Questions tagged [stress-testing]
Stress testing is a form of testing that is used to determine the stability of a given system or entity under load. It involves testing beyond normal operational capacity, often to a breaking point, in order to observe the results.
108
questions
0
votes
0
answers
34
views
stress-ng: Simulate specific CPU and Memory Percentage
Goal : For performance test I m using stress-ng and I want to consume 100% CPU of 3 out of 4 Core and 80% of entire memory for 30 min (this is very extreme test condition). And I have few other ...
0
votes
0
answers
19
views
How to cause a network down event on a server?
This may seem weird, but I actually would like to cause a network failure on a project I'm working on. It's a microcontroller that is running tcp/ip and I just want to see what would happen if the ...
0
votes
1
answer
26
views
Stress Test Interpretation
I ran a basic stress test and am having trouble interpreting the results.
Setup
Super simple node.js API (returns a string for a GET request) deployed on heroku's free tier
Increased RPS until I ...
- 99
0
votes
2
answers
1k
views
stress-ng limit cpu usage for vm stressor
I'm trying to test a server under specific workloads. I'm using stress-ng to simulate a x% cpu load: stress-ng -c 1 -l x
I also trying to use stress-ng to simulate a memory load of x megabytes: stress-...
- 210
0
votes
0
answers
99
views
Stress test a server running on the local machine?
I tried searching around and everything gives me completely different answers
I'm comparing nginx and a proprietary server my boss wants to use. We're trying to figure out if it's a lot slower or ...
- 101
1
vote
1
answer
202
views
DELL R320, Xeon E5-2450 v1, Oracle Linux 8 marks clocksource 'tsc' as unstable, random crashes under load
I recently acquired used Dell R320 with Xeon E5-2450 v1, all firmware's are updated to most recent versions using Lifecycle controller. On boot dmesg reports:
microcode: microcode updated early to ...
- 11
1
vote
1
answer
2k
views
why are there so few simultaneous requests in Locust?
Why are there 2 requests on average if I spawn 100 users simultaneously? Shouldn't there be 100 simultaneous requests at the beginning? What may be the reason that does not happen?
I have set up a ...
- 111
0
votes
1
answer
178
views
Creating an SRE Testing Interview VM
I'm working on hiring for a Site Reliability Engineering role and I want to create a "broken" VM for them to log into and debug.
What sort of scenarios would you suggest I put in place to ...
- 301
0
votes
1
answer
43
views
SpectreV1 Mitigation Performance profiling
I am trying to measure the system performance when spectreV1 mitigation is on. I am using stress-ng for that. So far I have tested the system with various stressors like cpu, qsort, str, matrix, ...
- 101
0
votes
1
answer
128
views
Supermicro X10DRL-i 4 Beeps while Running GPU Stress Test
As a bit of a testbench before deployment, I'm running a Supermicro X10DRL-i w/ dual Xeon E5-2620v4's and 64GB RAM. I have a Sapphire AMD Vega56 in the 16x slot.
I was running some stress tests ...
- 403
1
vote
1
answer
517
views
How can I variably stress test a server with Ubuntu?
I need to stress test a group of servers but is there a way to stress test a normal Ubuntu instance that doesn't just whack the CPU percentage up to 100%. Something that holds the CPU at 60% for ...
- 135
0
votes
2
answers
562
views
How to stress test SSL servers?
I'm attempting to test if a web server dies when SSL connections are "severed" at various points of the SSL handshake, etc.
I thought I saw a tool once that would "stress test" SSL connections by ...
- 577
0
votes
1
answer
228
views
Can a load stress test (for example with Loader.io) cause a Denial of Service?
I want to test the performance of my server using Loader.io service, but I'm worried about the impact.
From what I understand the site will load stress my server making multiple requests, what is the ...
- 143
1
vote
1
answer
284
views
AWS system failing on HEAD request but hardly on GET requests on stress test
I'm running a stress test with Locust on:
c4.xlarge (attacker has c4.4xlarge)
1 instance
amazonlinux 2017.03
The load balancer is:
classic type
internet-facing
stickiness is disabled for both 80 &...
- 121
0
votes
1
answer
78
views
Wordpress apache benchamrk CPU usage
I'm on a VPS, 4vCPU 4GB RAM.
During this apache benchmark test:
ab -k -n 10000 -c 3 -l URL
I get:
Server Load 3.393066 (4 CPUs)
Memory Used 35% (1,358,560 of 3,881,408)
Swap Used 23.7% (...
- 121
0
votes
0
answers
88
views
Using hdparam for more strenuous tests
So I am tasked with getting some strenuous raw hard drive performance tests. We started with FIO but this has proven to be ineffective as the results are poor in windows and linux.
I tried Bonnie++ ...
- 217
0
votes
1
answer
883
views
Testing Concurrent Users using Jmeter
If I have to load test an app for 40,000 users per hour with each user's average spent time of one minute then what should be my test approach?
Will running a test for 666 Threads/Users (40000/60=...
- 1
0
votes
0
answers
28
views
Samba fails Achilles Level 2 tests
During certain Achilles tests, CPU consumption of Samba rises to 100%.
I am doing Achilles tests on a Linux-based server. I have noticed that during certain tests (and UDP port discovery), the ...
- 427
3
votes
1
answer
452
views
haproxy session rate lower than single server qps
I setup a haproxy(1.6.3) on ubuntu 16.04 to load balancing two web servers. From my earlier tests, the web servers can handle over 20k request/s. The web servers were tested against wrk2, and I ...
- 163
0
votes
1
answer
559
views
How to revive nginx after it got beatup by stress testing
Background
I got two ec2 instances running laravel app on an nginx server behind a load balancer. We had the brilliant idea of running stress testing on the instances using apache ab like so:
ab -...
- 1,107
1
vote
1
answer
216
views
How to find limits of clustered Tomcat with Session Replication
I am working on a Tomcat cluster experimentally because of it may be need for us production environments. It must be scaleable, high available and support as much as multi concurrent users. Because of ...
- 11
1
vote
1
answer
124
views
Whats better: stress test the entire system vs profiling and stress testing specific parts? [closed]
I work in a company that is entirely on the cloud and we have started a stress testing project. The idea is to load everything in production to a new environment and run stress tests on it to find the ...
- 451
2
votes
1
answer
531
views
Is there any way to slow down hard disc writes on linux?
I want to anayse influence of slow disc storage on my application. In order to do it I want to decrease writes thougput to the storage. Can I do it by some configuration or is there any tool dedicated ...
0
votes
1
answer
128
views
Creating artificial CPU / memory load on CUCM server
I'm working on a small monitoring application for organization multicluster CUCM environment. For a demo purpose, I have a small lab, that consists of VMware CUCM installation and a couple of hardware ...
- 149
7
votes
1
answer
498
views
VMFleet Diskspd script shows zeros in output.
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 ...
- 454
0
votes
2
answers
2k
views
How to simulate high bandwidth traffic for server testing
I'm working on a personal CDN-like project and I would like to stress-test my server, which is a minimal nginx+nodejs+ubuntu running on a 10Gbps VPS. I want to simulate something that looks more like ...
- 113
-1
votes
1
answer
41
views
How can I make a server or PC use the most electrical power it is ever likely to?
I have several servers connected to a UPS. I would like to try and get those servers to draw the most power they are likely to as a load test of the UPS. What is the best way to cause a server or PC ...
- 233
1
vote
2
answers
116
views
What kind of "streamlining" occurs when you use a single machine to generate load/stress?
The title of this question represents my main concern, but if you read on beyond the question section, you'll find some background about our set up.. which may or may not be relevant / useful.
...
- 123
2
votes
1
answer
2k
views
How do I use stress-ng to simulate memory usage?
I found the command stress-ng -c 0 -l 60 which takes up 60% of the CPU. Is there a similar command for taking a certain percentage of the total memory available?
- 143
-6
votes
1
answer
545
views
How to test HA MySQL Database
Recently we have been testing an HA Database solution from a 3rd party provider.
I have done some stress tests to see some metrics for Master & Slave status etc, however I would like to test the ...
- 91
13
votes
2
answers
21k
views
stress-ng: Simulate specific cpu percentages
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 ...
- 426
-1
votes
1
answer
97
views
How to test to observe Latency Differences when running Cassandra on HDD vs SSD
We had a 3 node cluster running on HDDs. After migrating to SSDs, we ran a load test but haven't seen any latency difference.
So we are thinking about running a stress test. Is there any threshold or ...
- 25
2
votes
3
answers
4k
views
How do i install stress on a CentOS7 server?
How do i install stress on a CentOS 7 server?
I've read this and I have Package epel-release-7-7.noarch already installed and latest version. When I yum search stress I get:
Loaded plugins: ...
