[PERFORM] Direct I/O issues

2006-11-22 Thread Greg Smith
this value higher will help smooth response times during the period immediately following each checkpoint. That seems to match what I found in testing. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Lying drives [Was: Re: Which OS provides the _fastest_

2006-11-22 Thread Greg Smith
SGI warns about from happening; Hitachi's Feature Tool at http://www.hitachigst.com/hdd/support/download.htm is one example I've used successfully before. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Direct I/O issues

2006-11-23 Thread Greg Smith
position to fix it myself now. I just wanted to report the issue and get some initial feedback on what's wrong. I'll try to rewrite that code with an eye toward the Determine optimal fdatasync/fsync, O_SYNC/O_DSYNC options to-do item, which is what I'd really like to have. -- * Greg Smith

Re: [PERFORM] Bad iostat numbers

2006-12-03 Thread Greg Smith
it down, and you'd get much scarier messages out of smartd if the drives had a real problem. You should improve cooling in this case if you want to drives to have a healthy life, odds are low this is relevant to your performance issue though. -- * Greg Smith [EMAIL PROTECTED] http

Re: [PERFORM] Bad iostat numbers

2006-12-04 Thread Greg Smith
00:01:03 EST 2005) megaraid: 2.20.4.6-rh2 (Release Date: Wed Jun 28 12:27:22 EST 2006) -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 2: Don't 'kill -9' the postmaster

Re: [PERFORM] Bad iostat numbers

2006-12-05 Thread Greg Smith
what you get from a single disk, because you may have to wait for multiple discs to spin to the correct position and write data out before you can consider the transaction complete. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end

Re: [PERFORM] File Systems Compared

2006-12-06 Thread Greg Smith
(there are certainly two sides with valid points in that debate), to make them more compatible with flow-impaired clients, you can't expect that mail composition software is sophisticated enough to allow doing that for one section while still wrapping the rest of the text correctly. -- * Greg Smith [EMAIL

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-11 Thread Greg Smith
seeing, expecially when combined with a 20% greater raw CPU clock. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org/docs

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-12 Thread Greg Smith
will shift which optimizations are useful and which have minimal impact even if the processor is basically the same. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-12 Thread Greg Smith
that comes with current Postgres 8.1 versions. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org/docs/faq

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-12 Thread Greg Smith
of performance. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your friend

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-14 Thread Greg Smith
as soon as the number of transactions increases. With little or no actual disk writes, you should expect results to be ranked by CPU speed. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-14 Thread Greg Smith
/core systems. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 5: don't forget to increase your free space map settings

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-14 Thread Greg Smith
the same thing and have been meaning to figure out what the cause is. It's just doing a select in there; it's not even in a begin/end block. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9

Re: [PERFORM] New to PostgreSQL, performance considerations

2006-12-15 Thread Greg Smith
) into the mix people test. That one may stack usefully with -O2, but probably not with -O3 (3 includes optimizations that increase code size). -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 5: don't

Re: [PERFORM] Scaling concerns

2006-12-17 Thread Greg Smith
) FROM tmpMessages took a really long time before psql died with an out-of-memory error. Do you have the exact text of the error? I suspect you're falling victim to the default parameters being far too low here as well, but without the error it's hard to know exactly which. -- * Greg Smith

Re: [PERFORM] Shared buffers, db transactions commited, and write IO on Solaris

2007-03-29 Thread Greg Smith
the current line in the CVS tree for 8.3: write_timeout.it_value.tv_usec = (PGSTAT_STAT_INTERVAL % 1000) * 1000; That's all it took to resolve things for me. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] SCSI vs SATA

2007-04-05 Thread Greg Smith
. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org/docs/faq

Re: [PERFORM] SCSI vs SATA

2007-04-06 Thread Greg Smith
this happens. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 1: if posting/reading through Usenet, please send an appropriate subscribe-nomail command to [EMAIL PROTECTED] so that your

Re: [PERFORM] SCSI vs SATA

2007-04-06 Thread Greg Smith
processors produce massively more heat than those of even a few years ago has contributed to drive manufacturers moving their specs upwards as well. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Question about memory allocations

2007-04-12 Thread Greg Smith
so brazen as to turn off fsync. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your friend

Re: [PERFORM] Basic Q on superfluous primary keys

2007-04-16 Thread Greg Smith
these problems. If the key is a integer, it's always possible to figure out a trivial map that renumbers the entire database programmatically in order to merge two sets of data. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Basic Q on superfluous primary keys

2007-04-18 Thread Greg Smith
information at the time. The funny thing about unexpected changes to a business model is that you never expect them. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9: In versions below 8.0, the planner

Re: [PERFORM] TPC-H Scaling Factors X PostgreSQL Cluster Command

2007-04-23 Thread Greg Smith
that to 30, restart the server, and rebuild the index to see how much the 1GB case speeds up. If it's significantly faster (it should be), try the 5GB one again. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] postgres: 100% CPU utilization

2007-04-23 Thread Greg Smith
On Mon, 23 Apr 2007, Scott Marlowe wrote: I honestly kinda wondered if the original post came out of a time warp, like some mail relay somewhere held onto it for 4 years or something. That wouldn't be out of the question if this system is also his mail server. -- * Greg Smith [EMAIL

Re: [PERFORM] What`s wrong with JFS configuration?

