2586bade68
re-added support for configuration TLS options with environment variables
2020-02-26 15:33:48 -08:00
d60268123b
updated comment
2020-02-25 16:00:46 -08:00
6e7d2ff7dd
prevent the proxy from delaying too long based on an incorrect estimate of the compute time
2020-02-25 15:46:13 -08:00
65fbe0d0bc
revert AcceptSocket priority change because of bad performance results
2020-02-21 19:22:14 -08:00
6f1d3ccd35
Merge branch 'release-6.2' into feature-boost-ssl
2020-02-20 20:03:40 -08:00
7056c73f20
fixed a number of problems with findBestPolicySetSimple
2020-02-20 20:00:54 -08:00
dc3826e2fd
fix: tls throttling would re-insert the failure into the map
2020-02-20 18:17:39 -08:00
f04e311a1e
Merge commit 'b46d6e25e24993ab5a5f04091fd3235050b7cd09' into feature-boost-ssl
...
# Conflicts:
# fdbserver/SimulatedCluster.actor.cpp
# flow/Net2.actor.cpp
2020-02-20 17:36:38 -08:00
a50939417b
fix: zoneid is all lower case
2020-02-20 17:26:44 -08:00
f7a37077cc
handshake takes time in simulation
2020-02-20 15:26:56 -08:00
d7c841a28a
Merge pull request #2589 from etschannen/feature-proxy-delay
...
Improve version pipelining on the proxy
2020-02-20 15:23:30 -08:00
8b768e66df
Merge pull request #2694 from dongxinEric/feature/2663/specialize-policy-for-zoneid-in-cc
...
Added a specialized algorithm for PolicyOne and PolicyAcross(,'zoneId…
2020-02-20 14:46:23 -08:00
def8ca6da3
simulation advances timer() separately from now() to better model the real world
2020-02-20 12:10:20 -08:00
298d6cb3d7
Address review comments.
2020-02-20 09:34:01 -08:00
3c4d551647
improve prioritization of connection monitor and listen given that listen is no longer expensive (because handshake is done separately)
2020-02-19 18:50:21 -08:00
761da5a059
code cleanup
2020-02-19 17:59:45 -08:00
a6486766c2
fix: rebooting an unreliable process will make it reliable again, but while unreliable the files for that process could have already been corrupted so simulation will think a process is healthy that is actually corrupted
2020-02-19 15:18:57 -08:00
46d5f5e325
do not trigger the resetPing if we cannot actually remove the peer, because it will cause us to reset the timeout, so repeated calls to removePeer can keep a dead peer from being removed
2020-02-19 15:17:50 -08:00
efc0d7f9d5
Added a specialized algorithm for PolicyOne and PoilcyAcross(,'zoneId',PolicyOne()) to find a set of TLog servers which will be able to fulfill the policy later.
2020-02-19 09:25:57 -08:00
dcbce3593e
fixed TLS in simulation
2020-02-10 14:00:21 -08:00
6b921ac900
Stop building FDBLibTLS and stop linking against libtls.so
...
Which now means OpenSSL and LibreSSL are equally acceptable.
2020-02-06 21:13:58 -08:00
38d8d0d675
fixed simulation
2020-02-06 19:29:31 -08:00
69de430057
separate handshaking from connection to improve pipelining
2020-02-06 16:45:54 -08:00
53d0867a17
limit the number of connections a process can attempt to establish in parallel
2020-02-04 18:15:10 -08:00
84853dd1fd
switched SSL implementation to use boost ssl
2020-02-04 14:56:40 -08:00
231d7830a0
more accurate calculation on the amount of time that proxy should wait before getting a version from the master
2020-01-26 19:47:12 -08:00
afd3ec13ff
added knobs
2020-01-21 18:58:34 -08:00
4a716b85f6
we must still finish accept before the handshake completes
2020-01-21 16:55:34 -08:00
7a4b459f07
wait for a tls handshake to complete before returning a connection
...
wait for multiple tls errors before throttling
2020-01-21 16:45:15 -08:00
0e916fdbed
throttle client TLS errors longer than server errors so that when both happen simultaneously the server throttling will be disabled when the client makes its next attempt
2020-01-12 22:12:18 -08:00
bc4d33a55b
fixed compiler error
2020-01-12 17:01:08 -08:00
1f7eb1f738
throttle outgoing tls connections before establishing a network connection
...
store serverTLSConnectionThrottler map inside of g_network, so that it works properly with simulation
2020-01-12 16:44:30 -08:00
ccfbf04e20
Revert "Throttle both client and server side TLS connections if there is a handshake error."
...
This reverts commit 1b1be9f764
2020-01-10 18:41:02 -08:00
1b1be9f764
Throttle both client and server side TLS connections if there is a handshake error.
2020-01-10 18:08:02 -08:00
249e5a73b6
Minor optimization that erases an entry from the map only when it is present.
2020-01-10 16:39:25 -08:00
741aa523e6
Establishing TLS connection through the handshake process is expensive and the fdbserver process can get easily saturated with doing repeated TLS handshakes with only a few hundreds of clients have bad certificate. Hence throttle the number of handshakes done on the server per client ip if it has a bad certificate.
2020-01-10 16:19:41 -08:00
a9541f8066
Merge branch 'feature-addpeer-fix' of github.com:etschannen/foundationdb into feature-addpeer-fix
2020-01-03 12:15:45 -08:00
7152469cc3
log the base trace event before the endpoint messages
2020-01-03 12:15:38 -08:00
6b28e3b43b
Update fdbrpc/LoadBalance.actor.h
...
Co-Authored-By: A.J. Beamon <ajbeamon@users.noreply.github.com>
2020-01-02 17:37:58 -08:00
9e137d3b49
fix: addPeerReference only marks a connection as healthy if it is the first peerReference
...
added additional logging to long LoadBalance calls, and when the failure monitor state changes for an address
2019-12-19 18:26:29 -08:00
b126570a20
Augment tests to catch A.J.'s counterexample
2019-12-05 10:27:12 -08:00
bd9faae1e7
Add a unit test that repros #2406
2019-12-04 16:45:32 -08:00
46d10dc7dc
Fix "null passed as argument declared not null"
...
Fix several such reports from ubsan
E.g.
/Users/anoyes/workspace/foundationdb/flow/Arena.h:794:16: runtime error: null pointer passed as argument 1, which is declared to never be null
2019-12-03 14:46:53 -08:00
746b357b7f
fix: simulation should not allow connections to dead processes
2019-11-21 20:36:40 -08:00
27cb299d84
simulation can sometimes randomly hang or throw connection_failed, instead of always doing one or the other
2019-11-21 16:24:18 -08:00
067dc55bfb
fix: making _conn a state variable was keeping connections open that should be closed
2019-11-21 16:08:32 -08:00
569c6d4476
throws of connection_failed() from net()->connect did not result in clients marking a connection as failed in the failure monitor
2019-11-21 13:08:59 -08:00
2727b91c46
simulation tests network connections failing due to errors instead of just hanging
2019-11-21 12:33:07 -08:00
57fdbbf975
fix: in simulation dead connections need to stop receiving traffic after 1 second
2019-11-15 10:16:44 -08:00
aad9fa3baa
Don't check for too many connections closed on client connections
2019-11-13 13:00:43 -08:00
Evan Tschannen