From: Vlad Y. <vla...@hp...> - 2010-10-05 13:15:07
|
Hi Christian On 10/05/2010 12:25 AM, Christian Schoch wrote: > Hi Jon, > > The problem is inside the calculation of RTTVAR, which could last in > very high values for RTO. This wrong result exists when RTT is rising > and is bigger than SRTT (the subtraction goes negative). With this > patch is should be possible to set RTOmin = 1 and the RTO has its > minimum of 4 times the clock granularity - if the connection is fast > enough like a LAN connection. > > This patch should eliminate your problem. > I asked John (by mistake) to do the final patch. Since you are the original author, can you do a full submission with your sign-off? Thanks -vlad > Schoch Christian > > ----------------------------------------------------------------------- > > --- a/net/sctp/transport.c 2010-10-05 06:04:17.000000000 +0200 > +++ b/net/sctp/transport.c 2010-10-05 06:09:09.000000000 +0200 > @@ -334,7 +334,7 @@ > * 1/8, rto_alpha would be expressed as 3. > */ > tp->rttvar = tp->rttvar - (tp->rttvar>> sctp_rto_beta) > - + ((abs(tp->srtt - rtt))>> sctp_rto_beta); > + + (((__u32)abs((long)tp->srtt - (long)rtt))>> sctp_rto_beta); > tp->srtt = tp->srtt - (tp->srtt>> sctp_rto_alpha) > + (rtt>> sctp_rto_alpha); > } else { > > --------------------------------------------- > > > >> On 10/04/2010 04:04 PM, Jon Leighton wrote: >>> Has there been any resolution to this issue? Last July I reported a >>> problem I'd observed with timeout intervals jumping from 1 second to 60 >>> seconds, and which I presume is related to this problem. I saw the same >>> results in both the 2.6.31 and 2.6.34 kernels. I'm currently using >>> 2.6.31 and finding that file transfers over a lossy connection simply >>> halt because the server won't retransmit lost packets - at least not >>> within 2 hours. What is the maximum possible timeout value? If the >>> client closes the socket, I see the server start retransmitting the lost >>> packets. On 2.6.34 I haven't observed timeouts longer than 2 minutes, >>> but occasionally the system crashes. >>> >>> If there's been any resolution, such as a newer kernel or even just a >>> patch I can apply to my current kernel, I'd appreciate someone posting >>> that info. Thanks very much. >>> >> >> Hi Jon >> >> I dropped the ball on this on. I agree with your analysis and the proposed >> correction. Would you be willing to submit a formal patch for this with >> a full write-up in the description. >> >> Thanks >> -vlad >> >> >> >> ------------------------------------------------------------------------------ >> Virtualization is moving to the mainstream and overtaking non-virtualized >> environment for deploying applications. Does it make network security >> easier or more difficult to achieve? Read this whitepaper to separate the >> two and get a better understanding. >> http://p.sf.net/sfu/hp-phase2-d2d >> _______________________________________________ >> Lksctp-developers mailing list >> Lks...@li... >> https://lists.sourceforge.net/lists/listinfo/lksctp-developers >> > > > > > ------------------------------------------------------------------------------ > Beautiful is writing same markup. Internet Explorer 9 supports > standards for HTML5, CSS3, SVG 1.1, ECMAScript5, and DOM L2& L3. > Spend less time writing and rewriting code and more time creating great > experiences on the web. Be a part of the beta today. > http://p.sf.net/sfu/beautyoftheweb > _______________________________________________ > Lksctp-developers mailing list > Lks...@li... > https://lists.sourceforge.net/lists/listinfo/lksctp-developers > |