2007-04-25 Thread Greg Smith
is being measured usefully at all via pgbench. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9: In versions below 8.0, the planner will ignore your desire to choose an index scan if your

Re: [PERFORM] Fragmentation of WAL files

2007-04-26 Thread Greg Smith
to be. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives? http://archives.postgresql.org

Re: [PERFORM] Feature Request --- was: PostgreSQL Performance Tuning

2007-04-30 Thread Greg Smith
been running under load for a while, and make your recommendations based on all that information. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 7: You can help support the PostgreSQL project

Re: [PERFORM] Feature Request --- was: PostgreSQL Performance Tuning

2007-05-01 Thread Greg Smith
comparison of PostgreSQL with robust WAL vs. MySQL+MyISAM on write-heavy worksloads These are real issues, which of course stack on top of things like outdated opinions from older PG releases with performance issues resolved in the last few years. -- * Greg Smith [EMAIL PROTECTED] http

Re: [PERFORM] Feature Request --- was: PostgreSQL Performance Tuning

2007-05-01 Thread Greg Smith
myself for a second, it may very well be the case that writing the simpler tool is the only way to get a useful prototype for building the more complicated one; very easy to get bogged down in feature creep on a grand design otherwise. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com

[PERFORM] pg_stat_* collection

2007-05-03 Thread Greg Smith
data. You would thing there would be an organized project addressing this need around to keep everyone from reinventing that wheel, but I'm not aware of one. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Feature Request --- was: PostgreSQL Performance Tuning

2007-05-03 Thread Greg Smith
can work with. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 1: if posting/reading through Usenet, please send an appropriate subscribe-nomail command to [EMAIL PROTECTED] so that your

Re: [PERFORM] pg_stat_* collection

2007-05-03 Thread Greg Smith
environment I work in, because there really is no thought of security whatsoever in the whole thing. What I'm still thinking about is whether it's possible to fix that issue while still keeping the essential simplicity that makes Munin so friendly. -- * Greg Smith [EMAIL PROTECTED] http

Re: [PERFORM] Feature Request --- was: PostgreSQL Performance Tuning

2007-05-04 Thread Greg Smith
less useful results for predicting PostgreSQL performance than what you can find out running a real query. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ

Re: [PERFORM] Best OS for Postgres 8.2

2007-05-07 Thread Greg Smith
Debian software repository. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9: In versions below 8.0, the planner will ignore your desire to choose an index scan if your joining column's

Re: [PERFORM] Best OS for Postgres 8.2

2007-05-08 Thread Greg Smith
between the two. So someone who installs CentOS now could swap to RHEL very quickly in a pinch if they have enough cojones to do the required package substitutions. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Best OS for Postgres 8.2

2007-05-08 Thread Greg Smith
hardware support. The fact that he misunderstands such a fundamental point makes me wonder what other gigantic mistakes might be buried in his analysis. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM]

2007-05-08 Thread Greg Smith
will make more sense, and you'll be in a better position to figure out what you should do next: http://www.westnet.com/~gsmith/content/postgresql/TuningPGWAL.htm -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] [PATCHES] Automatic adjustment of bgwriter_lru_maxpages

2007-05-15 Thread Greg Smith
pass unless you're in a position to run some good tests to confirm you're not actually making things worse. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives

[PERFORM] New performance documentation released

2007-05-15 Thread Greg Smith
, but may be useful anyway so I've posted what I've got so far. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 2: Don't 'kill -9' the postmaster

Re: [PERFORM] Background vacuum

2007-05-17 Thread Greg Smith
straightforward way to cope with this problem. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives? http://archives.postgresql.org

Re: [PERFORM] 121+ million record table perf problems

2007-05-18 Thread Greg Smith
back in and see how it degrades. Then you'll know how adding each one of them impacts your performance. I suspect you're going to have to redesign your indexing scheme before this is over. I don't think your current design is ever going to work the way you expect it to. -- * Greg Smith [EMAIL

Re: [PERFORM] Background vacuum

2007-05-18 Thread Greg Smith
that you're satisfied with how nice has worked successfully for you doesn't have to conflict with an opinion that it's not the best approach for controlling vacuuming. I just wouldn't extrapolate your experience too far here. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] Postgres Benchmark Results

2007-05-21 Thread Greg Smith
to know on this subject if you're like to read more about it--and you really, really should if you intend to put important data into a PostgreSQL database. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Postgres Benchmark Results

2007-05-22 Thread Greg Smith
that have good controllers). One of these days... -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 1: if posting/reading through Usenet, please send an appropriate subscribe-nomail command

Re: [PERFORM] Tips Tricks for validating hardware/os

2007-05-23 Thread Greg Smith
that for a week, if it's still running your data should be safe under real conditions. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 7: You can help support the PostgreSQL project by donating

Re: [PERFORM] ECC RAM really needed?

2007-05-25 Thread Greg Smith
/papers/soft_errors_1_1_secure.pdf which is a summary of many other people's papers, and quite informative. I know I had no idea before reading it how much error rates go up with increasing altitute. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] upgraded to pgsql 8.2.4, getting worse performance then 7.4.x

2007-06-03 Thread Greg Smith
more upward tweaking of your kernel parameters to support. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives? http://archives.postgresql.org

Re: [PERFORM] PostgreSQL not fully utilizing system resources?

2007-06-04 Thread Greg Smith
for checkpoint_settings is at the default, that would be a killer with your workload as well. That should get you started. If you still aren't happy with performance after all that, post again with some details about your disk configuration and an EXPLAIN plan for something that's moving slowly. -- * Greg Smith

Re: [PERFORM] dbt2 NOTPM numbers

2007-06-05 Thread Greg Smith
likely to help here. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives? http://archives.postgresql.org

Re: [PERFORM] Getting Slow

2007-06-07 Thread Greg Smith
else needs to be done. See http://www.westnet.com/~gsmith/content/postgresql/pg-5minute.htm for more information on this topic. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you

Re: [PERFORM] VERY slow queries at random

2007-06-07 Thread Greg Smith
you know what you're playing with, there are some recovery implications invoved. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9: In versions below 8.0, the planner will ignore your desire

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-18 Thread Greg Smith
a good value to set for everything before releasing a beta, it's a lot easier for others to come in and help fix a couple of parameters once the basic framework is in place. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-18 Thread Greg Smith
On Mon, 18 Jun 2007, [EMAIL PROTECTED] wrote: do any of the text-mode browsers implement javascript? http://links.twibright.com/ -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-19 Thread Greg Smith
beyond that to having it pick the optimal parameters more automatically would take AI much stronger than just a genetic algorithm approach. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies

2007-06-20 Thread Greg Smith
Lance is building. The kind of optimizations you'd do based on that are just too complicated to expect a tool to get them right and still be accessible to a novice. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-20 Thread Greg Smith
into a setting for that parameter right now based on memory in their system, but I never see anybody going since your main table is X GB large, and its index is Y GB, you really need enough memory to set effective_cache_size to Z GB if you want queries/joins on that table to perform well. -- * Greg

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-20 Thread Greg Smith
isn't completely sure what to do with effective_cache_size either. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-20 Thread Greg Smith
when I could see this: $ cat postgresql.conf | grep brain # - Super-brain Query Optimizer - sbqo = on # Enables the super-brain sbqo_reconsider_interval = 5s # How often to update plans sbqo_brain_size = friggin_huge # Possible values are wee, not_so_wee, and -- * Greg Smith [EMAIL

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-21 Thread Greg Smith
that tricks like that are becoming marginal. Pushing more work toward the OS is a completely viable design choice that strengthens every year. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6

Re: [PERFORM] Hardware suggestions

2007-06-22 Thread Greg Smith
On Thu, 21 Jun 2007, Scott Marlowe wrote: And if they've gone to the trouble of implementing RAID-6, they're usually at least halfway decent controllers. Unfortunately the existance of the RAID-6 capable Adaptec 2820SA proves this isn't always the case. -- * Greg Smith [EMAIL PROTECTED

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies

2007-06-22 Thread Greg Smith
to get a first generation one that works fairly well before getting distracted at all by things like this. The people capable of filling out the intermediate/advanced settings can probably just do a bit of reading and figure out most of what they should be doing themselves. -- * Greg Smith [EMAIL

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies

2007-06-23 Thread Greg Smith
to the parameter documentation section. I think that anyone who has been working with the software long to know what should go into such a section has kind of forgotten about this part of the documentation by the time they get there. It is an oversight and yours is an excellent suggestion. -- * Greg Smith

