Alex Miller
@alexmillerdb.bsky.social
Database Papers as a Service
[PVLDB] Enhancing Transaction Processing through Indirection Skipping
www.vldb.org/pvldb/v...
Whereas VMCache improve pointer swizzing's complexity by removing the swizzling, this work points out that page and frame hints are highly effective, and okay if they're wrong.
www.vldb.org/pvldb/v...
Whereas VMCache improve pointer swizzing's complexity by removing the swizzling, this work points out that page and frame hints are highly effective, and okay if they're wrong.
October 17, 2025 at 4:02 AM
[PVLDB] Enhancing Transaction Processing through Indirection Skipping
www.vldb.org/pvldb/v...
Whereas VMCache improve pointer swizzing's complexity by removing the swizzling, this work points out that page and frame hints are highly effective, and okay if they're wrong.
www.vldb.org/pvldb/v...
Whereas VMCache improve pointer swizzing's complexity by removing the swizzling, this work points out that page and frame hints are highly effective, and okay if they're wrong.
[ASPLOS'25] Fusion: An Analytics Object Store Optimized for Query
Pushdown
www.cs.princeton.edu...
Tightly integrating an Iceberg catalog with an object store means that one could make file-format aware erasure coding decisions, to permit pushing down filters and aggregations.
Pushdown
www.cs.princeton.edu...
Tightly integrating an Iceberg catalog with an object store means that one could make file-format aware erasure coding decisions, to permit pushing down filters and aggregations.
September 28, 2025 at 11:42 PM
[ASPLOS'25] Fusion: An Analytics Object Store Optimized for Query
Pushdown
www.cs.princeton.edu...
Tightly integrating an Iceberg catalog with an object store means that one could make file-format aware erasure coding decisions, to permit pushing down filters and aggregations.
Pushdown
www.cs.princeton.edu...
Tightly integrating an Iceberg catalog with an object store means that one could make file-format aware erasure coding decisions, to permit pushing down filters and aggregations.
[VLDB] Towards Principled, Practical Document Database Design
www.vldb.org/pvldb/v...
If you've ever wished that there was a document database equivalent for relational databases' 3NF-style schema design guidance, then this is the paper for you.
www.vldb.org/pvldb/v...
If you've ever wished that there was a document database equivalent for relational databases' 3NF-style schema design guidance, then this is the paper for you.
September 23, 2025 at 5:23 PM
[VLDB] Towards Principled, Practical Document Database Design
www.vldb.org/pvldb/v...
If you've ever wished that there was a document database equivalent for relational databases' 3NF-style schema design guidance, then this is the paper for you.
www.vldb.org/pvldb/v...
If you've ever wished that there was a document database equivalent for relational databases' 3NF-style schema design guidance, then this is the paper for you.
Even as a disliker of YouTube videos as a way to learn things, I found www.youtube.com/watch?v=-XmJ... easier to understand than the paper www.cs.ox.ac.uk/dan.olteanu/... for factorized database work
Extending SQL to Return a Subdatabase dl.acm.org/doi/pdf/10.1... also seems related?
Extending SQL to Return a Subdatabase dl.acm.org/doi/pdf/10.1... also seems related?
September 21, 2025 at 4:56 PM
Even as a disliker of YouTube videos as a way to learn things, I found www.youtube.com/watch?v=-XmJ... easier to understand than the paper www.cs.ox.ac.uk/dan.olteanu/... for factorized database work
Extending SQL to Return a Subdatabase dl.acm.org/doi/pdf/10.1... also seems related?
Extending SQL to Return a Subdatabase dl.acm.org/doi/pdf/10.1... also seems related?
[arXiv] On the Theoretical Limitations of Embedding-Based Retrieval
arxiv.org/abs/2508.2...
It's impossible to retrieve all combinations of pairs of documents post-embedding. Thus, there's usecases that vector search won't do well at. Conversely, BM25 excels in these cases.
arxiv.org/abs/2508.2...
It's impossible to retrieve all combinations of pairs of documents post-embedding. Thus, there's usecases that vector search won't do well at. Conversely, BM25 excels in these cases.
