0
votes
0answers
36 views

Keepalived process not listening to advertisement

I have a keeplived setup working on RHEL 5.5 working file. Below is strace of keepalived master, which is reading advertisements off the network and sends its advertisement to the network. ...
0
votes
2answers
148 views

nginx or kernel queueing traffic

We have a setup that looks like this: nginx->haproxy->app servers We are terminating SSL with nginx and it sits in front of everything. During our peak load times, we are experiencing about a 2x ...
0
votes
0answers
49 views

Suspecting Wrong Configuration of Sysctl (Silent TCP Drops?)

I have a high load long TCP connections server and I had to tweak sysctl to make sure I get no errors, At the moment I get no errors, But I think i might get TCP drops without errors. Here is sysctl ...
2
votes
1answer
2k views

Netstat -s showing (and growing) “packets pruned from receive queue” and “packets collapsed in receive queue”

we are seeing the following: [root@primary data]# netstat -s | grep buffer ; sleep 10 ; netstat -s | grep buffer 20560 packets pruned from receive queue because of socket buffer overrun ...
2
votes
1answer
427 views

No buffer space available and tuning with sysctl

Not really a network guy so please bear with me. I'm currently hosting a web application that sends UDP to all IP addresses in it's subnet periodically. That's 2048 IPs. My problem is it throws No ...
4
votes
1answer
675 views

Linux networking port exhaustion

I've done as much research as I could on this without digging right off in the kernel source. There seems to be a large amount of disinformation/incorrect info on the subject, so I hope this answers ...
0
votes
1answer
2k views

nf_conntrack: table full, dropping packet

Mar 24 03:29:26 kernel: [1557411.243821] TCP: time wait bucket table overflow (CT0) Mar 24 03:29:26 kernel: [1557411.243828] TCP: time wait bucket table overflow (CT0) Mar 24 03:29:26 kernel: ...
0
votes
2answers
959 views

Writeback cache in linux

In linux how do I have a writeback cache on disks? Basically, I'd like to setup a 100MB RAM cache for writing that writes out every 3-5 minutes or when full. Is this possible? Is there a sysctl ...
1
vote
1answer
2k views

Linux webhost security settings in /etc/sysctl.conf

While searching for more ways to secure Linux servers, I found the following /etc/sysctl.conf configuration. It came as is, without much explanation. Before using it on production environment (using ...
2
votes
1answer
3k views

Higher rmem_max value leading to more packet loss

The rmem_max Linux setting defines the size of the buffer that receives UDP packets. When traffic becomes too busy, packet loss starts occurring. I made a graph showing how packet loss increases ...
1
vote
2answers
962 views

SYN Cookies on a LAN server - Ok / advisable to disable?

We are looking at tuning our linux tcp stack on one of our lan boxes. We were wondering if it is ok / advisable to disable SYN cookies on a server that doesnt have any sort of external (eg: ...
0
votes
0answers
2k views

sysctl tcp_max_syn_backlog dont work

I change value tcp_max_syn_backlog in sysctl in my ubuntu server 10.04 for growing SYN_RECV queue. But isnt work (I flood this server by hping). But, when i change somaxconn (in documentation its ...
4
votes
2answers
2k views

Suggestions for making sysfs parameters persist across reboots

I'm experimenting with large changes to Linux system runtime parameters exposed through the sysfs virtual file system. What is the most efficient way to maintain these parameters so that they persist ...
0
votes
3answers
3k views

Shared memory: shmget fails: No space left on device — how to increase limits?

I call shmget many times in my program, to get shm of of average size 85840 bytes. I obtain about 32771 shm ok, then shmget doesn't return a shm, but the error: "No space left on device". I have ...
18
votes
3answers
33k views

Improving TCP performance over a gigabit network with lots of connections and high traffic of small packets

I’m trying to improve my TCP throughput over a “gigabit network with lots of connections and high traffic of small packets”. My server OS is Ubuntu 11.10 Server 64bit. There are about 50.000 (and ...
2
votes
4answers
2k views

After reboot debian box ignore sysctl.conf values

Where is right place for sysctl redefined values? I have: > uname -a Linux note 3.1.0-1-amd64 #1 SMP Tue Jan 10 05:01:58 UTC 2012 x86_64 GNU/Linux > cat /etc/debian_version wheezy/sid ...
0
votes
1answer
1k views

sysctl setting for maximum connections from ip address

Is there any settings in sysctl that controls the maximum number of connections that are allowed from any one ip address? I'm having connection issues a redis server and a rabbitmq instance and I'd ...
1
vote
1answer
1k views

Optimize linux for serving http static content

What would be the system tunables to enhance serving static content? Like increase/decrease swappines, how to max out disk caching and so on...
4
votes
3answers
2k views

What does tcp_orphan_retries set to 0 mean?

Does setting tcp_orphan_retries to 0 mean there is no limit to retries, or does it mean that it won't retry at all?
1
vote
3answers
2k views

sysctl.conf not running on boot

At what point is sysctl.conf supposed to be read during boot, and why might it not be running? I have the following settings which are not being applied when I reboot: ...
1
vote
4answers
4k views

Persistent changes to /proc/sys/sunrpc/tcp_slot_table_entries

I'm trying to make a persistent change to sunrpc.tcp_slot_table_entries on a Linux CentOS 5.5. This value has been found important for the performance of our NFS clients, and must be set before the ...
4
votes
2answers
2k views

Persisting nf_conntrack_max Across Reboots

In /proc I have two entries for nf_conntrack_max: /proc/sys/net/netfilter/nf_conntrack_max /proc/sys/net/nf_conntrack_max The seem to point to the same value as changing one also changes the ...