + * then recover WAL rows, executing the trigger for each + * of them. */ { const char *engine = "blackhole";
next prev parent reply other threads:[~2018-08-22 17:04 UTC|newest] Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-08-21 11:15 [PATCH v2 0/7] vinyl: eliminate disk read on REPLACE/DELETE Vladimir Davydov 2018-08-21 11:15 ` [PATCH v2 1/7] vinyl: do not store meta in secondary index runs Vladimir Davydov 2018-08-21 15:08 ` Konstantin Osipov 2018-08-21 11:15 ` [PATCH v2 2/7] vinyl: teach write iterator to return overwritten tuples Vladimir Davydov 2018-08-21 15:14 ` Konstantin Osipov 2018-08-21 15:37 ` Vladimir Davydov 2018-08-21 11:15 ` [PATCH v2 3/7] vinyl: prepare write iterator heap comparator for deferred DELETEs Vladimir Davydov 2018-08-21 15:38 ` Konstantin Osipov 2018-08-21 11:15 ` [PATCH v2 4/7] vinyl: allow to skip certain statements on read Vladimir Davydov 2018-08-21 15:39 ` Konstantin Osipov 2018-08-21 11:15 ` [PATCH v2 5/7] Introduce _vinyl_deferred_delete system space Vladimir Davydov 2018-08-21 15:42 ` Konstantin Osipov 2018-08-22 17:04 ` Vladimir Davydov [this message] 2018-08-21 11:15 ` [PATCH v2 6/7] vinyl: zap vy_mem::min_lsn and rename max_lsn to dump_lsn Vladimir Davydov 2018-08-21 15:44 ` Konstantin Osipov 2018-08-22 13:00 ` Vladimir Davydov 2018-08-21 11:15 ` [PATCH v2 7/7] vinyl: eliminate disk read on REPLACE/DELETE Vladimir Davydov 2018-08-21 16:13 ` Konstantin Osipov 2018-08-22 17:08 ` Vladimir Davydov 2018-08-22 17:50 ` [PATCH v2 0/7] " Vladimir Davydov
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=20180822170459.o5mqviz2e3n43q37@esperanza \ --to=vdavydov.dev@gmail.com \ --cc=kostja@tarantool.org \ --cc=tarantool-patches@freelists.org \ --subject='Re: [PATCH v2 5/7] Introduce _vinyl_deferred_delete system space' \ /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