netem bug?
Hi all,
I'm running some tests with netem and I noticed some strange behaviour that looks like a bug: I'm pinging another machine and adding delay with netem. When I tell netem to give me a 10ms delay, it works fine. The problem is that when I ask for a 11ms delay, it gives me 20ms! It happens for any value between 11ms an 20ms, and it repeats for values over 20ms, now rounding up to 30ms.
Here is an example:
# ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time=0.197 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time=0.100 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time=0.081 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time=0.099 ms
# tc qdisc add dev eth0 root netem delay 10ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time=1.11 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time=9.04 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time=9.24 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time.0 ms
# tc qdisc change dev eth0 root netem delay 11ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time.1 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time .0 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time .0 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time .0 ms
# tc qdisc change dev eth0 root netem delay 23ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time".2 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time).8 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time).1 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time0.0 ms
# uname -a Linux yyy 2.4.27-1-386 #1 Fri Sep 3 06:24:46 UTC 2004 i686 GNU/Linux
Is this a known bug? Is there any fix? I also noticed that the first ping has always a smaller value. Can someone explain that?
Thanks,
Pedro.
_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
Quoted 43 lines
Hi all,
I'm running some tests with netem and I noticed some strange behaviour that looks like a bug: I'm pinging another machine and adding delay with netem. When I tell netem to give me a 10ms delay, it works fine. The problem is that when I ask for a 11ms delay, it gives me 20ms! It happens for any value between 11ms an 20ms, and it repeats for values over 20ms, now rounding up to 30ms.
Here is an example:
# ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time=0.197 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time=0.100 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time=0.081 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time=0.099 ms# tc qdisc add dev eth0 root netem delay 10ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time=1.11 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time=9.04 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time=9.24 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time.0 ms# tc qdisc change dev eth0 root netem delay 11ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time.1 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time .0 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time .0 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time .0 ms# tc qdisc change dev eth0 root netem delay 23ms # ping x.x.x.x PING x.x.x.x (x.x.x.x) 56(84) bytes of data. 64 bytes from x.x.x.x: icmp_seq=1 ttld time".2 ms 64 bytes from x.x.x.x: icmp_seq=2 ttld time).8 ms 64 bytes from x.x.x.x: icmp_seq=3 ttld time).1 ms 64 bytes from x.x.x.x: icmp_seq=4 ttld time0.0 ms
Quoted 6 lines
# uname -a Linux yyy 2.4.27-1-386 #1 Fri Sep 3 06:24:46 UTC 2004 i686 GNU/LinuxIs this a known bug? Is there any fix? I also noticed that the first ping has always a smaller value. Can someone explain that?
The "problem" is the 2.4 kernel because HZ is 100.
Ping is not rescheduled quickly enough to measure correctly the rtt.
On my 2.6 kernel (HZ00) it work almost perfect.
Hope it helps.
Quoted 9 lines
Thanks,
Pedro.
_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
---
Catalin(ux aka Dino) BOIE
catab at deuroconsult.ro
http://kernel.umbrella.ro/
_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/
Hi.
Quoted 1 line · Catalin(ux aka Dino) BOIE
The "problem" is the 2.4 kernel because HZ is 100.
That was my idea, too.
Quoted 1 line
On my 2.6 kernel (HZ00) it work almost perfect.
If the OP thinks of changing HZ, the following links might be a good help:
http://www.plumlocosoft.com/kernel/
(especially 013-j64.diff.bz2 and 014-vhz.diff.bz2)
http://kerneltrap.org/node/464/1528
The mentioned patches allow to change HZ to something else than 100 while retaining compatibility to userspace and other stuff that might rely on HZ being 100. Note that kernel image as well as (most probably all) modules have to be recompiled and replaced for the patch to take effect.
Bye, Mike
_______________________________________________
LARTC mailing list / [email protected]
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/