Re: [Maria-developers] 8a0f331: MDEV-7943 - pthread_getspecific() takes 0.76% in OLTP RO

2015-05-13 Thread Sergey Vojtovich
Hi Sergei, On Fri, May 08, 2015 at 06:52:19PM +0200, Sergei Golubchik wrote: > Hi, Sergey! > > On Apr 22, s...@mariadb.org wrote: > > revision-id: 8a0f3310275f7b4fa445f907140f677910e18999 > > parent(s): 7feee74dd30c96bd50d1c90e4ce3b06a656b17a5 > > committer: Sergey Vojtovich > > branch nick: mari

Re: [Maria-developers] Step#4: MDEV-7950 Item_func::type() takes 0.26% in OLTP RO

2015-05-13 Thread Alexander Barkov
Hi Sergey, I'm sending a new version, which takes into account your review suggestions and our skype discussion. Thanks. On 05/08/2015 12:27 PM, Sergey Vojtovich wrote: Hi Alexander, following profiler reports for build_equal_items* in your and mine patches. For OLTP RO they're equal. I gues

Re: [Maria-developers] Step#4: MDEV-7950 Item_func::type() takes 0.26% in OLTP RO

2015-05-13 Thread Sergey Vojtovich
Hi Alexander, ok to push. Thanks, Sergey On Wed, May 13, 2015 at 02:22:22PM +0400, Alexander Barkov wrote: > Hi Sergey, > > I'm sending a new version, which takes into account your review > suggestions and our skype discussion. > > Thanks. > > On 05/08/2015 12:27 PM, Sergey Vojtovich wrote:

Re: [Maria-developers] 8a0f331: MDEV-7943 - pthread_getspecific() takes 0.76% in OLTP RO

2015-05-13 Thread Sergei Golubchik
Hi, Sergey! On May 13, Sergey Vojtovich wrote: > > > > > > -while (is_on() && !thd_killed(NULL)) > > > +while (is_on() && !thd_killed(current_thd)) > > > > thd_killed() is a function of the kill_statement service > > (see include/mysql/service_kill_statement.h). It is created for plugin

Re: [Maria-developers] 8a0f331: MDEV-7943 - pthread_getspecific() takes 0.76% in OLTP RO

2015-05-13 Thread Sergey Vojtovich
Hi Sergei, On Wed, May 13, 2015 at 05:25:21PM +0200, Sergei Golubchik wrote: > Hi, Sergey! > > On May 13, Sergey Vojtovich wrote: > > > > > > > > -while (is_on() && !thd_killed(NULL)) > > > > +while (is_on() && !thd_killed(current_thd)) > > > > > > thd_killed() is a function of the kil

Re: [Maria-developers] 8a0f331: MDEV-7943 - pthread_getspecific() takes 0.76% in OLTP RO

2015-05-13 Thread Sergei Golubchik
Hi, Sergey! On May 13, Sergey Vojtovich wrote: > > > > But if you'll require thd_killed() always to take THD as an argument, > > then other plugins (that work strictly within plugin api limits) > > won't be able to check killed flag in places where THD isn't available. > > May be it's not a probl