Comments on: 5.0 journal: various issues, replication prefetching, our branch

By: Domas Mituzas

Domas Mituzas — Thu, 12 Jun 2008 10:22:34 +0000

Mats, our in-house builds force -O3 nowadays :)

By: Mats Kindahl

Mats Kindahl — Wed, 11 Jun 2008 18:58:17 +0000

On rereading this again I noted that you’re using -O2. Please consider using -O3, since function inlining (-finline-functions) is not turned on by default for optimization levels below 3, and that flag is a big win most of the time. Of course, you can also add that flag explicitly.

By: Mats Kindahl

Mats Kindahl — Mon, 09 Jun 2008 07:10:31 +0000

Regarding the rewrite of UPDATE to SELECT (a.k.a., the oracle algorithm presented by Paul Tuckfield). I actually have a feature clone involving adding scripting support to the replication threads, so that the oracle algorithm can be written in something like 20 lines of Lua.

We are in the middle of setting replication interfaces for Marc’s and Wei’s semi-sync patch, so once that is done, I can adapt the feature clone to use that interface instead.

By: Domas Mituzas

Domas Mituzas — Sun, 08 Jun 2008 20:42:31 +0000

Baron, patch was linked by the post, here it is as a plain url: http://dammit.lt/snippets/quick-mkprefetch-hack.txt ;-)

By: Baron

Baron — Sun, 08 Jun 2008 20:21:09 +0000

Please, share the hack to parallelize mk-slave-prefetch. Attached as a patch to a bugreport would be great.

I agree with you on the problems with only one index, etc etc — in specific cases, this may be possible to solve, but in general is impossible to solve outside the server IMO.

By: Domas Mituzas

Domas Mituzas — Sat, 07 Jun 2008 15:42:01 +0000

Yeah, log_sys->mutex shows up a lot, though now I seem still to hit bufpool giant mutex.

By: Mark Callaghan

Mark Callaghan — Sat, 07 Jun 2008 15:38:18 +0000

There is mutex contention on the InnoDB tx log mutex (log_sys->mutex) that limits SMP speedup for tests such as your (reloading a database). We don’t have a patch for it yet.

By: Alejandro Sánchez Marín

Alejandro Sánchez Marín — Sat, 07 Jun 2008 09:43:25 +0000

Great, i learn more with your blog than reading 10^2 fucked manuals of mysql.

And the most important, i can see all data benchmark to get a real aproximation to know how mysql runs and his limits.

Thanks a lot for this post and for your blog ;-D