Tarantool development patches archive
 help / color / mirror / Atom feed
From: Vladimir Davydov <vdavydov.dev@gmail.com>
To: Konstantin Osipov <kostja@tarantool.org>
Cc: tarantool-patches@freelists.org
Subject: Re: [tarantool-patches] Re: [PATCH 03/10] vinyl: move vylog recovery to vylog thread
Date: Mon, 10 Jun 2019 18:24:50 +0300	[thread overview]
Message-ID: <20190610152450.etzc4ynus3yvmmno@esperanza> (raw)
In-Reply-To: <20190607133954.GB31327@atlas>

On Fri, Jun 07, 2019 at 04:39:54PM +0300, Konstantin Osipov wrote:
> * Vladimir Davydov <vdavydov.dev@gmail.com> [19/06/06 13:24]:
> > > > We used coio, because vylog was written from a WAL thread, which
> > > > shouldn't be used for such a heavy operation as vylog recovery.
> > > > Now, we can move it to the dedicated vylog thread. This allows
> > > > us to simplify rotation logic as well: now most of work is done
> > > > from the same function (vy_log_rotate_f) executed by vylog thread,
> > > > not scattered between coio and WAL, as it used to be.
> > > 
> > > Why do we need to lock out the scheduler while rotating the log in
> > > the first place? 
> > 
> > We rotate vylog by first reading the old vylog and forming a recovery
> > context, then dumping this recovery context to the new vylog. If a new
> > record appears in the old vylog in between, it will be missing in the
> > new vylog. That's why we lock out writers.
> 
> We have two layers of abstractions intermixed here. During
> snapshotting, when we really rotate the vylog, no DDL can happen,
> it's locked out. So no one can take the problematic latch
> anyway.

Except compaction, which isn't locked out by checkpointing.

> So there is, strictly speaking, no problem at all. But
> since we're using a low level latch, and not a centralized
> mechanism to lock out writers, we wouldn't know.
> 
> One option could be to append the writes to vylog which happen
> during checkpointing to the vylog buffer, and not flush them to
> the vylog file which is about-to-become-obsolete.

We must flush those records to disk, otherwise we risk loosing data.

> 
> Anyway, I keep thinking that if you want to kill a latch, there is
> a dozen of ways of killing it, not an own thread.

What's so wrong about the new thread? Could you please give some insight
why we should avoid introducing a separate thread for vylog at all costs
at this point?

  reply	other threads:[~2019-06-10 15:24 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-17 14:52 [PATCH 00/10] vinyl: don't yield in DDL on_commit triggers Vladimir Davydov
2019-05-17 14:52 ` [PATCH 01/10] box: zap atfork callback Vladimir Davydov
2019-05-18 18:37   ` [tarantool-patches] " Konstantin Osipov
2019-05-20  8:13     ` Vladimir Davydov
2019-06-01  8:16     ` Konstantin Osipov
2019-06-06 10:04       ` Vladimir Davydov
2019-05-17 14:52 ` [PATCH 02/10] vinyl: add a separate thread for vylog Vladimir Davydov
2019-05-18 18:39   ` [tarantool-patches] " Konstantin Osipov
2019-05-20  8:17     ` Vladimir Davydov
2019-06-01  8:26   ` Konstantin Osipov
2019-06-06 10:20     ` Vladimir Davydov
2019-05-17 14:52 ` [PATCH 03/10] vinyl: move vylog recovery to vylog thread Vladimir Davydov
2019-06-01  8:36   ` [tarantool-patches] " Konstantin Osipov
2019-06-06 10:23     ` Vladimir Davydov
2019-06-07 13:39       ` Konstantin Osipov
2019-06-10 15:24         ` Vladimir Davydov [this message]
2019-06-07 13:40       ` Konstantin Osipov
2019-05-17 14:52 ` [PATCH 04/10] vinyl: rework vylog transaction backlog implementation Vladimir Davydov
2019-06-01  8:38   ` [tarantool-patches] " Konstantin Osipov
2019-06-06 11:58     ` Vladimir Davydov
2019-05-17 14:52 ` [PATCH 05/10] vinyl: don't purge deleted runs from vylog on compaction Vladimir Davydov
2019-05-18 18:47   ` [tarantool-patches] " Konstantin Osipov
2019-05-20  8:27     ` Vladimir Davydov
2019-06-01  8:39   ` Konstantin Osipov
2019-06-06 12:40     ` Vladimir Davydov
2019-05-17 14:52 ` [PATCH 06/10] vinyl: lock out compaction while checkpointing is in progress Vladimir Davydov
2019-05-17 14:52 ` [PATCH 07/10] vinyl: don't access last vylog signature outside vylog implementation Vladimir Davydov
2019-05-17 14:52 ` [PATCH 08/10] vinyl: zap ERRINJ_VY_LOG_FLUSH_DELAY Vladimir Davydov
2019-05-17 14:52 ` [PATCH 09/10] key_def: pass alloc callback to key_def_dump_parts Vladimir Davydov
2019-05-18 18:52   ` [tarantool-patches] " Konstantin Osipov
2019-05-20  8:34     ` Vladimir Davydov
2019-06-01  8:41     ` Konstantin Osipov
2019-06-10 15:28       ` Vladimir Davydov
2019-06-16 14:57         ` Konstantin Osipov
2019-05-17 14:52 ` [PATCH 10/10] vinyl: get rid of the latch protecting vylog buffer Vladimir Davydov
2019-06-01  8:44   ` [tarantool-patches] " Konstantin Osipov
2019-06-06 13:15     ` Vladimir Davydov
2019-05-18 18:35 ` [tarantool-patches] Re: [PATCH 00/10] vinyl: don't yield in DDL on_commit triggers Konstantin Osipov
2019-05-20  8:09   ` Vladimir Davydov
2019-06-01  8:09 ` Konstantin Osipov

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=20190610152450.etzc4ynus3yvmmno@esperanza \
    --to=vdavydov.dev@gmail.com \
    --cc=kostja@tarantool.org \
    --cc=tarantool-patches@freelists.org \
    --subject='Re: [tarantool-patches] Re: [PATCH 03/10] vinyl: move vylog recovery to vylog thread' \
    /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