Sorry for the delay in responding. I had familial obligations.
As a matter of fact, I am spending a decent amount of time on
this. I don't usually pore through documentation for compilers and
OS's to the degree I've been since this thread started. Nor do I
usually try and get access to the
Alexander Staubo wrote:
On Dec 15, 2006, at 17:53 , Ron wrote:
At 09:50 AM 12/15/2006, Greg Smith wrote:
On Fri, 15 Dec 2006, Merlin Moncure wrote:
The slower is probably due to the unroll loops switch which can
actually hurt code due to the larger footprint (less cache coherency).
At 07:06 PM 12/15/2006, Michael Stone wrote:
On Fri, Dec 15, 2006 at 12:24:46PM -0500, Ron wrote:
ATM, the most we can say is that in a number of systems with modest
physical IO subsystems
So I reran it on a 3.2GHz xeon with 6G RAM off a ramdisk; I/O ain't
the bottleneck on that one.
On Sat, Dec 16, 2006 at 10:53:21AM -0500, Ron wrote:
AFAICT, no one has stated there would be a blow-your-socks-off
dramatic performance improvement for pg due to compilation
options. Just that there might be some, and there might be some that
are arch specific.
FWIW, the original claim
On Sat, Dec 16, 2006 at 10:53:21AM -0500, Ron wrote:
The most important gain IMO is Knowledge, and I'd say there is
still more to learn and/or verify IMHO. YMMV.
Well, I think there are other areas where I can spend my time where
potential gains are more likely. YMMV (although, I note, you
On Dec 15, 2006, at 04:09 , Ron wrote:
At 07:27 PM 12/14/2006, Alexander Staubo wrote:
Sorry, I neglected to include the pertinent graph:
http://purefiction.net/paste/pgbench2.pdf
In fact, your graph suggests that using arch specific options in
addition to -O3 actually =hurts=
On Fri, Dec 15, 2006 at 10:53:25AM +0100, Alexander Staubo wrote:
The difference is very slight. I'm going to run without -funroll-
loops and -pipe (which are not arch-related) to get better data.
-pipe does not matter for the generated code; it only affects compiler speed.
(It simply means
At 04:54 AM 12/15/2006, Alexander Staubo wrote:
On Dec 15, 2006, at 04:09 , Ron wrote:
At 07:27 PM 12/14/2006, Alexander Staubo wrote:
Sorry, I neglected to include the pertinent graph:
http://purefiction.net/paste/pgbench2.pdf
In fact, your graph suggests that using arch specific options
On 12/15/06, Ron [EMAIL PROTECTED] wrote:
I'm looking more closely into exactly what the various gcc -O
optimizations do on Kx's as well.
64b vs 32b gets x86 compatible code access to ~ 2x as many registers;
and MMX or SSE instructions get you access to not only more
registers, but wider ones as
On Fri, 15 Dec 2006, Merlin Moncure wrote:
The slower is probably due to the unroll loops switch which can
actually hurt code due to the larger footprint (less cache coherency).
The cache issues are so important with current processors that I'd suggest
throwing -Os (optimize for size) into
At 09:23 AM 12/15/2006, Merlin Moncure wrote:
On 12/15/06, Ron [EMAIL PROTECTED] wrote:
It seems unusual that code generation options which give access to
more registers would ever result in slower code...
The slower is probably due to the unroll loops switch which can
actually hurt code
On 12/15/06, Ron [EMAIL PROTECTED] wrote:
At 09:23 AM 12/15/2006, Merlin Moncure wrote:
On 12/15/06, Ron [EMAIL PROTECTED] wrote:
It seems unusual that code generation options which give access to
more registers would ever result in slower code...
The slower is probably due to the unroll loops
At 09:50 AM 12/15/2006, Greg Smith wrote:
On Fri, 15 Dec 2006, Merlin Moncure wrote:
The slower is probably due to the unroll loops switch which can
actually hurt code due to the larger footprint (less cache coherency).
The cache issues are so important with current processors that I'd
At 10:55 AM 12/15/2006, Merlin Moncure wrote:
On 12/15/06, Ron [EMAIL PROTECTED] wrote:
There are many instances of x86 compatible code that get
30-40% speedups just because they get access to 16 rather than 8 GPRs
when recompiled for x84-64.
...We benchmarked PostgreSQL internally here and
On Dec 15, 2006, at 17:53 , Ron wrote:
At 09:50 AM 12/15/2006, Greg Smith wrote:
On Fri, 15 Dec 2006, Merlin Moncure wrote:
The slower is probably due to the unroll loops switch which can
actually hurt code due to the larger footprint (less cache
coherency).
The cache issues are so
On Fri, Dec 15, 2006 at 12:24:46PM -0500, Ron wrote:
ATM, the most we can say is that in a number of systems with modest
physical IO subsystems
So I reran it on a 3.2GHz xeon with 6G RAM off a ramdisk; I/O ain't the
bottleneck on that one. Results didn't show didn't show any signficant
On Wed, 13 Dec 2006, Ron wrote:
The slowest results, Michael's, are on the system with what appears to be the
slowest CPU of the bunch; and the ranking of the rest of the results seem to
similarly depend on relative CPU performance. This is not what one would
naively expect when benching a
On Thu, 14 Dec 2006, Tom Lane wrote:
The pgbench app itself becomes the bottleneck at high transaction rates.
Awhile back I rewrote it to improve its ability to issue commands
concurrently, but then desisted from submitting the changes --- if we
change the app like that, future numbers would
On Wed, Dec 13, 2006 at 01:03:04PM -0500, Ron wrote:
What I find interesting is that so far Guido's C2D Mac laptop has
gotten the highest values by far in this set of experiments, and no
one else is even close.
The slowest results, Michael's, are on the system with what appears
to be the
At 10:00 AM 12/14/2006, Greg Smith wrote:
On Wed, 13 Dec 2006, Ron wrote:
The slowest results, Michael's, are on the system with what appears
to be the slowest CPU of the bunch; and the ranking of the rest of
the results seem to similarly depend on relative CPU
performance. This is not what
Tom Lane wrote:
Joshua D. Drake [EMAIL PROTECTED] writes:
On Wed, 2006-12-13 at 18:36 -0800, Josh Berkus wrote:
Mostly, though, pgbench just gives the I/O system a workout. It's not a
really good general workload.
It also will not utilize all cpus on a many cpu machine. We recently
found
On Dec 14, 2006, at 16:00 , Greg Smith wrote:
On Wed, 13 Dec 2006, Ron wrote:
The slowest results, Michael's, are on the system with what
appears to be the slowest CPU of the bunch; and the ranking of the
rest of the results seem to similarly depend on relative CPU
performance. This is
Alexander, Good stuff.
Can you do runs with just CFLAGS=-O3 and just CFLAGS=-msse2
-mfpmath=sse -funroll-loops -m64 - march=opteron -pipe as well ?
As it is, you've given a good lower and upper bound on your
performance obtainable using compiler options, but you've given no
data to show
On Dec 14, 2006, at 20:28 , Ron wrote:
Can you do runs with just CFLAGS=-O3 and just CFLAGS=-msse2 -
mfpmath=sse -funroll-loops -m64 - march=opteron -pipe as well ?
All right. From my perspective, the effect of -O3 is significant,
whereas architecture-related optimizations have no
At 05:39 PM 12/14/2006, Alexander Staubo wrote:
On Dec 14, 2006, at 20:28 , Ron wrote:
Can you do runs with just CFLAGS=-O3 and just CFLAGS=-msse2 -
mfpmath=sse -funroll-loops -m64 - march=opteron -pipe as well ?
All right. From my perspective, the effect of -O3 is significant,
whereas
On Dec 15, 2006, at 01:16 , Ron wrote:
At 05:39 PM 12/14/2006, Alexander Staubo wrote:
On Dec 14, 2006, at 20:28 , Ron wrote:
Can you do runs with just CFLAGS=-O3 and just CFLAGS=-msse2 -
mfpmath=sse -funroll-loops -m64 - march=opteron -pipe as well ?
