Re: [PERFORM] amazon ec2

2011-05-05 Thread Dave Page
On Thu, May 5, 2011 at 1:02 AM, Josh Berkus wrote: > >> FWIW, EnterpriseDB's "InfiniCache" provides the same caching benefit. The >> way that works is when PG goes to evict a page from shared buffers that page >> gets compressed and stuffed into a memcache cluster. When PG determines that >> a

Re: [PERFORM] amazon ec2

2011-05-04 Thread Denis de Bernardy
- Original Message - > From: Josh Berkus > To: postgres performance list > Cc: > Sent: Thursday, May 5, 2011 2:02 AM > Subject: Re: [PERFORM] amazon ec2 > So memcached basically replaces the filesystem? > > That sounds cool, but I'm wondering if it'

Re: [PERFORM] amazon ec2

2011-05-04 Thread david
On Wed, 4 May 2011, Josh Berkus wrote: Date: Wed, 04 May 2011 17:02:53 -0700 From: Josh Berkus To: postgres performance list Subject: Re: [PERFORM] amazon ec2 FWIW, EnterpriseDB's "InfiniCache" provides the same caching benefit. The way that works is when PG goes to ev

Re: [PERFORM] amazon ec2

2011-05-04 Thread Josh Berkus
> FWIW, EnterpriseDB's "InfiniCache" provides the same caching benefit. The way > that works is when PG goes to evict a page from shared buffers that page gets > compressed and stuffed into a memcache cluster. When PG determines that a > given page isn't in shared buffers it will then check tha

Re: [PERFORM] amazon ec2

2011-05-04 Thread Shaun Thomas
On 05/03/2011 01:48 PM, Joel Reymont wrote: What are the best practices for setting up PG 9.x on Amazon EC2 to get the best performance? Use EC2 and other Amazon hosting for cloud-based client access only. Their shared disk services are universally despised by basically everyone who has trie

Re: [PERFORM] amazon ec2

2011-05-04 Thread Jim Nasby
On May 3, 2011, at 5:39 PM, Greg Smith wrote: > I've also seen over a 20:1 speedup over PostgreSQL by using Greenplum's free > Community Edition server, in situations where its column store + compression > features work well on the data set. That's easiest with an append-only > workload, and th

Re: [PERFORM] amazon ec2

2011-05-03 Thread Greg Smith
Greg Spiegelberg wrote: I ran pgbench tests late last year comparing EC2, GoGrid, a 5 year-old lab server and a new server. Whether I used a stock postgresql.conf or tweaked, the current 8.4 or 9.0, or varied the EC2 instance size EC2 was always at the bottom ranging from 409.834 to 693.100 tp

Re: [PERFORM] amazon ec2

2011-05-03 Thread Greg Smith
Mark Rostron wrote: the success/failure of it depends on your typical query activity, the size of your critical result set, and whether you are able to get enough RAM to make this work. Basically, it all comes down to "does the working set of data I access frequently fit in RAM?" If it does,

Re: [PERFORM] amazon ec2

2011-05-03 Thread Josh Berkus
On 5/3/11 11:48 AM, Joel Reymont wrote: > What are the best practices for setting up PG 9.x on Amazon EC2 to get the > best performance? Yes. Don't use EC2. There is no "best" performance on EC2. There's not even "good performance". Basically, EC2 is the platform for when performance doesn't

Re: [PERFORM] amazon ec2

2011-05-03 Thread david
Lang On Tue, 3 May 2011, Alan Hodgson wrote: Date: Tue, 3 May 2011 13:09:51 -0700 From: Alan Hodgson To: pgsql-performance@postgresql.org Subject: Re: [PERFORM] amazon ec2 On May 3, 2011 12:43:13 pm you wrote: On May 3, 2011, at 8:41 PM, Alan Hodgson wrote: I am also interested in tips for

Re: [PERFORM] amazon ec2

2011-05-03 Thread Mark Rostron
iowait is a problem on any platform that relies on spinning media, compared to RAM. no matter how fast a disk is, and no matter how intelligent the controller is, you are still dealing with an access speed differential of 10^6 (speed of disk access compared to memory access). i have had good result

Re: [PERFORM] amazon ec2

2011-05-03 Thread Greg Spiegelberg
On Tue, May 3, 2011 at 2:09 PM, Alan Hodgson wrote: > On May 3, 2011 12:43:13 pm you wrote: > > On May 3, 2011, at 8:41 PM, Alan Hodgson wrote: > > > I am also interested in tips for this. EBS seems to suck pretty bad. > > > > Alan, can you elaborate? Are you using PG on top of EBS? > > > > Tryin

Re: [PERFORM] amazon ec2

2011-05-03 Thread Alan Hodgson
On May 3, 2011 12:43:13 pm you wrote: > On May 3, 2011, at 8:41 PM, Alan Hodgson wrote: > > I am also interested in tips for this. EBS seems to suck pretty bad. > > Alan, can you elaborate? Are you using PG on top of EBS? > Trying to, yes. Let's see ... EBS volumes seem to vary in speed. Some

Re: [PERFORM] amazon ec2

2011-05-03 Thread Joel Reymont
On May 3, 2011, at 8:41 PM, Alan Hodgson wrote: > I am also interested in tips for this. EBS seems to suck pretty bad. Alan, can you elaborate? Are you using PG on top of EBS? -- - for hire: mac osx device driver ninja, ker

Re: [PERFORM] amazon ec2

2011-05-03 Thread Alan Hodgson
On May 3, 2011 11:48:35 am Joel Reymont wrote: > What are the best practices for setting up PG 9.x on Amazon EC2 to get the > best performance? > I am also interested in tips for this. EBS seems to suck pretty bad. -- Sent via pgsql-performance mailing list (pgsql-performance@postgresql.org) T

[PERFORM] amazon ec2

2011-05-03 Thread Joel Reymont
What are the best practices for setting up PG 9.x on Amazon EC2 to get the best performance? Thanks in advance, Joel -- - for hire: mac osx device driver ninja, kernel extensions and usb drivers -