Merlin Moncure [EMAIL PROTECTED] writes:
Alex wrote:
Without starting too much controvesy I hope, I would seriously
recommend you evaluate the AMCC Escalade 9500S SATA controller.
...
At the risk of shaming myself with another 'me too' post, I'd like to
say that my experiences back this
Greg Stark wrote:
Merlin Moncure [EMAIL PROTECTED] writes:
Alex wrote:
Without starting too much controvesy I hope, I would seriously
recommend you evaluate the AMCC Escalade 9500S SATA controller.
.
At the risk of shaming myself with another 'me too' post, I'd like to
say that
I assume AMCC == 3ware now?
Has anyone verified that fsync is safe on these controllers? Ie, that they
aren't caching writes and lying about the write completing like IDE
drives often do by default?
The higher end AMCC/3ware controllers actually warn you about using
write-cache. You have
Joshua D. Drake [EMAIL PROTECTED] writes:
I assume AMCC == 3ware now?
Has anyone verified that fsync is safe on these controllers? Ie, that they
aren't caching writes and lying about the write completing like IDE
drives often do by default?
The higher end AMCC/3ware controllers
Greg Stark wrote:
Joshua D. Drake [EMAIL PROTECTED] writes:
I assume AMCC == 3ware now?
Has anyone verified that fsync is safe on these controllers? Ie, that they
aren't caching writes and lying about the write completing like IDE
drives often do by default?
The higher end
Anyone using power5 platform? something like an ibm eserver p5 520
running red hat linux.
(http://www-1.ibm.com/servers/eserver/pseries/hardware/entry/520.html)?
klint.
+---+-+
: Klint Gore: Non rhyming:
: EMail
Bruce Momjian pgman@candle.pha.pa.us writes:
I asked 3ware this at the Linuxworld Boston show and they said their
controller keeps the information in cache until they are sure it is on
the platters and not just in the disk cache, but that is far from a 100%
reliable report.
Hm. Well, keeping
] On Behalf Of Josh Berkus
Sent: Tuesday, 11 January 2005 5:35 PM
To: pgsql-performance@postgresql.org
Cc: Christopher Browne
Subject: Re: [PERFORM] which dual-CPU hardware/OS is fastest for PostgreSQL?
Chris,
I don't know so much about FreeBSD's handling of this, but on Linux,
there's pretty strong
Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Josh Berkus
Sent: Tuesday, 11 January 2005 5:35 PM
To: pgsql-performance@postgresql.org
Cc: Christopher Browne
Subject: Re: [PERFORM] which dual-CPU hardware/OS is fastest for PostgreSQL?
Chris,
I don't know so
Jan Dittmer [EMAIL PROTECTED] writes:
You could always do raid 1 over raid 0, with newer kernels (2.6ish)
there is even a dedicated raid10 driver.
Aren't you much better off doing raid 0 over raid 1?
With raid 1 over raid 0 you're mirroring two stripe sets. That means if any
drive from the
Alex wrote:
Without starting too much controvesy I hope, I would seriously
recommend you evaluate the AMCC Escalade 9500S SATA controller. It
has many of the features of a SCSI controler, but works with cheaper
drives, and for half the price or many SCSI controlers (9500S-8MI goes
for abour
Merlin,
I think the danger about SATA is that many SATA components are not
server quality, so you have to be more careful about what you buy. For
example, you can't just assume your SATA backplane has hot swap lights
(got bit by this one myself, heh).
Yeah, that's my big problem with
Josh Berkus josh@agliodbs.com writes:
Merlin,
I think the danger about SATA is that many SATA components are not
server quality, so you have to be more careful about what you buy. For
example, you can't just assume your SATA backplane has hot swap lights
(got bit by this one myself,
Greg wrote:
Josh Berkus josh@agliodbs.com writes:
Merlin,
I think the danger about SATA is that many SATA components are not
server quality, so you have to be more careful about what you buy.
For
example, you can't just assume your SATA backplane has hot swap
lights
(got bit by
Greg Stark wrote:
Jan Dittmer [EMAIL PROTECTED] writes:
You could always do raid 1 over raid 0, with newer kernels (2.6ish)
there is even a dedicated raid10 driver.
Aren't you much better off doing raid 0 over raid 1?
With raid 1 over raid 0 you're mirroring two stripe sets. That
Joshua D. Drake wrote:
RAID controllers tend to use i960 or StrongARM CPUs that run at speeds
that _aren't_ all that impressive. With software RAID, you can take
advantage of the _enormous_ increases in the speed of the main CPU.
I don't know so much about FreeBSD's handling of this, but on
Infact the cache hit ratio that Oracle suggests is the minimum good
value is 95%. Anything below that is bad news. The reason is pretty
obvious - RAM transfer speed is around 3.2G/sec these days, whilst
even the best array isn't going to give more than 400MB/sec, and
that's not even starting to
Alex Turner [EMAIL PROTECTED] writes:
Infact the cache hit ratio that Oracle suggests is the minimum good
value is 95%. Anything below that is bad news.
