Server Fault Stack Exchange
Server Fault Stack Exchange

Questions tagged [benchmark]

Benchmarking is the process of gathering data about the performance of a system in different scenarios to measure the impact of changes to the system, to compare the system with other options, or to determine maximum capacity.

Benchmarking is the process of gathering data about the performance of a system in different scenarios to measure the impact of changes to the system, to compare the system with other options, or to determine maximum capacity.

Benchmarking is a multidisciplinary process and can require management, engineering, operations, data science. and user experience expertise.

A key concern when benchmarking is making sure the tests performed are analogous to how to system is actually used. When benchmarking a server, the following metrics may be considered (in addition to countless others):

  • Ping response time
  • Average Load
  • Number of Dropped Requests
  • Number of Concurrent Connections Possible
  • Power Consumption
273 questions
0
votes
1 answer

Latency in fio vs ioping

There are two tests: ioping -c 10 -S 4K -D . 9 requests completed in 2.49 ms, 36 KiB read, 3.61 k iops, 14.1 MiB/s generated 10 requests in 9.00 s, 40 KiB, 1 iops, 4.44 KiB/s min/avg/max/mdev = 259.5 us / 277.0 us / 325.0 us / 19.9 us sudo fio…
ogbofjnr
  • 173
  • 1
  • 10
0
votes
1 answer

Fio brandswitch measure

In disk benchmarking tool fio there is statistics for brandswitch Run status group 0 (all jobs): READ: bw=20.9MiB/s (21.9MB/s), 10.4MiB/s-10.8MiB/s (10.9MB/s-11.3MB/s), io=64.0MiB (67.1MB), run=2973-3069msec According for docs: Values outside of…
ogbofjnr
  • 173
  • 1
  • 10
0
votes
1 answer

fio numjobs & iodepth Values to Simulate Database PostgreSQL Workload?

I am trying to benchmark a ZFS RAID-10 array of SATA SSDs using fio with settings that are somewhat representative of database workloads like for PostgreSQL. For example, for random reads: fio --randrepeat=1 --ioengine=libaio --direct=1…
Nyxynyx
  • 1,459
  • 11
  • 39
  • 49
0
votes
1 answer

Will an E5-2660 be a major improvement over a Q9550 for a webserver?

I have an old production server that runs Debian on a Q9550 CPU. I want to upgrade the server but I am on a very tight budget. I can't spend more than around $600. I can get a refurbished HP ProLiant DL380P G8 with 32GB RAM and 2x E5-2660 CPU for…
Zippy1970
  • 247
  • 1
  • 4
  • 12
-1
votes
1 answer

Better stream performance when transparent hugepages are on

On rhel 7, when transparent hugepages are activated, I get a better stream benchmark performance than when transparent hugepages are off. Do you have any idea of a kernel parameter (or another thing) which could trigger this behavior ? I was…
user380763
-1
votes
1 answer

Simple Linux Benchmarking Test to Perform Throughout Install

I have a script that installs a lot of software. For debugging purposes I am looking for a way of simply benchmarking my system after each install to see which piece of software cripples my server. NPM installs are Godly slow.
ProfessorManhattan
  • 217
  • 1
  • 5
-1
votes
1 answer

Is there a way to determine what impact an upgrade will make other than benchmarking it myself?

Several posts on capacity planning tells me that the only way for me to determine what hardware I need is to test it myself and benchmark it. Benchmark your code on hardware similar to what you'll be using in production, identify any bottlenecks,…
Hello World
  • 107
  • 2
-1
votes
1 answer

measuring network throughput with netperf

I'm doing benchmark test of Linux server using netperf. According to information at networksecuritytoolkit the theoretical max throughput rate for 1514-bytes packets is 117.35 Mbp/s. However I'm getting 957 Mbp/s for UDP traffic of 1514 packets. I…
Mark
  • 249
  • 1
  • 5
  • 13
-1
votes
1 answer

AB speed test two different URLS

I have two different servers running locally with different configurations. I'm interested in seeing with is repeatedly better/faster. I'm using siege right now $ siege -r 100 -b http://localhost:3000 $ siege -r 100 -b http://localhost:3001 I…
Schneems
  • 187
  • 3
  • 12
-1
votes
1 answer

Where can I find more info about "Sbench"?

There's a program we are using for benchmarking our web apps that is called Sbench. Its help page shows: FAST - Sbench 2.0.0.beta1 - 2008-09-13 redhat3-i686 PLATFORM : linux2 / posix However I cannot find any information about it on the web. It…
Behrang
  • 289
  • 2
  • 3
  • 10
-1
votes
1 answer

How does this benchmark calculation work?

I am testing disk I/O performance on a server of mine, which will eventually run Postgresql. I am following this web site to perform my benchmarks. The benchmark consists of running dd and reading/writing N blocks the size of 8k (which is the size…
Eviler_Elf
  • 1
  • 2
-1
votes
1 answer

From where do I run the apache benchmark?

Im trying to tuneup my LAMP and would like to run the apache benchmark to see how many concurrent connections can the server handle on stress from where do i have to run the ab? is it from the webserver or it has to be from a remote machine…
웃mauri
  • 382
  • 1
  • 3
  • 14
-1
votes
1 answer

MySql benchmark written in Java

I want to compare the performance of two MySql servers. Since we are accessing the database using Java/JDBC, the benchmark should be written in Java. It does not have to be MySql specififc, any compatible JDBC program will do. Oh, and it should be…
user27451
  • 1,161
  • 2
  • 11
  • 14
-2
votes
1 answer

Why Windows Server network stack is so slow compared to Red Hat Linux?

According to the following paper... COMPARING NETWORK PERFORMANCE: RED HAT ENTERPRISE LINUX 6 VS. MICROSOFT WINDOWS SERVER 2012 Src: http://www.principledtechnologies.com/Red%20Hat/RHEL6_network_0613.pdf ... Windows Server network performance could…
Dmitry Sychov
  • 119
  • 5
-3
votes
1 answer

How to configure Fio to a more accurate result of IOPs

I am using fio to test how much iops my server can offer. My conf file says to write a 20GB file and read it. THe results show iops=27291. But the test last only 10 seconds. I wonder if the test last 2 hours for example, I would have a more accurate…
Felipe Gutierrez
  • 103
  • 1
1 2 3
…
18
19