Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-28 Thread Suchandra Thapa
On Mon, 2003-11-24 at 19:16, Greg Stark wrote: William Yu [EMAIL PROTECTED] writes: You're right, though, mirroring a solid state drive is pretty pointless; if power fails, both mirrors are dead. Actually no. Solid state memory is non-volatile. They retain data even without power.

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-26 Thread Tom Lane
William Yu [EMAIL PROTECTED] writes: I then tried to put the WAL directory onto a ramdisk. I turned off swapping, created a tmpfs mount point and copied the pg_xlog directory over. Everything looked fine as far as I could tell but Postgres just panic'd with a file permissions error. Anybody

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-26 Thread William Yu
Tom Lane wrote: William Yu [EMAIL PROTECTED] writes: I then tried to put the WAL directory onto a ramdisk. I turned off swapping, created a tmpfs mount point and copied the pg_xlog directory over. Everything looked fine as far as I could tell but Postgres just panic'd with a file permissions

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-26 Thread Dror Matalon
But the permissions of the base ramdisk might be wrong. I'd su to the user that you run postgres as (probably postgres), and make sure that you can go to the directory where the log and the database files are and make sure you can see the files. On Wed, Nov 26, 2003 at 10:03:47AM -0800, William

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-24 Thread William Yu
This is an intriguing thought which leads me to think about a similar solution for even a production server and that's a solid state drive for just the WAL. What's the max disk space the WAL would ever take up? There's quite a few 512MB/1GB/2GB solid state drives available now in the

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-24 Thread Josh Berkus
William, When my current job batch is done, I'll save a copy of the dir and give the WAL on ramdrive a test. And perhaps even buy a Sandisk at the local store and run that through the hooper. We'll be interested in the results. The Sandisk won't be much of a performance test; last I

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-24 Thread William Yu
Josh Berkus wrote: William, When my current job batch is done, I'll save a copy of the dir and give the WAL on ramdrive a test. And perhaps even buy a Sandisk at the local store and run that through the hooper. We'll be interested in the results. The Sandisk won't be much of a performance

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-24 Thread William Yu
Josh Berkus wrote: William, The SanDisks do seem a bit pokey at 16MBps. On the otherhand, you could get 4 of these suckers, put them in a mega-RAID-0 stripe for 64MBps. You shouldn't need to do mirroring with a solid state drive. I wouldn't count on RAID0 improving the speed of SANDisk's much.

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-24 Thread Greg Stark
William Yu [EMAIL PROTECTED] writes: You're right, though, mirroring a solid state drive is pretty pointless; if power fails, both mirrors are dead. Actually no. Solid state memory is non-volatile. They retain data even without power. Note that flash ram only has a finite number of write

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-23 Thread Tom Lane
William Yu [EMAIL PROTECTED] writes: [ we don't care about data integrity ] I already have fsync off. Short of buying more hardware -- which I will probably do anyways once I figure out whether I need more CPU, memory or disk -- what else can I do to max out the speed? Operation mix is about

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-23 Thread Joe Conway
William Yu wrote: My situation is this. We have a semi-production server where we pre-process data and then upload the finished data to our production servers. We need the fastest possible write performance. Having the DB go corrupt due to power loss/OS crash is acceptable because we can

Re: [PERFORM] Maximum Possible Insert Performance?

2003-11-23 Thread Shridhar Daithankar
William Yu wrote: My situation is this. We have a semi-production server where we pre-process data and then upload the finished data to our production servers. We need the fastest possible write performance. Having the DB go corrupt due to power loss/OS crash is acceptable because we can