enough IO bandwidth to satisfy the query.
Can we see an explain analyze of the query? Could be a bad plan and a
bad plan will never give good performance.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(e
ing ALL rows I doubt that will help
much.
Another option may be to use materialized views. Not sure how
"dynamic" your data model is. It could help.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadca
look at the si and so columns.
Linux is very swap happy and likes to swap things for fun and profit.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 2: you can get off all li
ersus php's persistent connections ? I'd strongly recommend looking
at pgpool. it does connection pooling correctly (A set of X connections
shared among the entire box rather than 1 per web server)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http
it also saves money since I don't
need machines sitting around serving up pixel.gif vs
myBigApplication.cgi)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 5: Have
ific date. This query pulls up al the data for a period of time.
ce.eventdate is indexed, and is used in the outer nestloop. Thinking
more about what is going on cache thrashing is certainly a possibility.
the amazing explain analyze overhead is also very curious - we all
know it adds overhead, b
3.4963 postgres slot_getattr
11509
aside from j2date (probably coming up due to that Join filter I'd
wager) nothing unexpected.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@pos
ed
ssd's have the same issue).
The write degradation could probably be monitored looking at svctime
from sar. We may be implementing that in the near future to detect
when this creeps up again.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pg
On Mar 29, 2011, at 10:16 AM, Jeff wrote:
Now that all sounds awful and horrible until you get to overall
performance, especially with reads - you are looking at 20k random
reads per second with a few disks. Adding in writes does kick it
down a noch, but you're still looking at 10k+
controller are you using on the 24 disk beast?
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance
Also, are you sure your numbers are not coming out of the mysql query
cache?
That might explain some of it - also with Tom seeing comprable
numbers in his test.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(
ght it be better to use refcursor or something or bite the bullet and
live with a giant procedure?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 1: subscribe and unsubscribe
state. Doing a simple ls -l somefile would take 10-15 seconds and of
course, db performance was abysmal.
I had a lowly P2 with a few disks in it that was able to run circles
around it for the simple fact the machine was not waiting for disk.
Again, proof that disk is far more important than CP
sting.
I've got a dual G4 at home, but for convenience Apple doesn't ship a
vmstat that tells context switches
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 5:
ght up, vanilla index scan. Nothing else getting in the way.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 9: the planner will ignore your desire to choose an index scan
e else using it?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 9: the planner will ignore your desire to choose an index scan if your
joining column's datatypes do not match
On Jun 17, 2004, at 7:10 AM, Adam Witney wrote:
Will this run on other platforms? OSX maybe?
I've run it on both linux (rh8) and osx (panther).
its java so it *should* run anywhere.
It isn't the fastest beast in the world though. takes a bit of time to
render the plan.
--
Jeff Tro
o you won't need to grab
everything.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 9: the planner will ignore your desire to choose an index scan if your
joining co
world. In 7.4 the rule of thumb is no
more than 10k shared_buffers.. beyond that the overhead of maintaining
it becomes excessive. (This isn't really the case in 7.5)
Curiously, what are your sort_mem and shared_buffers settings?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.
On Jun 27, 2004, at 8:37 PM, Jim wrote:
Hi,
I have one performance issue... and realy have no idea what's going
on...
When I set enable_seqscan to 0, query2 runs the same way...
upload => 60667 entities
uploadfield => 506316 entities
Have you vacuum analyze'd recentl
re you can use a SQL function instead
of plpgsql - PG has smart enough to push that function up into your
query and let the optimizer look at the whole thing.
You can also take a look at the various flags you can use while
creating functions such as immutable, strict, etc. they can help
--
Jeff Tro
interesting to run something like ntop that can show you
current network usage... unless you are doing a large COPY the PG
protocol has a lot of back and forth messages...
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of bro
ay.
I'm working on a project porting some things to Oracle and as a test I
also ported it to Postgres. And you know what? Postgres is running
about 30% faster than Oracle. The Oracle lovers here are not too happy
with that one :) Just so you know..
--
Jeff Trout <[EMAIL PROTECTED]>
necting to pgpool is very fast. We use it in production here and it
works wonderfully. And it is 100% transparent to your application.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)-
e a
champ
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
s 10x faster than local disk!) And
on the upside, when I originally researched the problem they hadn't
found the bug yet so there were no others around having issues like
mine so trying to figure it out was quite difficult.
I may see if using that acpi=ht makes any difference as well.