All right. From my perspective, the
At 07:27 PM 12/14/2006, Alexander Staubo wrote:
Sorry, I neglected to include the pertinent graph:
http://purefiction.net/paste/pgbench2.pdf
In fact, your graph suggests that using arch specific options in
addition to -O3 actually =hurts= performance.
...that seems unexpected...
Ron
On Thu, 14 Dec 2006, Alexander Staubo wrote:
Interestingly enough I see that PostgreSQL seems to be writing around 1MB/s
during the pgbench run, even though I'm running pgbench in the -S mode. I
haven't had the chance to look at the source yet; is it really only doing
selects?
I've noticed
Hi,
Did someone try '-mfpmath=sse -msse3'?
Would be interesting to know if -mfpmath=sse boost the performance.
I guess, the difference in the generated code isn't that much between
i686 and prescott. The bigger step is i386 to i686. '-mfpmath=sse
-msse3' will also use the SSE unit, which the
Michael Stone wrote:
On Tue, Dec 12, 2006 at 01:42:06PM +0100, Cosimo Streppone wrote:
-O0 ~ 957 tps
-O1 -mcpu=pentium4 -mtune=pentium4 ~ 1186 tps
-O2 -mcpu=pentium4 -mtune=pentium4 ~ 1229 tps
-O3 -mcpu=pentium4 -mtune=pentium4 ~ 1257 tps
-O6 -mcpu=pentium4 -mtune=pentium4 ~ 1254 tps
I'm
At 11:11 AM 12/13/2006, Cosimo Streppone wrote:
Interesting, eh?
Cosimo
What I find interesting is that so far Guido's C2D Mac laptop has
gotten the highest values by far in this set of experiments, and no
one else is even close.
The slowest results, Michael's, are on the system with what
What I find interesting is that so far Guido's C2D Mac laptop has
gotten the highest values by far in this set of experiments, and no
one else is even close.
The slowest results, Michael's, are on the system with what appears
to be the slowest CPU of the bunch; and the ranking of the rest of
At 01:49 PM 12/13/2006, Bucky Jordan wrote:
I've only seen pg_bench numbers 2,000 tps on either really large
hardware (none of the above mentioned comes close) or the results
are in memory due to a small database size (aka measuring update contention).
Which makes a laptop achieving such
On 13.12.2006, at 19:03, Ron wrote:
What I find interesting is that so far Guido's C2D Mac laptop has
gotten the highest values by far in this set of experiments, and no
one else is even close.
This might be the case because I have tested with fsync=off as my
internal harddrive would be
Tom Lane wrote:
Alvaro Herrera [EMAIL PROTECTED] writes:
While skimming over the pgbench source it has looked to me like it's
necessary to pass the -s switch (scale factor) to both the
initialization (-i) and the subsequent (non -i) runs.
No, it's not supposed to be, and I've never found
[offtopic];
hmm quite a long thread below is stats of posting
Total Messages:87Total Participants: 27
-
19 Daniel van Ham Colchete
12 Michael Stone
9 Ron
5 Steinar H. Gunderson
5 Alexander Staubo
4 Tom Lane
4
Bruce,
pgbench is designed to be a general benchmark, meanining it exercises
all parts of the system. I am thinking just reexecuting a single SELECT
over and over again would be a better test of the CPU optimizations.
Mostly, though, pgbench just gives the I/O system a workout. It's not a
On Wed, 2006-12-13 at 18:36 -0800, Josh Berkus wrote:
Bruce,
pgbench is designed to be a general benchmark, meanining it exercises
all parts of the system. I am thinking just reexecuting a single SELECT
over and over again would be a better test of the CPU optimizations.
Mostly,
Joshua D. Drake [EMAIL PROTECTED] writes:
On Wed, 2006-12-13 at 18:36 -0800, Josh Berkus wrote:
Mostly, though, pgbench just gives the I/O system a workout. It's not a
really good general workload.
