Ayende @ Rahien

Refunds available at head office

NuGet Perf, The Final Part – Load Testing – Results ^ 2

After seeing how well RavenDB does in perf testing, I decided to take it up a notch.

  • Starting from 10 users, with a  step duration of 1 sec, add 50 users for each step, all the way to 3,000.
  • Start with a warm up period of 20 seconds, then run the test for 10 minutes.

Let us see what happens, okay?

Just to be clear, this is a RavenDB application running with three thousands concurrent users, on an off the shelve laptop while I was busy doing other stuff.

One word of warning before hand, because I run everything on a single machine, just running so many users on the machine significantly slowed down how RavenDB is reacting. Basically, the code for managing the perf test took so many resources that RavenDB had to fight to get some to actually answer the queries.

Scared yet, because here are the results in graph form.

image

Now you can actually see that we have some fluctuations in the graphs, the number of users grows and grows until we get to 3,000 and we have 0.37 seconds response times.

Again, I remind you, we have done zero optimizations and this is idiomatic RavenDB code. And we were able to serve requests at a frankly pretty amazing rate of speed.

And here are they in their full details:

 

Load Test Summary
Test Run Information
Load test name LoadTest1
Description  
Start time 04/09/12 15:28:48
End time 04/09/12 15:38:48
Warm-up duration 00:00:20
Duration 00:10:00
Controller Local run
Number of agents 1
Run settings used Load
Overall Results
Max User Load 3,000
Tests/Sec 196
Tests Failed 0
Avg. Test Time (sec) 14.3
Transactions/Sec 0
Avg. Transaction Time (sec) 0
Pages/Sec 741
Avg. Page Time (sec) 0.37
Requests/Sec 741
Requests Failed 0
Requests Cached Percentage 0
Avg. Response Time (sec) 0.37
Avg. Content Length (bytes) 3,080
Key Statistic: Top 5 Slowest Pages
URL (Link to More Details) 95% Page Time (sec)
Page 1 0.83
Page 0 0.82
Page 2 0.82
Page 1 0.82
http://localhost:52688/api/search 0.81
Key Statistic: Top 5 Slowest Tests
Name 95% Test Time (sec)
Browsing 20.8
BrowseAndSearch 19.8
Searching 12.9
Test Results
Name Scenario Total Tests Failed Tests (% of total) Avg. Test Time (sec)
Browsing Load 31,843 0 (0) 17.4
BrowseAndSearch Load 33,989 0 (0) 16.8
Searching Load 51,650 0 (0) 10.8
Page Results
URL (Link to More Details) Scenario Test Avg. Page Time (sec) Count
Page 2 Load Browsing 0.40 32,338
Search yui Load Searching 0.39 52,597
Page 1 Load Browsing 0.39 32,627
http://localhost:52688/api/search Load BrowseAndSearch 0.39 68,576
Page 0 Load Browsing 0.38 32,803
Search grid Load Searching 0.38 52,283
Page 1 Load BrowseAndSearch 0.37 34,766
Page 0 Load BrowseAndSearch 0.36 34,982
Search debug Load Searching 0.35 51,991
Search ravendb Load Searching 0.33 51,846
Transaction Results
Name Scenario Test Response Time (sec) Elapsed Time (sec) Count
System Under Test Resources
Machine Name % Processor Time Available Memory at Test Completion (Mb)
Controller and Agents Resources
Machine Name % Processor Time Available Memory at Test Completion (Mb)
RAVEN 85.4 1,203
Errors
Type Subtype Count Last Message

Note that the reason fro the high CPU usage is that the tests and RavenDB were running on the same machine.

Comments

njy
09/17/2012 02:19 PM by
njy

These numbers are so great that i would like to see what would came out of a production environment with an even higher number of users like... i mean... vulgar display of power :)

adam
09/17/2012 02:54 PM by
adam

Too bad ravendb can't serve odata or this would be a no-brainer for the nuget team to implement.

This is a great series of posts. I think this clearly demonstrates how a traditional rdbms is not designed to handle the average use case of today's applications. Yes, you could optimize the heck out of your model and db to try and make it perform but the out of the box experience of ravendb just works, and works well. Even with an optimized rdbms things like search are always going to perform poorly just because they are not designed for this use case. A rdbms still has its place, but its not for the traditional web app anymore.

Chris Eldredge
09/18/2012 04:37 PM by
Chris Eldredge

Reviewing the test plan it seems only 6 search terms are used: orm, nhibernate, yui, grid, debug, ravendb. My analysis shows there are over 3,400 unique terms in the Tags field, 6,500 in ReleaseNotes and 9,000 in Description.

No phrase queries, no variation in sort order and only 6 term queries does not seem like an adequate simulation of the types of queries that nuget.org is likely to experience in high volume.

With such a small number of unique queries, the server can simply return cached results without experiencing virtually any memory pressure or CPU spikes.

Since no packages are being added to the index nor are download counters being incremented, the data store is effectively in read-only mode, making the simulation even less accurate in comparison to real traffic.

With all of those considerations, I don't think this load test fairly compares RavenDB to the SQL Server/EF solution in use on nuget.org.

Comments have been closed on this topic.