Bulk allocate objects for nmslib index creation #773
Conversation
jmazanec15
added
Enhancements
Codecov Report
📣 This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more @@ Coverage Diff @@
## main #773 +/- ##
=========================================
Coverage 85.14% 85.14%
Complexity 1079 1079
=========================================
Files 151 151
Lines 4370 4370
Branches 390 390
=========================================
Hits 3721 3721
Misses 472 472
Partials 177 177 Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
| @@ -66,7 +66,7 @@ target_include_directories(${TARGET_LIB_COMMON} PRIVATE ${CMAKE_CURRENT_SOURCE_D | |||
| set_target_properties(${TARGET_LIB_COMMON} PROPERTIES SUFFIX ${LIB_EXT}) | |||
| set_target_properties(${TARGET_LIB_COMMON} PROPERTIES POSITION_INDEPENDENT_CODE ON) | |||
|
|
|||
| if (WIN32) | |||
| if (NOT "${WIN32}" STREQUAL "") | |||
There was a problem hiding this comment.
is if (WIN32) and if (NOT "${WIN32}" STREQUAL "") are same?
There was a problem hiding this comment.
WIN32 is not a variable it is just the string "WIN32". "${WIN32}" is a variable.
Signed-off-by: John Mazanec <jmazane@amazon.com>
For nmslib, we need to allocate objects that wrap vectors with metadata. This commit updates the objects to be allocated in one buffer as opposed to allocating objects individually. This was shown to prevent memory fragmentation. Signed-off-by: John Mazanec <jmazane@amazon.com>
Signed-off-by: John Mazanec <jmazane@amazon.com>
|
Failure on windows related to: opensearch-project/OpenSearch#7080. Please review |
|
Let's make sure that we run the perf tests to see how much gain we are getting. |
For nmslib, we need to allocate objects that wrap vectors with metadata. This commit updates the objects to be allocated in one buffer as opposed to allocating objects individually. This was shown to prevent memory fragmentation. Signed-off-by: John Mazanec <jmazane@amazon.com> (cherry picked from commit ef44fca)
Description
For nmslib, we need to allocate objects that wrap vectors with metadata. This PR updates the objects to be allocated in one buffer as opposed to allocating objects individually. This was shown to prevent memory fragmentation.
For this change, I ran the same experiments as were run for #772 and they showed significant improvements in the RSS of the process after the indexing workload was run.
Specifically, the change in RSS decreases by about 78% with this change in the experiment above.
In addition to this, fix bug in CMakeLists.txt file preventing unit tests from being created.
Issues Resolved
#772
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.