Well that seems very workload dependent. No amount of cache is going to be
able to achieve that for a DSS system chugging sequentially
No - I agree - Analysis cache hit rate as a single indicator is
dangerous. You can easily increase cache hit rate by de-optimizing a
good query so it uses more CPU cylces, and therefore has a higher
cache hit rate. All information has to be taken as a whole when
performing optimization on a
On Mon, Jan 10, 2005 at 08:31:22PM -0800, Joshua D. Drake wrote:
Unless something has changed though, you can't run raid 10
with linux software raid
Hm, why not? What stops you from making two RAID-0 devices and mirroring
those? (Or the other way round, I can never remember :-) )
/* Steinar */
...and on Mon, Jan 10, 2005 at 08:31:22PM -0800, Joshua D. Drake used the
keyboard:
RAID controllers tend to use i960 or StrongARM CPUs that run at speeds
that _aren't_ all that impressive. With software RAID, you can take
advantage of the _enormous_ increases in the speed of the main
On 11 Jan 2005 04:25:04 GMT
Christopher Browne [EMAIL PROTECTED] wrote:
Xeon sux pretty bad...
Linux or FreeBSD or _?_
The killer question won't be of what OS is faster, but rather of
what OS better supports the fastest hardware you can get your hands
on.
Well, if multiple OSs work on
Subject: [PERFORM] which dual-CPU hardware/OS is fastest for
PostgreSQL?
I'm sorry if there's a URL out there answering this, but I couldn't
find
it.
For those of us that need the best performance possible out of a
dedicated dual-CPU PostgreSQL server, what is recommended?
AMD64
while you weren't looking, Merlin Moncure wrote:
2 way or 4 way Opteron depending on needs (looking on a price for 4-way?
Go here: http://www.swt.com/qo3.html).
Try also the Appro 1U 4-way Opteron server, at:
http://www.appro.com/product/server_1142h.asp
I specced a 4-way 842 (1.6 GHz:
Rosser Schwarz [EMAIL PROTECTED] writes:
Try also the Appro 1U 4-way Opteron server, at:
http://www.appro.com/product/server_1142h.asp
Back in the day, we used to have problems with our 1U dual pentiums. We
attributed it to heat accelerating failure. I would fear four opterons in 1U
would be
nuts, they have
an 8U with 40xSATA backplane.
Alex Turner
NetEconomist
On Tue, 11 Jan 2005 08:33:09 -0500, Merlin Moncure
[EMAIL PROTECTED] wrote:
Subject: [PERFORM] which dual-CPU hardware/OS is fastest for
PostgreSQL?
I'm sorry if there's a URL out there answering this, but I couldn't
$4000 is not going to get you much disk - If you buy components from
the cheapest source I know (newegg.com) you end up around $5k with
14x36gig Raptor SATA drives and a 4U chasis with a 14xSATA built in
back plane packing 2x9500S AMCC Escalade RAID cards, which are
supported in Linux, 4Gig
while you weren't looking, Greg Stark wrote:
Back in the day, we used to have problems with our 1U dual pentiums. We
attributed it to heat accelerating failure. I would fear four opterons in 1U
would be damned hard to cool effectively, no?
Opterons actually run pretty coolly, comparatively.
Merlin Moncure [EMAIL PROTECTED] writes:
heh, our apps do tend to be CPU bound. Generally, I think the extra CPU
horsepower is worth the investment until you get to the really high end
cpus.
I find that while most applications I work with shouldn't be cpu intensive
they do seem end up being
Steinar H. Gunderson wrote:
On Mon, Jan 10, 2005 at 08:31:22PM -0800, Joshua D. Drake wrote:
Unless something has changed though, you can't run raid 10
with linux software raid
Hm, why not? What stops you from making two RAID-0 devices and mirroring
those? (Or the other way round, I can
I'm sorry if there's a URL out there answering this, but I couldn't find it.
For those of us that need the best performance possible out of a
dedicated dual-CPU PostgreSQL server, what is recommended?
AMD64/Opteron or i386/Xeon?
Linux or FreeBSD or _?_
I'm assuming hardware RAID 10 on 15k SCSI
Miles Keaton wrote:
I'm sorry if there's a URL out there answering this, but I couldn't find it.
For those of us that need the best performance possible out of a
dedicated dual-CPU PostgreSQL server, what is recommended?
AMD64/Opteron or i386/Xeon?
AMD64/Opteron
Linux or FreeBSD or _?_
This
Quoth [EMAIL PROTECTED] (Miles Keaton):
I'm sorry if there's a URL out there answering this, but I couldn't
find it.
For those of us that need the best performance possible out of a
dedicated dual-CPU PostgreSQL server, what is recommended?
AMD64/Opteron or i386/Xeon?
Xeon sux pretty
Xeon sux pretty bad...
Linux or FreeBSD or _?_
The killer question won't be of what OS is faster, but rather of
what OS better supports the fastest hardware you can get your hands
on.
We tried doing some FreeBSD benchmarking on a quad-Opteron box, only
to discover that the fibrechannel
RAID controllers tend to use i960 or StrongARM CPUs that run at speeds
that _aren't_ all that impressive. With software RAID, you can take
advantage of the _enormous_ increases in the speed of the main CPU.
I don't know so much about FreeBSD's handling of this, but on Linux,
there's pretty
Chris,
I don't know so much about FreeBSD's handling of this, but on Linux,
there's pretty strong indication that _SOFTWARE_ RAID is faster than
hardware RAID.
Certainly better than an Adaptec. But not necessarily better than a
medium-end RAID card, like an LSI. It really depends on the
36 matches
Mail list logo
