Skip to content

MDEV-39858: Reloading COSINE metric index from disk degrades search r… #5184

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

Open
shabbann wants to merge 1 commit into
base: 11.8
Choose a base branch
from
+2 −0
Open

MDEV-39858: Reloading COSINE metric index from disk degrades search r… #5184

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
2 changes: 2 additions & 0 deletions sql/vector_mhnsw.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -883,6 +883,8 @@ int FVectorNode::load_from_record(TABLE *graph)
FVector *vec_ptr= FVector::align_ptr(tref() + tref_len());
memcpy(vec_ptr->data(), v->ptr(), v->length());
vec_ptr->postprocess(ctx->vec_len);
if (ctx->metric == COSINE)
vec_ptr->abs2= 0.5f;
Comment on lines +886 to +887
Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot Jun 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

Calling vec_ptr->postprocess(ctx->vec_len) on line 885 dynamically recomputes abs2 using floating-point math (including an expensive dot product over the vector dimensions). Since this calculated value is immediately overwritten with 0.5f for the COSINE metric, the entire computation in postprocess is redundant and wasted.\n\nThis can cause a significant performance bottleneck when reloading large, high-dimensional indexes from disk.\n\nIf postprocess only computes abs2, consider skipping it entirely for the COSINE metric:\n\ncpp\n if (ctx->metric == COSINE)\n vec_ptr->abs2= 0.5f;\n else\n vec_ptr->postprocess(ctx->vec_len);\n


longlong layer= graph->field[FIELD_LAYER]->val_int();
if (layer > 100) // 10e30 nodes at M=2, more at larger M's
Expand Down