It also will not utilize all cpus on a many cpu machine. We recently
found that the only way
On Dec 14, 2006, at 14:44 , Tom Lane wrote:
The pgbench app itself becomes the bottleneck at high transaction
rates. Awhile back I rewrote it to improve its ability to issue
commands concurrently, but then desisted from submitting the
changes --- if we change the app like that, future numbers
Benchmarks, like any other SW, need modernizing and updating from time to time.
Given the multi-core CPU approach to higher performance as the
current fad in CPU architecture, we need a benchmark that is appropriate.
If SPEC feels it is appropriate to rev their benchmark suite
regularly, we
; pgsql-performance@postgresql.org; Bruce
Momjian; Alvaro Herrera; Alexander Staubo; Michael Stone
Subject:Re: [PERFORM] New to PostgreSQL, performance considerations
On Dec 14, 2006, at 14:44 , Tom Lane wrote:
The pgbench app itself becomes the bottleneck at high transaction
rates
Mike,
are you using -mtune/-mcpu or -march with GCC?
Witch GCC version? Are you working with a 32bits OS or 64bits?
Daniel
On 12/11/06, Michael Stone [EMAIL PROTECTED] wrote:
Can anyone else reproduce these results? I'm on similar hardware (2.5GHz
P4, 1.5G RAM) and my test results are more
On 12.12.2006, at 02:37, Michael Stone wrote:
Can anyone else reproduce these results? I'm on similar hardware
(2.5GHz P4, 1.5G RAM) and my test results are more like this:
I'm on totally different hardware / software (MacBook Pro 2.33GHz
C2D) and I can't reproduce the tests.
I have
On Dec 11, 2006, at 23:22 , Daniel van Ham Colchete wrote:
I ran this test at a Gentoo test machine I have here. It's a Pentium 4
3.0GHz (I don't know witch P4)
Try cat /proc/cpuinfo.
TESTS RESULTS
==
On a dual-core Opteron 280 with 4G RAM with an LSI PCI-X Fusion-MPT
SAS
On Tue, Dec 12, 2006 at 01:35:04AM -0500, Greg Smith wrote:
These changes could easily explain the magnitude of difference in results
you're seeing, expecially when combined with a 20% greater raw CPU clock.
I'm not interested in comparing the numbers between the systems (which
is obviously
On Tue, Dec 12, 2006 at 07:10:34AM -0200, Daniel van Ham Colchete wrote:
are you using -mtune/-mcpu or -march with GCC?
I used exactly the options you said you used.
Witch GCC version? Are you working with a 32bits OS or 64bits?
3.3.5; 32
Mike Stone
---(end of
On Tue, Dec 12, 2006 at 12:29:29PM +0100, Alexander Staubo wrote:
I suspect the hardware's real maximum performance of the system is
~150 tps, but that the LSI's write cache is buffering the writes. I
would love to validate this hypothesis, but I'm not sure how.
With fsync off? The write
Luke Lonergan wrote:
Can you try this with just -O3 versus -O2?
Thanks to Daniel for doing these tests.
I happen to have done the same tests about 3/4 years ago,
and concluded that gcc flags did *not* influence performance.
Moved by curiosity, I revamped those tests now on a test
machine
On Tue, Dec 12, 2006 at 01:42:06PM +0100, Cosimo Streppone wrote:
-O0 ~ 957 tps
-O1 -mcpu=pentium4 -mtune=pentium4 ~ 1186 tps
-O2 -mcpu=pentium4 -mtune=pentium4 ~ 1229 tps
-O3 -mcpu=pentium4 -mtune=pentium4 ~ 1257 tps
-O6 -mcpu=pentium4 -mtune=pentium4 ~ 1254 tps
For the record, -O3 = -O6
On Tue, Dec 12, 2006 at 01:42:06PM +0100, Cosimo Streppone wrote:
-O0 ~ 957 tps
-O1 -mcpu=pentium4 -mtune=pentium4 ~ 1186 tps
-O2 -mcpu=pentium4 -mtune=pentium4 ~ 1229 tps
-O3 -mcpu=pentium4 -mtune=pentium4 ~ 1257 tps
-O6 -mcpu=pentium4 -mtune=pentium4 ~ 1254 tps
I'm curious now to get the same
On Tue, Dec 12, 2006 at 07:48:06AM -0500, Michael Stone wrote:
I'd be curious to see -O2 with and without the arch-specific flags,
since that's mostly what the discussion is about.
That came across more harshly than I intended; I apologize for that.
It's certainly a useful data point to
On Mon, 2006-12-11 at 20:22 -0200, Daniel van Ham Colchete wrote:
I'm thinking about writing a script to make all the tests (more than 3
times each), get the data and plot some graphs.
I don't have the time right now to do it, maybe next week I'll have.
Check out the OSDL test suite stuff.
On Dec 12, 2006, at 13:32 , Michael Stone wrote:
On Tue, Dec 12, 2006 at 12:29:29PM +0100, Alexander Staubo wrote:
I suspect the hardware's real maximum performance of the system
is ~150 tps, but that the LSI's write cache is buffering the
writes. I would love to validate this hypothesis,
1= In all these results I'm seeing, no one has yet reported what
their physical IO subsystem is... ...when we are benching a DB.
2= So far we've got ~ a factor of 4 performance difference between
Michael Stone's 1S 1C Netburst era 2.5GHz P4 PC and Guido Neitzer's
1S 2C MacBook Pro 2.33GHz
* Cosimo Streppone:
-O0 ~ 957 tps
-O1 -mcpu=pentium4 -mtune=pentium4 ~ 1186 tps
-O2 -mcpu=pentium4 -mtune=pentium4 ~ 1229 tps
-O3 -mcpu=pentium4 -mtune=pentium4 ~ 1257 tps
-O6 -mcpu=pentium4 -mtune=pentium4 ~ 1254 tps
-mcpu and -mtune are synonymous. You really should -march here (but
the
In response to Ron [EMAIL PROTECTED]:
3= Daniel van Ham Colchete is running Gentoo. That means every SW
component on his box has been compiled to be optimized for the HW it
is running on.
There may be a combination of effects going on for him that others
not running a system optimized
Alexander Staubo [EMAIL PROTECTED] writes:
No, fsync=on. The tps values are similarly unstable with fsync=off,
though -- I'm seeing bursts of high tps values followed by low-tps
valleys, a kind of staccato flow indicative of a write caching being
filled up and flushed.
It's notoriously
On 12/12/06, Florian Weimer [EMAIL PROTECTED] wrote:
* Cosimo Streppone:
-O0 ~ 957 tps
-O1 -mcpu=pentium4 -mtune=pentium4 ~ 1186 tps
-O2 -mcpu=pentium4 -mtune=pentium4 ~ 1229 tps
-O3 -mcpu=pentium4 -mtune=pentium4 ~ 1257 tps
-O6 -mcpu=pentium4 -mtune=pentium4 ~ 1254 tps
-mcpu and -mtune
Alexander Staubo wrote:
No, fsync=on. The tps values are similarly unstable with fsync=off,
though -- I'm seeing bursts of high tps values followed by low-tps
valleys, a kind of staccato flow indicative of a write caching being
filled up and flushed.
Databases with checkpointing
On Tue, 12 Dec 2006, Tom Lane wrote:
Um, you entirely missed the point: the hardware speedups you mention are
quite independent of any compiler options. The numbers we are looking
at are the relative speeds of two different compiles on the same
hardware, not whether hardware A is faster than
Tom Lane wrote:
Alexander Staubo [EMAIL PROTECTED] writes:
No, fsync=on. The tps values are similarly unstable with fsync=off,
though -- I'm seeing bursts of high tps values followed by low-tps
valleys, a kind of staccato flow indicative of a write caching being
filled up and
On Tue, 12 Dec 2006, Alvaro Herrera wrote:
While skimming over the pgbench source it has looked to me like it's
necessary to pass the -s switch (scale factor) to both the
initialization (-i) and the subsequent (non -i) runs.
