c3299b8ebe
if tls cannot be initialized, throw an error from createDatabase
2020-02-26 18:53:06 -08:00
65fbe0d0bc
revert AcceptSocket priority change because of bad performance results
2020-02-21 19:22:14 -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
7d54acf4ca
removed an unnecessary yield
2020-02-20 14:41:49 -08:00
69b5a1fbe3
more priority improvements
2020-02-20 10:11:43 -08:00
fd8a58b035
re-added support for the TLS_DISABLED flag
2020-02-19 18:37:47 -08:00
761da5a059
code cleanup
2020-02-19 17:59:45 -08:00
88d36af9c7
Fix --tls_password and add better error logging
...
This refactors all tls settings into a TLSParams object so that we can
set the password before loading any certificates.
It turns out that the FDBLibTLS code did really nice things with error
logging, but I just didn't understand openssl enough before to realize
what pieces I should be copying.
2020-02-19 00:57:05 -08:00
693e469003
Changed the handshake lock to a BoundedFlowLock, which will enforce that old handshakes complete before starting to initiate new handshakes
2020-02-14 16:49:52 -08:00
dcbce3593e
fixed TLS in simulation
2020-02-10 14:00:21 -08:00
e390dbd36c
Add a non-FDBLibTLS verify peers framework to new TLS impl
2020-02-06 21:06:52 -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
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
e65760eb46
Merge pull request #2536 from etschannen/feature-commit-latency
...
Improved commit latency in large clusters
2020-01-13 19:12:02 -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
2e20c12200
Merge pull request #2475 from ajbeamon/priority-busy-fixes
...
Fix PriorityBusy calculation and add PriorityMaxBusy
2020-01-10 12:47:17 -08:00
d8c3c2fda4
Improved prioritization of commit path on the proxies
2019-12-18 16:56:35 -08:00
a093021855
Fix priority time calculation. Track max priority busy rather than seconds squared.
2019-12-17 09:14:54 -08:00
5a6bc2aa71
increase the priority of cluster controller recruitment to prefer recruitment over sending serverDBInfo
2019-12-04 16:28:41 -08:00
5f1ef53f62
increase the priority at which the cluster controller registers workers to avoid having a saturated cluster controller recruit a master without all available workers
2019-12-04 16:17:41 -08:00
1e5677b55a
increase the priority of reboot and recruitment requests
2019-11-11 15:17:11 -08:00
fa6e45a852
Separate AsioReactor sleep and react into two different functions. Track slow tasks and time spent in react, track time spent in launch. Don't track react time at priority 0.
2019-08-28 14:35:48 -07:00
da8163fd5a
allow one requests every second to skip there all_alteratives_failed delay, because if a client has a timeout longer than the delay we will never invalidate the key servers cache
2019-08-09 13:03:40 -07:00
370ba8b841
Remove --object-serializer flag from executables
2019-08-06 09:25:40 -07:00
98c3b24036
Merge pull request #1869 from alexmiller-apple/sharded-txs-performance
...
Raise the priority of TLogRejoin above TLogPeekReply
2019-07-26 13:30:13 -07:00
df7f0cffa1
Raise the priority of TLogRejoin above the default work priority.
...
With sharded txs tags, the master now receives data from transaction
logs at an order of magnitude higher rate. This is the intentional
desires result of sharding the txs tag. With a sufficient number of
TLogs, the master will saturate its CPU time handling the peek
responses.
Performance tests revealed some unstable oddities in how long a recovery
would take, which was eventually root caused to a priority inversion
between TLogRejoin requests and TLog peek replies.
Once peek replies saturate the CPU, the master would proceed to ignore
further TLogRejoin messages. TLogRejoin is what marks a TLog as
available to the failure monitor, which is also what decides between a
ServerPeekCursor and a MergePeekCursor for a SetPeekCursor. Ignoring
TLogRejoins meant that the sharded txs locality tags for those servers
would be merge peeked over all TLogs. This is much less efficient than
just peeking one copy of data from the one preferred server.
Depending on the race between TLogPeek replies saturating the CPU and
TLogRejoin requests being submitted, a variable number of tags would be
affected, and thus the performance test would have some variance in its
results.
2019-07-19 16:55:04 -07:00
c3a8ae4752
Merge pull request #1791 from fzhjon/fetch-keys-requests-priority
...
Introduce priority to fetchKeys requests from data distribution
2019-07-19 14:54:51 -07:00
6a4a129cf5
fixed silly boost visitor bug
2019-07-16 15:10:55 -07:00
b18666d942
statically link libstdc++ on Linux and remove std::variant
...
this will hopefully fix #1610
2019-07-16 14:53:16 -07:00
f707d186fe
added new priority for fetchkeys requests and adjusted ddmetrics workload to run parallel with mako
2019-07-11 09:56:58 -07:00
69d7c4f79c
Merge branch 'master' into track-run-loop-busyness
...
# Conflicts:
# documentation/sphinx/source/release-notes.rst
# flow/Net2.actor.cpp
# flow/network.h
2019-07-09 18:39:23 -07:00
888f4f92e0
Fix errors and TaskPriority more priorities.
2019-07-03 21:03:58 -07:00
ea6898144d
Merge remote-tracking branch 'upstream/master' into flowlock-api
2019-07-03 20:44:15 -07:00
5ea2e69016
Remove a fdbprc header from flow library
...
Flow should be an independent library.
2019-07-03 19:56:38 -07:00
3fb0999e10
revert storage server priority changes
2019-07-02 16:54:47 -07:00
8e1ab6e7db
Merge remote-tracking branch 'upstream/master' into flowlock-api
2019-06-28 17:32:54 -07:00
4cef1d3937
Experimental change of storage write priority
2019-06-28 16:54:22 -07:00
7f23814841
Track run loop busyness and report it in status.
2019-06-26 14:03:02 -07:00
bf883d7055
Merge remote-tracking branch 'upstream/master' into flowlock-api
2019-06-25 14:26:50 -07:00
0fe6edc254
Merge pull request #1678 from mpilman/features/external-workload
...
Features/external workload
2019-06-25 13:53:19 -07:00
7a500cd37f
A giant translation of TaskFooPriority -> TaskPriority::Foo
...
This is so that APIs that take priorities don't take ints, which are
common and easy to accidentally pass the wrong thing.
2019-06-25 02:47:35 -07:00
2eff2b7e21
First simple test is working (but very buggy)
2019-06-19 13:03:41 -07:00
68ce9a5e75
ProtocolVersion type - second try
2019-06-18 17:55:27 -07:00
a8e408e268
run clang-format on changes
2019-06-10 14:10:24 -07:00
6b4d30c3ae
failmon: Identify client vs server when starting failure monitoring client
2019-06-09 00:43:12 -07:00
Evan Tschannen