- 323
-1
votes
1
answer
811
views
Record and replay HTTP requests/posts between a given period of time (Apache)
Disclaimer: I know that what I'm about to ask is not even close to best practices but due to very specific requirements, I see this as probably one of very few solutions.
Context:
We wish to ...
- 101
2
votes
1
answer
5k
views
Simulate massive network traffic [closed]
We want to stress test our pfsense box with a massive amount of connections and traffic. Right now we are using iperf, but reaching a number of more than ~300 parallel connections the test clients ...
- 133
7
votes
1
answer
760
views
Right way of measuring overlay network performance
I am currently examining the performance (especially UDP throughput) of different Docker overlay networks. I do this by creating point-to-point connections between two hosts that are connected with a ...
- 357
0
votes
2
answers
703
views
I'm trying to stress test a site but no hosting company will let me. What can I do?
We need to know what to expect if a rogue actor DDOSes one of our production sites, so I'm looking to spin up a few VPSes with web apps on so that I can simulate a DDOS against them with an online ...
- 103
1
vote
4
answers
595
views
Heavy stress test on Apache [closed]
We have a production server running Apache that sometimes crashes because of too much load, I'm trying to replicate the situation on a test server in order to test Monit.
So my goal here is to ...
- 35
-1
votes
1
answer
630
views
I launch stress-ng -d 9 and my server crashes
I'm trying to understand why my server crashes. It reboots itself after some minutes when launching
stress-ng -d 9
The last logs I received are these ones:
[pid 1547] write(3, "Z\26\260\2273\0Z\...
- 59
2
votes
1
answer
2k
views
Windows Azure autoscaling other than CPU usage
I have a rather simple .NET MVC app. There's not a lot of computing power required. However, we are expecting an enormous amount of traffic.
I've been using Blitz.IO to simulate concurrent users and ...
- 561
1
vote
2
answers
3k
views
Stress Test on Wi-Fi Acess Point
I installed a Wi-Fi access point in a school hall. About a thousand iPad App is going to use the iPad App via this AP to submit information to server.
How can I ensure the AP is sufficient for such ...
- 1,001
3
votes
0
answers
1k
views
What exactly constitutes a bad TCP segment?
What constitutes a bad segment as in bad segments received in the netstat output below? I would think a TCP header's checksum could do it, but are there other things? If a segment arrives after its ...
- 135
3
votes
0
answers
190
views
Stress Test Hard Drive attached to a LSI controller on Hyper-V
I have a LSI 9265-8i controller running on Hyper-V.
How can I stress-test the hard disks in-situ?
I'd like to test things like iOPS, seek times etc.
- 159
2
votes
0
answers
819
views
test connection status and speed between azure vm and client
We have some VMs up and running, but we are seeing slow performance on some of them. We are unsure if it is a VM problem (Azure overloaded), an intermediate network problem or a problem on the client ...
- 243
0
votes
1
answer
1k
views
fio on virtual disk created with dd to stress disk
I am trying to create a script for my coworkers to use in the field that will stress the internal disks to a Linux server. I plan to put some logic in for finding the /dev/sd's available and such. But ...
- 171
2
votes
1
answer
6k
views
Http proxy server performance analyzing
I have implemented a http proxy client/server. Currently I intended to test performance of this proxy client/server. Can anybody tell me what kind of tests should I take to analyze it's performance? ...
- 123
1
vote
0
answers
901
views
Interpreting Siege results with Nginx
I am trying to compare the performance of a clutch of web servers using Siege. Whilst the results from all the other servers are easy to understand I am having some difficulty understanding the ...
- 173
-1
votes
1
answer
337
views
How to automatically test the audio quality of a telephone line that randomly goes bad?
I am a computer scientist and I'm working as sysadmin of a small firm where I've been managing also the telephone system that my predecessor put in place.
Albeit I don't really have the skill set for ...
- 127
0
votes
1
answer
778
views
How do I interpret this Load Test result?
We used BlazeMeter to evaluate our site's capability to handle load.
I set up a simple script that logs in (using a special page which ensures each load test user has a different account), visits ...
- 323
0
votes
1
answer
125
views
Put NIC under heavy load [closed]
I think I've got a faulty NIC so I want to put it under heavy but controlled load to see if and when it dies.
How can I generate such a load?
The NIC is in a Hyper-V host with Windows and Linux ...
- 1,588