>From AMD's suit against Intel. Perhaps relevant to some PG/AMD issues.
"...125. Intel has designed its compiler purposely to degrade performance when
a program
is run on an AMD platform. To achieve this, Intel designed the compiler to
compile code
along several alternate code paths. Some paths
I had a similar experience.
regardless of scaling, etc, I got same results. almost like flags
are not active.
did
pgbench -I template1
and
pgbench -c 10 -t 50 -v -d 1
and played around from there
This is on IBM pSeries, AIX5.3, PG8.0.2
-Original Message-
From: [EMAIL PROTECTED]
Richard,
thanks for info.
"...the RH supplied Postgres binary has issues..."
Would you have the time to provide a bit more info?
Version of PG? Nature of issues? Methods that resolved?
Thanks again,
-- Ross
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Beh
You just couldn't help yourself, could you? :-)
---(end of broadcast)---
TIP 2: you can get off all lists at once with the unregister command
(send "unregister YourEmailAddressHere" to [EMAIL PROTECTED])
,
Ross Mohan
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]] On Behalf Of Mohan, Ross
Sent: Wednesday, May 25, 2005 1:11 PM
To: [EMAIL PROTECTED]
Subject: Re: [PORTS] Which library has these symbols?
Tom,
they're all over the place, repeated in different
libra
kSQL. )
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Chris Browne
Sent: Tuesday, May 10, 2005 4:14 PM
To: pgsql-performance@postgresql.org
Subject: Re: [PERFORM] Prefetch - OffTopic
[EMAIL PROTECTED] ("Mohan, Ross") writes:
> for time-serie
for time-series and "insane fast", nothing beats kdB, I believe
www.kx.com
Not trying to Quisling-out PG here, just hoping to respond to Mr. Olson
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Tom Lane
Sent: Tuesday, May 10, 2005 2:54 PM
To: Gr
Maybe he needs to spend $7K on performance improvements?
;-)
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Josh Berkus
Sent: Tuesday, April 26, 2005 8:00 PM
To: Richard Huxton
Cc: [EMAIL PROTECTED]; pgsql-performance@postgresql.org
Subject: Re: [PERF
verSidePrepare=0"
|| that's about all I can see, prima facie. I'll be very curious to know if
ODBC is
any part of your performance equation.
HTH,
Ross
-Original Message-
From: Joel Fradkin [mailto:[EMAIL PROTECTED]
Sent: Thursday, April 21, 2005 10:54 AM
To: Moh
FWIW, ODBC has variables to tweak, as well. fetch/buffer sizes, and the like.
Maybe one of the ODBC cognoscenti here can chime in more concretely
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Joel Fradkin
Sent: Thursday, April 21, 2005 10:36 AM
T
/19/05, Jim C. Nasby <[EMAIL PROTECTED]> wrote:
> On Mon, Apr 18, 2005 at 06:41:37PM -, Mohan, Ross wrote:
> > Don't you think "optimal stripe width" would be
> > a good question to research the binaries for? I'd
> > think that drives the answer,
PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Dawid Kuroczko
Sent: Wednesday, April 20, 2005 4:56 AM
To: pgsql-performance@postgresql.org
Subject: Re: [PERFORM] How to improve db performance with $7K?
On 4/19/05, Mohan, Ross <[EMAIL PROTECTED]> wrote:
> Clustered file systems is the
TED]
Sent: Tuesday, April 19, 2005 8:12 PM
To: Mohan, Ross
Cc: pgsql-performance@postgresql.org
Subject: Re: [PERFORM] How to improve db performance with $7K?
On Mon, Apr 18, 2005 at 06:41:37PM -0000, Mohan, Ross wrote:
> Don't you think "optimal stripe width" would be
> a good qu
uests from multiple hosts
can be queued.
-Original Message-
From: Bruce Momjian [mailto:[EMAIL PROTECTED]
Sent: Tuesday, April 19, 2005 12:16 PM
To: Mohan, Ross
Cc: pgsql-performance@postgresql.org
Subject: Re: [PERFORM] How to improve db performance with $7K?
Mohan, Ross wrote:
&
Clustered file systems is the first/best example that
comes to mind. Host A and Host B can both request from diskfarm, eg.
