Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adjust estimated replay operation cost for more tensor attribute vect… #33387

Merged
merged 1 commit into from
Feb 21, 2025
Merged

Adjust estimated replay operation cost for more tensor attribute vect… #33387

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Adjust estimated replay operation cost for more tensor attribute vect… 
…ors.
  • Loading branch information
@toregge
toregge committed Feb 21, 2025
commit 92d03e1b7a43cdf7f1b567a1854bc3f15f80352e
3 changes: 1 addition & 2 deletions searchcore/src/vespa/searchcore/proton/attribute/flushableattribute.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,8 +173,7 @@ FlushableAttribute::FlushableAttribute(AttributeVectorSP attr,
{
_lastStats.setPathElementsToLog(8);
auto &config = attr->getConfig();
if (config.basicType() == search::attribute::BasicType::Type::TENSOR &&
config.tensorType().is_dense() && config.hnsw_index_params().has_value())
if (config.basicType() == search::attribute::BasicType::Type::TENSOR && config.hnsw_index_params().has_value())
{
_replay_operation_cost = 400.0; // replaying operations to hnsw index is 400 times more expensive than reading from tls
}
Expand Down