IMPALA-15585: Detect fast CLOCK_MONOTONIC on ARM

In IMPALA-2407, Impala added logic to detect whether clock_gettime's
CLOCK_MONOTONIC has a fast implementation. At the time, some clock
implementations like Xen were very slow. To avoid the performance
penalty, it uses CLOCK_MONOTONIC_COARSE when the clock source
is not known to be fast.

ARM has a fast clock source for CLOCK_MONOTONIC, but it is not being
detected properly because it has a different name than x86_64.
ARM currently uses CLOCK_MONOTONIC_COARSE, which makes profile
time counters considerably less useful.

This adds detection for the ARM fast time counter (arch_sys_counter)
in addition to the x86_64 version (tsc).

Testing:
 - Ran a perf-AB-test on ARM and verified that the profiles have
   more exact time values (without performance regression)

Change-Id: I6512e5dbbb11c4816716deccce3c0e212f73cf33
Reviewed-on: http://gerrit.cloudera.org:8080/25149
Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
Reviewed-by: Yida Wu <wydbaggio000@gmail.com>
Reviewed-by: Jason Fehr <jfehr@cloudera.com>
1 file changed
tree: 3e5acbca41503ae0081215b85ae4ef84cbd018a7
  1. .agents/
  2. .devcontainer/
  3. .devcontainer-build/
  4. .vscode-defaults/
  5. be/
  6. bin/
  7. cmake_modules/
  8. common/
  9. docker/
  10. docs/
  11. fe/
  12. helm/
  13. infra/
  14. java/
  15. lib/
  16. operator/
  17. package/
  18. security/
  19. shell/
  20. ssh_keys/
  21. testdata/
  22. tests/
  23. www/
  24. .asf.yaml
  25. .clang-format
  26. .clang-tidy
  27. .gitattributes
  28. .gitignore
  29. .isort.cfg
  30. AGENTS.md
  31. buildall.sh
  32. CMakeLists.txt
  33. EXPORT_CONTROL.md
  34. LICENSE.txt
  35. LOGS.md
  36. NOTICE.txt
  37. README-build.md
  38. README.md
  39. SECURITY.md
  40. setup.cfg
README.md

Welcome to Impala

Lightning-fast, distributed SQL queries for petabytes of data stored in open data and table formats.

Impala is a modern, massively-distributed, massively-parallel, C++ query engine that lets you analyze, transform and combine data from a variety of data sources:

More about Impala

The fastest way to try out Impala is a quickstart Docker container. You can try out running queries and processing data sets in Impala on a single machine without installing dependencies. It can automatically load test data sets into Apache Kudu and Apache Parquet formats and you can start playing around with Apache Impala SQL within minutes.

To learn more about Impala as a user or administrator, or to try Impala, please visit the Impala homepage. Detailed documentation for administrators and users is available at Apache Impala documentation.

If you are interested in contributing to Impala as a developer, or learning more about Impala's internals and architecture, visit the Impala wiki.

Supported Platforms

Impala only supports Linux at the moment. Impala supports x86_64 and arm64 (as of Impala 4.4). Impala Requirements contains more detailed information on the minimum CPU requirements.

Supported OS Distributions

Impala runs on Linux systems only. The supported distros are

  • Ubuntu 20.04/22.04/24.04
  • Rocky/RHEL 8/9/10

Other systems, e.g. SLES15/16, may also be supported but are not tested by the community.

Export Control Notice

This distribution uses cryptographic software and may be subject to export controls. Please refer to EXPORT_CONTROL.md for more information.

Build Instructions

See Impala's developer documentation to get started.

Detailed build notes has some detailed information on the project layout and build.