Learned sparse retrieval (LSR) models such as SPLADE have traditionally used BERT-style masked language models as backbone encoders. A natural expectation is that replacing BERT with stronger pretrained encoders should improve retrieval effectiveness. However, we find that under standard SPLADE training recipes, backbones with large MLM-head L2 norms can suffer performance degradation and even training collapse under standard SPLADE training rec... Read more ›
How can cloud providers efficiently supply durable virtual block devices? Remote Direct Memory Access (RDMA) provides a way for servers in a cluster to share chunks of memory, but there still needs to be a protocol that operates on top of RDMA to provide the guarantees expected of a block device. The kernel's RDMA transport library (RTRS) provides a way to send messages via RDMA. I : Reliable Multicast over RTRS (RMR) and Block device over RMR (BRMR). These modules, which I am working on with... Read more ›
In this post, we show you how to use EXPLAIN plans to diagnose and improve query performance in Amazon Aurora DSQL. We introduce a three-layer filter model as a practical framework for understanding where your predicates are evaluated, and walk through the architecture differences that make Aurora DSQL plans unique, the anatomy of an EXPLAIN output, access method selection, and a step-by-step query improvement workflow. Read more ›
The European Commission has a survey requesting feedback regarding EuroQCI, Europe's sky-high investment in "quantum communication infrastructure". Read more ›
Managing data retention policies is one of the most common operational tasks in MySQL. Applications continuously generate transactional, audit, logging, telemetry, and event data. Over time, these tables can grow to billions of rows, causing: Larger backups Longer recovery times Reduced buffer pool efficiency Slower index maintenance Increased storage costs Degraded query performance To address … The post appeared first on <a href=" Read more ›
Vector databases are increasingly used in security sensitive contexts with Retrieval Augmented Generation and organizational AI pipelines; however, their security capabilities remain limited. Specifically, Fine-grained Access Control (FGAC) which is required to ensure that data access adheres to user-specific policies is not fully supported in modern vector databases. Unlike relational databases, vector databases combine structured and unstructu... Read more ›
Linus has . "So it's only Sunday morning back home, but it's Sunday afternoon where I am right now, so I'm doing the 7.1 release at the regular time - just not in the regular timezone." Significant changes in 7.1 include the removal of support for some old 486-based architectures, some clone() flags making process management easier, for io_uring, zero-copy-I/O support for the in sched_ext, more , a , and much more. See the LWN merge-window summaries (<a href=" <a href=" for details. Read more ›
This is Part 1 of a two-part series covering the key features in PostgreSQL 18. In this post, we focus on performance enhancements: skip scan optimization for multicolumn indexes, enhanced EXPLAIN output, automatic removal of unnecessary self-joins, and several vacuum and autovacuum improvements that help keep your database running efficiently. Read more ›
Streaming Retrieval-Augmented Generation (Streaming RAG) reduces user-perceived latency by issuing tool queries in parallel with ongoing user input, before the utterance is complete. Reported gains are aggregate, yet the mechanism's benefit is fundamentally query-intrinsic: speculation can only help when the correct tool query becomes determinable before the user stops speaking or typing. We isolate and measure this property -- tool-intent sta... Read more ›
Security updates have been issued by AlmaLinux (.NET 9.0), Debian (apache2, chromium, jpeg-xl, librabbitmq, and openssl), Fedora (apptainer, bind9-next, chezmoi, chromium, collectd, composer, dnsdist, gh, python-django5, python-python-multipart, varnish, varnish-modules, vmod-querystring, vmod-uuid, weasyprint, and xorg-x11-server-Xwayland), Mageia (cups, expat, libpng, libssh, memcached, nghttp2, openimageio, packages, proftpd, and radare2), Oracle (.NET 10.0, .NET 8.0, .NET 9.0, and firefox... Read more ›
Remote and disaggregated memory tiers expand the effective memory capacity of analytical database engines, but they also reshape the cost structure of out-of-memory query processing. When an operator spills beyond local DRAM, moving pages to remote memory incurs both data-transfer time and a fixed round-trip latency per transfer. Classical operator analyses and buffer-allocation heuristics primarily target disk spilling by minimizing total I/O v... Read more ›
In this post, we show you how to use Amazon CloudWatch Database Insights for lock analysis in Amazon Aurora PostgreSQL. You learn how to enable the feature, interpret lock tree visualizations, resolve common lock-related issues, and maintain optimal database performance. This lock tree analysis feature also applies to Amazon RDS for PostgreSQL. Read more ›
We argue here that traditional network models, which are overwhelmingly based on the mathematical construct of a simple graph, are fundamentally insufficient for capturing the complexity of modern distributed systems. Such systems are characterized by heterogeneous agents with diverse capabilities, high-dimensional and multi-modal data streams, and intricate, context-dependent relationships that cannot be adequately described by a simple connect... Read more ›
Efficient query optimization is crucial for relational database systems, especially for optimizing join orders in complex queries. This work introduces a hybrid approach that integrates Eliminating Cartesian Products (ECP) with splitting the QUBO search space (SQSS) to reduce the size of the QUBO problem, minimizing binary variables and constraints. This improves the performance of the quantum algorithm while lowering hardware requirements. We e... Read more ›
Database configuration tuning is critical for workload performance, but practical tuning on real deployments remains difficult. Existing automatic tuners mostly formulate tuning as iterative search over DBMS knob values. This formulation leads to high execution cost, prematurely narrows the configuration space, and leaves practical requirements insufficiently addressed: diagnosing runtime bottlenecks from system feedback, exploring OS-level reco... Read more ›
Security updates have been issued by AlmaLinux (hplip, kernel, kernel-rt, libpng12, libpng15, libxml2, libxslt, mysql:8.0, mysql:8.4, opencryptoki, openssl, postfix, postgresql:15, rsync, and webkit2gtk3), Debian (asterisk, atril, gsasl, and libreoffice), Fedora (ack, bird, chromium, firefox, ldns, librabbitmq, nextcloud, nss, openslide, perl-Protocol-HTTP2, tig, vorbis-tools, and xen), Mageia (coturn, log4cxx, and python-tornado), SUSE (389-ds, buildah, container-suseconnect, distribution, e... Read more ›
In Part 1 of this series, we explored the performance enhancements in PostgreSQL 18, including skip scan optimization, enhanced EXPLAIN output, automatic self-join removal, and vacuum/autovacuum improvements. In this second part, we focus on security, monitoring, developer productivity, and logical replication enhancements that improve operational efficiency and the overall developer experience. Read more ›
We present MonaVec, a deterministic, embedded vector-search kernel for edge and offline AI -- settings where server infrastructure, network connectivity, and training data are all unavailable. Existing vector-search systems assume a persistent server, gigabytes of RAM, or a training pass over the corpus; MonaVec instead targets the deployment profile of SQLite: one file, one function call, runs anywhere. Its quantization core is training-free by... Read more ›
A filtered approximate-nearest-neighbor (ANN) query returns the k nearest vectors among those satisfying an attribute predicate P of selectivity s. The best execution strategy -- pre-filter, post-filter, or in-filter -- changes with s, so a system must estimate s and choose. We model this as an argmax over a landscape with phases (regions where each strategy wins) separated by boundaries, and show that selectivity-estimation error produces plan ... Read more ›
Log-structured merge (LSM) trees attach an approximate-membership filter to every run and must split a fixed memory budget across them. The static optimum is known (Monkey); a large systems literature then makes the allocation adaptive, tracking shifting hotness online. We ask a prior question: when is that adaptivity worth its machinery? We give three analytical answers and validate them on synthetic sweeps, real Twitter production cache traces... Read more ›