krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-06 03:18:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update qdrant-landing/content/blog/qdrant-1.14.x.md

Browse Source 
Co-authored-by: Tim Visée <tim@visee.me>
This commit is contained in:
David Myriel
2025-04-14 20:50:35 +02:00
committed by GitHub
co-authored by Tim Visée
parent 51fefdef1c
commit 4210f176f2
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/qdrant-1.14.x.md
+6 -6
View File
@@ -200,12 +200,12 @@ We ran the same test of large queries for the following configurations:
| Configuration | Segments | Shards | Indexing Threshold | Before | After | Improvement | | Configuration | Segments | Shards | Indexing Threshold | Before | After | Improvement |
|--------------|----------|---------|-------------------|---------|--------|-------------| |--------------|----------|---------|-------------------|---------|--------|-------------|
| Single Segment | 1 | 1 | - | 10.5s | 4.5s | 57% | | Single Segment | 1 | 1 | 20k | 10.5s | 4.5s | 57% |
| Multi Segment | 10 | 1 | - | 5.5s | 5.1s | 7% | | Multi Segment | 10 | 1 | 20k | 5.5s | 5.1s | 7% |
| Single Segment, Multi Shard | 1 | 4 | - | 5.2s | 4.6s | 12% | | Single Segment, Multi Shard | 1 | 4 | 20k | 5.2s | 4.6s | 12% |
| Multi Everything | 10 | 4 | 1000 | 5.1s | 4.5s | 12% | | Multi Everything | 10 | 4 | 1k | 5.1s | 4.5s | 12% |
| High Shard, Single Segment | 1 | 16 | 1000 | 5.2s | 3.7s | 29% | | High Shard, Single Segment | 1 | 16 | 1k | 5.2s | 3.7s | 29% |
| High Shard, Multi Segment | 10 | 16 | 1000 | 2.5s | 1.7s | 32% | | High Shard, Multi Segment | 10 | 16 | 1k | 2.5s | 1.7s | 32% |
As you can see, the improvement is **most significant (57%) in single-segment configurations** where parallelization was previously limited. Even in already-optimized multi-shard setups, we still see good gains of 12-32%. As you can see, the improvement is **most significant (57%) in single-segment configurations** where parallelization was previously limited. Even in already-optimized multi-shard setups, we still see good gains of 12-32%.