Questions tagged [benchmarking]
The process of running a computer program to assess performance.
201
questions
1
vote
0
answers
61
views
New external drive already slow to mount and to read/write
I just bought a 5TB Seagate STJL5000400 external USB hard drive.
It takes at least 20 seconds to mount before being available to browse folders in the file manager and writing / reading is so slow.
I ...
0
votes
0
answers
14
views
What are the FIO options for jobs to split files in to different directories?
I'm trying to get used to FIO command, and I can find the right option combinations to use. What I'm trying to do is to use processes(jobs) to split the IO requests in two different directories.
...
0
votes
0
answers
22
views
How can sysbench fileio throughput be only 6.92MiB/s on fast NVMe disk?
I followed guide to benchmark WD_Black 1TB SN750 SE NVMe disk (read: 3600 MB/s, write: 2830 MB/s) on HP EliteDesk 800 G2 (i5-6500T).
$ sysbench fileio --file-total-size=8G prepare
…
8589934592 bytes ...
0
votes
0
answers
37
views
Are iodepth and iodepth_batch the same in fio?
Wanted to know the difference between iodepth parameter and iodepth_batch parameter in fio. Here is what is mentioned in fio read the docs :
iodepth=int Number of I/O units to keep in flight against ...
0
votes
0
answers
38
views
How to troubleshoot this HDD performance issue?
I purchased WD60EZAZ for usage in Synology DS118 NAS. I put around 500GB of data onto the disk, however I noticed very slow read/write performance.
I decided to run some tests on the disk directly, to ...
0
votes
1
answer
32
views
Inconsistent 3DMark CPU Score
I completed a new Ryzen based PC build, and have been trying to optimize it by doing some minor overclocking. While doing so, I've noticed that I'm getting inconsistent 3dMark CPU results that are ...
0
votes
0
answers
33
views
Alienware 13 R3 - laptop shuts down without warning under heavy load ONLY when on battery
I've been an AW13R3 owner for almost 2 years, i bought a used model without warranty in order to have something to bring with me during job travels.
For a year or so the laptop has been performing ...
1
vote
0
answers
15
views
Testing Devices in Hostile Wireless Networks
I'm attempting to benchmark the power usage of a device that sends data over wifi. This device uses some logic to attempt to retry sending data in the event of network failures. To better simulate the ...
2
votes
3
answers
82
views
Testing health of laptop hardware
I recently bought a second-hand laptop and I have installed Ubuntu 20.04 LTS on it.
Everything appears on the surface to be working fine, but before I switch over to using this laptop as my main ...
0
votes
0
answers
230
views
Very low random IOPS reported on SSDs
I have two Samsung SSDs in my computer, an 840 Pro and 860 Evo, reporting very low random IOPS numbers, about 1/5 of the nominal, connected via a SATA3 interface, using an i7-3770K CPU in a P8Z77-V ...
2
votes
0
answers
74
views
Windows 10 UDP Socket Benchmark a lot faster in safe mode
I made a simple SendReceive benchmark for UDP sockets and noticed, that the perofrmance in Windows safe mode is considerably faster than in normal mode. Why is this the case? In normal mode I was very ...
0
votes
1
answer
128
views
Too low bandwith in RAM benchmark
I'd like to ask for help in interpretation of Memtest benchmark. I have G.SKILL 16GB (2x8GB) 3200MHz CL16 Ripjaws V Black. I've done some benchmarking and here's a result. It's showing under 16000MB/s ...
0
votes
0
answers
103
views
Ways to flush page cache without reboot?
I am running a benchmark on Disk IO + data compression, and the benchmark to be accurate has to include time from disk fetch. The issue being that once I compress a file once, I can't do a second ...
0
votes
2
answers
110
views
How can PC's be bottlenecked by GPUs if they have gotten so much faster than CPUs over the last 5 years?
I am thinking of upgrading my gaming PC. Currently, my specs are:
CPU: Intel Core i5-4690K,
GPU: Nvidia GeForce GTX 970
According to this, I am currently slightly bottlenecked by my CPU. I am ...
0
votes
1
answer
130
views
is there a method to benchmark only the filters in an ffmpeg chain, ignoring the encoder operations?
I've found a number of examples of how to use a null muxer to prevent writing the actual output to disk, which saves the disk space and all the time/work to do the writes themselves. I'm interested ...
0
votes
1
answer
294
views
Precondition SSDs
Are there still good reasons to "preconditioning" your SSD, especially before doing benchmark?
And if so, why?
Today we have better SSDs and almost all system-configurations support TRIM.
1
vote
1
answer
122
views
Benchmark turned out inconclusive, need help troubleshooting
I just got a new CPU/Mobo/RAM after a long overdue upgrade. Everything boots and seems to be working normal. My last upgrade will be a new GPU but not right now, so in the meantime I ran a ...
12
votes
7
answers
7k
views
Why does a server CPU perform faster tasks than a Macbook Pro CPU with the same benchmark score? [closed]
Given the following CPUs and GeekBench scores:
Amazon EC2 z1d.large instance: Intel Xeon Platinum 8151 4061 MHz (1
cores) Single-Core Score: 1094, Multi-core score: 1300
Macbook Pro Laptop: Intel ...
0
votes
0
answers
29
views
Why is my SSD performing so far over spec? [duplicate]
While setting up a new laptop, I plugged in an SSD from an old computer, a 1TB Samsung 840 EVO 2.5" SATA III. This drive is rated for 540 MB read / 520 write according to Samsung.
At first it only ...
1
vote
1
answer
493
views
How can I recreate CrystalDiskMark's disk benchmark on Linux?
I want to be able to test the read/write performance of my disks on Windows and in Linux, and get as accurate a comparison as possible.
On Windows I'm using CrystalDiskMark, because hey, it's OSS and ...
0
votes
1
answer
391
views
Are the Geekbench multicore scores done using embarrassingly parallel processes?
For each processor, the benchmarks at geekbench.com present both a single-core and multi-core score. For example, this 64-core processor has a single-core score of 1220 and a multi-core score of 23688....
1
vote
0
answers
67
views
Benchmark an Truecrypt-encrypted HDD
I have a TrueCrypt encrypted Disk (Full Disk encryption of a non-system Partition), which looks like this while being mounted:
Question is: What happens when I try to benchmark this HDD using HDTune? ...
1
vote
0
answers
17
views
Displaced SSD drives benchmark results
I have these two ssd drives:
SATA3 Samsung SSD 850 PRO 128 GB
NVME Samsung SSD 970 EVO Plus 240 GB with PCIExpress adapter
It seems the benchmark results are displaced. As you know the sata3 model ...
0
votes
2
answers
71
views
Difference between the MacBook CPUs
I have an old 2011 13-inch MacBook Pro and I am thinking to buy a new one. I am wondering if the difference between the CPUs is different. I checked the benchmarks here.
MacBook Pro (13-inch Early ...
0
votes
1
answer
150
views
Very sporadic videocard benchmark results on new laptop. Cause?
I just got a new Thinkpad P53 with a Quadro RTX 3000 graphics card (roughly equivalent to the GeForce RTX 2060 consumer card), and am getting sporadic benchmark results for the graphics card. 3D Mark "...
1
vote
1
answer
4k
views
Slow Read/Write speeds on Samsung 970 Evo Plus after switching to a new motherboard?
I think the problem might be that the device is using PCIe Gen. 3 x 2 instead of Gen. 3 x 4 PCIe? Is there any way to change this in the bios?
I am running a PC with a 1TB Samsung 970 EVO Plus that ...
0
votes
2
answers
79
views
How to benchmark two Windows PC's performance
My old work laptop is a HP ProBook 640 G2 running Windows 7 Enterprise and has a Intel(R) Core(TM) i5-6300U CPU @ 2.40GHz, 2401 Mhz, 2 Core(s), 4 Logical Processor(s) with 8.00 GB of RAM.
My new work ...
0
votes
1
answer
454
views
Mongo 2.6.12 VS Mongo 4.0 benchmark
I have problem, I use the old 2.6.12 version of mongodb on a new computer and it does not show high speed results and I do not know why. Mongo 2.6.12 doesn’t even try to use my computer at 100% using ...
1
vote
1
answer
50
views
Temporary freezes even on small load
I have the following setup:
ASUS B360M-E TUF Aura Sync
Intel Core i7-9700K 4.9GHz
16GB DDR4 3000 MHz Dual channel memory
NVidia GeForce GTX 1660 6GB DDR5
500GB SSD Western Digital Blue
Chieftec E85 ...
0
votes
1
answer
173
views
Can I force a specific unit of measure for sync percentiles in fio output?
I'm using fio 3-13 to benchmark an SSD. The job file contains multiple jobs to be run sequentially (with the stonewall parameter), but they all contain fdatasync=1. As a consequence, the output ...
0
votes
0
answers
718
views
IOmeter v/s FIO on Windows VM
I have a Windows VM which have disks on high performance storage. I have both FIO(http://bluestop.org/fio/) and IOmeter(http://www.iometer.org/) installed on it. I want to be able to saturate the ...
0
votes
0
answers
12
views
Load Balancer Poor External Query Results in Benchmark
I created a Load Balancer. When testing internally in the Load Balancer Server using wrk, I received a benchmark of 300,000 Requests Per Second.. Then, I created a droplet in Digital Ocean and ran the ...
0
votes
1
answer
2k
views
Low SSD Performance Adata SU650
I recently got a new computer and am slightly concerned by the benchmark scores I am getting with a CrystalDiskMark and AS SSD. I have an Adata SU650 240 GB SSD.
Here are the scores I get in AS SSD:
...
5
votes
1
answer
795
views
What are the differences between a physical and virtual RAM disk?
I'm using ImDisk to create a RAM disk for the purposes of creating an environment where I can run some performance benchmarks and ensure that all benchmarks run are consistent, by making sure any ...
1
vote
1
answer
181
views
Benchmarking bash commands with time and tee
I have a directory containing more than 80GB of simple text file databases that I anticipate needing to grep through often. For this reason, I'm trying to create some tests to compare GNU grep with ...
1
vote
1
answer
98
views
Router performance tests
628/5000
Hello all,
I am looking for tools or ways to test router performance. I am not only concerned about WiFi bandwidth, coverage and etc, but also about the performance of the hardware itself in ...
0
votes
0
answers
185
views
Is that normal behaviour of ZOTAC AMP Extreme Core Edition 1080 Ti (ZT-P10810F-10P)?
Is it okay that ZOTAC AMP Extreme Core Edition 1080 Ti GPU with i7 7700 CPU gives:
20~30FPS in Sniper Ghost Warrior 3
30~40FPS in Fallout4
30FPS in GTA V
( at 4K with ultra graphics? Isn't it slow ...
0
votes
1
answer
218
views
Detect and qualify flash memory (sd card) wear
What is the best way to detect and evaluate/qualify flash memory wear that usually occurs after a lot of data has been written the flash? I mean especially a wear caused by continuous writes by dash ...
0
votes
1
answer
153
views
How to compare 2 specific processors with the same benchmark side by side? [closed]
I want to compare my old AMD Phenom X4 9500 with the new Intel Core i5 8400 to see how much faster the new Intel processor is. Does anyone know of a website that can compare those two processors side ...
0
votes
0
answers
221
views
Phoronix vs Sysbench benchmarks
I have 3 x86 xeon machines [with RHEL 7.4], machines are using Haswell, Broadwell and Skylake based CPUs.
When I run prime number calculation using sysbench [using varying number of threads], I get ...
48
votes
3
answers
33k
views
Why is my HDD so slow on the "4K" speed tests?
What is wrong with my speed at 4K? Why is it so slow? Or is it supposed to be like that?
Is that speed okay? Why do I have such low speed at 4K?
1
vote
0
answers
72
views
Directly interrogating video card to confirm spec?
I just bought a ASUS OEM Radeon R9 370 second-hand online and I'm not sure if it's okay or not.
I probably have no reason to suspect anything wrong, the labels look fine, except that I just ...
0
votes
0
answers
675
views
Are CPU benchmarks of desktop versus laptop CPU indicative or real life performance?
According to benchmarks, it seems like the i5-8250u is about the same as an i5-7400.
i5-7400 passmark = 7415
https://www.cpubenchmark.net/cpu.php?cpu=Intel+Core+i5-7400+%40+3.00GHz
i5-8259u ...
0
votes
0
answers
24
views
How do I find comparable benchmarks between LG G4's processor and Xeon x5675 [duplicate]
My friend said that a modern phone's CPU will be more powerful than an old PC's CPU.
So to test, I have a Qualcomm Snapdragon 808 processor in my LG G4 phone.
My PC has a Xeon x5675 processor, which ...
0
votes
1
answer
43
views
Are Geekbench scores related to software version?
I was looking at MacBook Pro and macbook models of 2016 and 2017 and I noticed that the same model in Geekbech scores has much lover scores that in Geekbench 4
I also noticed that some review compare ...
2
votes
0
answers
434
views
Both AMD CPUs max out 33-35% performance with low temperatures
tl;dr: See "Facts" section towards the bottom.
For almost 4 years, I had an AMD FX-8350 CPU on a GIGABYTE 970A-UD3 motherboard as part of a general-purpose computer with no compute performance ...
0
votes
1
answer
64
views
Is it worth to put a UHS micro SD in a class 10 device?
Here is speed test I found for Lexar x633 class 10 UHS-1
I'm interested in 4k Q32 and 4k. Typically, class 10 cards will reach no more than 0.1 to 0.2 MB/s. If I put a class 10 UHS-1 card in a device,...
0
votes
1
answer
84
views
Why is my new PC 40% slower to calculate and write a grid surface?
I've just updated a PC to do scientific calculations more quickly. The focus of the change was to step up to the Nvidia 1080Ti from the 980Ti.
Now I'm running a test model. I get the following ...
8
votes
2
answers
23k
views
SSD with write cache buffer flushing turned on is way slower in AS SSD but not CDM
When running a benchmark using the program AS SSD on an NVMe drive, When the second checkbox seen in the image below is unchecked, the drive gets terrible write performance in AS SSD (see first ...
0
votes
1
answer
153
views
How can I benchmark the bandwidth and latency of the connection between my PC and wireless router?
It seems like this should be easy in theory, especially the latency part. Just spam the router with packets and see how many get returned and how long they take. Is there any way to do this?