Re: [LARTC] Extremely inaccurate results using either TBF or HTB

[sufcrusher]

This worked miracles for me:   change /usr/src/linux/include/net/pkt_sched.h PSCHED_CLOCK_SOURCE to PSCHED_CPU if you have a cpu with timestamp counter (TSC) that will give you Mhz timer granularity.   (don't forget to recompile of course) Jannes Faber ----- Original Message ----- From: Dan Farino To: [EMAIL PROTECTED] Sent: Tuesday, November 12, 2002 9:57 AM Subject: [LARTC] Extremely inaccurate results using either TBF or HTB Hi everyone,   I am getting extremely inaccurate results from my setup: - RedHat 8.0 on a Compaq ProLiant 1600, dual PII/450, Intel Dual 100 NIC - I�ve tried both SMP and non-SMP kernels. - I�m using the updated tc from the HTB home page. - I�m using the HTB that comes with the RH8 kernel.   Here�s what�s happening. If I, for instance:      tc qdisc add dev eth2 root tbf rate 1.9mbit buffer 20Kb/8 limit 15Kb   Then my download rate goes at 360,000 bytes/s, which, by my calculations, is 2.77mbit. I am using Win2k perfmon to test the speed. The line is flat and the speed is very consistent (consistently *wrong*, unfortunately�)   Immediately after, I do:      tc qdisc change dev eth2 root tbf rate 1.8mbit buffer 20Kb/8 limit 15Kb   My download speed is then 243,000 bytes/s, or 1.85mbit. Again, very flat, consistent line.   I have played with the parameters on both TBF and HTB in many different configurations. I always seem to have a large jump between 1.8-1.9. I can�t find any number between those two that will actually produce a 2mbit limit. I know 1.85 is close to 2.0, but is this the expected margin of error? (Then again, 2.77 isn�t close to 1.9 at all, so I hope not!)   Has anyone else experienced anything like this?   Thank you very much for any help you can provide!   Dan Farino Sr. System Engineer Stamps.com, Inc. Santa Monica, CA