- Queries
- All Stories
- Search
- Advanced Search
- Transactions
- Transaction Logs
Advanced Search
Oct 27 2021
Oct 26 2021
This method is fine, I will withdraw my fab in favor if this :)
While where at it, there is a duplicate srtt that should be just one var at the higher scope. Lets fix
that and make the needed casts when comparing to slot. That way we never can get a
confused compiler :)
Oct 25 2021
Overall I think this is a good fix for an ugly problem. I.e. that other
CC algo's use newreno. I think we should re-look at this and have the
"reused" functions put into the kernel as just non-static functions that
can be used by CC modules. Pass in beta etc...
Michael has shown me how to add the right magic to git to get full context yeah!
Update the diff with offline comments from Jonathan
I don't see any hpts changes in this review.. which is what I was looking for. I suppose
you have it in another review then??
In D32373#735881, @lstewart wrote:I haven't finished reviewing yet but some initial thoughts in addition to my inline comments:
- Nit: please submit diffs with full context as it makes reviewing easier
- You need to address how enabling Hystart++ when using cc_newreno with the default FreeBSD stack will work
- The implementation pessimises the common case where newreno will be used without ABE or Hystart++ which is probably undesirable. The module's lack of a cb_init() hook implementation was very deliberate to avoid such pessimisation and also as noted inline, assumptions are made elsewhere that cc_newreno can always be used as an algo of last resort so we cannot allow init to ever fail.
Oct 24 2021
Opps one typo to fix
I believe this is the more generic approach or at least closer to what Gleb wants. The names
might be wrong but I think it gets at what he has been saying..
In D32600#736198, @glebius wrote:I'm in the process of writing more generic patch to cover this. I would ask not to commit the intermediate version.
Note that already existing IPV6_USE_MIN_MTU handling in tcp_ctloutput is pretty much the same problem.
For IPv4 options and rack, there is also IP_TTL socket option that (I believe) needs same handling as IP_TOS.
This remix's things so that we create a t_fb function that can be called
by the codepoint changes i.e. the socket option if the transport wants
it and this updates the rack fsb.
Oct 23 2021
Let's not mess in ip or ip6 but intercept this in TCP. This also makes it so
we don't try this on UDP.
Oct 22 2021
Fix my DHCP/DSCP typos :)
Oct 20 2021
Address Michael's comments.
Oct 8 2021
Oct 1 2021
This refactors so that we end up with the data in netstat instead
so that it can be used by others besides NF. I also add the hooks
into tcp_sack so the counters are maintained for the base stack, though
we don't track TLPs (or do TLPs for that matter). BBR has the netstats
removed and now uses the proper api. Note that it does do TLP but
as of yet does not track what dsack bytes were caused by TLPs.
Sep 27 2021
Sep 23 2021
Sep 22 2021
Sep 14 2021
Aug 17 2021
Aug 11 2021
Jul 19 2021
Jul 16 2021
Committed
Jul 15 2021
Correct the bug in the calculation as well as subtracting out the outer
header size from the m_len on the second inner header parse.
Add Hans predict false around the hopefully never exercised returns
We can add predict false here, since the majority of times we would
never go those paths. That makes sense, but we need to have the
checks. If we don't then at some point a driver writer that is not
as good as you will send in packets in an invalid way and we
won't catch it.
Ok just got through testing this, and it works great.. no problems as I saw before ;-)
Michael and I have chatted on the transport sync. I am going to remove
this review, and he is going to separate out the EPOCH review on its own.
Drew
Here is the bug Michael did the epoch thing over
A couple of bits..
another extra nl
Spacing issues
Jul 13 2021
Update with Hans and Michael's suggestions.
Jul 12 2021
Opps forgot the tcp_subr.c and tcp_var.h changes too
Jul 8 2021
Jul 7 2021
Jul 6 2021
Opps forgot to include the include file ;)
Jun 25 2021
Jun 24 2021
Jun 17 2021
I wound not advise putting names in the man page.