For non-custom runs, it's computed based on the number of branches.
Mike,
I'm making some other tests here at another hardware (also Gentoo). I
found out that PostgreSQL stops for a while if I change the -t
parameter on bgbench from 600 to 1000 and I have ~150 tps instead of
~950tps.
I don't know why PostgreSQL stoped, but it was longer than 5 seconds
and my
Alvaro Herrera [EMAIL PROTECTED] writes:
While skimming over the pgbench source it has looked to me like it's
necessary to pass the -s switch (scale factor) to both the
initialization (-i) and the subsequent (non -i) runs.
No, it's not supposed to be, and I've never found it needed in
Daniel van Ham Colchete [EMAIL PROTECTED] writes:
I'm making some other tests here at another hardware (also Gentoo). I
found out that PostgreSQL stops for a while if I change the -t
parameter on bgbench from 600 to 1000 and I have ~150 tps instead of
~950tps.
I don't know why PostgreSQL
At 10:47 AM 12/12/2006, Tom Lane wrote:
It's notoriously hard to get repeatable numbers out of pgbench :-(
That's not a good characteristic in bench marking SW...
Does the ODSL stuff have an easier time getting reproducible results?
A couple of tips:
* don't put any faith in short
I just made another test with a second Gentoo machine:
Pentium 4 3.0Ghz Prescott
GCC 4.1.1
Glibc 2.4
PostgreSQL 8.1.5
Kernel 2.6.17
Same postgresql.conf as yesterday's.
First test
==
GLIBC: -O2 -march=i686
PostgreSQL: -O2 -march=i686
Results: 974.638731 975.602142 975.882051
At 01:35 PM 12/12/2006, Daniel van Ham Colchete wrote:
I just made another test with a second Gentoo machine:
snip
The results showed no significant change. The conclusion of today's
test would be that there are no improvement at PostgreSQL when using
-march=prescott.
I only see 3
I just made another test with a second Gentoo machine:
Pentium 4 3.0Ghz Prescott
GCC 4.1.1
Glibc 2.4
PostgreSQL 8.1.5
Kernel 2.6.17
Same postgresql.conf as yesterday's.
First test
==
GLIBC: -O2 -march=i686
PostgreSQL: -O2 -march=i686
Results: 974.638731 975.602142
On Tue, 12 Dec 2006, Daniel van Ham Colchete wrote:
I'm making some other tests here at another hardware (also Gentoo). I
found out that PostgreSQL stops for a while if I change the -t
parameter on bgbench from 600 to 1000 and I have ~150 tps instead of
~950tps.
Sure sounds like a checkpoint
[EMAIL PROTECTED] (Alexander Staubo) wrote:
On Dec 12, 2006, at 13:32 , Michael Stone wrote:
On Tue, Dec 12, 2006 at 12:29:29PM +0100, Alexander Staubo wrote:
I suspect the hardware's real maximum performance of the system is
~150 tps, but that the LSI's write cache is buffering the
writes.
On Dec 11, 2006, at 04:35 , Tatsuo Ishii wrote:
That's not the whole story. UTF-8 and other variable-width encodings
don't provide a 1:1 mapping of logical characters to single bytes; in
particular, combination characters opens the possibility of multiple
different byte sequences mapping to the
On 12/11/06, Alexander Staubo [EMAIL PROTECTED] wrote:
On Dec 11, 2006, at 02:47 , Daniel van Ham Colchete wrote:
I never understood what's the matter between the ASCII/ISO-8859-1/UTF8
charsets to a database. They're all simple C strings that doesn't have
the zero-byte in the midlle (like
Hi Dave,
On 12/11/06, Dave Cramer [EMAIL PROTECTED] wrote:
Hi Daniel
On 10-Dec-06, at 8:02 PM, Daniel van Ham Colchete wrote:
Hi Gene,
at my postgresql.conf, the only non-comented lines are:
fsync = off
This can, and will result in lost data.