Re: [PERFORM] Volunteer to build a configuration tool

2007-06-23 Thread Greg Smith
to real application data as you can get in order to make good forward progress. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies - feedback adjustable control

2007-06-23 Thread Greg Smith
variables set to reasonable values. Trying to satisfy every possible user is the path that leads to a design so complicated that it's unlikely you'll ever get a finished build done at all. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies

2007-06-26 Thread Greg Smith
would come out of how the current sample is asking about read vs. write workloads and expected database size. Those simple to understand questions might capture enough of the difference between your two types here. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] PostgreSQL Configuration Tool for Dummies

2007-06-26 Thread Greg Smith
out of a different type of tool that connects to the database. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org

Re: [PERFORM] High IOWAIT times, low iops? Need Help with configuration

2007-06-28 Thread Greg Smith
-5minute.htm for a quick intro to things to consider. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your friend

Re: [PERFORM] PostgreSQL 8.0 occasionally slow down

2007-06-28 Thread Greg Smith
), and see if the problem stops happening as frequently. Your problem looks exactly like a pause at every checkpoint, and I'm not sure what Richard was thinking when he suggested having them more often would improve things. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] PostgreSQL 8.0 occasionally slow down

2007-07-02 Thread Greg Smith
is really spread out, you may find my paper at http://www.westnet.com/~gsmith/content/linux-pdflush.htm a good place to start looking into that. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9

Re: [PERFORM] PostgreSQL publishes first real benchmark

2007-07-09 Thread Greg Smith
in the database server storage array, while the PostgreSQL one had 15K RPM ones. A few other small differences as well if you dig into the configurations, all of which I noted favored the PG system. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] best use of an EMC SAN

2007-07-11 Thread Greg Smith
a fairly short downtime operation. If you don't reach a wall, the extra drives might serve as spares to help mitigate concerns about the WAL drives burning out faster than average because of their high write volume. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] WALL on controller without battery?

2007-07-11 Thread Greg Smith
or for troubleshooting isolation you could always get any data you needed off any 4-disk set with either controller. The little 2-disk unit is providing no such redundancy. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] WALL on controller without battery?

2007-07-11 Thread Greg Smith
trying to separate out the WAL. If you expected hundreds of updates per second, that's where you need to start thinking about a separate WAL disk, and even then with 8 disks to spread the load out and a good caching controller you might still be fine. -- * Greg Smith [EMAIL PROTECTED] http

[PERFORM] Estimating WAL volume

2007-07-11 Thread Greg Smith
of indexes factor into things--just add the width of the index in bytes to the size of the record, or is it worse than that? -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 5: don't forget

Re: [PERFORM] PostgreSQL publishes first real benchmark

2007-07-12 Thread Greg Smith
significantly if you're not very systematic about testing it many times at various client counts. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 9: In versions below 8.0, the planner will ignore

Re: [PERFORM] Postgres configuration for 64 CPUs, 128 GB RAM...

2007-07-17 Thread Greg Smith
this parameter. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 5: don't forget to increase your free space map settings

Re: [PERFORM] User concurrency thresholding: where do I look?

2007-07-19 Thread Greg Smith
productive speculating about the cause here will be until there's a test script available so other people can see where the tipping point is on their system. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] User concurrency thresholding: where do I look?

2007-07-20 Thread Greg Smith
a PG database, but the code is very immature. Last time I tried there were plenty of crashes and there seemed to be some transaction wrapping issues that caused deadlocks with some tests.] -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] Dell Hardware Recommendations

2007-08-09 Thread Greg Smith
now. Every dollar spent on work to quantify that early will easily pay for itself in helping guide your purchase and future plans; that's what I'd be bringing in people in right now to do if I were you, if that's not something you're already familiar with measuring. -- * Greg Smith [EMAIL

Re: [PERFORM] io storm on checkpoints, postgresql 8.2.4, linux

2007-08-22 Thread Greg Smith
team for the upcoming 8.3 beta. Probably more productive use of your time than going crazy trying to fix the issue in 8.2.4. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched

Re: [PERFORM] io storm on checkpoints, postgresql 8.2.4, linux

2007-08-23 Thread Greg Smith
, in earlier versions that didn't happen. The test I'd like to see more people run is to simulate their workloads with checkpoint_completion_target set to 0.5, 0.7, and 0.9 and see how each of those settings works relative to the 8.2 behavior. -- * Greg Smith [EMAIL PROTECTED] http

Re: [PERFORM] 8.2 Autovacuum BUG ?