September 21, 2025 at 3:38 AM
[arXiv] On the Theoretical Limitations of Embedding-Based Retrieval
arxiv.org/abs/2508.2...
It's impossible to retrieve all combinations of pairs of documents post-embedding. Thus, there's usecases that vector search won't do well at. Conversely, BM25 excels in these cases.
arxiv.org/abs/2508.2...
It's impossible to retrieve all combinations of pairs of documents post-embedding. Thus, there's usecases that vector search won't do well at. Conversely, BM25 excels in these cases.
[VLDB] NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
www.vldb.org/pvldb/v...
It feels like a follow-on/improvement to ACORN. Also interesting to see HNSW built directly on a graph database working well.
www.vldb.org/pvldb/v...
It feels like a follow-on/improvement to ACORN. Also interesting to see HNSW built directly on a graph database working well.
September 5, 2025 at 5:11 AM
[VLDB] NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
www.vldb.org/pvldb/v...
It feels like a follow-on/improvement to ACORN. Also interesting to see HNSW built directly on a graph database working well.
www.vldb.org/pvldb/v...
It feels like a follow-on/improvement to ACORN. Also interesting to see HNSW built directly on a graph database working well.
Philz funding round vs post-money valuation history isn’t looking too great
August 3, 2025 at 7:17 PM
Philz funding round vs post-money valuation history isn’t looking too great
Not only did GaussDB run TPC-C wrong (without stating so!), they gave cockroach a capitalized R.
> We compared the end-to-end performance of GaussDB with System-X and CockRoachDB on TPC-C with 10,000 warehouses.
> We compared the end-to-end performance of GaussDB with System-X and CockRoachDB on TPC-C with 10,000 warehouses.
August 3, 2025 at 5:48 AM
Not only did GaussDB run TPC-C wrong (without stating so!), they gave cockroach a capitalized R.
> We compared the end-to-end performance of GaussDB with System-X and CockRoachDB on TPC-C with 10,000 warehouses.
> We compared the end-to-end performance of GaussDB with System-X and CockRoachDB on TPC-C with 10,000 warehouses.
In line with previous research [16, 29], we set the think/keying time in TPC-C to zero.
July 30, 2025 at 5:42 AM
In line with previous research [16, 29], we set the think/keying time in TPC-C to zero.
I'm getting tired of these new paper announcements on LinkedIn which are like
June 24, 2025 at 11:08 PM
I'm getting tired of these new paper announcements on LinkedIn which are like
[arXiv] TreeTracker Join: Simple, Optimal, Fast
arxiv.org/abs/2403.0...
TreeTracker gives a very simple breakdown of what the core differences are between a naive binary join and an optimal multi-way join.
arxiv.org/abs/2403.0...
TreeTracker gives a very simple breakdown of what the core differences are between a naive binary join and an optimal multi-way join.
June 20, 2025 at 2:15 AM
[arXiv] TreeTracker Join: Simple, Optimal, Fast
arxiv.org/abs/2403.0...
TreeTracker gives a very simple breakdown of what the core differences are between a naive binary join and an optimal multi-way join.
arxiv.org/abs/2403.0...
TreeTracker gives a very simple breakdown of what the core differences are between a naive binary join and an optimal multi-way join.
[EDBT'22] Integrating the Orca Optimizer into MySQL
openproceedings.org/...
Huawei Taurus folk plugged Orca into MySQL to get a better query optimizer for OLAP queries in MySQL.
openproceedings.org/...
Huawei Taurus folk plugged Orca into MySQL to get a better query optimizer for OLAP queries in MySQL.
June 19, 2025 at 6:48 PM
[EDBT'22] Integrating the Orca Optimizer into MySQL
openproceedings.org/...
Huawei Taurus folk plugged Orca into MySQL to get a better query optimizer for OLAP queries in MySQL.
openproceedings.org/...
Huawei Taurus folk plugged Orca into MySQL to get a better query optimizer for OLAP queries in MySQL.
Wisdom on btree prefix compression from someone who has implemented and benchmarked it. From lobste.rs/s/za4cxl/b...
June 17, 2025 at 8:28 PM
Wisdom on btree prefix compression from someone who has implemented and benchmarked it. From lobste.rs/s/za4cxl/b...
I really appreciate the authors pursuing and accepting ugly solutions because they're what's needed to achieve the required result practically.
June 10, 2025 at 11:39 PM
I really appreciate the authors pursuing and accepting ugly solutions because they're what's needed to achieve the required result practically.
[arXiv] Fast Userspace Networking for the Rest of Us
arxiv.org/abs/2502.0...
"if it doesn't work on the cloud does it even matter?" but applied to kernel bypass networking.
arxiv.org/abs/2502.0...
"if it doesn't work on the cloud does it even matter?" but applied to kernel bypass networking.
June 10, 2025 at 11:39 PM
[arXiv] Fast Userspace Networking for the Rest of Us
arxiv.org/abs/2502.0...
"if it doesn't work on the cloud does it even matter?" but applied to kernel bypass networking.
arxiv.org/abs/2502.0...
"if it doesn't work on the cloud does it even matter?" but applied to kernel bypass networking.
Something about how the title is done makes it render like an eldritch horror?
May 28, 2025 at 6:42 PM
Something about how the title is done makes it render like an eldritch horror?
XFS is doing it mostly because they can have unaligned extents.
You’re also welcome to join eatonphil.com/discord.html
You’re also welcome to join eatonphil.com/discord.html
May 14, 2025 at 8:16 PM
XFS is doing it mostly because they can have unaligned extents.
You’re also welcome to join eatonphil.com/discord.html
You’re also welcome to join eatonphil.com/discord.html
[arXiv] Compressing integer lists with Contextual Arithmetic Trits
arxiv.org/abs/2209.0...
Which was an interesting skim, partly just because I've never seen trits (bit in base 3) applied to solve a problem effectively before.
arxiv.org/abs/2209.0...
Which was an interesting skim, partly just because I've never seen trits (bit in base 3) applied to solve a problem effectively before.
May 8, 2025 at 8:12 PM
[arXiv] Compressing integer lists with Contextual Arithmetic Trits
arxiv.org/abs/2209.0...
Which was an interesting skim, partly just because I've never seen trits (bit in base 3) applied to solve a problem effectively before.
arxiv.org/abs/2209.0...
Which was an interesting skim, partly just because I've never seen trits (bit in base 3) applied to solve a problem effectively before.
[arXiv] BMTree: Designing, Learning, and Updating Piecewise Space-Filling Curves for Multi-Dimensional Data Indexing
arxiv.org/abs/2505.0...
I've seen a lot of morton/hilbert curves before, but learning a space filling curve and adapting it to the data distribution is new to me.
arxiv.org/abs/2505.0...
I've seen a lot of morton/hilbert curves before, but learning a space filling curve and adapting it to the data distribution is new to me.
May 8, 2025 at 6:21 AM
[arXiv] BMTree: Designing, Learning, and Updating Piecewise Space-Filling Curves for Multi-Dimensional Data Indexing
arxiv.org/abs/2505.0...
I've seen a lot of morton/hilbert curves before, but learning a space filling curve and adapting it to the data distribution is new to me.
arxiv.org/abs/2505.0...
I've seen a lot of morton/hilbert curves before, but learning a space filling curve and adapting it to the data distribution is new to me.
[arXiv] Efficient Role-based Access Control for Vector
Databases via Dynamic Partitioning
arxiv.org/abs/2505.0...
Which fuses RBAC into the vector partitioning scheme, so that it's not just a post-filter on results.
Databases via Dynamic Partitioning
arxiv.org/abs/2505.0...
Which fuses RBAC into the vector partitioning scheme, so that it's not just a post-filter on results.
May 7, 2025 at 7:32 PM
[arXiv] Efficient Role-based Access Control for Vector
Databases via Dynamic Partitioning
arxiv.org/abs/2505.0...
Which fuses RBAC into the vector partitioning scheme, so that it's not just a post-filter on results.
Databases via Dynamic Partitioning
arxiv.org/abs/2505.0...
Which fuses RBAC into the vector partitioning scheme, so that it's not just a post-filter on results.
Dynamic symbols required by AlloyDB:
April 10, 2025 at 1:36 AM
Dynamic symbols required by AlloyDB: