Linked Questions
11 questions linked to/from How to reduce number of sockets in TIME_WAIT?
8
votes
1
answer
108k
views
Avoid TIME_WAIT connections [duplicate]
When I use netstat command it shows..
tcp 0 0 localhost:18056 localhost:mysql TIME_WAIT
tcp 0 0 localhost:16683 localhost:mysql ...
5
votes
1
answer
9k
views
Relationship between tcp state TIME_WAIT & HTTP keep-alive
What is the relationship between keep-alive on a HTTP request and a tcp socket in TIME_WAIT - should they be correlated?
Furthermore, should system and web server settings be aligned e.g. server.max-...
- 182
3
votes
2
answers
7k
views
nginx reverse proxy greatly increases worst-case latency
(edit: partially understood and worked around, see comment)
I have a setup with nginx acting as a reverse proxy in front of a CherryPy app server. I'm using ab to compare performance going through ...
- 313
1
vote
2
answers
8k
views
Mysterious HAProxy request errors
I see tons of request errors on one of my frontend proxies (on the order of a few per second), but I can't figure out what's causing them. I've tried using the "show errors" command on the stats ...
- 3,355
3
votes
1
answer
2k
views
Munin's fw_conntrack reports strange number of sockets in TIME_WAIT
Ubuntu Server 10.04.1 x86
Munin 1.4.4
Here is what Munin tells me about connections through firewall on my server:
Here is what netstat -n has to say about this:
$ netstat -an|awk '/tcp/ {print $6}'|...
- 2,573
2
votes
1
answer
3k
views
How to monitor socket connection usage and exhaustion on a server?
I have a service endpoint (java) that will be getting bursts of thousands of requests per second.
In my load testing I had to tweak the server because I would run out of open sockets as there were ...
- 121
6
votes
1
answer
2k
views
Running some benchmarks using ab, and tomcat starts to really slow down
I'm running some benchmarks using apache bench for a java app that is running on tomcat.
Say I run a test like:
ab -c 10 -n 10000 http://localhost:8080/hello/world
It will run just fine. If I ...
- 503
3
votes
0
answers
3k
views
Reaching maximum TIME_WAIT sockets (tried tcp_fin_timeout)
tl;dr: How do i get the kernel to drop TIME_WAIT/closing sockets as forcibly and fast as possible? I don't care about data being lost since I'm not sending any.
I'm currently running a little test ...
- 237
2
votes
2
answers
809
views
Error: Can't alloc conntrack
What does the message in kernel.log:
nf_conntrack_alloc: Can't alloc conntrack
- 35
1
vote
0
answers
2k
views
nginx does not close loopback connections
I'm using nginx in reverse-proxy mode. Here's relevant part of config file:
server {
listen 80;
server_name ~^web.redhelper\.ru$ ;
access_log off;
location /http-bind {
...
- 1,319
0
votes
1
answer
948
views
Limiting outgoing connections by port to control nf_conntrack usage
I would like to make my system more resilient against certain failure. When the
system makes rapid outbound TCP connections fail, the nf_conntrack table
fills up with TIME_WAIT entries. This ...
- 628