-
Notifications
You must be signed in to change notification settings - Fork 220
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
v0.9.8 #1800
v0.9.8 #1800
Commits on Oct 22, 2021
-
Configuration menu - View commit details
-
Copy full SHA for 6c70022 - Browse repository at this point
Copy the full SHA 6c70022View commit details -
Configuration menu - View commit details
-
Copy full SHA for 78e829a - Browse repository at this point
Copy the full SHA 78e829aView commit details -
Make sure we apt-get update in the build
The base image can get out of date.
Configuration menu - View commit details
-
Copy full SHA for c741066 - Browse repository at this point
Copy the full SHA c741066View commit details -
Configuration menu - View commit details
-
Copy full SHA for f3bac4a - Browse repository at this point
Copy the full SHA f3bac4aView commit details -
Merge pull request #1779 from jagerman/ci-python-deps
Add python packages to ci images
Configuration menu - View commit details
-
Copy full SHA for 808c2df - Browse repository at this point
Copy the full SHA 808c2dfView commit details
Commits on Oct 25, 2021
-
Configuration menu - View commit details
-
Copy full SHA for b5f5d07 - Browse repository at this point
Copy the full SHA b5f5d07View commit details
Commits on Oct 26, 2021
-
Add a bunch of base CI images for building debs
Installs just the base tools (which are quite substantial), but not the deps (which get installed as part of the build).
Configuration menu - View commit details
-
Copy full SHA for cbbee59 - Browse repository at this point
Copy the full SHA cbbee59View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1c4332a - Browse repository at this point
Copy the full SHA 1c4332aView commit details -
Configuration menu - View commit details
-
Copy full SHA for 9b7ec7d - Browse repository at this point
Copy the full SHA 9b7ec7dView commit details -
Configuration menu - View commit details
-
Copy full SHA for 2064ca0 - Browse repository at this point
Copy the full SHA 2064ca0View commit details -
Shows statuses that "fill in" when run interactively.
Configuration menu - View commit details
-
Copy full SHA for 09e97ee - Browse repository at this point
Copy the full SHA 09e97eeView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0572713 - Browse repository at this point
Copy the full SHA 0572713View commit details -
Add hacks; add --distro to rebuild just one
Bionic is broken and needs a hack to create some dumb pgm include directory. Add --distro cli argument so that you can rebuild just one distro.
Configuration menu - View commit details
-
Copy full SHA for 0b4c56d - Browse repository at this point
Copy the full SHA 0b4c56dView commit details
Commits on Oct 27, 2021
-
Merge pull request #1781 from majestrate/bump-static-deps-2021-10-25
bump libunbound static dep hashpin
Configuration menu - View commit details
-
Copy full SHA for 52f8273 - Browse repository at this point
Copy the full SHA 52f8273View commit details
Commits on Oct 28, 2021
-
Merge pull request #1778 from majestrate/net-range-detection-bug-2021…
…-10-22 check for intersecting ip ranges correctly, add unit test
Configuration menu - View commit details
-
Copy full SHA for fd81ee7 - Browse repository at this point
Copy the full SHA fd81ee7View commit details -
Configuration menu - View commit details
-
Copy full SHA for cd49031 - Browse repository at this point
Copy the full SHA cd49031View commit details -
Configuration menu - View commit details
-
Copy full SHA for e6622c1 - Browse repository at this point
Copy the full SHA e6622c1View commit details -
Merge pull request #1784 from jagerman/deb-docker-images
Generate CI images with much DRY-er Python dockerfile generating script
Configuration menu - View commit details
-
Copy full SHA for 60c1b69 - Browse repository at this point
Copy the full SHA 60c1b69View commit details
Commits on Oct 29, 2021
-
do not requeue nodes for testing from failing queue if we do not have…
… them marked as failing anymore
Configuration menu - View commit details
-
Copy full SHA for fcba709 - Browse repository at this point
Copy the full SHA fcba709View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0ec50e6 - Browse repository at this point
Copy the full SHA 0ec50e6View commit details -
Merge pull request #1791 from majestrate/exclude-failing-from-queue-2…
…021-10-29 exclude fully failed nodes from service node testing list
Configuration menu - View commit details
-
Copy full SHA for 1ddfb74 - Browse repository at this point
Copy the full SHA 1ddfb74View commit details
Commits on Nov 9, 2021
-
Configuration menu - View commit details
-
Copy full SHA for 22d4b88 - Browse repository at this point
Copy the full SHA 22d4b88View commit details
Commits on Nov 14, 2021
-
prevent 100% cpu usage on service nodes
call_soon wakes up the mainloop and is often reentrant, we dont want to ever way up the event loop but we also want to always defer the call so we always use the workers
Configuration menu - View commit details
-
Copy full SHA for 8744c93 - Browse repository at this point
Copy the full SHA 8744c93View commit details -
Configuration menu - View commit details
-
Copy full SHA for bb86996 - Browse repository at this point
Copy the full SHA bb86996View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8a9025e - Browse repository at this point
Copy the full SHA 8a9025eView commit details -
Configuration menu - View commit details
-
Copy full SHA for faf95cb - Browse repository at this point
Copy the full SHA faf95cbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 633431b - Browse repository at this point
Copy the full SHA 633431bView commit details -
Configuration menu - View commit details
-
Copy full SHA for cf5c4e7 - Browse repository at this point
Copy the full SHA cf5c4e7View commit details -
transit hop: drop instead of flushing when full
If full happens we are going to trigger a bunch of flushes which probably isn't very useful, so drop instead.
