Обсуждение: Re: Performance with 2 AMD/Opteron 2.6Ghz and 8gig
I would be interested in what numbers you would get out of bonnie++ (http://www.coker.com.au/bonnie++) and BenchmarkSQL (http://sourceforge.net/projects/benchmarksql) on that hardware, for comparison with our DL385 (2xOpteron 280, 16Gb ram) and MSA1500. If you need help building benchmarksql, I can assist you with that. Actually, I would be interested if everyone who's reading this that has a similar machine (2 cpu, dual core opteron) with different storage systems could send me their bonnie + benchmarksql results! /Mikael -----Original Message----- From: pgsql-performance-owner@postgresql.org [mailto:pgsql-performance-owner@postgresql.org] On Behalf Of Luke Lonergan Sent: den 28 juli 2006 08:55 To: Kjell Tore Fossbakk; pgsql-performance@postgresql.org Subject: Re: [PERFORM] Performance with 2 AMD/Opteron 2.6Ghz and 8gig Kjell, > I got 4 150GIG SCSI disks in a Smart Array 5i 1+0 RAID. The Smart Array 5i is a terrible performer on Linux. I would be surprised if you exceed the performance of a single hard drive with this controller when doing I/O from disk. Since your database working set is larger than memory on the machine, I would recommend you use a simple non-RAID U320 SCSI controller, like those from LSI Logic (which HP resells) and implement Linux software RAID. You should see a nearly 10x increase in performance as compared to the SmartArray 5i. If you have a good relationship with HP, please ask them for some documentation of RAID performance on Linux with the SmartArray 5i. I predict they will tell you what they've told me and others: "the 5i is only useful for booting the OS". Alternately they could say: "we have world record performance with our RAID controllers", in which case you should ask them if that was with the 5i on Linux or whether it was the 6-series on Windows. - Luke ---------------------------(end of broadcast)--------------------------- TIP 4: Have you searched our list archives? http://archives.postgresql.org
Mikael Carneholm wrote: > I would be interested in what numbers you would get out of bonnie++ > (http://www.coker.com.au/bonnie++) and BenchmarkSQL > (http://sourceforge.net/projects/benchmarksql) on that hardware, for > comparison with our DL385 (2xOpteron 280, 16Gb ram) and MSA1500. If you > need help building benchmarksql, I can assist you with that. > > Actually, I would be interested if everyone who's reading this that has > a similar machine (2 cpu, dual core opteron) with different storage > systems could send me their bonnie + benchmarksql results! > Here's the bonnie++ results from our Sun Fire V40z (2x Opteron 250, 4GB RAM) with 6 15krpm 73GB drives connected to an LSI MegaRAID 320-2X controller with 512MB cache. It's running Linux, and I'm using what seems to be a fairly typical 6-drive setup: 2 drives in RAID-1 for OS and WAL, and 4 drives in RAID-10 for data. This is from the 4-drive RAID-10 array: Version 1.03 ------Sequential Output------ --Sequential Input- --Random- -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks-- Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP gaz 8G 56692 88 73061 12 33048 6 44994 64 132571 14 474.0 0 ------Sequential Create------ --------Random Create-------- -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete-- files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP 16 19448 88 +++++ +++ 18611 72 19952 90 +++++ +++ 15167 65 This system is actually in production currently, and while it's a rather quiet time at the moment, it still wasn't _entirely_ inactive when those numbers were run, so the real performance is probably a little higher. I'll see if I can run some BenchmarkSQL numbers as well. Thanks Leigh > /Mikael > > > -----Original Message----- > From: pgsql-performance-owner@postgresql.org > [mailto:pgsql-performance-owner@postgresql.org] On Behalf Of Luke > Lonergan > Sent: den 28 juli 2006 08:55 > To: Kjell Tore Fossbakk; pgsql-performance@postgresql.org > Subject: Re: [PERFORM] Performance with 2 AMD/Opteron 2.6Ghz and 8gig > > Kjell, > >> I got 4 150GIG SCSI disks in a Smart Array 5i 1+0 RAID. > > The Smart Array 5i is a terrible