Re: [quicwg/base-drafts] kDefaultInitialRtt too large (#752)

[Christian Huitema <[e-mail]>]

On 8/30/2017 6:59 AM, Ryan Hamilton wrote:
> We have RTT data from Chrome which shows that the initial RTT
> distribution:
>
> PercentileValue
> 25.00% 22.58
> 50.00% 46.28
> 75.00% 88.08
> 95.00% 240.0
> 99.00% 733.9
> 99.50% 1187
>
>
> From this table, 100ms looks like a fine choice. 1s, on the other hand, is
> more than 10x the value at the median and is larger than the RTT for
> 99% of
> users. As Patrick says, I think the goal of QUIC is to make the web faster
> and would prefer to err on the side of faster.

>From the table, 150 or 200 would be OK -- no retransmit in 90% of the cases.

There is another way to view this. Currently, the spec specifies a
series of retransmissions with exponential increase of the RTT: T, 2*T,
4*T, 8*T, give up after 16*T. For T at 1 sec, that means retries can
take up to 30 seconds.  That's way too long for many applications. For
100 ms, that's 3 seconds, which is OK-ish but still high. Of course, we
have to cover the 99.5% case above.



-- 
Christian Huitema




-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/quicwg/base-drafts/issues/752#issuecomment-326018075