1
vote
0answers
26 views

Difference between all servers in one cluster and more than one cluster with servers? [closed]

Not sure I understand what´s the difference or how it works when servers a running in one cluster or if there are more than one clusters with servers in it - regard High availability & Load ...
0
votes
0answers
88 views

Apache Load Balancer With JBoss

I have Apache acting as a load balancer in front of 5 JBoss nodes. When I put a load of more than 200 concurrent users on the environment through my load testing tool, my response times are going ...
-2
votes
2answers
72 views

How should I host a website with infrequent, planned load spikes? [closed]

I have a smallish site which I expect to have extremely high concurrent traffic for a few hours each month. I'm trying to work out what hosting solution will ensure the site never goes down. Here are ...
0
votes
0answers
89 views

Is it time to add a server [duplicate]

This question is about figuring out if horizontal scaling by adding servers is the next step or not. Here is the context: About 1400 concurrent users at peak time (between 11:00am-4:00pm) in Google ...
0
votes
0answers
271 views

High Load average in Linux kernel 2.6.26 even cpu time is available?

I have 2 machine. both the machine I have kernal 2.6.26. Both machines are getting more then 300 load averages even cpu idle time is 80%-90%. In the wa column also very less. The followings are top ...
0
votes
1answer
94 views

Looking for the best ec2 setup for 3 sites totaling in 1.5 mil in traffic monthly [closed]

I am looking to consolidate our current aws setup of 2 Large ubuntu ec2 servers and 2 large RDS server for our 3 websites that have a total of about 1.5 million hits a month and increasing every month ...
3
votes
1answer
463 views

How to forcast the spec of a Linux load balancer?

I would like to build a Linux load balancer with SSL off load with sticky sessions. I would like to do this with either Pound or Pound and HAProxy. I haven't done this before, and I have been wanting ...
1
vote
2answers
105 views

How to implement master slave with minimum overhead? [closed]

I have 2 machines (linux machine run my cpp application). About application: application collect packet from NFQUEUE and log them , based on some logic. The application is simple cpp application that ...
5
votes
4answers
506 views

Is there an advantage to load balancing using multiple VMs all on the same hardware?

Some collegues are suggesting a web load balancing schema with multiple web servers (IIS7) on different virtual machines all running on the same hardware. Is this a truly advantageous setup? All ...
0
votes
2answers
120 views

Distribute the load all around the world

Let's say we're starting a project which is meant to be served all around the world How am I supposed to distribute the database and server load, and increase (optimize) the service for large ...
0
votes
2answers
134 views

New server: use for SQL Server or Windows (Web)? [closed]

I picked up a new Dell R410 2.8 Ghz 12M cache 32 GB Ram RAID-1/RAID-1 for a good year-end deal. It was purchased mainly to replace my Dell PowerEdge 2850 which is my main WEB server. I run Windows ...
1
vote
2answers
426 views

Increasing the concurrent user performance in LAMP application

We have a LAMP application where we have started to feel the performance pinch due to large number of concurrent users connecting to the application. I have looked at the individual parameters of ...
2
votes
3answers
258 views

Multiple IP addresses vs. Reverse Proxy / Apache Rewriting

We're a small business and trying to decide on the best architecture for our internal boxes. We have some dev, production and staging environments. All of them are publicly accessible (but of course ...
1
vote
0answers
346 views

Performance issues on LAN with Load balancing

I recently set up a network which is running "slow" and I can't seem to debug the situation. I'm fairly noobie at networks I'll explain the setup and hopefully you can give me possible solutions. I ...
4
votes
3answers
4k views

IIS slows down at 1000 concurrent connections

I am looking at a performance problem of an asp.net web site. It appears that when we hit 1000 concurrent connections per server things slow down. We have several web servers behind a hardware load ...
2
votes
2answers
489 views

10tb file storage design question on media website

I have a fairly busy media website where MP3 audio files are uploaded by members and streamed / downloaded from 2 Windows servers which are load balanced at the moment...both servers simply mirror ...
0
votes
2answers
1k views

How does Round Robin verus Sticky IP affect performance

I am analysing a performance problem on a Load Balanced WSS 3.0 site. The site uses Round Robin load balancing and Windows autentication with NTLM. One of the problems appears to be excessive http ...
2
votes
2answers
113 views

Is this server specification good?

Sorry for this newbie question, but I was going to order this server to run my PHP and MySQL web application, I'm doing a project for the students in my class, and it's going to have about 1000 users ...
1
vote
3answers
153 views

Server speed: sharing one script.php or using many copies the same script.php

Let's assume: I have thousands of domains on same Apache server. Each domain is in a folder under server public_html document folder, so it can be accessed by calling "www.somedomain.com" or by ...
14
votes
3answers
12k views

GlusterFS vs Ceph, which is better for production use for the moment? [closed]

I am evaluating GlusterFS and Ceph, seems Gluster is FUSE based which means it may be not as fast as Ceph. But looks like Gluster got a very friendly control panel and is ease to use. Ceph was ...
1
vote
1answer
1k views

Performance issue with Apache, PHP and Symfony

Updated: ================================================================ I finally found the reason with oprofile. It was because the routing cache of Symfony. We have lots of pages with different ...