Questions about server hardware and software performance, or network performance.

learn more… | top users | synonyms (2)

-4
votes
0answers
12 views

Hard Disk read/write latency calculations in linux

How do i calculate Disk read and write latency in Linux? Is it possible to do the calculation using /proc or /sys file system? else is it possible to get through iostat command ?. screenshot here
-1
votes
1answer
27 views

Handling the potential risk of writing random bits to storage during power loss with RAID

Is it possible for a power failure to cause some part of a machine to write one or more random bits to a storage device? Someone proposed the following idea to address such a risk: create multiple ...
0
votes
0answers
13 views

LSI SAS1068E (aka LSI SAS 3442E-R) bandwidth

Recently I connected LSI SAS 3442E-R and two HP SAS 600GB 10k HDD. My motherboard is AsRock Z97 Extreme6. Disk are configured as JBOD, no raid. Linux lspci shows: 0b:00.0 SCSI storage controller: ...
2
votes
1answer
40 views

CPU is only used 50% on full load on a Windows Server 2012 R2

I use Windows Server 2012 R2 on my home server (it's a mini-ITX PC based on an Asrock E350M1/USB3 motherboard, so it's not a strong enterprise server). My problem is that even when I run multiple ...
0
votes
0answers
21 views

The difference in performance of different memory mount in dell poweredge R430

There are 3 servers R430 (S1, S2, S3). All of them have 2 procesors and 8*8GB of ram in slots A1-A4 and B1-B4. There is a need of extending memory. I've read dell recomendations ...
0
votes
1answer
26 views

Is it bad to use swap with SSD when running a server out of memory?

I have DigitalOcean VPS, which has 2GB of memory. I'm soon running or am about to run out of it. How big is the performance hit if I use big swap? DO use SSD has harddrives, and I'm not the one who ...
1
vote
0answers
33 views

Redis parent process smashing disk despite appendfsync = no

We are seeing loads of IO from redis-server despite our save operations being set to occur once every 15 minutes only. The workload is a "full page cache"; we store blobs of compressed HTML. The HTML ...
1
vote
1answer
41 views

Slow file io performance after large network copy on Win7

In a step of our build process we run a tool that generates about 125,000 files. When generation is complete we copy them up to a network share so other systems can copy them down to process further. ...
1
vote
1answer
30 views

Debugging slow server response time [closed]

I'm testing response time of my VPS server: curl -s -w %{time_total}\\n -o /dev/null http://www.example.com The values are typically round 300ms, Google suggests that it should be lower than 200. ...
3
votes
2answers
83 views

Linux: Why does the CPU frequency fluctuate when using the performance governor?

I'm using a Debian 8 amd64 machine for benchmarking. During experimentation, I would like the CPU to operate at a fixed frequency (preferably the maximum possible). This will rule out the CPU clock ...
2
votes
2answers
31 views

Can idle NFS mounts on several clients impact performance

We had a NFS server at work which was working with slight lag. However as more mount points were getting created at several clients(serviced by the same server) we noticed the performance coming to a ...
4
votes
0answers
21 views

HP MSA P2000 G3 Disk Scrubbing performance?

I have a HP P2000 G3 array with two 10Gbit iSCSI controllers in it that presents storage to my virtualisation cluster. It is soon to be expanded with two D2700 shelves each loaded with 25 10k RPM ...
0
votes
0answers
31 views

apache 2.2 to 2.4 sporadic performance drop

I updated apache from 2.2 to 2.4 and php from 5.3 to 5.4. For some reason I am experiencing huge performance drops in around 5% of requests to the server. On average, sites load in less than 2 seconds ...
0
votes
0answers
14 views

Conservative Azure Windows VM to Run SQL Server 2008 R2 [duplicate]

For testing purposes I need to set up three Azure Windows VMs to each run an instance of SQL Server 2008 R2 each holding one DB of approx 100GB. There will be quite a few complex stored ...
-2
votes
3answers
55 views

how to detect remote switch speed and duplex? [on hold]

We have a linux (RHEL) system which will be deployed in unknown networks. To support old networks we want to have autoneg configurable. how do you how detect if remote switch is autoneg on|off, and ...
0
votes
0answers
16 views

Performance monitors

I would need to create a performance monitor on windows server 2012 R2 to monitor the following for a particular period(may be one hour) CPU usage Memory usage Network bandwidth I'm little ...
0
votes
0answers
20 views

Sudden increase in my CPU usage during random moments(Win Server 2012)

At random times, no matter if I am online or not I see that my server having increased Process usage spikes, as you can see in the picture: So I go inside the Dashboard on the Server Manager, look ...
2
votes
3answers
78 views

Apache - drawback to high number of httpd processes always running

Is there any issue with having a high number of spare httpd processes always running? I ran a test where I increased StartServers and MinSpareServers by 1,000 and measured the increase in memory ...
1
vote
0answers
35 views

VMWare ESXi and iSCSI via FreeNAS

I've recently been setting up a sandbox ESXi environment with a VM running FreeNAS providing a volume which is connected as a datastore on the host via iSCSI. I've created a VM on this datastore and ...
2
votes
1answer
64 views

Nginx performance when running multiple instances on the same machine

I'm trying to understand the performance impact of having multiple nginx instances (masters) running on the same machine, rather than having them all load into a single instance using different server ...
-1
votes
1answer
24 views

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

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 ...
1
vote
1answer
35 views

RAID1 write penalty using mdadm - what's the cause?

When doing some performance tests writing to a SSD-based 3-way RAID 1 mirror powered by mdadm, it appears we suffer a significant write penalty of about 2.2x slower than doing the same test on just ...
1
vote
2answers
495 views

Can one root server handle over 50M requests per month? [duplicate]

I am running a LAMP Application installed on one server, happily serving about 1M PI per month. Now I am looking into a potential partnership where my app might serve around 50-80M requests per month. ...
1
vote
0answers
98 views

100% CPU, load average 0 - how is this possible?

Here's the top output: top - 19:20:47 up 1 day, 4:30, 1 user, load average: 0.01, 0.07, 0.12 Tasks: 170 total, 1 running, 169 sleeping, 0 stopped, 0 zombie %Cpu(s): 0.6 us, 0.9 sy, 0.0 ...
1
vote
0answers
13 views

Force disk cache even if guest uses direct i/o

Have IBM db2 on Rhel on Hyper-V on Windows Server. The *.vhdx file is on CSV. e.g. C:\ClusterStorage\volume1\hyper-v\oktest-lb1\oktest-lb1.vhdx. db2 uses O_DIRECT flag (uncached i/o) for its database ...
1
vote
1answer
37 views

Different network speeds from servers on same subnet

I have a pretty strange issue, I'm looking for advice on how I can debug it. I have two servers (A) and (B) on the same subnet and switch. Server A->B transfers at a full 12MB/s and vice-versa. ...
1
vote
0answers
24 views

How to track down bad performance on an api-server

If my api-server shows bad performance, such as high cpu - can this be blamed on the service or on the server? If a regular app-server shows bad performance, all I can do is track down the methods ...
0
votes
0answers
22 views

SSD vs RAM - Optimal ratio for different data sets / databases [duplicate]

I am looking for an advice or even better some studies / benchmarks to read for different scenarios (data sets) when it comes to the best ratio between actual RAM and SSDs. I know that fitting the ...
1
vote
2answers
118 views

ZFS reads on FreeBSD incredibly slow

I have a FreeBSD 10.0 system on which I have MySQL running with its InnoDB database files stored on ZFS. It seemed to have been going fine for months, but lately, and seemingly suddenly, performance ...
0
votes
0answers
35 views

vSphere | VMs are balooning and swapping | sched.mem.max paratmetar does not exist

I have two VMs in ESXi5.5 environment that are swapping memory. After a long research I found out the below two articles where it is explained that one must compare the values of memsize and ...
0
votes
0answers
18 views

How can I adjust buffer settings when using xbootmgr?

I am trying to analyze our clients which suffer from long boot & logon delays, so I installed Windows Performance Toolkit. This is the command line I have used to capture a startup: xbootmgr ...
0
votes
0answers
15 views

How to estimate max request per second of web servers? [duplicate]

I'm planning on a system that handles quite a huge amount of requests per second (say 500,000 requests / second). How to estimate maximum request per second of my web server can handle (so that I can ...
2
votes
2answers
53 views

Migrating Vmware to Hyper-V - number of Virtual CPU

I'm performing a migration from VmWare to Hyper-V and the Virtual CPU that you are assigning to a Virtual Machine is different and I'd like to know what should be the equivalent values when we move a ...
0
votes
1answer
44 views

Sata Disk very poor performance

I have a HP MicroServer NL54, stock BIOS, with 4 HDs Seagate Barracuda ST2000DM001 2TB 7200 RPM 64MB Cache. If I run a dd benchmark I get: $ dd if=/dev/zero of=/dev/sdb bs=4K count=4096 4096+0 ...
-2
votes
1answer
43 views

Servers in different DC's - performance impact

Today Linode eat my nerves completely by shutting down main DB server for 25 minutes due to their internal network problems. Right today I was going to set up another one server at linode to set up ...
0
votes
1answer
20 views

HP ProLiant BL460c Configuring Memory

I hope you can help me. I need to install 48GB of RAM in an HP BL460c G1. The CPU is 48W, and I've researched the specification and I can do it for this kind of processor. I've also read the basic ...
0
votes
0answers
22 views

KVM Virtual Machines and Public IPs

I currently have some Virtual Machines on my business dedicated server using the KVM layer as apposed to Xen or other virtualization methods. I was wondering if I could get a "best practice" on ...
-1
votes
4answers
90 views

MYSQL - is LOCALHOST speedy than i.e. (domain) mysql.domain.com [closed]

I am interested, on some hosting(although they are paid hostings, for example, DreamHost. probably 000webhost too), in database server, you have to insert: mysql.domain.com (instead of: localhost). I ...
3
votes
0answers
31 views

NGINX Worker Process, Burst Read Speed to only 1918kb/s

I am running an NGINX/1.8 server on Centos6.6 with multiple worker_processes, however while observing iotop I notice they burst up to 1918kb/s Read speed and rarely if at all pass that limit. I want ...
3
votes
2answers
164 views

NGINX Serving Large mp4 Files extremely inefficiently

I am currently running nginx/1.0.15 on a Centos 6.6 OS. The server has the following specs: Intel(R) Atom(TM) CPU C2750 @ 2.40GHz (8 cores) 32GB Ram 5 x 6000 GB 7200 RPM (Raid 10) The Problem The ...
1
vote
1answer
37 views

postfix SMTP outgoing gateway server, Software RAID1 vs RAID1 + RAID 0 on 2 disks

I have this old smtp server that is currently running Windows 2003 and with EOL I want to move it to something that will continue to get security upgrades but at same time I want to improve ...
0
votes
1answer
37 views

MySQL slow connection

I am running a laravel application that is on a separate server than my MySQL database. If I run the query on the Mysql server it takes the expected 0.00 - 0.01 seconds to return. However when I log ...
1
vote
1answer
37 views

Use in-memory database or search engine for read only to make website faster

I have an application which require doing a lot of queries for every single page which make it slower. I have tried to use cache systems (Redis) but implementation are little bit complicated and will ...
1
vote
1answer
93 views

nginx loading page very slow

I just deployed nginx in a new environment with the same configuration that I've used previously and I am seeing some very odd behavior. Nginx is configured as a reverse proxy for Solr, when I try ...
3
votes
1answer
87 views

How to find source of system running slow clock?

I've a problem on one of my Gentoo server. After some time, the clock starts running very very slow. It takes about one minute for one second to go. The major problem is that not only the clock is ...
2
votes
1answer
58 views

cloud server performance vs same specification dedicated server?

I have a web application written in php (5.6.10) and using Postgresql (9.4) we have about 4k users per day and about 20k page views per days, my main issue that we are running in cloud host with 2 ...
5
votes
2answers
185 views

cpufreq-info differs from /proc/cpuinfo?

I have a server and I want to ensure it's always running at maximum speed, never in energy-saving mode. I've tried a few strategies (aside from rebooting and changing the setting in the bios, which I ...
3
votes
2answers
106 views

Performance azure disks, high average queue length

I'm having a classic developer-system admin battle where I am stating that there is an IO problem on the disk of the shared sql server while the system admin tells me that the capacity hasn't been ...
1
vote
2answers
95 views

PHP5-FPM pm.max_children affect RAM or CPU+RAM?

Recently inherited a Nginx+PHP5-FPM server, and I'm learning and trying to optimize PHP5-FPM settings. Server info: 4 CPUs (8 threads) 7.5 GiB RAM PHP5-FPM info: pm.max_children = 5 ...
-2
votes
2answers
71 views

Is it normal to have 400~600ms of waiting for first byte? [closed]

I have optimized my website and apply many advices found on the Google search. but finally i have about 400~600ms of time to first byte. Does it normal or I can lower it? For dynamic data it it about ...