[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

**To**:**Thor Lancelot Simon <tls%coyotepoint.com@localhost>****Subject**:**Re: very old rtt calculation bug?****From**:**Greg Troxel <gdt%ir.bbn.com@localhost>**- Date: Wed, 10 Nov 2010 08:06:03 -0500

Thor Lancelot Simon <tls%coyotepoint.com@localhost> writes: > A coworker is looking at some ad-hoc stack tuning for heavy load which > has parameters that depend on rtt. We are seeing the smoothed rtt vary > for TCP connections on loopback in ways we don't expect. > > We have begun to suspect that the changes in tcp_input.c 1.16 and 1.27 > are wrong. In particular, as my coworker points out: > > | I am pretty sure the NetBSD algo is wrong: > | > | if (tp->t_srtt != 0) { > | /* > | * srtt is stored as fixed point with 3 bits after the > | * binary point (i.e., scaled by 8). The following magic > | * is equivalent to the smoothing algorithm in rfc793 with > | * an alpha of .875 (srtt = rtt/8 + srtt*7/8 in fixed > | * point). Adjust rtt to origin 0. > | */ > | delta = (rtt << 2) - (tp->t_srtt >> TCP_RTT_SHIFT); > | if ((tp->t_srtt += delta) <= 0) > | tp->t_srtt = 1 << 2; > | > | The (rtt << 2) means that we are adding 1/2 the RTT to srtt, rather than > 1/8. > | Given that srtt is << 3, if we do not shift rtt by anything, adding it to > | srtt adds rtt/8 to it. > > FreeBSD shifts rtt by two here, but they keep 5 bits of precision vs our 3, > so there it's correct. > > Are we missing something? Bev Schwartz, Laura Ma, and I have been looking at this. This is from memory -- defuzzed version and patch to follow probably next week. There are several problems in the RTT code. value is stored with a +1 to let 0 be special, but it's not subtracted before use rounding errors when dealing with very low RTTs "very low" is not that low because this is based on a long timer tick We have a fix for the first two problems; with the fix TCP performs better under loss due to faster RTO processing.

**Attachment:
pgpU4sAkxz88w.pgp**

**Follow-Ups**:**Re: very old rtt calculation bug?***From:*YAMAMOTO Takashi

**Re: very old rtt calculation bug?***From:*Thor Simon

**References**:**very old rtt calculation bug?***From:*Thor Lancelot Simon

- Prev by Date:
**passing an if-specific string via ifconfig** - Next by Date:
**Re: proper SACK behavior?** - Previous by Thread:
**very old rtt calculation bug?** - Next by Thread:
**Re: very old rtt calculation bug?** - Indexes: