Questions tagged [performance]
Questions about server hardware and software performance, or network performance.
3,012
questions
0
votes
1answer
18 views
Suspicious ksoftirqd_1 process using high cpu
I run this webserver that serves data to a couple of apps. In the last couple of days I have noticed that some requests take some more time than usual, so I did a top to find out what's running and ...
0
votes
0answers
19 views
How to increase amount of concurrent connections in apache2?
I am running into traffic issues as apache 2.4.18 maxes out on concurrent connections:
ps auxf | grep apache2 | wc -l
258
As soon as 258 is reached the server is waiting to serve new connections ...
1
vote
1answer
245 views
Intermittent KVM performance issues causing performance glitches
We are currently hosted on a hosting provider that allows us to set up multiple virtual machines using KVM, where each virtual machine runs on it's own physical box (ie: one hypervisor, one VM with ...
3
votes
2answers
34 views
Performance differences between EXT4 and XFS on kernel 4.15.0-76
OS: Ubuntu 18.04.4 LTS
Kernel version: 4.15.0-76-generic
Storage type: RAID10 (4 x SSD)
Question: is it a bug for this version of kernel? EXT4 run a lot slower when we perform same SQL insert test; ...
0
votes
0answers
31 views
How to find the bottleneck on a virtual server?
I have purchased a cheap virtual server (running with Ubuntu, with 4 virtual? CPUs and guaranteed 8GB RAM, SSD). I started Tomcat8 with my web application (with -Xmx4096m). The startup time is very, ...
1
vote
1answer
26 views
Wrong link speed; what happens if manually set speed using ethtool fails?
I've got a remote xen server and I noticed that the speed link in autoneg is 100 Full Duplex; all my network is 1000 Full Duplex; do you know any reason for this? Ethtool mentions on both my server ...
0
votes
0answers
26 views
Performance Issue
I'm doing some experiments with my application. My application is in a Docker container and it is programmed to send 4 request every second to a web-server. When I host 30 containers on a single ...
2
votes
2answers
46 views
Why are concurrent downloads faster
Many download managers like this, this and this support downloading a file over multiple parallel connections, one per thread.
The concept is that each connection will download one part of the file ...
0
votes
1answer
36 views
Huge MFT and slow performance
I have a Windows Server 2012 R2 with huge MFT and slow performance when listing file in folder. Filesystem is about 350.000 files but in past many millions file was created and delete with crap Backup ...
0
votes
0answers
146 views
TTFB on AKS rises to ~7 seconds after ~100 concurrent API calls
I have a setup of AKS->Traefik(Ingress)->Docker(pod)->NGINX->Gunicorn->Django->SQL Server on Azure.
on AWS my response times for a page that does ~100 requests to my API ~4.5 seconds to fully render, ...
0
votes
0answers
38 views
How does avgqu-sz size in iostat output relate to r_await and w_await?
Can someone explain what does avgqu-sz mean in the output of iostat? The manual page states like this.
avgqu-sz:
The average queue length of the requests that were issued to the device.
Can ...
2
votes
0answers
31 views
zfs not using full disk I/O
I have setup zfs on a fresh Ubuntu 20.04. But speed seems awfully slow.
The disks can deliver 140 MB/s if run in parallel:
$ parallel -j0 dd if={} of=/dev/null bs=1M count=1000 ::: /dev/disk/by-id/...
2
votes
0answers
113 views
Pages load only when you restart php-fpm
So here's more context in a GIF
Notice how pages do not load on link clicks, but as soon as you run service php7.2-fpm restart it instantly loads the page and like that with every page.
What is ...
0
votes
1answer
23 views
If you have fetched a subdomain, what lookup related performance implications are there for accessing another subdomain on the same TLD?
Consider this example. My browser visits the following URL:
foo.foobar.com
The page on the domain creates an iframe for
bar.foobar.com
Both domains are hosted in AWS Route53 as aliased A records =>...
1
vote
0answers
32 views
DELL PowerEdge R740xd - NUMA - memory performance
I have two physical database servers (both Windows Server 2016):
test server (5 years old):
DELL PowerEdge R730xd, 1x Intel(R) Xeon(R) CPU E5-2637 v4 @ 3.50GHz (4C/8T), 192 GB RAM (12x 16GB PC4-...
0
votes
0answers
14 views
appropriate server size for a PHP application that does heavy processing and expecting large number of records [duplicate]
We are using Ubuntu 18.04.4, Nginx, MySQL, PHP7.2, and Laravel 5.8
Current Nginx and PHP settings to handle large data processing:
PHP
php_admin_value[memory_limit] = 8000M
php_admin_value[...
0
votes
0answers
12 views
server response time for SSH git clone operation
I found the git server application prints server response time in log only after below step completed during an git clone operations. ( I am using Bitbucket server)
Example : Receiving objects: 100% (...
0
votes
0answers
13 views
Calculating server performance versus cost over time
I'm trying to come up with a generic formula for what essentially boils down to a "like-for-like" replacement cost for servers.
Every year servers get faster, storage (typically) gets cheaper, ...
0
votes
0answers
9 views
New build not getting full bandwidth from SSDs?
I'm building a new FreeNAS server that I'm looking to use for 4k video editing (fast copy/streaming of large files). I've got everything built out and I thought I had it spec'd and designed correctly ...
0
votes
0answers
16 views
What is the performance effect of distributing data on multiple SSD disks?
I have a quite busy web server ruining on Linux. The whole filesystem is on a SSD which is half full.
I'm wondering if I move /www containing the web data to a fresh SSD of the same type, what will ...
1
vote
1answer
44 views
How do I know if SSD is the bottleneck in Linux?
I have a database server which uses a Samsung 840 pro disk. The load is constantly higher than usual, even if there is not much activity on the website. So I suspect the disk has worn out. But how can ...
0
votes
0answers
71 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 ...
1
vote
1answer
59 views
Is my server drive on SATA2 or SATA3 based on this output?
smartctl output:
# smartctl -a /dev/sda | grep SATA
SATA Version is: SATA 3.1, 6.0 Gb/s (current: 3.0 Gb/s)
dmesg output (empty):
# dmesg | grep SATA
hdparm output:
# hdparm -I /dev/sda | grep ...
0
votes
0answers
15 views
lmd(linux malware detect) maldet -m --monitor, impact on performance [duplicate]
Maybe there are other places that talk about this, but I didn't found them.
I want to know if someone have measured the impact that has having the maldet --monitor activated on the computer.
I'm ...
0
votes
0answers
24 views
Gunicorn timeout for optimized performance with unreliable underlying service APIs
We have got a FLASK/Gunicorn webapp requiring high performance. However, we call some external APIs upon user requests (from workers of course) with the APIs quite unreliable, sometimes long delays, ...
0
votes
0answers
27 views
Nginx disk high io read
Please help me.
I am having problem on my nginx server, centos based. In server I have thousands of big size files (1gb approx earch file) and traffic is 500 approx files are downloading at read time. ...
0
votes
1answer
52 views
VPS is slow despite low memory and cpu usages
recently the website hosted on VPS becomes very hard to reach at times, and I am trying to figure out why. I noticed the following things:
CPU and memory usages are very low (always <15% if we sum ...
0
votes
0answers
40 views
Dell Precision 490 Shut Down by itself after exactly 1 hour
I have a Dell Precision 490 and i cleaned it with a Plower but after i cleaned it, It keeps shutting down by itself after 1 hour every time i turn it on, So i'm not able to use it since this issue ...
0
votes
0answers
28 views
Index rollover latency
I have created an ILM policy as follows,
{
"policy": {
"phases": {
"hot": {
"min_age": "0ms",
"actions": {
"rollover": {
"max_docs": 30
},
...
4
votes
1answer
168 views
Slow RAID performance for Samsung EVO's
So I've been suspecting performance bottlenecks on a Samsung EVO 850 RAID1 for sometime, but honestly been too lazy to look into it. Now I was starting a new home project, involving a Vmware ESXi host ...
0
votes
0answers
31 views
IIS Number of threads worker process for ASP.NET application
TL;DR; Give the worker process more threads!
Background
We have an ASP.NET application that expose a Web API where one of the "endpoints/methods" makes a set of queries to external system (SQL, AD ...
1
vote
2answers
196 views
RAID 50 vs RAID 10 for performance?
I have a server with 6 SSD's and a raid controller card that supports both RAID 10 and RAID 50 the plan is to use this as our Build server. It will be pulling in NPM Packages and many small code files,...
0
votes
1answer
77 views
My.ini issues with server trying to host multiple connections
I am hosting a game server on a dedicated host. all my ini information and screenshots along with my task manager
please assist with this issue
______
# Example MySQL config file for small systems.
#...
0
votes
1answer
43 views
When should we use containerized application on Linux
I would like to create a Linux server but I'm stuck on one question:
How to know when I should use Docker or Lxc for a given application instead of installing it natively ?
For example, on my server ...
1
vote
1answer
119 views
Strange Azure VM performance Issues
We have 5 VMs on Azure for a customer. All VMs have been running smoothly.
Now since Monday the VM of one of the users is losing performance every day at 4 PM UTC+1 (+-1h). When we have these ...
0
votes
0answers
20 views
Amazon Lightsail wordpress slows down till unresponsive
Wordpress site slows down so much it sometimes its unresponsive. Stopping and restarting the instance is a temporary fix. cpu usage is max around 45%. I have tried disabling and reactivating plugins ...
1
vote
0answers
27 views
AWS Performance Insight Huge Load from “Other” SQL
Engine: MySQL 5.7.26
Looking at my AWS Performance Insight metrics, I noticed that most of my Database load consumes the query marked "Other" Can I check what is hidden under this label?
Screenshot:
-2
votes
1answer
37 views
Buy new VPS just for Mysql or upgrade current one and keep the whole stack on the same server [duplicate]
This is not a question about capacity planning, its about mysql performance over local network vs on the same virtual machine (where it needs to share cpu with other processes)
I have a wordpress+...
0
votes
0answers
40 views
Is it possible to prioritize writing over reading in disks?
We have a hadoop cluster, with data-node machines that use the HDFS file-system.
We want to prioritize writing to disks over reading from disks.
we have read the - Using the Deadline IO Scheduler ( ...
1
vote
1answer
225 views
Bottleneck identification using iostat, vmstat, mpstat
I am doing some Apache and MySQL performance tests, then upgrading a single component and running tests again to see where the bottlenecks are. I have a local used server warehouse (Tams in Lindon UT) ...
0
votes
1answer
19 views
jdb2 spike every hour for few seconds
I get IO hang up every hour on the exact same time on my Ubuntu 18.04 server.
iotop indicate that jbd2 spike to araong 30% around this time.
The hangup last only few seconds.
I started noticing this ...
0
votes
1answer
397 views
Ceph hardware sizing calculator
I would like to calculate the Hardware sizing for a ceph cluster. There are so few references to the sizing, that I try to get these details here in the community.
E.g. what shall i have depending on
...
1
vote
1answer
53 views
Virtual machine disk I/O latency spikes
Since past few days I have strange I/O spikes in one virtual machine.
Its
2.6.32-504.el6.x86_64 #1 SMP Tue Sep 16 01:56:35 EDT 2014 x86_64 x86_64 x86_64 GNU/Linux
Red Hat Enterprise Linux Server ...
0
votes
1answer
218 views
Nearly 100% disk utilization after upgrading to debian 10 without any reason
We recently upgraded our servers to debian 10. The setup is completely the same as with debian9 beside of course some new software packages.
We are running the default kernel:
$ uname -a
Linux ...
1
vote
1answer
116 views
SQLite WAL concurrent write performance on UNIX systems
I have two setups: one runs on windows 10 (ntfs partition), the other on debian (ext4 partition). The R source code is the same. The main process starts 8 child-processes (P-SOCKS) -- on 8 vcores -- ...
-2
votes
2answers
34 views
VM Performance on Different Hardware [closed]
I just bought a new server to act as a Hyper-V host for our current VMs. The hardware specs are better than our existing server (faster CPU speed, fast disk IO, etc) and I expect to see our VMs ...
0
votes
1answer
20 views
is there something like the stem-and-leaf plot for timeseries?
When wanting to quickly take a look at the distribution of a sequence of values, the stem-and-leaf plot is an incredibly simple, yet powerful tool. It takes a few minutes to teach the computer to draw ...
0
votes
0answers
27 views
nginx slower than apache2
I migrate my nextcloud-instance from apache2 to nginx and I hoped that is faster than apache, but it isn't. We've around 30requests/s on this page.
With apache2 I've 160req/s and with nginx I got ...
0
votes
0answers
41 views
Windows 10 becoming un-responsive when receiving lots of UDP multi-cast network traffic (but not with unicast traffic)
By coincidence we found that our Windows 10 machines (running version 1607 or 1809) becomes sluggish and/or start stalling when we throw lots of UDP multicast traffic on them. This happens if we send ...
0
votes
0answers
33 views
kafka + Enabling High Performance Data Transfers
when we look on kafka best practice we see the following details:
Max socket buffer size , can be increased to enable high-performance data transfer. More details are here http://www.psc.edu/index....
