way as this is normally done with Postgres.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your sub
On 6/20/13 4:32 PM, Josh Berkus wrote:
First, cc'ing Greg Smith to see if he can address this with the Fusion
folks so that they stop giving out a bad guide.
I'm working on a completely replacement of that guide, one that actually
gives out a full set of advice. Right now I'
r. Sample from a busy system with
moderately tuned BGW and checkpoint_timeout at 15 minutes:
-[ RECORD 1 ]---+---
alloc_mbps | 246.019686474412
checkpoint_mbps | 0.0621780475463596
clean_mbps | 2.38631188442859
backend_mbps| 0.777490109599045
write_mbps | 3.2
what you're seeing
there. It doesn't actually use any significant amount of memory on its own.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pg
.
-Does this happen on every test run? Is it at the same time?
-You can run "top -bc" to dump snapshots of what the system is doing
every second. With some work you can then figure out what was actually
happening during the two seconds around when the throughput dropped.
--
es-and-ncq/
With that loose end sorted, I'll be kicking off a brand new round of SSD
tests on a 24 core server here soon. All those will appear on my blog.
The 320 drive is returning as the bang for buck champ, along with a DC
S3700 and a Seagate 1TB Hybrid drive with NAND durable write
es to flash wear or bytes
written, either. Several of the SMART attributes are labeled
"Vendor-specific," but you'll need to guess what they track and read the
associated values using third-party software."
That's a serious problem for most business use of this s
better protocol for handling things.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http:
efore abandoning it altogether.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www
et, and I haven't recommended anyone buy a 710 since the
announcement. However, "hit the street" is still an issue. No one has
been able to keep DC S3700 drives in stock very well yet. It took me
three tries through Newegg before my S3700 drive actually shipped.
--
Greg Smi
de 710 drives that
aim for 900TB instead. But I do have standby servers using the low
grade stuff, so anything I can do to decrease SSD burn rate without
dropping performance is useful. And only the top tier of transaction
rates will outrun a RAID1 pair of 15K drives dedicated to WAL.
--
them on traditional drives can be cost effective in a few ways. That
approach is lucky to hit 10K TPS though, so it can't compete against
what a PCI-E card like the FusionIO drives are capable of.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Ser
gh, so I'm still waiting for more
data before I feel comfortable saying exactly what the worst case looks
like.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing
almost free it's so
fast? Sure. But presuming all systems will look like that is
optimistic, and it sets unreasonable expectations.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgs
s. My
test server's 100GB DC S3700 was $250. That's still not two orders of
magnitude faster though.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing li
thing that's happened since the last base backup happened.
That can easily result in a week of downtime if you're only shipping
backups once per month, for example.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Suppor
flushed to disk.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.or
t this type of work going on in the background.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subs
systems are relatively small.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.p
ash and leave it on. Purchasing and
management people tend to get annoyed if they discover the core count of
the server is half what they thought they were buying. The potential
downside of HT isn't so big that its worth opening that can of worms,
unless you've run real application lev
safely and as fast as it should be, 2ndQuadrant
does offer a hardware benchmarking service to do that sort of thing:
http://www.2ndquadrant.com/en/hardware-benchmarking/ I think we're even
generating those reports in German now.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Bal
ake a look at http://www.postgresql.org/support/versioning/ and you'll
see 8.4 only has a little over a year before it won't get bug fixes
anymore. Also, your server would really appreciate the performance
gains added to 9.2. If that's a bit too leading edge for you, I don'
nge. Nowadays there really is no
reason to consider running pgbench on a system with a smaller scale than
that. I normally get a rough idea of things by running with scales 100,
250, 500, 1000, 2000.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training
; line in /proc/meminfo as the test runs will give
you an idea if write cache filling is actually an issue here. If that
number just keeps going up and speeds keep on dropping, that's at least
one cause here. This could easily be both that and an autovacuum
related too thoug
delay needed to vary a bit based on
the number of the siblings was one of the challenges I kept butting into
then. Making the GUC settings even more complicated for this doesn't
seem a productive step forward for the average user.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com
how can
I create a real-time replica of this data?" to protect databases, and
the standby server for that doesn't need to be an expensive system.
