Re: Parallel bitmap heap scan

Robert Haas <robertmhaas@gmail.com>

From: Robert Haas <robertmhaas@gmail.com>

To: Andres Freund <andres@anarazel.de>

Cc: Dilip Kumar <dilipbalaut@gmail.com>, Haribabu Kommi <kommi.haribabu@gmail.com>, Rafia Sabih <rafia.sabih@enterprisedb.com>, tushar <tushar.ahuja@enterprisedb.com>, Amit Khandekar <amitdkhan.pg@gmail.com>, Amit Kapila <amit.kapila16@gmail.com>, pgsql-hackers <pgsql-hackers@postgresql.org>

Date: 2017-02-07T21:36:55Z

Lists: pgsql-hackers

Attachments

rework-simplehash-allocator.patch (application/octet-stream) patch

On Tue, Feb 7, 2017 at 4:15 PM, Andres Freund <andres@anarazel.de> wrote:
> FWIW, I think it'd have been better to not add the new callbacks as
> parameters to *_create(), but rather have them be "templatized" like the
> rest of simplehash.  That'd require that callback to check the context,
> to know whether it should use shared memory or not, but that seems fine
> to me.  Right now this pushes the head of simplehash above a
> cacheline...

Something like the attached?

-- 
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company

Commits

Pass DSA_ALLOC_HUGE when allocating a shared TIDBitmap.
- a171f01501e1 10.0 landed
Support parallel bitmap heap scans.
- f35742ccb7aa 10.0 landed
tidbitmap: Support shared iteration.
- 98e6e89040a0 10.0 landed
Shut down Gather's children before shutting down Gather itself.
- acf555bc53ac 10.0 landed
Revise the way the element allocator for a simplehash is specified.
- c3c4f6e1740b 10.0 cited
Refactor bitmap heap scan estimation of heap pages fetched.
- da08a6598973 10.0 landed
Use more efficient hashtable for tidbitmap.c to speed up bitmap scans.
- 75ae538bc316 10.0 cited