Super User is a question and answer site for computer enthusiasts and power users. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am getting this error in squid (which goes away after about 20 seconds but annoys the users to no end) (105) No buffer space available Then if I go to the command line and try and ping I get this error

ping www.google.com connect: No buffer space available

So the error seems to be kernel related.

So I added these lines to /etc/sysctl.conf

net.core.rmem_max = 16777216 net.core.wmem_max = 16777216 net.ipv4.tcp_rmem = 4096 87380 16777216 net.ipv4.tcp_wmem = 4096 65536 16777216 net.ipv4.tcp_timestamps = 1 net.ipv4.tcp_sack = 1 net.ipv4.tcp_no_metrics_save = 1 net.core.netdev_max_backlog = 5000

and reloaded the changes .... But still getting the error

Any suggestions?

share|improve this question

A fast search on google for: ping no buffer space available returns various forum thread which seems to agree on this point:

The two NICs share the same IRQ or maybe one of them shares it with another card/ide/usb device.

You could try a cat /proc/interrupts and see if that's the case.

For example on a server with two NICs I have:

0:      105539   IO-APIC-edge      timer
1:           2   IO-APIC-edge      i8042
2:           0   XT-PIC-XT         cascade
8:           1   IO-APIC-edge      rtc0
10:          0   IO-APIC-fasteoi   ohci_hcd:usb1
12:          4   IO-APIC-edge      i8042
14:  882208736   IO-APIC-edge      ide0
15:          0   IO-APIC-edge      ide1
22: 3552346607   IO-APIC-fasteoi   eth0
23: 3776214353   IO-APIC-fasteoi   eth1

so no sharing here.

share|improve this answer

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .