Search for: All records

R-tree is a foundational data structure used in spatial databases and scientific databases. With the advancement of networks and computer architectures, in-memory data processing for R-tree in distributed systems has become a common platform. We have observed new performance challenges to process R-tree as the amount of multidimensional datasets become increasingly high. Specifically, an R-tree server can be heavily overloaded while the network and client CPU are lightly loaded, and vice versa. In this article, we present the design and implementation of Catfish, an RDMA-enabled R-tree for low latency and high throughput by adaptively utilizing the available network bandwidth and computing resources to balance the workloads between clients and servers. We design and implement two basic mechanisms of using RDMA for a client-server R-tree data processing system. First, in the fast messaging design, we use RDMA writes to send R-tree requests to the server and let server threads process R-tree requests to achieve low query latency. Second, in the RDMA offloading design, we use RDMA reads to offload tree traversal from the server to the client, which rescues the server as it is overloaded. We further develop an adaptive scheme to effectively switch an R-tree search between fast messaging and RDMA offloading, maximizing the overall performance. Our experiments show that the adaptive solution of Catfish on InfiniBand significantly outperforms R-tree that uses only fast messaging or only RDMA offloading in both latency and throughput. Catfish can also deliver up to one order of magnitude performance over the traditional schemes using TCP/IP on 1 and 40 Gbps Ethernet. We make a strong case to use RDMA to effectively balance workloads in distributed systems for low latency and high throughput. 

With the advancement and dominant service of Internet videos, the content-based video deduplication system becomes an essential and dependent infrastructure for Internet video service. However, the explosively growing video data on the Internet challenges the system design and implementation for its scalability in several ways. (1) Although the quantization-based indexing techniques are effective for searching visual features at a large scale, the costly re-training over the complete dataset must be done periodically. (2) The high-dimensional vectors for visual features demand increasingly large SSD space, degrading I/O performance. (3) Videos crawled from the Internet are diverse, and visually similar videos are not necessarily the duplicates, increasing deduplication complexity. (4) Most videos are edited ones. The duplicate contents are more likely discovered as clips inside the videos, demanding processing techniques with close attention to details. To address above-mentioned issues, we propose Maze, a full-fledged video deduplication system. Maze has an ANNS layer that indexes and searches the high dimensional feature vectors. The architecture of the ANNS layer supports efficient reads and writes and eliminates the data migration caused by re-training. Maze adopts the CNN-based feature and the ORB feature as the visual features, which are optimized for the specific video deduplication task. The features are compact and fully reside in the memory. Acoustic features are also incorporated in Maze so that the visually similar videos but having different audio tracks are recognizable. A clip-based matching algorithm is developed to discover duplicate contents at a fine granularity. Maze has been deployed as a production system for two years. It has indexed 1.3 billion videos and is indexing ~800 thousand videos per day. For the ANNS layer, the average read latency is 4 seconds and the average write latency is at most 4.84 seconds. The re-training over the complete dataset is no longer required no matter how many new data sets are added, eliminating the costly data migration between nodes. Maze recognizes the duplicate live streaming videos with both the similar appearance and the similar audio at a recall of 98%. Most importantly, Maze is also cost-effective. For example, the compact feature design helps save 5800 SSDs and the computation resources devoted to running the whole system decrease to 250K standard cores per billion videos. 

Visual contents, including images and videos, are dominant on the Internet today. The conventional search engine is mainly designed for textual documents, which must be extended to process and manage increasingly high volumes of visual data objects. In this paper, we present Mixer, an effective system to identify and analyze visual contents and to extract their features for data retrievals, aiming at addressing two critical issues: (1) efficiently and timely understanding visual contents, (2) retrieving them at high precision and recall rates without impairing the performance. In Mixer, the visual objects are categorized into different classes, each of which has representative visual features. Subsystems for model production and model execution are developed. Two retrieval layers are designed and implemented for images and videos, respectively. In this way, we are able to perform aggregation retrievals of the two types in efficient ways. The experiments with Baidu's production workloads and systems show that Mixer halves the model production time and raises the feature production throughput by 9.14x. Mixer also achieves the precision and recall of video retrievals at 95% and 97%, respectively. Mixer has been in its daily operations, which makes the search engine highly scalable for visual contents at a low cost. Having observed productivity improvement of upper-level applications in the search engine, we believe our system framework would generally benefit other data processing applications. 

We derived the angular response function ($W_{\mathrm{N}}$) for scattering sensors that automatically satisfies the normalization criterion and its corresponding weight ($W_{\mathrm{T}}$).$W_{\mathrm{N}}$’s, derived for two commercial sensors, HydroScat-6 (HOBI Labs) and ECO-BB (Sea-Bird Inc.), agrees well with the Monte Carlo simulation and direct measurements. The backscattering measured for microbeads of known sizes agrees better with Mie calculation when the derived$W_{\mathrm{N}}$was applied. We deduced that the reduction of$W_{\mathrm{T}}$with increasing attenuation coefficient is related to path length attenuation and showed that this theoretically derived correction factor performs better than the default methods for the two commercial backscattering sensors. The analysis conducted in this study also leads to an estimate of uncertainty budget for the two sensors. The major uncertainty for ECO-BB is associated with its angular response function because of its wide field of view, whereas the main uncertainty for the HydrScat-6 is due to attenuation correction because of its relatively long path length.

 

Nested queries are commonly used to express complex use-cases by connecting the output of a subquery as an input to the outer query block. However, their execution is highly time consuming. Researchers have proposed various algorithms and techniques that unnest subqueries to improve performance. Since this is a customized approach that needs high algorithmic and engineering efforts, it is largely not an open feature in most existing database systems. Our approach is general-purpose and GPU-acceleration based, aiming for high performance at a minimum development cost. We look into the major differences between nested and unnested query structures to identify their merits and limits for GPU processing. Furthermore, we focus on the nested approach that is algorithmically simple and rich in parallels, in relatively low space complexity, and generic in program structure. We create a new code generation framework that best fits GPU for the nested method. We also make several critical system optimizations including massive parallel scanning with indexing, effective vectorization to optimize join operations, exploiting cache locality for loops and efficient GPU memory management. We have implemented the proposed solutions in NestGPU, a GPU-based column-store database system that is GPU device independent. We have extensively evaluated and tested the system to show the effectiveness of our proposed methods. 

Because the diffusivity of particles undergoing the Brownian motion is inversely proportional to their sizes, the size distribution of submicron particles can be estimated by tracking their movement. This particle tracking analysis (PTA) has been applied in various fields, but mainly focused on resolving monodispersed particle populations and is rarely used for measuring oceanic particles that are naturally polydispersed. We demonstrated using Monte Carlo simulation that, in principle, PTA can be used to size natural, oceanic particles. We conducted a series of lab experiments using microbeads of NIST‐traceable sizes to evaluate the performance of ViewSizer 3000, a PTA‐based commercial instrument, and found two major uncertainties: (1) the sample volume varies with the size of particles and (2) the signal‐to‐noise ratio for particles of sizes < 200–250 nm was reduced and hence their concentration was underestimated with the presence of larger particles. After applying the volume correction, we found the instrument can resolve oceanic submicron particles of sizes greater than 250 nm with a mean absolute error of 3.9% in size and 38% in concentration.