Configuration menu - View commit details
-
Copy full SHA for 41807f1 - Browse repository at this point
Copy the full SHA 41807f1View commit details -
- Modernize some iterator loops - Simplify a couple places by using `if (init; ...)` - Replace various std::binds with lambdas
Configuration menu - View commit details
-
Copy full SHA for bfc6d35 - Browse repository at this point
Copy the full SHA bfc6d35View commit details
Commits on Nov 15, 2021
-
This redoes how/when we pump so that we should only be calling the idempotent PumpLL() when we actually have (or may have) something to pump.
Configuration menu - View commit details
-
Copy full SHA for 9113a6b - Browse repository at this point
Copy the full SHA 9113a6bView commit details -
Configuration menu - View commit details
-
Copy full SHA for b03f3c2 - Browse repository at this point
Copy the full SHA b03f3c2View commit details -
Configuration menu - View commit details
-
Copy full SHA for 362fda5 - Browse repository at this point
Copy the full SHA 362fda5View commit details -
Configuration menu - View commit details
-
Copy full SHA for aa1dc83 - Browse repository at this point
Copy the full SHA aa1dc83View commit details -
Fix link layer delivery race condition (fix random ping delays)
We trigger a pump immediately, but this is racey because we add to our plaintext data in a worker thread; if the worker thread runs after the pump then it ends up leaving plaintext to be handled, but there's no wakeup until the next one. This was the cause of seeing a random +1s and bunching added to ping responses sometimes: it wasn't until the *next* ping goes through the network that the plaintext queue gets processed, at which point it flushes the old one and often the new one together. The fix here gets rid of the map of sessions needing wakeups and instead adds an atomic flag to all of them to let us figure out which ones need to be flushed.
Configuration menu - View commit details
-
Copy full SHA for 74215fc - Browse repository at this point
Copy the full SHA 74215fcView commit details -
Get rid of external event loop direct wakeups
If something needs to wake up the event loop it should be using an async, as we are now with PumpLL(); but we had various code triggering a wakeup, expecting that PumpLL gets called on every wakeup, which isn't true anymore.
Configuration menu - View commit details
-
Copy full SHA for 031ea7a - Browse repository at this point
Copy the full SHA 031ea7aView commit details -
And rename the actual pump implementation back to PumpLL.
Configuration menu - View commit details
-
Copy full SHA for 78cc466 - Browse repository at this point
Copy the full SHA 78cc466View commit details -
Increase plaintext queue size from 32 to 512
In testing we were sometimes hitting a full queue error, which makes sense because the queue size seems really small. Increase it to 512.
Configuration menu - View commit details
-
Copy full SHA for e47d309 - Browse repository at this point
Copy the full SHA e47d309View commit details -
Configuration menu - View commit details
-
Copy full SHA for 99b1294 - Browse repository at this point
Copy the full SHA 99b1294View commit details -
- Make the main PumpLL also pump hidden services, rather than using separate wakers in each TunEndpoint. It seems there is some interactions that just one or the other is not enough. - Eliminate TunEndpoint send queue -- it isn't needed as we can just send directly.
Configuration menu - View commit details
-
Copy full SHA for 9844d35 - Browse repository at this point
Copy the full SHA 9844d35View commit details -
Configuration menu - View commit details
-
Copy full SHA for f9395cd - Browse repository at this point
Copy the full SHA f9395cdView commit details -
Configuration menu - View commit details
-
Copy full SHA for 0924dd8 - Browse repository at this point
Copy the full SHA 0924dd8View commit details -
This has to happen before pumping links because it is putting things on links.
Configuration menu - View commit details
-
Copy full SHA for b3a8160 - Browse repository at this point
Copy the full SHA b3a8160View commit details -
Configuration menu - View commit details
-
Copy full SHA for 8cdde74 - Browse repository at this point
Copy the full SHA 8cdde74View commit details -
Configuration menu - View commit details
-
Copy full SHA for 846577a - Browse repository at this point
Copy the full SHA 846577aView commit details -
Configuration menu - View commit details
-
Copy full SHA for bce7e2e - Browse repository at this point
Copy the full SHA bce7e2eView commit details -
Configuration menu - View commit details
-
Copy full SHA for fbc5cb0 - Browse repository at this point
Copy the full SHA fbc5cb0View commit details -
The TriggerPump just below this is *already* going to trigger a flush, so the extra flush call here can't do anything useful (and in particular, it won't clear up the queue *immediately*, which is what this code looks like it was aimed at doing).
Configuration menu - View commit details
-
Copy full SHA for 70553c7 - Browse repository at this point
Copy the full SHA 70553c7View commit details -
Fix client latency bug; De-shared_ptr IHopHandler queues
- Replace m_FlushWakeup with a call to the router's god mode pump method. m_FlushWakeup apparently isn't enough to get things out, and we can end up with incoming packets that don't get properly handled right away without it. - The shared_ptr around the ihophandler queues isn't needed and is just adding a layer of obfuscation; instead just exchange the list directly into the lambda. - Use std::exchange rather than swap - A couple other small code cleanups.
Configuration menu - View commit details
-
Copy full SHA for 0fe7153 - Browse repository at this point
Copy the full SHA 0fe7153View commit details -
This test isn't very useful, but also broken with the other changes on this branch.
Configuration menu - View commit details
-
Copy full SHA for f63fff3 - Browse repository at this point
Copy the full SHA f63fff3View commit details -
Configuration menu - View commit details
-
Copy full SHA for 711038d - Browse repository at this point
Copy the full SHA 711038dView commit details -
Configuration menu - View commit details
-
Copy full SHA for 687b54f - Browse repository at this point
Copy the full SHA 687b54fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 09c2b31 - Browse repository at this point
Copy the full SHA 09c2b31View commit details -
Merge pull request #1795 from majestrate/try-reducing-cpu-usage-2021-…
…11-09 make PumpLL idempotent to reduce cpu use a bit
Configuration menu - View commit details
-
Copy full SHA for f270d74 - Browse repository at this point
Copy the full SHA f270d74View commit details -
Avoid std::function in hot pump code
We're seeing overhead here of the std::function invocation, which we can easily avoid in this case by not using a std::function around the callback.
Configuration menu - View commit details
-
Copy full SHA for 7a04911 - Browse repository at this point
Copy the full SHA 7a04911View commit details -
Merge pull request #1796 from jagerman/hotloop-optimization
Avoid std::function in hot pump code
Configuration menu - View commit details
-
Copy full SHA for 3fc172f - Browse repository at this point
Copy the full SHA 3fc172fView commit details -
Optimization: eliminate unneeded shared_ptrs
We have a few cases where we're making an extra shared_ptr which we copy into a lambda, which then results in an extra unnecessary refcount decrement in the parent; this changes them to give an rvalue reference to the lambda to avoid the extra incr/decr instead. The one in Session::Pump is particularly noticeable and shows up in profiling.
Configuration menu - View commit details
-
Copy full SHA for b2ee003 - Browse repository at this point
Copy the full SHA b2ee003View commit details -
Use libuv's cached current time for
time_now()
We are calling time_now() a huge amount, and it is a major consumer of CPU cycles, but we don't need it: most of the time the current event loop time is enough.
Configuration menu - View commit details
-
Copy full SHA for 5115162 - Browse repository at this point
Copy the full SHA 5115162View commit details
Commits on Nov 16, 2021
-
Merge pull request #1797 from jagerman/random-optimizations
Random optimizations
Configuration menu - View commit details
-
Copy full SHA for b95e53d - Browse repository at this point
Copy the full SHA b95e53dView commit details -
in static linux ci pipeline disable building lokinet-bootstrap and bu…
…ndle a bootstrap.signed
Configuration menu - View commit details
-
Copy full SHA for e7d2829 - Browse repository at this point
Copy the full SHA e7d2829View commit details -
Merge pull request #1799 from majestrate/static-ci-disable-lokinet-bo…
…otstrap-2021-11-16 disable lokinet-bootstrap in static linux ci pipeline
Configuration menu - View commit details
-
Copy full SHA for e4514ae - Browse repository at this point
Copy the full SHA e4514aeView commit details -
Configuration menu - View commit details
-
Copy full SHA for d24f891 - Browse repository at this point
Copy the full SHA d24f891View commit details