performer on Linux. I would be > surprised if you exceed the performance of a single hard drive with this > controller when doing I/O from disk. Since your database working set is > larger than memory on the machine, I would recommend you use a simple > non-RAID U320 SCSI controller, like those from LSI Logic (which HP > resells) and implement Linux software RAID. You should see a nearly 10x > increase in performance as compared to the SmartArray 5i. > > If you have a good relationship with HP, please ask them for some > documentation of RAID performance on Linux with the SmartArray 5i. I > predict they will tell you what they've told me and others: "the 5i is > only useful for booting the OS". Alternately they could say: "we have > world record performance with our RAID controllers", in which case you > should ask them if that was with the 5i on Linux or whether it was the > 6-series on Windows. > > - Luke > > > ---------------------------(end of broadcast)--------------------------- > TIP 4: Have you searched our list archives? > > http://archives.postgresql.org > > > ---------------------------(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 datatypes do not > match >
> systems could send me their bonnie + benchmarksql results!
I am one of the authors of BenchmarkSQL, it is similar to a DBT2. But, its very easy to use (&/or abuse). It's a multithreaded Java Swing client that can run the exact same benchmark (uses JDBC prepared statements) against Postgres/EnterpriseDB/Bizgres, MySQueeL, Horacle, Microsloth, etc, etc. You can find BenchmarkSQL on pgFoundry and SourceForge.
As expected, Postgres is good on this benchmark and is getting better all the time.
If you run an EnterpriseDB install right out of the box versus a PG install right out of the box you'll notice that EnterpriseDB outperforms PG by better than 2x. This does NOT mean that EnterpriseDB is 3x faster than Postgres... EnterpriseDB is the same speed as Postgres. We do something we call "Dynatune" at db startup time. The algorithm is pretty simple in our current GA version and really only considers the amount of RAM, SHARED Memory, and machine usage pattern. Manual tuning is required to really optimize performance....
For great insight into the basics of quickly tuning PostgreSQL for a reasonable starting point, check out the great instructions offered by Josh Berkus and Joe Conway at http://www.powerpostgresql.com/PerfList/.
The moral of this unreasonably verbose email is that you shouldn't abuse BenchmarkSQL and measure runs without making sure that, at least, quick/simple best practices have been applied to tuning the db's you are choosing to test.
--Denis Lussier
CTO
>
Denis, On 7/29/06 11:09 AM, "Denis Lussier" <denisl@enterprisedb.com> wrote: > We do something we call "Dynatune" at db startup time. Sounds great - where do we download it? - Luke
Not sure that EnterpriseDB's Dynatune is the general purpose answer that the PG community has been searching to find. Actually, I think it could be, but... the community process will decide.
We are presently planning to create a site that will be called http://gforge.enterprisedb.com that will be similar in spirit to BizGres. By this I mean that we will be open sourcing many key small "improvements" (in the eye of the beholder) for PG that will potentially make it into PG (likely in some modified format) depending on the reactions and desires of the general Postgres community.
In case anyone is wondering... NO, EnterpriseDB won't be open sourcing the legacy Horacle stuff we've added to our product (at least not yet). This stuff is distributed under our Commercial Open Source license (similar to SugarCRM's). Our Commercial Open Source license simply means that if you buy a Platinum Subscription to our product, then you can keep the source code under your pillow and use it internally at your company however you see fit.
--Denis Lussier
CTO
On 7/29/06, Luke Lonergan <llonergan@greenplum.com> wrote:
Denis,
On 7/29/06 11:09 AM, "Denis Lussier" < denisl@enterprisedb.com> wrote:
> We do something we call "Dynatune" at db startup time.
Sounds great - where do we download it?
- Luke