Message ID | 1387764856-13948-8-git-send-email-chenweilong@huawei.com |
---|---|
State | Superseded, archived |
Delegated to: | David Miller |
Headers | show |
On Mon, 2013-12-23 at 10:14 +0800, Chen Weilong wrote: > From: Weilong Chen <chenweilong@huawei.com> [] > diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c [] > @@ -15,13 +15,13 @@ > > #include "tcp_vegas.h" > > -#define TCP_YEAH_ALPHA 80 //lin number of packets queued at the bottleneck > -#define TCP_YEAH_GAMMA 1 //lin fraction of queue to be removed per rtt > -#define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss > -#define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion > -#define TCP_YEAH_PHY 8 //lin maximum delta from base > -#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss > -#define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count > +#define TCP_YEAH_ALPHA 80 /* lin number of packets queued at the bottleneck */ > +#define TCP_YEAH_GAMMA 1 /* lin fraction of queue to be removed per rtt */ > +#define TCP_YEAH_DELTA 3 /* log minimum fraction of cwnd to be removed on loss */ > +#define TCP_YEAH_EPSILON 1 /* log maximum fraction to be removed on early decongestion */ > +#define TCP_YEAH_PHY 8 /* lin maximum delta from base */ > +#define TCP_YEAH_RHO 16 /* lin minimum number of consecutive rtt to consider competition on loss */ > +#define TCP_YEAH_ZETA 50 /* lin minimum number of state switchs to reset reno_count */ Does anyone actually use this? Does "lin" add anything useful? lin should probably be removed otherwise. What does it mean anyway? link? linear? The link to the paper in the file is dead. http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf archive.org has it at: https://web.archive.org/web/20080316215752/http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf btw, spelling: s/switchs/switches/ -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On 2013/12/23 10:59, Joe Perches wrote: > On Mon, 2013-12-23 at 10:14 +0800, Chen Weilong wrote: >> From: Weilong Chen <chenweilong@huawei.com> > [] >> diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c > [] >> @@ -15,13 +15,13 @@ >> >> #include "tcp_vegas.h" >> >> -#define TCP_YEAH_ALPHA 80 //lin number of packets queued at the bottleneck >> -#define TCP_YEAH_GAMMA 1 //lin fraction of queue to be removed per rtt >> -#define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss >> -#define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion >> -#define TCP_YEAH_PHY 8 //lin maximum delta from base >> -#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss >> -#define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count >> +#define TCP_YEAH_ALPHA 80 /* lin number of packets queued at the bottleneck */ >> +#define TCP_YEAH_GAMMA 1 /* lin fraction of queue to be removed per rtt */ >> +#define TCP_YEAH_DELTA 3 /* log minimum fraction of cwnd to be removed on loss */ >> +#define TCP_YEAH_EPSILON 1 /* log maximum fraction to be removed on early decongestion */ >> +#define TCP_YEAH_PHY 8 /* lin maximum delta from base */ >> +#define TCP_YEAH_RHO 16 /* lin minimum number of consecutive rtt to consider competition on loss */ >> +#define TCP_YEAH_ZETA 50 /* lin minimum number of state switchs to reset reno_count */ > > Does anyone actually use this? > Does "lin" add anything useful? > lin should probably be removed otherwise. > What does it mean anyway? link? linear? > > The link to the paper in the file is dead. > http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf > > archive.org has it at: > https://web.archive.org/web/20080316215752/http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf > > btw, spelling: s/switchs/switches/ > > > . > Thanks for pointing out shortcomings in my patch,I'll fix it. I agree with you that 'lin' can be removed. I think 'lin' means 'socket link', according to the code,they are used for 'struct yeah',that is placed in each 'struct sock'. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 20cfaab..aeeae9e 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -15,13 +15,13 @@ #include "tcp_vegas.h" -#define TCP_YEAH_ALPHA 80 //lin number of packets queued at the bottleneck -#define TCP_YEAH_GAMMA 1 //lin fraction of queue to be removed per rtt -#define TCP_YEAH_DELTA 3 //log minimum fraction of cwnd to be removed on loss -#define TCP_YEAH_EPSILON 1 //log maximum fraction to be removed on early decongestion -#define TCP_YEAH_PHY 8 //lin maximum delta from base -#define TCP_YEAH_RHO 16 //lin minimum number of consecutive rtt to consider competition on loss -#define TCP_YEAH_ZETA 50 //lin minimum number of state switchs to reset reno_count +#define TCP_YEAH_ALPHA 80 /* lin number of packets queued at the bottleneck */ +#define TCP_YEAH_GAMMA 1 /* lin fraction of queue to be removed per rtt */ +#define TCP_YEAH_DELTA 3 /* log minimum fraction of cwnd to be removed on loss */ +#define TCP_YEAH_EPSILON 1 /* log maximum fraction to be removed on early decongestion */ +#define TCP_YEAH_PHY 8 /* lin maximum delta from base */ +#define TCP_YEAH_RHO 16 /* lin minimum number of consecutive rtt to consider competition on loss */ +#define TCP_YEAH_ZETA 50 /* lin minimum number of state switchs to reset reno_count */ #define TCP_SCALABLE_AI_CNT 100U