I know... If there is a power failure things
On 11-Dec-06, at 5:36 AM, Daniel van Ham Colchete wrote:
Hi Dave,
On 12/11/06, Dave Cramer [EMAIL PROTECTED] wrote:
Hi Daniel
On 10-Dec-06, at 8:02 PM, Daniel van Ham Colchete wrote:
Hi Gene,
at my postgresql.conf, the only non-comented lines are:
fsync = off
This can, and will result
Mike,
unfortunally I don't have any benchmarks right now. Doing something
like this with the same machine would be a 2-day work (at least).
Installing a Gentoo and putting it to run well is not a quick task
(although is easy).
But, trust me on this one. It's worth it. Think of this: PostgreSQL
How much memory does this machine have and what version of postgresql
are you using?
It's only a test server with 512MB RAM, I only used it to see how well
would the PostgreSQL do in a ugly case.
Given that optimal performance for postgresql can require up to 50%
of available memory, you
On Mon, Dec 11, 2006 at 09:05:56AM -0200, Daniel van Ham Colchete wrote:
But, trust me on this one. It's worth it.
You know what? I don't.
Think of this: PostgreSQL and GNU LibC use a lot of complex algorithms:
btree, hashes, checksums, strings functions, etc... And you have a lot of
ways to
On Mon, Dec 11, 2006 at 09:05:56AM -0200, Daniel van Ham Colchete wrote:
unfortunally I don't have any benchmarks right now.
That's fairly normal for gentoo users pushing their compile options.
Mike Stone
---(end of broadcast)---
TIP 4: Have
On 12/11/06, Steinar H. Gunderson [EMAIL PROTECTED] wrote:
On Mon, Dec 11, 2006 at 09:05:56AM -0200, Daniel van Ham Colchete wrote:
But, trust me on this one. It's worth it.
You know what? I don't.
So test it yourself.
Think of this: PostgreSQL and GNU LibC use a lot of complex algorithms:
This is very very very true :-)!
I just remebered one case with MySQL. When I changed the distro from
Conectiva 10 (rpm-based ended brazilian distro) to Gentoo, a MySQL
operation that usually took 2 minutes to run, ended in 47 seconds.
This is absolutely vage. I don't have how to prove it to
Oops! [EMAIL PROTECTED] (Daniel van Ham Colchete) was seen spray-painting on
a wall:
But, trust me on this one. It's worth it.
No, the point of performance analysis is that you *can't* trust the
people that say trust me on this one.
If you haven't got a benchmark where you can demonstrate a
You are right Christopher.
Okay. Let's solve this matter.
What PostgreSQL benchmark software should I use???
I'll test PostgreSQL 8.1 on a Fedora Core 6 and on a Gentoo. I'll get
the same version FC6 uses and install it at my Gentoo. I'll use the
same hardware (diferent partitions to each).
On Mon, Dec 11, 2006 at 11:09:13AM -0200, Daniel van Ham Colchete wrote:
You know what? I don't.
So test it yourself.
You're making the claims, you're supposed to be proving them...
As I said, it is an example. Take floatpoint divisions. You have
plenty of ways of doing it: 387, MMX, SSE,
On 12/11/06, Steinar H. Gunderson [EMAIL PROTECTED] wrote:
On Mon, Dec 11, 2006 at 11:09:13AM -0200, Daniel van Ham Colchete wrote:
You know what? I don't.
So test it yourself.
You're making the claims, you're supposed to be proving them...
As I said, it is an example. Take floatpoint
On Mon, Dec 11, 2006 at 11:17:06AM -0200, Daniel van Ham Colchete wrote:
I just remebered one case with MySQL. When I changed the distro from
Conectiva 10 (rpm-based ended brazilian distro) to Gentoo, a MySQL
operation that usually took 2 minutes to run, ended in 47 seconds.
How do you know
On Mon, Dec 11, 2006 at 11:31:48AM -0200, Daniel van Ham Colchete wrote:
What PostgreSQL benchmark software should I use???
Look up the list archives; search for TPC.
I'll test PostgreSQL 8.1 on a Fedora Core 6 and on a Gentoo. I'll get
the same version FC6 uses and install it at my Gentoo.
On 12/11/06, Daniel van Ham Colchete [EMAIL PROTECTED] wrote:
But, trust me on this one. It's worth it. Think of this: PostgreSQL
and GNU LibC use a lot of complex algorithms: btree, hashes,
checksums, strings functions, etc... And you have a lot of ways to
compile it into binary code. Now you
[EMAIL PROTECTED] (Daniel van Ham Colchete) writes:
You are right Christopher.
Okay. Let's solve this matter.
What PostgreSQL benchmark software should I use???
pgbench is one option.
There's a TPC-W at pgFoundry
(http://pgfoundry.org/projects/tpc-w-php/).
There's the Open Source
This definitely is the correct approach.
Actually, Daniel van Ham Colchete may not be as all wet as some
around here think. We've had previous data that shows that pg can
become CPU bound (see previous posts by Josh Berkus and others
regarding CPU overhead in what should be IO bound tasks).
On Mon, Dec 11, 2006 at 12:15:51PM -0500, Ron wrote:
I'd say the fairest attitude is to do everything we can to support
having the proper experiments done w/o presuming the results.
Who's presuming results?[1] It is fair to say that making extraordinary
claims without any evidence should be
Statements like these can not be reasonably interpreted in any manner
_except_ that of presuming the results:
I expect that you'll discover, if you actually do these tests, that
this belief (that using arch specific compiler options lead to
better performing SW) is fairly much nonsense.
Michael,
On 12/11/06 9:31 AM, Michael Stone [EMAIL PROTECTED] wrote:
[1] I will say that I have never seen a realistic benchmark of general
code where the compiler flags made a statistically significant
difference in the runtime.
Here's one - I wrote a general purpose Computational Fluid
On Mon, Dec 11, 2006 at 01:20:50PM -0500, Ron wrote:
(The validity of the claim has nothing to do with the skills or
experience of the claimant or anyone else in the discussion. Only on
the evidence.)
Please go back and reread the original post. I don't think the response
was unwarranted.
On Mon, Dec 11, 2006 at 10:30:55AM -0800, Luke Lonergan wrote:
Here's one - I wrote a general purpose Computational Fluid Dynamics analysis
method used by hundreds of people to perform aircraft and propulsion systems
analysis.
That's kinda the opposite of what I meant by general code. I was
On 12/11/06, Ron [EMAIL PROTECTED] wrote:
Statements like these can not be reasonably interpreted in any manner
_except_ that of presuming the results:
I expect that you'll discover, if you actually do these tests, that
this belief (that using arch specific compiler options lead to
better
At 01:47 PM 12/11/2006, Michael Stone wrote:
On Mon, Dec 11, 2006 at 01:20:50PM -0500, Ron wrote:
(The validity of the claim has nothing to do with the skills or
experience of the claimant or anyone else in the discussion. Only
on the evidence.)
Please go back and reread the original post.
On 12/11/06, Steinar H. Gunderson [EMAIL PROTECTED] wrote:
On Mon, Dec 11, 2006 at 11:17:06AM -0200, Daniel van Ham Colchete wrote:
I just remebered one case with MySQL. When I changed the distro from
Conectiva 10 (rpm-based ended brazilian distro) to Gentoo, a MySQL
operation that usually
At 02:28 PM 12/11/2006, Merlin Moncure wrote:
also, some people posting here, not necessarily me, are authority figures. :-)
merlin
Noam Chomsky was one of the most influential thinkers in Linguistics
to yet have lived. He was proven wrong a number of times. Even
within Linguistics.
1 - 100 of 112 matches
Mail list logo