--
Jeff Tro
"closest matches" when an
exact match cannot be found... granted you may not want that for a
dating site : )
"You asked for a blond female, blue eyes.. but I couldn't find any...
but I *DID* find a brown haired male with brown eyes! Is that good
enough?"
--
Jeff Trout
sible to do a "poor man"'s query cache with triggers..
which would just leave you with basically a materialized view.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
cpus are pretty idle that is an indicator of being IO
bound).
good luck.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
x27;d have
BEGIN
insert
insert
insert
...
COMMIT
Your numbers will suddenly sky rocket.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 2: you can get off all lists at once wit
0), but I still have no
idea why this plan is getting chosen
looks like your stats are incorrect on the sparc.
Did you forget to run vacuum analyze on it?
also, do both db's have the same data loaded?
there are some very different numbers in terms of actual rows floating
around there...
-
nt? Which systems and
Have you also considered a replicated approach?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 6: Have you searched our list archives?
http://archives.postgresql.org
success. It is quite
easy to corrupt a PG (Or most any db really) on an IDE drive. Check
the archives for more info.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don&#
e ago on it. They are likely in the
archives.
Maybe we can get him to pipe up :)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 5: Have you checked our extensive FAQ?
121.80.
I'm fairly sure that the pi and po numbers include file IO in Solaris,
because of the unified VM and file systems.
Curiously, what are your shared_buffers and sort_mem set too?
Perhaps they are too high?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stu
o not sure how Solaris reports shared memory usage for apps... a
lot of that could be shared mem.
Can you watch say, vmstat 1 for a minute or two while PG is running and
see if you're actually swapping?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuartham
to partiition
data among several boxes and then join the results together.
Or you could fork over hundreds of thousands of dollars for Oracle's
RAC.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)--
eements on the other db's. I know Oracle forbids the
release of benchmark numbers without their approval.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 5: Have you chec
!"
After using oracle in the last few months.. I can see why they'd want
to prevent those numbers.. Oracle really isn't that good. I had been
under the impression that it was holy smokes amazingly fast. It just
isn't. At least, in my experience it isn't. but that i
ish when I get time (that is a funny idea) is having explain analyze
report when a step required the use of temp files.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP
no use in
storing the data if a query will take ages. Query's should be quite
fast if possible.
And make sure you tune your queries.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)-
veral occasions I was moving a
largish table and the COPY part went plenty fast, but when it hit
index creation it slowed down to a crawl due to low maint_work_mem..
--
Jeff Trout <[EMAIL PROTECTED]>
www.dellsmartexitin.com
www.stuarthamm.net
---(end of broad
heduler I admit I sat there
flipping back and forth going "disk go fast.. disk go slow.. disk go
fast... " :)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org
mber,
or try out my pgiosim tool on pgfoundry which "sort of" simulates an
index scan. I posted numbers from that a month or two ago here.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance maili
logging_collector=on, the same
statement needs 15 seconds to return.
In syslog.conf is the destination for PG marked with a "-"? (ie -/var/
log/pg.log) which tells syslog to not sync after each line logged.
That could explain a large chunk of the difference in time.
--
Jeff Tro
ed into about
8 10k rpm sata disks.
thanks
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
finally removed the Areca
controllers from our database server and replaced them with HP P800s.
My main db has a p600 plugged into an msa70 which works well - does
the HP junk work in non-hp boxes?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
ipped a bit from the previous one.
It does look like the 9600 series fixed a lot of the 9550 issues.
(and for the record, yes, either card I get will have a bbu. tis
silly to get a controller without one)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
er process = 112074.58 KB/sec
Min xfer= 1024000.00 KB
CPU utilization: Wall time9.137CPU time0.510CPU
utilization 5.58 %
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.stuarthamm.net/
http://www.del
arted the array building the new logical drive some
magical things happened.
Bugs happen. The [bad word] of it is catching the culprit with its
fingers in the cookie jar.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing
it for a pg_restore compatible dump "just in case".
It takes a long time to restore a 300GB db, even if you cheat and
parallelify some of it. 8.4 may get a pg_restore that can load in
parallel - which will help somewhat.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.
On Jan 26, 2009, at 3:00 PM, Joshua D. Drake wrote:
On Mon, 2009-01-26 at 14:58 -0500, Jeff wrote:
voila. I have 2 full copies of the db. You could even expand it a
bit
and after the rsync & friends have it fire up the instance and run
pg_dump against it for a pg_restore compatible
numbers, that is
crazy impressive for a plain old mirror pair. I also did not do much
tweaking of PG itself.
