>-----Original Message----- >From: AJG [mailto:ay...@gera.co.nz] >Sent: Wednesday, June 27, 2018 3:21 AM >To: pgsql-hack...@postgresql.org >Subject: Re: Global shared meta cache > >Ideriha, Takeshi wrote >> 2) benchmarked 3 times for each conditions and got the average result >> of TPS. >> |master branch | prototype | >> proto/master (%) >> >> ------------------------------------------------------------------------------------ >> pgbench -c48 -T60 -Msimple -S | 131297 |130541 |101% >> pgbench -c48 -T60 -Msimple | 4956 |4965 |95% >> pgbench -c48 -T60 -Mprepared -S |129688 |132538 |97% >> pgbench -c48 -T60 -Mprepared |5113 |4615 |84% >> >> >> 001_global_meta_cache.patch (6K) >> <http://www.postgresql-archive.org/attachment/6026686/0/001_global_ >> meta_cache.patch> > > >Hello, >Apologies for question. I thought I would just double check percentages that >have >been presented. >Is the percentage calculation correct? >as #1 and #3 look inverted to me (say lower when should be higher and vice >versa), >and >#2 and #4 look incorrect generally (percentages look much larger than they >should be >based on numbers. > >I.e. Msimple -S the protype had slightly worse tps performance (130541) versus >Master (131297). I would expect the percentage to be e.g. 99% not 101% > >But I may be misunderstanding something :) > >Also, Msimple is 4956 master versus 4965 prototype. Just 9 tps change. A very >slight >improvement in tps. but the percentage provided is 95%. I would expect it to >be just >over 100%? >Again, maybe im not understanding, and hoping it is just my error :) > > > >-- >Sent from: http://www.postgresql-archive.org/PostgreSQL-hackers-f1928748.html > Hi, Thank you for comments and sorry for late replay. Thanks to you, I noticed I made a mistake. As you pointed out, I think my calculation is wrong.
I also need to change some settings of postgresql.conf and pgbench. So I'm going to measure performance again and submit the result. Regards, Takeshi Ideriha