2007-08-31 Thread Greg Smith
how to add manpower to it usefully. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 2: Don't 'kill -9' the postmaster

Re: [PERFORM] SAN vs Internal Disks

2007-09-06 Thread Greg Smith
into an area where your support situation is fuzzy just to save that money. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http

Re: [PERFORM] SAN vs Internal Disks

2007-09-07 Thread Greg Smith
of those situations, then perhaps the salesman's claim could have some merit. There are lots of reasons one might want to use a SAN, but a higher I/O rate when fairly comparing to connecting disks directly is unlikely to be on that list. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com

Re: [PERFORM] DRBD and Postgres: how to improve the perfomance?

2007-09-09 Thread Greg Smith
On Sat, 8 Sep 2007, Joshua D. Drake wrote: You would have to have lightning handed by God to your server to have a total power failure without proper shutdown in the above scenario. Do you live somewhere without thunderstorms? This is a regular event in this part of the world during the

Re: [PERFORM] Barcelona vs Tigerton

2007-09-11 Thread Greg Smith
going to need a database-specific benchmark before there's useful data for your case. Yesterday's meta-coverage at Ars was a nice summary of the current state of things: http://arstechnica.com/news.ars/post/20070910-barcelonas-out-and-the-reviews-are-out.html -- * Greg Smith [EMAIL PROTECTED

Re: [PERFORM] random_page_costs - are defaults of 4.0 realistic for SCSI RAID 1

2007-09-11 Thread Greg Smith
the data, but if I'm watching it I always use dstat now. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your friend

Re: [PERFORM] [Again] Postgres performance problem

2007-09-12 Thread Greg Smith
. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 5: don't forget to increase your free space map settings

Re: [PERFORM] Long Running Commits - Not Checkpoints

2007-09-13 Thread Greg Smith
may make more sense. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 6: explain analyze is your friend

Re: [PERFORM] Long Running Commits - Not Checkpoints

2007-09-14 Thread Greg Smith
. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org/docs/faq

Re: [PERFORM] Linux mis-reporting memory

2007-09-21 Thread Greg Smith
when I want a better idea what's going on. As good of an article on this topic as I've found is http://gentoo-wiki.com/FAQ_Linux_Memory_Management which recommends using free to clarify how big the disk cache really is. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD

Re: [PERFORM] Low CPU Usage

2007-09-22 Thread Greg Smith
suggested at http://www.westnet.com/~gsmith/content/postgresql/pg-disktesting.htm and see how your results compare to the single SATA disk example I give there. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast

Re: [PERFORM] building a performance test suite

2007-10-10 Thread Greg Smith
see what I mean. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 3: Have you checked our extensive FAQ? http://www.postgresql.org/docs/faq

Re: [PERFORM] Bunching transactions

2007-10-26 Thread Greg Smith
sins are committed in the name of efficiency (without necessarily achieving it) than for any other single reason - including blind stupidity. That was back in 1972. Both his and Knuth's papers centered on abusing GOTO, which typically justified at the time via performance concerns. -- * Greg

Re: [PERFORM] Migrating to 8.3 - checkpoints and background writer

2007-11-04 Thread Greg Smith
are weakest relative to what's normally in a server-class system. -- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 7: You can help support the PostgreSQL project by donating

Re: [PERFORM] hp ciss on freebsd

2007-11-05 Thread Greg Smith
-- * Greg Smith [EMAIL PROTECTED] http://www.gregsmith.com Baltimore, MD ---(end of broadcast)--- TIP 4: Have you searched our list archives? http://archives.postgresql.org

Re: [PERFORM] PostgreSQL vs MySQL, and FreeBSD

2007-11-09 Thread Greg Smith
On Fri, 9 Nov 2007, Sebastian Hennebrueder wrote: If the queries are complex, this is understable. The queries used for this comparison are trivial. There's only one table involved and there are no joins. It's testing very low-level aspects of performance. -- * Greg Smith [EMAIL

Re: [PERFORM] dell versus hp

2007-11-09 Thread Greg Smith
). On a real server, I'd suggest being more worried about how good the disk controller is, what the expansion options are there, and relative $/core. In the x86/x64 realm, I don't feel CPU architecture is a huge issue right now when you're running a database. -- * Greg Smith [EMAIL PROTECTED

Re: [PERFORM] autovacuum: recommended?

2007-11-19 Thread Greg Smith
. And I cannot upgrade the libraries without damaging other programs. You're also right that this is tricky. I've written a guide that goes over the main issues involved at http://www.westnet.com/~gsmith/content/postgresql/pgrpm.htm if you ever wanted to explore this as an option. -- * Greg

  1   2   3   4   5   6   7   8   9   10   >