While I'm in the testing mood, are there some other tests folks would
like me to try out?
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent
less as they tend to be tons of random IO.
I've got some Raptors here too I'll post numbers wed or thu.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your
of an ssd where a seek is
basically free. I haven't tested this yet (I can do that next week),
but logically, in this scenario wouldn't lowering random_page_cost be
ideal or would it not really matter in the grand scheme of things?
--
Jeff Trout
http://www.stuarthamm.net/
http:
, just select * from pg_stat_activity where
current_query <> '';
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.or
(I usually use dd to
do that, and make sure it is at least 2xRAM in size)
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.or
them does not take that long, so it may not
be worth the overhead of the journaling.
The win for the journal on the heap is simply so you don't need to
spend $longtime fsck'ing if you crash, etc.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
you've got beefy IO. One sucky thing though is if a slave
is down sl_log can grow very large (I've had it get over 30M rows, the
slave was only down for hours) and this causes major cpu churn while
the queries slon issues sift through tons of data. But, to be fair,
that'll h
ript.sql
$ londiste conf/londiste_db3.ini change-provider --provider=rnode1
$ londiste conf/londiste_db1.ini switchover --target=rnode2
ok, so londiste can't do failover yet, or is it just somewhat
convoluted at this point?
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexi
u can fire
up something such as pgbench or pgiosim, fire up an iostat and then
watch your iops jump high when you flip to noop or deadline and
plummet on cfq. Try it. it's neat!
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance ma
ting around (I'm looking at you jmicron based disks!)
Have you gone through the normal process of checking your query plans
to ensure they are sane? There is always a possibility a new index can
vastly reduce IO.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
one :)
Here's the old post:
http://archives.postgresql.org/pgsql-performance/2008-04/msg00155.php
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to you
On Feb 10, 2010, at 1:37 AM, Greg Smith wrote:
Jeff wrote:
I'd done some testing a while ago on the schedulers and at the time
deadline or noop smashed cfq. Now, it is 100% possible since then
that they've made vast improvements to cfq and or the VM to get
better or similar p
02-17 08:15:51.067886 | 789 | 0
| 1
perhaps some stats buffering occurring or something or some general
misunderstanding of some of these tunables?
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing li
t is, I just didn't include them in the mail.
--
Jeff Trout
http://www.stuarthamm.net/
http://www.dellsmartexitin.com/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance
ux's uptime wraparound of 496 days :) and the only
reason it went down then was because the power supply failed. (That can
be read: pg7.0.2 had over a year of uptime. lets hope 7.3 works as good :)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.st
to 30 seconds and wal_buffers
to 128. (I'm just guessing on wal_buffers).
Machine is weenucks 2.2.17 on a dual p3 800, 2gb ram, 18gb drive (mirrored).
If you guys need other info (shared_buffers, etc) I'll be happy to funish
them. but the issue isn't query slowness.. just wan
readers to do the read. Result: nice and fast (Yes, It
may not always spawn the three readers, only when it thinks it will be a
good thing to do)
I think for PG the effort would be much better spent on other features...
like replication and whatnot.
--
Jeff Trout <[EMAIL PROTECTED]>
http://w
t. Easy to scrape and interact with pages: YES. It has all sorts of
things for locating fields, locating table cells, etc. (I used it for
writing a prototype that would scrape a competitors site and import the
data into our application :)
but if it doesn't work LWP isn't _that_ bad. You
w the next 1000" - it should get you the speed you
want.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 1: subscribe and unsubscribe commands go to [EMAIL PROTECTED]
stamp with time zone))
Total runtime: 1042.54 msec
(6 rows)
They are loaded with the exact same dataset - 53k rows, ~10MB
Notice the estimates are roughly the same, but the execution time is
different.
I don't think it is the IO system, since 10MB will be cached by the O
zone) AND (dob <=
'1985-08-26 00:00:00-04'::timestamp with time zone))
Total runtime: 372.63 msec
(6 rows)
I ran this query 100 times per beater (no prepared queries) and ran
19 beaters in parellel.
