25 votes

How to measure req/sec by analyzing apache logs

This great article helped me a lot... http://www.inmotionhosting.com/support/website/server-usage/view-level-of-traffic-with-apache-access-log I had created a set of prepered commands that I am ...
  • 431
21 votes

Why the discrepancy between Speedtest and Wget?

ISPs often prioritize traffic to speedtest.net so that they can brag how fast their connections are, while in reality, they don't provide that much bandwidth. They're perfectly aware that most users ...
  • 880
19 votes

Measure total latency of SSH session

See the sshping utility: https://github.com/spook/sshping Example: # sshping 172.16.47.143 --- Login: 1725 msec --- Minimum Latency: 4046 nsec --- Median Latency: 11026 nsec +/- 0 std dev --- ...
17 votes
Accepted

Why the discrepancy between Speedtest and Wget?

In addition to the other reasons posted, TCP connections don't work well with large files when the bandwidth-delay product becomes large. Like on an otherwise fast connection to an island. See ...
  • 1,262
15 votes

At what point is a server considered idle?

A machine is idle when it's not performing the task it's supposed to perform for lack of requests. For example, if you had an email server, you could determine if it was fielding any requests from the ...
  • 7,026
15 votes

sar: enable data collecting

On Ubuntu 16.04 I just ran into this same issue. After some grousing around I found I needed to enable the service by editing the file /etc/default/sysstat Change ENABLED="false" to true: # Should ...
12 votes
Accepted

How to see disk usage graph on Windows Server 2012

By default Windows hide the entry because of a noted significant performance impact in collecting Disk metrics on a Server: You need to register the Disk Perfcounter before you see this entry. close ...
11 votes

sar: enable data collecting

The sysstat service and associated timers need to be started: systemctl start sysstat sysstat-collect.timer sysstat-summary.timer To auto-start on next system startup: systemctl enable sysstat ...
  • 1,055
9 votes

How to compare mainframe CPU performance?

Comparing the number of CPUs of a mainframe image isn't meaningful, most likely. Mainframes are designed to run multiple tasks at the same time, and give priority to whatever the business says is ...
9 votes

How to compare mainframe CPU performance?

Kevin mentions a number of great points, but it might help to start the analysis at a little higher level: what are the two machines and, since we're talking about Tomcat which runs in a JVM, do both ...
9 votes

Measure total latency of SSH session

I skipped some steps suggested by @nicht-verstehen: python -m timeit --setup 'import subprocess; p = subprocess.Popen(["ssh", "user@host", "cat"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, ...
8 votes

Measure total latency of SSH session

Was trying to do this myself and came up with this. Probably there is a simpler way, but this is what I came up with. First, prepare pipes which will be used to make the benchmarking program ...
8 votes

At what point is a server considered idle?

"Idle" is not a black and white concept: even a busy server can have free CPU cycles, IOPs and memory to run some other application. As a rule of thumb, target CPU load should be at around ~80% and ...
  • 45.5k
7 votes

What exactly do the colors in htop status bars mean?

There are several different colors for each of the bars, except the Swap bar. Here are the color keys used inside of htop:
7 votes

Why the discrepancy between Speedtest and Wget?

wget give good practical measure of the speed. The tests of Speedtest probably include kind of parallelism which can explain higher numbers. For good average speed test I think the time for download ...
  • 4,292
6 votes
Accepted

BUG CONFIRMED: No performance data for VMXNET3 in ESXi 6.0?

Did ESXi 6.0 completely removed the performance data for VMXNET3 or is there is a way, how can enable throughput logging/graphing for VMXNET3? No, it's just there in vCenter - if you're not ...
  • 101k
6 votes

Measure total latency of SSH session

My idea was to use terminal query sequences for this; the advantage is that this can simply be run on the server, the disadvantage is that it measures terminal latency, not only the latency of the ...
  • 161
6 votes
Accepted

How to guarantee CPU time for VPS?

Typically you get what you pay for and relatively cheap hosting providers can only offer their services at a competitive price by overcommitting CPU several times i.e. on a server with 48 cores and ...
  • 74k
5 votes
Accepted

Does it make sense to use perfmon in a vSphere infrastructure?

Of course it would. Why wouldn't it? There's nothing saying you can't use both perfmon and vCenter counters to monitor the performance of your VMs - perfmon is better at or easier to set up for some ...
  • 53.6k
5 votes
Accepted

Windows / NTFS - is it possible to measure completion time of file operations?

Hire somebody to write either monolithic or mini filter driver for file system. You'll be able to intercept all calls from particular app of interest and track them right to NTFS or any other FS ...
4 votes
Accepted

Solaris: how to list swap space per process?

You can use the command: pmap -S <pid> to see all the memory statistics, including swap usage. With little shell magic you can wrap it in a bash loop: cd /proc for i in *; do SWAP=`pmap -...
  • 5,257
4 votes
Accepted

Resource Monitor - Disk - Response Time

The numbers are different because the two counters are measuring different things. The "Avg. Disk Sec/Transfer" counter in perfmon is simply telling you the average time taken for any disk transfer ...
  • 55.3k
4 votes

Find out which task is generating a lot of context switches on linux

In newer kernel version sudo perf record -e context-switches -a # record the events # then ctrl+c sudo perf report # inspect the result This will give you the exactly result about context-...
  • 141
4 votes
Accepted

Configure Windows Server Performance Monitor to create new log for every day

To have onr file per day, you can do like this. On my server I store on file per day during 7 days. It deletes the oldest files. In the properties of yours performances counters : You can prefix the ...
  • 1,315
4 votes

Why the discrepancy between Speedtest and Wget?

One reason could be that often the maximum speed cannot be reached by just a single TCP connection. Speedtest.net recently introduced a single connection mode. Try this and see if it makes a ...
  • 381
4 votes

ESXi (Free Versions) Notifications when there is sustained high CPU usage

There's no way to do this natively with the free version of ESXi, but you can use a third party program to do this for you. I use Veeam One Community Edition. It's free and it's a great product. ...
  • 109k
3 votes

Optimal configuration of "Processor load is too high" trigger in Zabbix

I would suggest something like this: {Template OS Linux:system.cpu.load[percpu,avg15].avg(15m)}>1.8 The purpose being that you want a slower response time on your alarms rather than raising to a ...
  • 31
3 votes

Performance counter alert not working

So after a lot more googling (I hoped somebody here will do it for me ;) I figured it out! Task field The Run this task when an alert is triggered: field is not a path to a program, but name of a task ...
  • 157
3 votes

Windows Azure autoscaling other than CPU usage

For web apps, you basically have data in/out, memory, CPU, disk queue and HTTP queue (use preview portal to see all of them). By only watching how any of these values in the monitor behave while you ...
  • 3,804
3 votes
Accepted

Current Number of Requests per Second with Apache 2.4

Using the log files has the added problem that they only contain completed requests and not the actively (long) running requests... Enable the Status module and you can query the web server directly ...
  • 74k

Only top scored, non community-wiki answers of a minimum length are eligible