A year or two back, I did some performance work with solid-state SCSI devices (ie hard drives emulated as SCSI drive, but using RAM DIMMs). However, the machine I was testing on, wasn't short of memory. So paging was of the pre-emptive, always-going-to-happen variety. And try as I might, with the limited time and resources I had at hand at the time, I couldn't simulate sufficient load / user counts (using CSTK) to really make the machine struggle. So I didn't see anything in the way of performance boost. And being pragmatic, given that there's a certain degree of paging activity that's always going to be present, I could only theorise that if I could get the product to make a difference, I'd perhaps trade waiting I/O times, for context switches and up the CPU load instead. I struggle to see a great area for impact for them - unless you need a total Rolls Royce, no expense spared implementation, with maximum performance, money no object. Otherwise, I would have thought it more cost-effective to simply add RAM, or more servers. Neil > -----Original Message----- > From: Bernd Harzog [mailto:Bernd.Harzog@xxxxxxxxxxx] > Sent: 16 February 2004 13:28 > To: thin@xxxxxxxxxxxxx > Subject: [THIN] Re: RAMDISK > > Good product, good people. What is does is allow you to > replace part of = your mechanical rotating magnetic disk > storage with a solid state disk = storage. So, you can put > things like your page file (or part of it) on a = drive that > is much faster than an ordinary disk drive, and almost as = > fast as memory. Since you are not reducing the amount of RAM > available = to applications when you do this, this is not a > case of robbing Peter to = pay Paul. It is however, quite a > bit more expensive, than for example = our product TScale, > which works by reducing the number of things that = have to > be kept in the page file. > > Cheers,=20 > > Bernd Harzog > CEO > RTO Software, Inc. > bernd.harzog@xxxxxxxxxxx > 678-455-5506 x701 > www.rtosoft.com > > -----Original Message----- > From: Steve Snyder [mailto:steven_snyder@xxxxxxxxx]=20 > Sent: Sunday, February 15, 2004 11:21 PM > To: thin@xxxxxxxxxxxxx > Subject: [THIN] Re: RAMDISK > > Or for those of you who recall Digital's non-voltile > ramdrives for VAXs, here's the modern equivalent (they > claim to increase a citrix box's scalabilty, so I'm > interested to read what Bernd thinks about it) > > http://www.tigicorp.com/tigijet.htm > > fwiw - I used to use ramdrives in the old days to > increase compiling performance until disk-caching > pretty much gave me the same advantage, which is why I > think its largely unused these days *********************************************** This e-mail and its attachments are confidential and are intended for the above named recipient only. If this has come to you in error, please notify the sender immediately and delete this e-mail from your system. You must take no action based on this, nor must you copy or disclose it or any part of its contents to any person or organisation. Statements and opinions contained in this email may not necessarily represent those of Littlewoods. Please note that e-mail communications may be monitored. The registered office of Littlewoods Limited and its subsidiaries is 100 Old Hall Street, Liverpool, L70 1AB. Registered number of Littlewoods Limited is 262152. ************************************************ ******************************************************** This weeks sponsor Vizioncore, Inc. --> vc-iMonitor - Performance Monitoring, Control & Reporting --> vc-iControl - Desktop & Start Menu Management & Reporting --> vc-iMapper - Drive, Printer & COM Management & Reporting http://vizioncore.com/products.html ********************************************************** Useful Thin Client Computing Links are available at: http://thethin.net/links.cfm *********************************************************** For Archives, to Unsubscribe, Subscribe or set Digest or Vacation mode use the below link: http://thethin.net/citrixlist.cfm