Summary: We rely on a basic evaluation logic: when using an expression `A || B`, the `B` part will only get evaluated when `A` fails. Therefore the task creation tool is guaranteed to run if previous build/test step failed. To indicate the correct return value to shell, the task creation tool will call `exit(1)` which will cause Sandcastle to mark it as a failure.
Test Plan:
- Land the changes.
- Trigger a RocksDB contrun - observe the results.
- Look at the results from the nightly runs and fix issues as necessary.
Current testing so far has been in isolation for various components.
Reviewers: andrewkr, IslamAbdelRahman, sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60909
Summary:
Removing moreutils from sandcastle and adding gnu parallel.
Then passing in J= nproc command
Test Plan: Testing on sandcastle
Reviewers: sdong, kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D61017
Summary: Increase test timeout to some tests to unblock CI.
Test Plan: watch how it runs.
Reviewers: kradhakrishnan, andrewkr, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: IslamAbdelRahman, leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D61263
Summary:
Tsan crash white-box test was disabled because it never ends. Re-enable it with reduced killing odds.
Add a parameter in crash test script to allow we pass it through an environment variable.
Test Plan: Run it manually.
Reviewers: IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D61053
Summary: RocksDB behavior is slightly different between data on tmpfs and normal file systems. Add a test case to run RocksDB on normal file system.
Test Plan: See the tests launched by Phabricator
Reviewers: kradhakrishnan, IslamAbdelRahman, gunnarku
Reviewed By: gunnarku
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60963
Summary: I tried on my host and TSAN black box test runs well. I didn't see any problem with white box crash test too but it chance of hitting crash point is too low that it may run almost forever. First re-enable black box crash test to unblock the job.
Test Plan: Run it locally.
Reviewers: kradhakrishnan, andrewkr, IslamAbdelRahman
Reviewed By: IslamAbdelRahman
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60951
Summary: As Title.
Test Plan: See how the diff works.
Reviewers: kradhakrishnan, andrewkr, gunnarku
Reviewed By: gunnarku
Subscribers: leveldb, andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60933
Summary: To make sure that we'll have additional verification for release builds, define a new category and add `make release` to per-diff/post-commit tests. This should in theory prevent the release MyRocks integration builds breaks from happening.
Test Plan:
- `[p]arc diff --preview`
- Observe the execution in Sandcastle and make sure that release build and tests are executed.
Reviewers: sdong
Reviewed By: sdong
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D60441
Summary: Have sandcastle run unit test in lite mode for every diff.
Test Plan: seems sandcastle picked up changes here and running lite_test for this diff.
Reviewers: kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D57741
Summary:
Added a python script to parse combined stdout/stderr of legocastle
steps. Previously we just matched words like 'Failure', which didn't work since
even our test names matched that pattern.
I went through all the legocastle steps to come up with strict failure regexes
for the common failure cases. There is also some more complex logic to present
gtest failures, since the test name and failure message are not on the same
line.
There will definitely be error cases that don't match any of these patterns, so
we can iterate on it over time.
Test Plan:
no end-to-end test. I ran the legocastle steps locally and piped to
my script, then verified output, e.g.,
$ set -o pipefail && TEST_TMPDIR=/dev/shm/rocksdb COMPILE_WITH_ASAN=1 OPT=-g make J=1 asan_check |& /usr/facebook/ops/scripts/asan_symbolize.py -d |& python build_tools/error_filter.py asan
==2058029==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x60200000a414 at pc 0x4c12f6 bp 0x7ffcfb7a0520 sp 0x7ffcfb7a0518
Reviewers: kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D56691
Summary:
proxy config tools are not available in sandcastle environment. Hard
coding the proxy information in the job.
Test Plan: Run manually
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D56775
Summary:
Java build is downloading junit when not available. Without the proxy
settings exported that would not work.
Test Plan: Run manually
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D56751
Summary: System was not able to locate javac
Test Plan: Run command manually and observe output
Subscribers: andrewkr, dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D56709
Summary:
Undefined Behavior Sanitizer (ubsan) is //a good thing// which will help us to find sneaky bugs with low cost. Please see http://developerblog.redhat.com/2014/10/16/gcc-undefined-behavior-sanitizer-ubsan/ for more details and official GCC documentation for more context: https://gcc.gnu.org/onlinedocs/gcc/Instrumentation-Options.html.
Changes itself are quite simple and pretty much imitating whatever is implemented for ASan.
Hooking the UBsan validation build to Sandcastle is a separate step and will be dealt as separate diff because code is in internal repository.
Test Plan: Make sure that that there no regressions when it comes to builds and test pass rate.
Reviewers: leveldb, sdong, IslamAbdelRahman, yhchiang
Reviewed By: yhchiang
Subscribers: andrewkr, dhruba
Differential Revision: https://reviews.facebook.net/D56049
Summary: Improving the parser string to make better error report. Currently the
error report fails to capture the assert details. This fix addresses the issue.
Test Plan: None
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: As title. Let's run it for 1 hour.
Test Plan: How can I test legocastle changes?
Reviewers: IslamAbdelRahman, yhchiang, rven, sdong, anthony, kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D49653
Summary: Update rocksdb-lego-determinator to include running make check under ROCKSDB_LITE
Test Plan: will be tested after landing in fbcode
Reviewers: sdong, yhchiang, igor, kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: dhruba
Differential Revision: https://reviews.facebook.net/D49065
Summary: Adding the ability to upload logs and db content to storage after the
completion of the job
Test Plan: Manual run
Reviewers:
CC: leveldb@
Task ID: #8754201
Blame Rev:
Summary: The parser will help parse the output in order to send meaningful
notifications.
Test Plan: Manual testing
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: unity_test will compile db_test with unity.a instead of librocksdb.a. This will test both the compilation and some small amount of runtime.
Test Plan: This is a test :)
Reviewers: kradhakrishnan
Reviewed By: kradhakrishnan
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D48297
Summary: Sandcastle does not raise a task if assignee is specified. Removing the
assignee will force the system to use the oncall.
Test Plan: Manual
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Added following capability
(1) Ability to do configurable reports using args
(2) Support to generating a task on failure
(3) Ability to configure email trigger condition
Test Plan: Manual testing
Reviewers:
CC:leveldb@
Task ID: #6968635
Blame Rev:
Summary: Added email notification for a few jobs and fixed a bug in
no_compression script
Test Plan: Manual test
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Our valgrind testing is buggy and cumbersome in terms of locating the
error. It originates from the fact we accumulate all output for the tests. It is
extremely hard to locate the point of error.
The communication between valgrind and the script is not sturdy. We are
experiencing bugs.
Simplifying to stop on first error.
Test Plan: Run manually
Reviewers: sdong igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: The job errors with log print step. Removing the step and re-enabling
the test case.
Test Plan: Manual test run
Reviewers:
CC: levledb@
Task ID: #6968635
Blame Rev:
Summary: Parallel test CI is failing. Reducing noise by temporarily disabling
the job
Test Plan: Manual
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Long running jobs are blocking the queue due to lack of adequate
machines in the CI
Test Plan: Manual testing
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: The approach to serialize long scripts as string is flawed. Instead
adding args to invoke the long scripts.
Test Plan: Manual test
Reviewers:
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Migrating the long script jobs and the left overs from Jenkin.
Test Plan: Run command manually
Reviewers: sdon igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Command level timeouts are not working. Moving it to step level.
Test Plan: Manual testing sending commands
Reviewers: sdong igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Fixed
- Added timeouts for crash tests. They take around 9hrs.
- Added oncall so we can get notifications for timeout etc.
- Fixed a bug in the valgrind script
- Cosmetic fix
Test Plan: Manual run
Reviewers: sdong igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Fix the issue where compilation error will not result in log file not
found error
Test Plan: None
Reviewers: sdong igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Added more jobs and refactored code express the jobs more cleanly
Test Plan: Manual test
Reviewers: igor sdong
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Dropping parallel compilation since that seen to introduce compilation
errors spuriously
Test Plan: Run the command manually
Reviewers: sdon igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: The email notifications needs to be at command level and the job level.
Adding command level notification.
Test Plan: Run command manually
Reviewers: igor sdong
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Fixed the glitch in Sandcastle and added gcc-4.9 support. Moving the
jobs to 4.9
Test Plan: Manually run the script
Reviewers: sdon igor
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: Added commands to spawn crash, stress, asan, asan_crash, clang CI jobs
Test Plan: Manual test
Reviewers: sdong
CC: leveldb@
Task ID: #6968635
Blame Rev:
Summary: This fuels commands to be executed for different sandcastle jobs. This is a nice way to separate RocksDB specific commands from Sandcastle specific job definition.
Test Plan: None. Will be tested when we add Sandcastle job.
Reviewers: igor, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D45741
