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