That said, there is no reason to set things up so that they only work
with that Intel RAID controller, given that it's not a very good
ermittently, you'll see one incredibly slow
query periodically while most are fast. All depends on exactly what
core is executing, where the memory it needs is at, and whether the
server wants to reclaim memory (and just what that means its own
complicated topic) as part of tha
their TPS numbers are useless without a contest of how big each
transaction is, and we don't know. I can take MemSQL seriously when
there's a press release describing how to replicate their benchmark
independently. Then it's useful to look at the absolute number.
--
Greg Smith
of writing that feature?" and "how can we
get them sponsored to focus on it?" I can tell from your comments yet
what role(s) in that process VMWare wants to take on internally, and
which it's looking for help with. The job of convincing people it's a
useful feature isn&
was CPU bound, that
would be an awesome world to live in.
Anyway, guessing at causes here is premature speculation. When there's
some code for the test kit published, at that point discussing the
particulars of why it's not running well will get interesting.
--
Greg Smith 2ndQua
t toward
leading edge SSD only to discover their real working set fits in memory
just fine, so it doesn't even matter. Or that the bottleneck is
somewhere else entirely.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support ww
e type MySQL is usually faster
than PostgreSQL on (i.e. ones using simple operations and operators), or
they could be ones where PostgreSQL is usually faster than MySQL (i.e.
more complicated joins). All I can tell you for sure if that they used
a query mix that makes MemSQL look much fast
IOPS of writes that are done more efficiently in terms of
flash longevity (710). You can't get both at the same time. The 710
may ultimately throttle its speed back to meet lifetime specifications
as the drive fills, it's really hard to benchmark the differences
between the tw
performance, consider running your own more
application-like benchmarks instead.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org
ented acceleration here and
b) on Solaris. You won't find a compelling performance improvement
listed at
https://ext4.wiki.kernel.org/articles/c/l/a/Clarifying_Direct_IO%27s_Semantics_fd79.html
and Linux has generally ignored direct I/O as something important to
optimize for.
--
Greg Smith 2ndQ
chive
archive
To make sure the difference wasn't some variation on "gets slower after
each run". pgbench suffers a lot from problems in that class.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
jects/reorg/
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.com
15:39:55.489344 semop(16777323, 0x7fffd09dac00, 1) = 0
Process 12634 detached
pg_locks for this 12634 shows all granted ones, nothing exciting there.
I asked how well this executes with enable_nestloop turned off, hoping
to see that next.
This all seems odd, and I get interested and concerned w
eliminate several of them.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.post
ng,
you may not find as much about ZFS tuning and SSDs as you'd like though.
http://www.2ndquadrant.com/en/talks/ has some updated material about
things discovered since the book was published. The "Bottom-Up Database
Benchmarking" there shows the tests I'm running nowadays
sons I keep so many samples on that
program's page is to help people navigate this whole maze, and have some
data points to set expectations against. See
https://github.com/gregs1104/stream-scaling for the code and the samples.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Bal
aluate RHEL6 to see how it's doing soon, just haven't had
time/requests for it.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performanc
onds on one of their servers if I try
to make that problem bad, you're only seeing the middle range of latency
issues so far.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-perfor
y the ext4 changes. In just about every other way but commit
performance, ext4 is faster than most other filesystems.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
t now there's no mention of that
parameter in the section that talks about parameters to configure; there
really should be.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-perform
ts=16 is a low setting.
You might as well set it to a large number, say 128, and let checkpoints
get driven by time instead. The existing limit isn't working
effectively anyway, and having more segments lets the checkpoint
spreading code work more evenly.
--
Greg Smith 2ndQuadrant US
plenty of times that the reason
behind "why isn't it using my index?" is "the index is too fat to
navigate efficiently", because the actual number of blocks involved is
factored into the cost computations.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimor
e trouble. I did a few blog
entries and mailing list posts about this earlier this year, and that
was as much documentation as I could justify at the time. If there's a
user-visible behavior changes here, that's the point where an update to
the manual would be in order.
--
Greg Smi
ere have been beating out improvements made to the
database fast enough that it's hard to innovate in this area within
Postgres.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-pe
7;d have to put a kernel bug on the list of suspects with this
unusual vmstat output.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@p
x27;s hard to do
that in the position you're in now though.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make chan
ose things. The advantage to making them happen less often is that
you get less total writes. People need to be careful about going a long
*time* between checkpoints. But there's very few cases where you need
to worry about the segment count going too high before another one is
trigg
useful.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref
-scaling but it's
still quite rough to use.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
<>
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to you
and I
haven't come across someone yet who wants to fund that size of project
for this purpose yet.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-p
more pieces, and see if one of them results in the query not
excluding partitions anymore or not. I can't figure out if you're
running into a basic error here, where constraint exclusion just isn't
working at all, or if you are only having this problem because the query
is too
to do that. A multi-gigabyte table can
easily be unavailable for several hours if you execute VACUUM FULL
against it. CLUSTER is almost always faster.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
determining if bloat is likely increasing or decreasing--which is
the purpose of that query. The value returned is a rough estimate, and
should not be considered useful as any sort of absolute measurement.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training
r what people really want to know nowadays. That's
going live to the world at the end of the month, at #PgWest:
http://pgwest2011.sched.org/event/875b87d8d237bef3a53ab27ac9c8057c
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24
lot of your test results seem like they may be using different levels
of write reliability, which makes things less fair than they should be
too--in favor of the cheap IDE drives normally. Check out
http://wiki.postgresql.org/wiki/Reliable_Writes for more information
about that topic.
the shared_buffers parameters on Windows--no
more than 512MB. That makes your server a bit less likely to run in the
nasty checkpoint spike issues Kevin was alluding to. I don't think
we've seen any reports of that on Windows. The problem is worst on Linux.
--
Greg Smith 2ndQuadra
On 08/24/2011 01:42 PM, David Boreham wrote:
On 8/24/2011 11:41 AM, Greg Smith wrote:
I've measured the performance of this drive from a couple of
directions now, and it always comes out the same. For PostgreSQL,
reading or writing 8K blocks, I'm seeing completely random worklo
#x27;s just over 2500 IOPS. It's quite possible
that number can go lower under pressure of things like internal drive
garbage collection however, which I believe is going into the 600 IOPS
figure. I haven't tried to force that yet--drive is too useful to me to
try and burn it out
h as looking at pg_stat_activity, will
sometimes miss one.
If you're willing to lose a connection sometimes, a cron job that polls
pg_stat_activity and saves a summary of what it finds will normally use
less resources. But connections that start and end between runs will be
missed.
--
Greg Sm
, but it sounds like you're not planning to run one of those
anyway. If I had 24 drives to connect, I'd prefer an LSI controller
just because I know those scale fine to that level; I'm not sure how
well Adaptec does there. Haven't found anyone brave enough to try that
te
together in the
future, that may be an option for improving performance one day.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
t to find slow lock issues by turning on log_lock_waits,
you're just going to put it right back to the default again--or lower it.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
On 08/15/2011 07:49 PM, Greg Smith wrote:
News update for anyone else who's trapped like me, waiting for a fix
to the Intel 320 SSD bug where they can truncate themselves to 8MB.
Over the weekend Intel has announced a firmware fix for the problem is
done, and is due to ship "withi
barrier" just because I'm used to that name on XFS systems.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make
esults. They should be between the ext3 and the XFS results,
not far lower than either. Normally this only comes from using a bad
set of mount options. With a battery-backed write cache, you'd want to
use "nobarrier" for example; if you didn't do that, that can cru
The most common source of dead drives is sudden, catastrophic
electronics failure. These are not predicted by SMART, and have nothing
to do with hitting the drive's wear limits.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24
hit as hard
yet by users. My paranoid raving about this particular bug isn't
strongly supported; I'll concede that with the additional data you've
provided. But I don't think it's completely unfounded either.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltim
;t assure
you'll a checkpoint begin and end in all circumstances, but it is the
expected case.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-perfor
kernels to provide this more efficient mechanism of ensuring
ordering...these future block layer improvements will change some kernel
interfaces..." Yikes, that does not inspire confidence to me.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
rom them is no fun.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.
read/written once, so the database cache is no
better than the OS one).
