Questions tagged [performance-monitoring]
Questions about monitoring server hardware and software performance, or network performance.
504
questions
0
votes
1answer
21 views
pidstat: difference between task and process?
The pidstat command has options relating to tasks and others relating to processes (e.g. -C and -G). What's the difference?
3
votes
1answer
48 views
ESXi (Free Versions) Notifications when there is sustained high CPU usage
I'm looking for a way to have the free version of ESXi notify me (Email is fine) when CPU usage is over 60% for at least 60 minutes. Generally, my CPU usage is around 25%. If it stays high for a ...
0
votes
0answers
6 views
Monitor performance of IIS UrlRewrite Extensibility Sample SQL Custom Rewrite Provider
I've implemented the SQL provider from IIS UrlRewrite Extensibility Samples and it seems to work well, but I'm wondering about the performance impact of IIS calling a stored procedure on an Azure SQL ...
1
vote
0answers
21 views
Variance in memory reported with perfmon vs Task Manager in Windows
I am recording Memory\% Committed Bytes In Use with perfmon every 15 seconds but I see that it doesn't always tie to task manager's reported memory %. They almost always tie but when memory starts to ...
0
votes
0answers
82 views
Monitoring SLA/SLO/SLI using Prometheus
I have done much research about monitoring SLI metrics with Prometheus. I have found only how to monitor a cluster using Kubernetes. I'm hoping to find a response here for simple monitoring.
I also ...
0
votes
0answers
27 views
What do the various “fit” algorithms mean in Kibana?
In Timelion visualisations in Kibana there is the option to interpolate/upsample an infrequent measurement, i.e. "invent" samples in the empty timestamps between known values to fill out a line plot.
...
0
votes
0answers
62 views
How to view CSV performance log formatted with one counter per line?
Short: How can I view a CSV performance log formatted with one counter per line?
Details: Some process I don't control provided me with a csv performance log that looks like this:
"TimeStamp","Path",...
2
votes
1answer
345 views
AWS CloudWatch alarm not populating data points - Insufficient state always
I am configuring CloudWatch alarm from the custom metric. Custom metric for disk space is configured, and I can see that every 5 minutes I am able to see the data. But when I set the alarm, the data ...
0
votes
1answer
147 views
Slow initial connection to database (php / mssql)
Our webserver and database server are on a local network and the webserver uses an IP address to connect to the database.
$con = new \PDO('sqlsrv:Server=10.200.2.1\sql2017;Database=dbname, $user, $...
0
votes
0answers
13 views
Recording Window Name on Perfmon
Under the manual configuration window in Perfmon, it is possible to select counters that record at the instance level (e.g. record Microsoft Excel usage).
Is it possible to further disaggregate this ...
3
votes
3answers
655 views
Rsync to /dev/null overwrites it
I am seeing a random behavior when copying from one server to another using rsync to the /dev/null of the destination server. This is as part my network performance testing, and I want to avoid Disk I/...
0
votes
0answers
30 views
SVN server performance and Load testing
What is the best approach to perform Load & Performance testing on SVN server which is configured for http? Are there any tools/Frameworks available?
As there are no recommendations for SVN ...
0
votes
0answers
27 views
Windows performance counter returning strange value
When asking the value for the performance counter [\Terminal Services\Active sessions] the Windows Server 2019 sometimes returns values like 3.616667, 6.800000 or 6.766667. How is this possible?
7
votes
1answer
219 views
How to record and replay htop?
TL;DR Is there an option to run htop in a way that will generate some report and the load it using htop later? Similar to perf record and perf report.
I'm a big fan of htop. I use it quite a lot when ...
2
votes
0answers
41 views
How can I count EC2 instances over time in AWS?
I want to know the number of EC2 instances I have running over time. I am able to view this data from the following menu:
ec2 dashboard
Auto Scaling Groups
select my group from the table of groups
...
2
votes
1answer
448 views
how to gracefully kill linux perf tool process
I'm trying to use the linux performance tool perf to monitor kvm events on a host where a guest VM exists.
The command I invoke perf is
perf kvm stat record
After some time, I'll press Ctrl + C to ...
0
votes
1answer
89 views
How to identify the source of growing blocked processes on a system container (LXC/OpenVZ)
When the number of blocked processes grow indefinitely, how to identify exactly what are these processes.