-Original Message-
From: Bruce Momjian [mailto:[EMAIL PROTECTED]
Sent: Tuesday, April 19, 2005 12:10 PM
To: Mohan, Ross
Cc: pgsql-performance@postgresql.org
Good question. If the SCSI system was moving the head from track 1 to 10, and
a request then came in for track 5, could the system make the head stop at
track 5 on its way to track 10? That is something that only the controller
could do. However, I have no idea if SCSI does that.
|| SCSI, A
Don't you think "optimal stripe width" would be
a good question to research the binaries for? I'd
think that drives the answer, largely. (uh oh, pun alert)
EG, oracle issues IO requests (this may have changed _just_
recently) in 64KB chunks, regardless of what you ask for.
So when I did my stri
Greg, et al.
I never found any evidence of a "stop and get an intermediate request"
functionality in the TCQ protocol.
IIRC, what is there is
1) Ordered
2) Head First
3) Simple
implemented as choices. *VERY* roughly, that'd be like
(1) disk subsystem satisfies requests as submitted, (2) let's
Sorry to blend threads, but in my kinda longish, somewhat thankless,
essentially anonymous, and quite average career as a dba, I have
found that the 7K would be best spent on a definitive end-to-end
"application critical path" test (pretty easy to instrument apps
and lash on test harnesses these
I've been doing some reading up on this, trying to keep up here,
and have found out that (experts, just yawn and cover your ears)
1) some SATA drives (just type II, I think?) have a "Phase Zero"
implementation of Tagged Command Queueing (the special sauce
for SCSI).
2) This SATA "TCQ" is
sorry, don't remember whether it's SCSI or SATA II, but IIRC
the Areca controllers are just stellar for things.
If you do get SATA for db stuff..especially multiuser...i still
haven't seen anything to indicate an across-the-board primacy
for SATA over SCSI. I'd go w/SCSI, or if SATA for $$$ reaso
Imagine a system in "furious activity" with two (2) process regularly occuring
Process One: Long read (or write). Takes 20ms to do seek, latency, and
stream off. Runs over and over.
Process Two: Single block read ( or write ). Typical database row access.
O
Adam -
Is compiling postmaster with profiling support just a flag
in the build/make? Or is there something more involved?
I'd like to be able to do this in the future and so am
curious about means/methods.
If this is a RTFM, just let me know that (am currently
Reading The F Manual), but if y
giving oracle
yearly.
-Original Message-
From: Rod Taylor [mailto:[EMAIL PROTECTED]
Sent: Wednesday, April 06, 2005 12:41 PM
To: Mohan, Ross
Cc: pgsql-performance@postgresql.org
Subject: Re: RE : RE: [PERFORM] Postgresql vs SQLserver for thisapplication ?
On Wed, 2005-04-06 at 16:12
How close to this is PG's COPY? I get surprisingly good results using COPY
with jdbc on smallish systems (now if that patch would make into the mainstream
PG jdbc support!) I think COPY has a bit more overhead than what a Bulkload
feature may have, but I suspect it's not that much more.
|| S
From: Alex Turner [mailto:[EMAIL PROTECTED]
Sent: Wednesday, April 06, 2005 11:38 AM
To: [EMAIL PROTECTED]
Cc: pgsql-performance@postgresql.org; Mohan, Ross
Subject: Re: RE : RE: [PERFORM] Postgresql vs SQLserver for this application ?
I think everyone was scared off by the 5000 inserts per seco
ading recommendations
[EMAIL PROTECTED] wrote:
>>Mohan, Ross wrote:
>>
>>>VOIP over BitTorrent?
>>
>>Now *that* I want to see. Aught to be at least as interesting as the
>>"TCP/IP over carrier pigeon" experiment - and more challenging to
>>boot!
cellmates in Camp
X-Ray,
and watching pigeons fly overhead.
-Original Message-
From: Steve Wampler [mailto:[EMAIL PROTECTED]
Sent: Wednesday, March 30, 2005 11:52 AM
To: Mohan, Ross
Cc: pgsql-performance@postgresql.org
Subject: Re: [PERFORM] Reading recommendations
Mohan, Ross wrote
VOIP over BitTorrent?
;-)
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
Sent: Wednesday, March 30, 2005 11:27 AM
To: Michael Fuhr
Cc: Marc Burgauer; pgsql-performance@postgresql.org; [EMAIL PROTECTED]
Subject: Re: [PERFORM] Reading
29 matches
Mail list logo
