Andrew Pollack's Blog

Technology, Family, Entertainment, Politics, and Random Noise

Followup - more test data with really interesting results

By Andrew Pollack on 02/23/2004 at 01:35 PM EST

I modified the test (described here: http://www.thenorth.com/apblog2.nsf/0/816E292DD0A455E385256E3F0079C823 ) to try to make it resist things like random server performance changes due to whatever else the machine is doing. I've also tried to eliminate a few other variables.

The four tests were performed all at once. Each was performed 10 times, but not in order. A loop to 40 was created, and a modulus function was used to determine which test ran (e.g. if counter equaled 23, then 23/4 = 5 r3, so test 3 was run). The times listed are cumulative from all tens runs of each test. That should have mixed it up enough.

I've put the results in order. You'll notice that pipelined communication to the Domino server is clearly indicated over multiple concurrent communication. Within that, however, is the interesting result that even pipelined there is about a small advantage to having multiple Domino sessions. Personally, I think this is a terribly small advantage and in a servlet environment where the concurrency will not be quite so exact the contention should be lessened enough to make this negligible.

My own conclusion from this, is that based on the compromises of code simplicity, performance, and stability a single pipelined I/O queue thread as a static class should be the best way to handle all the Domino I/O for a single server. At some point I'll test multiple server access through the DIIOP thread.

The three machines are all running the same jvm (1.4) though the code is compiled as 1.3 compatible classes.

The single processor machine is my workstation, a cheap 1.7ghz Celeron with 1gb of RAM.

The "faster" of the two duals is a Dual P4 700mhz with 1gb of RAM, but its running a bunch of other stuff too. Also, that was the same machine as the Domino server, which tosses in some weird possibilities for contention but matches the real world case of where many java agents and servlets run.

The slower of the two duals is a Dual P-II 350mhz with 512megs of RAM running Windows NT (Yeah, yeah, but its still nice machine).


Single Processor Machine:

Test 2: 34,220ms. Pipelined, two sessions.
Test 1: 42,423ms. Pipelined, one session.
Test 4: 47,722ms. Threaded, two sessions.
Test 3: 53,765ms. Threaded, one session.

Dual Processor Machine, same machine as Domino:

Test 2: 37,596ms. Pipelined, two sessions.
Test 1: 40,155ms. Pipelined, one session.
Test 4: 51,767ms. Threaded, two sessions.
Test 3: 53,032ms. Threaded, one session.

Slower dual processor machine:

Test 2: 43,327ms. Pipelined, two sessions.
Test 1: 45,576ms. Pipelined, one session.
Test 3: 57,874ms. Threaded, one session.
Test 4: 67,298ms. Threaded, two sessions.


There are  - loading -  comments....



Other Recent Stories...

  1. 12/04/2014Looking for a few people who want to beta test my new SSL Certificate Request tool.I plan to open source this tool once I've done just a little more testing with other people. Drop me an email if you're interested. I'm looking for around 5 people who have the time, know how to deal with SSL stuff already, and already have the Notes 9.x admin client on their machines. The idea behind open sourcing for me, is that I've created the functional tool, and there's a lot of room for making it nicer looking and adding other kinds of functionality. For example, this tool allows you to create and ...... 
  2. 12/01/2014Well, it's official. IBM ConnectedED does not feel my contribution is worth the session time.I know I'm in good company, and I don't deserve a session slot any more than anyone else -- but I'd be lying if I didn't admit to being a bit frustrated and disappointed. For now, I'll hold my tongue about the decision process,wish the best of luck to those who will be speaking,hope the people attending find the content helpful,and say that if you want the content I've been deliveringyou'll have to come to some of the user groups or to Rudi's"Admin / Developer Camp" ...... 
  3. 12/01/2014First look at a new free Domino SSL certificate tool I've coded something that I plan to release to the community if there is enough interest. It's designed to make the process of getting SHA2 certificates a little easier. I've had to request a fair number of these recently and the command line stuff is tedious and it's easy to make mistakes or misplace the various files. This tool uses the same steps as the process IBM documents and the same tools. You still have to install openSSL and the kyrtool update on your 9.x Admin client machine. The tool checks to ...... 
  4. 11/10/2014Simplified explanation and steps for upgrading to SHA-2 encrypted SSL certificates for Domino 
  5. 11/04/2014Warning: IBMs Interim Fix¬†adding TLS 1.0 to Domino can break connections from Python and some other scripting clients 
  6. 11/04/2014Patch for the SSL v3 POODLE exploit has escaped IBM and can now be downloaded. You REALLY need this patch 
  7. 10/29/2014Automatic Spam Report to Provider Agent 
  8. 10/21/2014Quick update on the Domino SSL v3 "POODLE" , TLS, and SHA-2 issues -- Good news 
  9. 10/16/2014Summary Recommendation for dealing with the POODLE SSLv3 Vulnerability on Domino servers 
  10. 10/14/2014Speaking tonight ath the ICU One (aka NE Notes Users Group) 
Click here for more articles.....


pen icon Comment Entry
Subject
Your Name
Homepage
*Your Email
* Your email address is required, but not displayed.
 
Your thoughts....
 
Remember Me  

Please wait while your document is saved.