Questions[stress-testing](server)

Speaking shortly, I decided to stress-test my brand new 4-node S2D cluster.

I started with IOMeter and got the initial results (max IOPS/Throughput on different patterns). Then I thought it would be a good idea to find IOmeter configs that would simulate the real production workload. Sadly, I didn't find anything useful for IOmeter, but discovered the fancy Powershell script called VMFleet that uses MS Diskspd to stress the storage and simulates the "bootstorm".

I followed this blog article during the configuration process to prepare and configure the lab.

set-vmfleet.ps1 script showed me some errors so I replicated all the steps manually.

Next I ran start-vmfleet.ps1 but it seems that output just shows zeros instead of actual results.

For how long should I run the watch-cluster.ps1 to see the results? Have anyone used VMFleet before? This doesn't look like the expected behaviour.

Thanks in advance!

Linux environment: Debian, Ubuntu, Centos

Goal:
Test monitoring program that set alarms and trigger different alarms at different cpu percentages.
ex: (30-50%), (51-70%) and >90%

So I need a cpu stresser that can simulate specific cpu percentage per core.
stress-mg looks like the most advanced.

According to its documentation http://kernel.ubuntu.com/~cking/stress-ng/ it is possible to set load values between 0 and 100%:

-l P --cpu-load P load CPU by P %, 0=sleep, 100=full load (see -c)

stress-ng -c 1 -p 30

stress-ng: info: [12650] dispatching hogs: 0 I/O-Sync, 1 CPU, 0 VM-mmap, 0 HDD-Write, 0 Fork, 0 Context-switch, 30 Pipe, 0 Cache, 0 Socket, 0 Yield, 0 Fallocate, 0 Flock, 0 Affinity, 0 Timer, 0 Dentry, 0 Urandom, 0 Float, 0 Int, 0 Semaphore, 0 Open, 0 SigQueue, 0 Poll

Undesired result:
But it doesn't seem to work, aLL cores are hogged at 100%

Any ideas how to achieve this?

I need testing the performance of the reserved area of my website. I want use Siege for this goal.

For accessing to reserved area you must be logged to my site.

How can I send with Siege a Login-Cookie to my web application ?

I'm giving a hands on presentation in a couple weeks. Part of this demo is for basic mysql trouble shooting including use of the slow query log. I've generated a database and installed our app but its a clean database and therefore difficult to generate enough problems.

I've tried the following to get queries in the slow query log:

Set slow query time to 1 second.

Deleted multiple indexes.

Stressed the system:

stress --cpu 100 --io 100 --vm 2 --vm-bytes 128M --timeout 1m

Scripted some basic webpage calls using wget.

None of this has generated slow queries. Is there another way of artificially stressing the database to generate problems? I don't have enough skills to write a complex Jmeter or other load generator. I'm hoping perhaps for something built into mysql or another linux trick beyond stress.

There seems to be something taking our server off-line and we are having trouble tracing the cause, if it is down to load of a particular site or a script. It does seem to be Apache related.

Does anyone know of any Linux based tools we can run from another server to stress test our problematic server by seeing how many requests it takes before it goes down?

Thanks, Shadi