Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-08-15 Thread Bruce Momjian
This has been saved for the 8.2 release: http://momjian.postgresql.org/cgi-bin/pgpatches_hold --- Hiroki Kataoka wrote: > Hi all, > > This small patch improves the performance of INSERT and UPDATE. By my > machin

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-08-15 Thread Hiroki Kataoka
Tom Lane wrote: I've been testing this patch a bit, and I'm unable to measure any consistent improvement in pgbench times (sometimes it seems to win, and some other times it doesn't). And gprof still swears up and down that PageAddItem is only about 0.1% of the runtime, which would make it impos

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-08-13 Thread Stefan Kaltenbrunner
Tom Lane wrote: > Hiroki Kataoka <[EMAIL PROTECTED]> writes: > This small patch improves the performance of INSERT and UPDATE. By my machine, these changes raised the performance about 5%~10% in pgbench. >>> >>>BTW, in profiling the backend I've never seen PageAddItem take more than >>>ab

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-08-13 Thread Tom Lane
Hiroki Kataoka <[EMAIL PROTECTED]> writes: >>> This small patch improves the performance of INSERT and UPDATE. By my >>> machine, these changes raised the performance about 5%~10% in pgbench. >> >> BTW, in profiling the backend I've never seen PageAddItem take more than >> about 1% of the runtime

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-17 Thread Hiroki Kataoka
Tom Lane wrote: This small patch improves the performance of INSERT and UPDATE. By my machine, these changes raised the performance about 5%~10% in pgbench. BTW, in profiling the backend I've never seen PageAddItem take more than about 1% of the runtime, and in pgbench in particular it seems t

[HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-17 Thread Hiroki Kataoka
Hi all, This small patch improves the performance of INSERT and UPDATE. By my machine, these changes raised the performance about 5%~10% in pgbench. Please take a benchmark in a reliable environment. Since I may forget some required changes, I specify that this patch is experimental. But n

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-17 Thread Hiroki Kataoka
Tom Lane wrote: > Hiroki Kataoka <[EMAIL PROTECTED]> writes: > >>This small patch improves the performance of INSERT and UPDATE. By my >>machine, these changes raised the performance about 5%~10% in pgbench. > > Wouldn't it be a lot less invasive to search down from the end, instead > of changin

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-16 Thread Tom Lane
Hiroki Kataoka <[EMAIL PROTECTED]> writes: > This small patch improves the performance of INSERT and UPDATE. By my > machine, these changes raised the performance about 5%~10% in pgbench. BTW, in profiling the backend I've never seen PageAddItem take more than about 1% of the runtime, and in pgbe

Re: [HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-16 Thread Tom Lane
Hiroki Kataoka <[EMAIL PROTECTED]> writes: > This small patch improves the performance of INSERT and UPDATE. By my > machine, these changes raised the performance about 5%~10% in pgbench. Wouldn't it be a lot less invasive to search down from the end, instead of changing the page header format?

[HACKERS] Changes improve the performance of INSERT and UPDATE

2005-07-16 Thread Hiroki Kataoka
Hi all, This small patch improves the performance of INSERT and UPDATE. By my machine, these changes raised the performance about 5%~10% in pgbench. Please take a benchmark in a reliable environment. Since I may forget some required changes, I specify that this patch is experimental. But note