Since I'm inside a system container (LXC/OpenVZ), I can't modify the hosts' kernel modules to ...
asked May 10 '19 at 12:56
Paulo Coghi - Reinstate Monica
4361 gold badge8 silver badges20 bronze badges
1
vote
0answers
42 views
Profiling CPU, memory, networking performance and generating reports
Background
I have a performance-intensive (i.e. consumes a lot of CPU cycles, memory, and network resources) application. Multiple instances of this application, along with some third-party vendor-...
18
votes
6answers
7k views
Why the discrepancy between Speedtest and Wget?
My customer complains about low internet speeds. When measured with Speedtest.net speeds are acceptable. Periodic measured downloads are 10% to 30% of the nominal speed. I cannot explain that.
Some ...
1
vote
0answers
499 views
Unexplainable high load average on a QNAP NAS
we have two QNAP TS-1635 NASes (one per location), running at identical configuration and firmware versions. However, one of them has ever higher and higher load averages and actually needs to be ...
0
votes
0answers
39 views
Icinga configuring error
After configuring Icinga host list in host conf i got error like
root@server scripts]# icinga2 feature list
Disabled features: api gelf influxdb opentsdb
Enabled features: checker command compatlog ...
0
votes
0answers
72 views
High wa but no IO usage
My VPS is having extremely high wa (around 90), but there is no IO usage taking place.
htop:
iotop:
nethogs:
What can be the problem here?
0
votes
2answers
249 views
Can a high load on a VPS be caused by the underlying infrastructure?
My VPS started to have random stints of high load (around 2-3, but the system becomes extremely slow, running ls takes like 30 seconds). I hadn’t changed anything on it, there was pretty much nothing ...
2
votes
0answers
138 views
How to get PCI Tx/Rx byte counters?
I know how to read statistics about the configured network interfaces, for example via cat /proc/net/dev.
Is there a way to read similar byte counters of PCI or PCIe traffic?
Apparently, according ...
1
vote
1answer
2k views
Windows Performance Monitoring - “Packets Received Discarded” Never Changes
I wrote the following short PowerShell script to help diagnose some performance issues on a server:
$counters = @("\Process(*)\% Processor Time","\Process(*)\Working Set","\Process(*)\IO Read Bytes/...
0
votes
5answers
880 views
Configure JMeter to test a proxy service
I have developed a proxy service using ballerina language by referring the following [1] and [2]. It works perfectly fine. Now I want to run a load test via JMeter. That is JMeter should be configured ...
-1
votes
2answers
1k views
How to backtrace slowness of a shared hosting web server
I have a shared hosting plan (godaddy), and time to time I suffer slowness problem. When this happens, I try to login to cpanel to double check if the problem is me or the server, and it also takes 1-...
0
votes
0answers
18 views
How to sort the system calls by frequency generated by the perf command?
I have collected the perf syscall events using the perf tool by executing the command
perf record -F 99 -e 'syscalls:*' -p <pid>
The perf report command displays the system calls and its ...
1
vote
2answers
49 views
Can Perfmon be configured to survive a hard-reset or flush reports on the go?
I am having trouble configuring perfmon here (Windows Server 2016 if it's relevant). My situation: our server recently get random hit and we are diagnosing the problem, so I put a Data Collector Set. ...
0
votes
1answer
755 views
iperf3 UDP not reliable with iptables drop random
I'm performing some local test on my network with iperf3 using UDP connections between 2 Ubuntu 18.04 hosts. But it seems that the UDP iperf3 connections it is not robust to support a random packet ...
3
votes
1answer
1k views
How to get load average in Windows
In linux by "uptime" command you can get the load average in last 15 minutes. But how to get that in windows?
Many had suggested alternative found here. But it is about CPU utilization where load ...
0
votes
2answers
925 views
docker container linux-tools-generic package
My goal is to use perf to run performance tests on some Docker images. By default, the images I'm using don't come with perf. As such, I tried
apt-get update
apt-get install linux-tools-generic
to ...
0
votes
1answer
41 views
What's the significance of the *initially* displayed data when launching atop?
I've just started using atop to try to get to the bottom of some system bottlenecks.
I've found https://linux.die.net/man/1/atop which is very useful and explains most of what it does just fine.
...
0
votes
1answer
34 views
Azure reporting metrics via powershell driving the Stop-AzureRmVM command
Good afternoon all,
I am apparently in search of a unicorn.
I've been through Azure Metrics, not wide enough...
I've been through automation and the automation library... nada
I have a basic ...
4
votes
3answers
6k views
sar: enable data collecting
I've just installed the sysstat package on Manjaro. When running sar for the first time I see:
Cannot open /var/log/sa/sa21: No such file or directory
Please check if data collecting is enabled
How ...
0
votes
1answer
1k views
Docker performance monitoring - how to query I/O busy time and exact block reads/writes?
The "docker stats" command provides some basic info about containers. For example:
CONTAINER ID NAME CPU % MEM USAGE / LIMIT ...
2
votes
0answers
137 views
Cant remote manage server “Access is denied”
Im trying to work with performance monitor on windows server 2016 core. I have my PC a VM a new or was atleast new Installation of server core and i got some other VMs running. All im trying to do is ...
-1
votes
1answer
683 views
Performance monitor access is denied
I've been seaching for about the last 5 hour about perforamce monitor and how it works, and it has been a pain. I'm trying to get Performance monitor working on Windows Hyper-v Server 2016. I also ...
1
vote
1answer
1k views
Does Azure allow to monitor RAM and CPU usage of an on-premises server?
I have an on-premises server and an Azure MSDN account. I heard that Azure supports the concept of a hybrid cloud where some server may be on-premises, not sure if I understand it correctly, though.
...
1
vote
1answer
102 views
How can I access steal time data in Solaris SunOS 5.10
I think that the version of Solaris that we are running is too old to report steal time in top. Is there a way to get this information on this older version of Solaris. Here is the basic version ...
0
votes
1answer
423 views
What is the most accurate way of measuring cpu utilization of processes in Windows based systems
I have been trying to find out the best way to measure the CPU utilization of processes in a Windows Server 2012R2 system and I found out that there are many inconsistencies among the methods used to ...
-1
votes
1answer
95 views
Diagnose Sudden Slowness on Linux
I have two identical Linux laptops (Core™ i7-4810MQ with 32GB RAM) both running Ubuntu 16.04. Running seemingly any command on machine 2 takes about 4-12 times as long as on machine 1, depending on ...
0
votes
1answer
2k views
High response time on Azure Web App
I have developed a RESTful api that I deployed on Azure Web App. While performing the load test using JMeter, I see that the response time is huge i.e ~18secs. This response time appalls me because ...
0
votes
1answer
252 views
Performance counter files in Windows Server 2016 are limited to 2 GB in size
We want to record performance counters in files up to 6 GB in size. This worked on Windows Server 2008 R2 but on Windows Server 2016 the recording stops when the file has reached in 2 GB in size.
We ...
8
votes
6answers
3k views
At what point is a server considered idle?
Conceptually, what is the definition of an idle server?
What resource metrics would you look at to make an assumption on whether or not a server was idle?
Would you look at:
CPU utilization
Disk ...
1
vote
2answers
148 views
Track User CPU usage for a period of time
I need to track amount of processes that a single user invoked and how much CPU-time (or % ) these processes consumed for a given period of time.
The trick is that each of these processes normally ...
2
votes
1answer
526 views
Measuring Only Page Faults That Reach the Disk
I would like to measure "truly" hard page faults, i.e. page faults that result in a disk IO.
It looks as if Memory\Page Reads/sec might do the trick, but as was explained in this answer, the page ...
3
votes
1answer
3k views
Performance Monitor: Memory\Page Faults/sec vs Process\Page Faults/sec
When I was investigating some Hard Page Faults I came across this. Objects Memory & Process give different value's from the same counter: Page Faults/Sec. Are there some OS related processes that ...
-1
votes
1answer
85 views
How to monitor EMC VNXe3200? [closed]
Currently, I'm using Solarwind to monitor my system, but VNXe can not. Any solution to monitor this? I just get a notification via email or SMS when my disk or array is failed.
Thanks.
8
votes
1answer
164 views
Windows / NTFS - is it possible to measure completion time of file operations?
I'm looking for possibility of measuring how much time it takes to finish file operation issued to NTFS driver (open file close file delete file, write, read etc) and to be able to log it. I can't ...