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make cha
the situation, the version of PostgreSQL you use won't matter
too much--the database will still be unreliable if the hardware is
configured to do the wrong thing.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant
ans ">8GB" right now.
Note that the problems you can run into with too much buffer cache are
much worse with a low setting for checkpoint_segments...and this
configuration doesn't change it at all from the tiny default. That
should go to at least 64 on a server this size.
x27;s commentary about network speed heavily influencing results.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make chan
ly need to separate out "bad driver" from the
other possibilities here given what you've described, and that's a low
impact way to do it.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us
disk before
returning to the client, but all the validation checks are done before
that. The sole risk with synchronous_commit off is that a client will
get COMMIT, but the server will lose the transaction completely--when
there's a crash before it's written to disk.
--
newsroom/blog/2011/05/19/chip-shot-new-5-year-limited-warranty-on-intel-ssd-320
We just need to figure out how/where they're drawing the "enterprise
usage levels" line at.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent via pgsql-performance mailing
8
18184 - 18159 = 25; exactly the count I used in 32MB blocks.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance
d up commits--you will
only see minimal benefit from with these SSDs.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance
ould
happen is that total speed keeps going up as you add more threads on the
newer system, while the old DDR2 model stays as the same basic total.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent via pgsql-performance mailing list (pgsql-performance@postgres
ssage-id/4d9d1fc3.4020...@2ndquadrant.com
And there's a larger discussion of this topic at
http://blog.2ndquadrant.com/en/2011/04/intel-ssd-now-off-the-sherr-sh.html
that answers this question in a bit more detail.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
-
lucky one to find it free of a write backlog. So the
best case is much better than a typical spinning drive with no such
cache. The worst case is in the 100ms+ range though on EBS.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent via pgsql-performance mailing
ays gotten seriously good
performance relative to the dollars spent with that series. Only one of
these Dell storage arrays I've heard two disappointing results from (but
not tested directly yet) is the MD3220.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
--
Sent
e), this can work much faster
than a normal load. It's able to skip the pg_xlog WAL writes in this
situation.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
djust how much work autovacuum does at any moment in time, it isn't
involved in any prioritization.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
Sent via pgsq
to coin a new acronym for: those are part
of the Most Important Values in that column. The MIV set is the MCV
information plus information about the rare but critical columns. And
the easiest way to expose that data to the planner is with a partial index.
I smell a blog post coming on th
l for this case is
http://pgbulkload.projects.postgresql.org/
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
Sent via pgsql-performance mailing list (pg
k transparently
the application is a nice benefit of EDB's commercial product. But it's
usually the case that if you really want to do the best possible
implementation of an approach, optimizing very specifically for your
application is what's needed.
--
Greg Smith 2nd
er performance, I aim for a 10X speedup and
often do much better than that.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
Sent via pgsql-performance mailin
ed table, but the way PostgreSQL
does it may make that hard to realize on Windows.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
Sent via pgsql-performance maili
the vacuum part of that is
the painful one.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http://www.2ndquadrant.us/postgresql-training/
--
Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org
on makers who feel they should be able to query any
way they want, regardless of its impact on the database. Finding a
middle ground there is usually challenging.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
Comprehensive and Customized PostgreSQL Training Classes:
http:
the set of data to be processed to become much larger than RAM,
it can be a bad decision. The performance drop when things stop fitting
in memory is not a slow one, it's like a giant cliff you fall off.
--
Greg Smith 2ndQuadrant USg...@2ndquadrant.com Baltimore, MD
PostgreSQL Tra
On 06/24/2011 02:55 PM, Shaun Thomas wrote:
On 06/24/2011 11:18 AM, Greg Smith wrote:
sync=14525.296 s, total=14786.868 s
What!? 6% of 8GB is just shy of 500MB. That's not a small
amount, exactly, but it took 14525 seconds to call syncs for those
writes? What kind of ridiculo
in 8.3-9.0, as a bug fix because this turns into a "system is too
slow to be considered operational" performance problem when it flares
up. This was a rare thing I'd never seen before back in September when
I started working on this area again; now I see it once a month on a new
system
1 - 100 of 1007 matches
Mail list logo
