Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Alvaro Herrera
Simon Riggs escribió: > On Fri, 2007-03-02 at 18:37 -0300, Alvaro Herrera wrote: > > Bruce Momjian escribió: > > > Simon Riggs wrote: > > > > CLUSTER does not need changes for HOT, as things stand currently, mainly > > > > because its MVCC behaviour is broken. > > > --

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Simon Riggs
On Fri, 2007-03-02 at 18:37 -0300, Alvaro Herrera wrote: > Bruce Momjian escribió: > > Simon Riggs wrote: > > > CLUSTER does not need changes for HOT, as things stand currently, mainly > > > because its MVCC behaviour is broken. > > > > > > That's oddly disco

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Alvaro Herrera
Bruce Momjian escribió: > Simon Riggs wrote: > > On Thu, 2007-03-01 at 22:35 +0530, Pavan Deolasee wrote: > > > Merlin Moncure wrote: > > > > On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: > > > >> > > > > seems pretty solid except for one possible problem...at one point when > > > > I dr

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Bruce Momjian
Tatsuo Ishii wrote: > Just for curiosity, I would like to ask you why you need to modify > pgbench. pgbench can accept custom SQL scripts... > > P.S. HOT seems to be one of the greatest enhancements since PostgreSQL > was born! Yep, I share your enthusiasm. -- Bruce Momjian <[EMAIL PROTECTED

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Bruce Momjian
Pavan Deolasee wrote: > Zeugswetter Andreas ADI SD wrote: > >>> accounts 157895 (initial size) 49284 (increase) > >>> accounts_pkey 19709 (initial size) 19705 (increase) > >>> > >>> > >> Just to clarify, the relation size and increase is in number > >> of blocks. > > > > The n

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Bruce Momjian
Simon Riggs wrote: > On Thu, 2007-03-01 at 22:35 +0530, Pavan Deolasee wrote: > > Merlin Moncure wrote: > > > On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: > > >> > > > seems pretty solid except for one possible problem...at one point when > > > I dropped then later added the index on 'a

Re: [HACKERS] HOT - preliminary results

2007-03-02 Thread Pavan Deolasee
On 3/2/07, Tatsuo Ishii <[EMAIL PROTECTED]> wrote: Just for curiosity, I would like to ask you why you need to modify pgbench. pgbench can accept custom SQL scripts... Oh yes, there was no real need to modify pgbench. Thanks, Pavan -- EnterpriseDB http://www.enterprisedb.com

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Tatsuo Ishii
Just for curiosity, I would like to ask you why you need to modify pgbench. pgbench can accept custom SQL scripts... P.S. HOT seems to be one of the greatest enhancements since PostgreSQL was born! -- Tatsuo Ishii SRA OSS, Inc. Japan > Hi All, > > Here are some preliminary numbers with the HOT 4

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Pavan Deolasee
Zeugswetter Andreas ADI SD wrote: accounts 157895 (initial size) 49284 (increase) accounts_pkey 19709 (initial size) 19705 (increase) Just to clarify, the relation size and increase is in number of blocks. The numbers are quite impressive :-) Have you removed the select

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Simon Riggs
On Thu, 2007-03-01 at 22:35 +0530, Pavan Deolasee wrote: > Merlin Moncure wrote: > > On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: > >> > > seems pretty solid except for one possible problem...at one point when > > I dropped then later added the index on 'abalance', I got spammed > > 'W

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Pavan Deolasee
Merlin Moncure wrote: > On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: >> > seems pretty solid except for one possible problem...at one point when > I dropped then later added the index on 'abalance', I got spammed > 'WARNING: found a HOT-updated tuple' from psql prompt. Thats intentional.

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Merlin Moncure
On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: Hi All, Here are some preliminary numbers with the HOT 4.0 patch that I sent out earlier today. These are only indicative results and should not be used to judge the performance of HOT in general. I have intentionally used the setup favorabl

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Zeugswetter Andreas ADI SD
> > accounts 157895 (initial size) 49284 (increase) > > accounts_pkey 19709 (initial size) 19705 (increase) > > > > > Just to clarify, the relation size and increase is in number > of blocks. The numbers are quite impressive :-) Have you removed the selects on accounts too

Re: [HACKERS] HOT - preliminary results

2007-03-01 Thread Pavan Deolasee
On 3/1/07, Pavan Deolasee <[EMAIL PROTECTED]> wrote: accounts 157895 (initial size) 49284 (increase) accounts_pkey 19709 (initial size) 19705 (increase) Just to clarify, the relation size and increase is in number of blocks. Thanks, Pavan -- EnterpriseDB http://w

[HACKERS] HOT - preliminary results

2007-03-01 Thread Pavan Deolasee
Hi All, Here are some preliminary numbers with the HOT 4.0 patch that I sent out earlier today. These are only indicative results and should not be used to judge the performance of HOT in general. I have intentionally used the setup favorable to HOT. The goal here is to point out the best usage