Re: GIN improvements part2: fast scan - Mailing list pgsql-hackers

From Rod Taylor
Subject Re: GIN improvements part2: fast scan
Date
Msg-id CAKddOFDMUn+b+LgAHYGGLTAwuN1Y6U_e1O65m3RF64tVf+qsNw@mail.gmail.com
Whole thread Raw
In response to Re: GIN improvements part2: fast scan  (Alexander Korotkov <aekorotkov@gmail.com>)
List pgsql-hackers



On Fri, Nov 15, 2013 at 2:42 PM, Alexander Korotkov <aekorotkov@gmail.com> wrote:
On Fri, Nov 15, 2013 at 11:39 PM, Rod Taylor <rod.taylor@gmail.com> wrote:

The patched index is 58% of the 9.4 master size. 212 MB instead of 365 MB.

Good. That's meet my expectations :)
You mention that both master and patched versions was compiled with debug. Was cassert enabled?

Just debug. I try not to do performance tests with assertions on.

Patch 7 gives the results I was looking for on this small sampling of data.


gin-fast-scan.6.patch/9.4 master performance
=================
the:              1147.413 ms 1159.360 ms  1122.549 ms
and:              1035.540 ms  999.514 ms  1003.042 ms
hotel:              57.670 ms   61.152 ms    58.862 ms
and & the & hotel: 266.121 ms  256.711 ms   267.011 ms
hotel & and & the: 260.213 ms  254.055 ms   255.611 ms


gin-fast-scan.7.patch
=================
the:              1091.735 ms 1068.909 ms  1076.474 ms
and:               985.690 ms  972.833 ms   948.286 ms
hotel:              60.756 ms   59.028 ms    57.836 ms
and & the & hotel:  50.391 ms   38.715 ms    46.168 ms
hotel & and & the:  45.395 ms   40.880 ms    43.978 ms

Thanks,

Rod
 

pgsql-hackers by date:

Previous
From: Peter Geoghegan
Date:
Subject: Re: INSERT...ON DUPLICATE KEY LOCK FOR UPDATE
Next
From: David Johnston
Date:
Subject: Re: Suggestion: Issue warning when calling SET TRANSACTION outside transaction block