P2 Machine: 345sec avg
Sun:565sec avg
I know solaris/sun isn't the pr
e data set is
small enough that it is all cached (~10MB). iostat reports 0 activity on
the disks on both the sun and p2.
and I just ran teh test again with 40 clients: 730s for hte p2, 1100 for
the sun. (0% idle on both of them, no IO). I think the next I may try is
recompiling with a new
nth or
two.
thanks for the ideas / comments.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 6: Have you searched our list archives?
http://archives.postgresql.org
o a profile for hte p2 and send post that in an hour or two
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
any postgresql.conf tweaks - or did you just use
whatever came with each distro?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 6: Have you searched our list archives?
http://archives.postgresql.org
;cached' - a lot of people probably get bad first impressions because of
that)
Would it be possible ot rewrite your queries replacing min/max with a
select stock_id from bigtable where blah = blorch order by stock_id
(desc|asc) limit 1? because that would enable PG to use an index and
magically
t random ther eis no need to bother with an order and that'll
save a sort.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
On Thu, 11 Sep 2003, [EMAIL PROTECTED] wrote:
>
> The Vacuum full is performed once at the end of the whole job.
>
have you also tried vacuum analyze periodically - it does not lock the
table and can help quite a bit?
still odd why it would be that much slower between those versions.
he
question really).
any thoughts?
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 1: subscribe and unsubscribe commands go to [EMAIL PROTECTED]
ording to
bonnie. You could have an IO bottleneck. (I once went running around
trying to figure it out and then discovered the issue was IO).
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)--
ened?
>
Did you reload the db? If you did perhaps you didn't use the "C" locale?
That can cause a huge slowdown.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)--
o try out - Given your configuration I expect you
have lots of concurrent activity.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 9: the planner will ignore your desire to choose an index scan if your
joining column's datatypes do not match
On Wed, 1 Oct 2003, Oleg Lebedev wrote:
> Jeff,
> I would really appreciate if you could send me that lengthy presentation
> that you've written on pg/other dbs comparison.
> Thanks.
>
After I give the presentation at work and collect comments from my
coworkers (and remove
Oracle does too.
Mysql with InnoDB does the same thing PG does. (MyISAM caches it)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
hope to post it tuesday after
I update with comments I receive and remove confidential information.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 2: you can get off all li
ted at the
moment of why (with proof, not antecdotal) Solaris is so much slower than
Linux and what we cna do about this. We're looking to move a rather large
Informix db to PG and ops has reservations about ditching Sun hardware.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
h
inter-process flag or something) to see if I can get those numbers a
little closer.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 7: don't forget to increase your free space map settings
in the table the query hits).
I'll be digging up more info later today.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 4: Don't 'kill -9' the postmaster
exciting world of seeing what I can do about it.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 2: you can get off all lists at once with the unregister command
(send "
t may be less in reality...
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 7: don't forget to increase your free space map settings
erhaps newer ones make even better code?)
I'm not sure of PG's policy of non-gcc things in configure, but perhaps if
we detect sunsoft we toss in the -fast flag and maybe make it the
preferred one on sun? [btw, it compiled with no changes but it did spew
out tons of warnings]
comments?
--
J
go, we found more or less no difference
> once we added more than 5 connections (and we always have more than 5
> connections). It might be worth trying again, though, since we moved
> to Sol 8.
>
The 20x column are the results when I fired up 20 beater concurrently.
--
Jeff Trout
and surprising that the performance differential is that
> large, to me at least). Can you tell if the performance gain comes from
> an improvement in a particular subsystem? (i.e. could you get a profile
> of Sun/gcc and compare it with Sun/sunsoft).
>
I'll get these
here.
Maybe even slightly more subtle blatant errors :)
The people here thought it was good.
http://postgres.jefftrout.com/
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 1:
0.11 16.36 937576 0.0001 MemoryContextAlloc
0.50.09 16.45 150453 0.0006 hash_search
> -Neil
>
>
>
> ---(end of broadcast)---
> TIP 1: subscribe and unsubscribe commands go to [EMAIL PR
ice, but I got mad at it. So I switched to
powerpoint and got mad at that too :)
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net/
---(end of broadcast)---
TIP 3: if posting/reading through Usenet
nice
set of "real" web pages.
> Can you rip out informix migration? It could be a good guide by itself.
>
I agree. It would be good to rip out. I think we have the oracle guide
somewhere..
I've put this updated on up on hte postgres.jefftrout.com site
ust for compiling pg)
I'll go run the regression test suite with my gcc -O2 pg and the suncc pg.
See if they pass the test.
If they do we should consider adding -O2 and -fast to the CFLAGS.
--
Jeff Trout <[EMAIL PROTECTED]>
http://www.jefftrout.com/
http://www.stuarthamm.net
1 - 100 of 878 matches
Mail list logo
