Since memory is now limited with RSS size, add RSS size in status json for
reporting. Also change how available_bytes is calculated from:
(available + virtual memory) * process_limit / machine_limit
to:
(available memory) * process_limit / machine_limit
* Fix a heap-use-after-free in a unit test
The data passed to IAsyncFile::write must remain valid until the future
is ready.
* Use holdWhile instead of a new state variable
* Add logic for DDSketch in mako
* Return double from percentile() and fix crash in deserialize()
* make sure to serialize and print result from mergeSketchReport()
* clean up comments
* move ddsketch into its own file
* remove LatencySampleBin and add DDSketch to ThreadStatistics
* Update DDSketch implementation
* remove assertions that cause circular references
* add DDSketchMako as a subsclass from DDSketch
* Merge branch 'ddsketch_mako' of github.com:sfc-gh-khoxha/foundationdb into ddsketch_mako
* Revert "Merge branch 'ddsketch_mako' of github.com:sfc-gh-khoxha/foundationdb into ddsketch_mako"
This reverts commit cc29a68aef.
* add ddsketch mako class and rename export flag
* remove redundant decimal roundings
* print max/min/avg from ddsketch
* remove latency sample bin completly
* Make ThreadStatistics dump latency to a file and read from file in printReport()
* make sure to add latency data from file to final stats
* change mergeSketchReport to use new ThreadStatistics serialization (1)
* use C-style string arrays in Arguments instead of std::string
* remove unused header
* only serialize non-empty sketches
* fix CentOS build error
* Update report file count properly
* avoid deserializing empty sketches
* fix segmentation fault when getting file name for export_sketch_path
* make sure to properly add file to report_files list
* fix printing bugs when running in report mode
* fix incorrect insertion of report files
* don't use range based loop for char array
* don't reset args.num_report_files
* Update the usage info for new options
* switch to using std::vector for sketches instead of std::array
* make sure to use true/false instead of 1/0 for booleans
* remove op_name if not being used
* remove fp code in dumpThreadSamples
* replace lambda with function in printReport
* merge and print stats in seperate functions
* make sure to exit after printing report
* address review feedback
* make defaultMin, defaultMax static and move setBucketSize to protected
* switch to reverse iterators when moving backwards along bucket array
* Add simulation test for 1 data hall + 1 machine failure case.
* Disable BUGGIFY for DEGRADED_RESET_INTERVAL.
A simulation test discovered a situation where machines attempting to connect
to a dead coordinator (with a well-known endpoint) were getting themselves
marked degraded. This flapping of the degraded state prevented recovery from
completing, as it started over any time it noticed that tlogs on degraded
hosts could be relocated to non-degraded ones.
bin/fdbserver -r simulation -f tests/rare/CycleWithDeadHall.toml -b on -s 276841956
Description
Major changes proposed include:
1. Update EncryptKeyServer APIs to be tenant aware.
2. Update KmsConnector APIs to be tenant aware
Client of above APIs such as: CP, SS and BlobWorker need to supply
encryption domain info that includes: tenantId and tenantName
Testing
1. Update EncryptKeyProxyTest
2. Update RESTKmsConnectorTest
3. Update SimKmsConnectorTest
* Add JWT support to TokenSign
* Encapsulate OpenSSL public/private key type
Type-safe passing around of keys without having to DER/PEM-serialize
(OpenSSL doesn't have distinct types for public and private key)
* Apply Clang format
* Add verify benchmark for JWT and FlatBuffers token
* Unit test base64url::{encode, decode}
* Make all payload fields optional
Let user code validate non-signature fields
* Make all payload fields optional
Completely defer field check to user code
* Move rapidjson from fdbclient to contrib
* Make fdbrpc's rapidjson linkage private
Currently only sources include them.
* Modify rapidjson path in apiversioner.py
* Algorithm::Unknown > Algorithm::UNKNOWN
also in order to continue tracing the pending network thread activity.
Poll event throttler only in the network thread in order to avoid a race condition.
Jingyu Zhou