Buffer Pool Research Articles

Buffer pools and file processing projects for an undergraduate data structures course

This paper presents a family of programming projects appropriate to a sophomore-level data structures course, centered around the concept of a buffer pool serving as the access intermediary to a disk file. These projects provide a meaningful vehicle for practicing object-oriented design techniques and teach fundamental material on file processing and manipulating binary data. I begin with a concrete example, a heap stored on disk and mediated by a buffer pool. Several important intellectual concepts introduced by such a project are enumerated. Significant extensions and alternatives to the basic project are then described. I conclude with some observations on the role of file processing in modern CS curricula, and the significance of recent trends away from coverage of these topics.

Sarco-endoplasmic reticulum Ca2+ ATPase (SERCA) inhibitors identify a novel calcium pool in the central nervous system.

Ca2+ uptake into the endoplasmic reticulum (ER) is mediated by Ca2+ ATPase isoforms, which are all selectively inhibited by nanomolar concentrations of thapsigargin. Using ATP/Mg2+-dependent 45Ca2+ transport in rat brain microsomes, tissue sections, and permeabilized cells, as well as Ca2+ imaging in living cells we distinguish two ER Ca2+ pools in the rat CNS. Nanomolar levels of thapsigargin blocked one component of brain microsomal 45Ca2+ transport, which we designate as the thapsigargin-sensitive pool (TG-S). The remaining component was only inhibited by micromolar thapsigargin, and thus designated as thapsigargin resistant (TG-R). Ca2+ ATPase and [32P]phosphoenzyme assays also distinguished activities with differential sensitivities to thapsigargin. The TG-R Ca2+ uptake displayed unique anion permeabilities, was inhibited by vanadate, but was unaffected by sulfhydryl reduction. Ca2+ sequestered into the TG-R pool could not be released by inositol-1,4,5-trisphosphate, caffeine, or cyclic ADP-ribose. The TG-R Ca2+ pool had a unique anatomical distribution in the brain, with selective enrichment in brainstem and spinal cord structures. Cell lines that expressed high levels of the TG-R pool required micromolar concentrations of thapsigargin to effectively raise cytoplasmic Ca2+ levels. TG-R Ca2+ accumulation represents a distinct Ca2+ buffering pool in specific CNS regions with unique pharmacological sensitivities and anatomical distributions.

Database recovery using incomplete page versions in a multisystem data sharing environment

Coupling multiple computing nodes for transaction processing for the sake of capacity and availability has received considerable interest. A multisystem data sharing environment (MDSE) is one of the representative architecture of the coupling [2,4]. In the MDSE, all coupled nodes are connected via a high-speed network and share a common database at the disk level. Each node in the MDSE has its own buffer pool and caches database pages in the buffer. Caching may substantially reduce the number of disk I/O operations by utilizing the locality of reference. However, since a particular page may be simultaneously cached in different nodes, modification of the page in any buffer invalidates copies of that page in other nodes. This necessitates the use of a cache coherency scheme so that the nodes always see the most recent version of database pages [3,6]. The subject of this paper is about database recovery that has to be performed when one or more nodes are failed. The complexity of recovery schemes in the MDSE is heavily dependent on the dirty page

I/O reference behavior of production database workloads and the TPC benchmarks—an analysis at the logical level

As improvements in processor performance continue to far outpace improvements in storage performance, I/O is increasingly the bottleneck in computer systems, especially in large database systems that manage huge amoungs of data. The key to achieving good I/O performance is to thoroughly understand its characteristics. In this article we present a comprehensive analysis of the logical I/O reference behavior of the peak productiondatabase workloads from ten of the world's largest corporations. In particular, we focus on how these workloads respond to different techniques for caching, prefetching, and write buffering. Our findings include several broadly applicable rules of thumb that describe how effective the various I/O optimization techniques are for the production workloads. For instance, our results indicate that the buffer pool miss ratio tends to be related to the ratio of buffer pool size to data size by an inverse square root rule. A similar fourth root rule relates the write miss ratio and the ration of buffer pool size to data size. In addition, we characterize the reference characteristics of workloads similar to the Transaction Processing Performance Council (TPC) benchmarks C (TPC-C) and D(TPC-D), which are de facto standard performance measures for online transaction processing (OLTP) systems and decision support systems (DSS), respectively. Since benchmarks such as TPC-C and TPC-D can only be used effectively if their strengths and limitations are understood, a major focus of our analysis is to identify aspects of the benchmarks that stress the system differently than the production workloads. We discover that for the most part, the reference behavior of TPC-C and TPC-D fall within the range of behavior exhibited by the production workloads. However, there are some noteworthy exceptions that affect well-known I/O optimization techniques such as caching (LRU is further from the optimal for TPC-C, while there is little sharing of pages between transactions for TPC-D), prefetching (TPC-C exhibits no significant sequentiality), and write buffering (write buffering is lees effective for the TPC benchmarks). While the two TPC benchmarks generally complement one another in reflecting the characteristics of the production workloads, there remain aspects of the real workloads that are not represented by either of the benchmarks.

Changes in Phosphorus Fractions in Soils under Intensive Plant Growth

The total quantity of P and plant‐available P often differ greatly in soils of the tropics, which typically range in weathering intensity. Assessing available P is fundamental to managing P in many of these soils. Phosphorus availability in some soils has been inferred from the Hedley sequential extraction assuming that each P fraction reflects similar plant availability in different soils. However, experimental measurements of plant P availability were either of short duration or involved multiple P applications, which complicates assessment of the plant availability of P fractions. The objectives of this study were to examine the changes in P fractions under exhaustive cropping on diverse soils and to discern the differences in plant availability among P fractions. Eight soils ranging in weathering from Vertisols and Mollisols to Ultisols and Oxisols were amended with Ca(H2PO4)·H2O to raise soil solution P to 0.2 mg L−1 and planted for 14 crops to remove available P. The results indicated that the Fe‐impregnated strip–P and inorganic NaHCO3–P (NaHCO3–Pi) decreased the most in response to plant P withdrawal in all soils. The inorganic NaOH‐P (NaOH‐Pi) also declined with plant P uptake in all soils. The HCl‐P and residual P seemed to act as a buffer for the strip‐P and the NaHCO3–Pi in the slightly weathered soils, whereas NaOH‐Pi seemed to act as a buffering pool for strip‐P and NaHCO3–Pi in the highly weathered soils. Residual P in the slightly weathered soils was plant‐available on a relatively short time scale. In contrast, residual P in the highly weathered soils accumulated in the presence of intensive plant P removal, indicating that it was unavailable to plants. Organic P (NaHCO3‐ and NaOH‐Po) fractions were not significant contributors to available P in these soils that received high levels of inorganic P. Phosphorus fractions separated by the same sequential method were not of equal availability to plants in all soils.

PARTIAL PURIFICATION and CHARACTERIZATION of ASPARTATE AMINOTRANSFERASE from the HEPATOPANCREAS of the MUSSEL Mytilus galloprovincialis Lam.

In this study aspartate and alanine aminotransferase enzymes of Mytilus galloprovincialis Lam., the mussel species specific to the Turkish coast were examined. Because it was found that aspartate aminotransferase activity in the hepatopancreas was superior to alanine aminotransferase while surveying the activities of these enzymes in the whole body, hepatopancreas and mantle tissues; among these two enzymes, aspartate aminotransferase was partially purified from hepatopancreas and its kinetic properties were studied. Molluscs were collected daily from the Rumelikavagl coast of the Bosphonts and hepatopancreases were homogenized with 0.9% NaCl solution after dissection from the body. The fraction obtained after 35%-65% ammonium sulphate precipitation was applied to hydroxylapatite column. The elution performed by increasing molarity gradient of the phosphate buffer, pH 6.8, resulted in the recovery of the aspartate arninotransferase activity in 100 mM phosphate buffer pool. The 83 fold purified enzyme was applied to polyacrylamide gel electrophoresis and the existence of two activity bands indicated two isoenzymes of the aspartate aminotransferase. Effect of temperature on the activity of the enzyme was examined and it was found that the enzyme exhibited maximum activities at 25 °C and 40 °C; the activity completely dissappeared at 60 °C. Aspartate aminotransferase activity was maximum at pH 7.6, Km values for aspartate,and 2-oksoglutarate were 1.7 mM and 6.6x10 -2 mM, Vmax for the same substrates were I62 U/ml and 0.149 U/ml, respectively. Key words: Mussel, Mytilus galloprovincialis Lam., aspartate aminotransferase, alanine aminotransferase, transaminase

Simulation of dynamic input buffer space in multistage interconnection networks

This paper presents a simulation study of a new dynamic allocation of input buffer space in multistage interconnection networks (MINs). MINs are composed of an interconnected set of switching elements (SEs), connected in a specific topology. The SEs are composed of input and output buffers which are used to store received and forwarded packets, respectively. The performance of these networks depends on the design of these internal buffers and the clock mechanism in synchronous MINs. Various cycle models exist which include the big cycle, small cycle and the smart cycle, each of which provides a more efficient cycle timing. The smart cycle model achieves a superior performance by using output buffers and acknowledgement. However, it suffers from lost and out-of-order packets at high traffic loads. This paper, presents a variation of the smart cycle model, whereby, the input buffer space of each SE is allocated dynamically as a function of traffic load, in order to overcome the above-mentioned drawbacks. A shared buffer pool is provided, which supplies the required input buffer space as required by each SE. Simulation results are presented, which show the required buffer pool for various network sizes and for different network loads. Also, comparison with a static allocation scheme shows an increased network throughput, and the elimination of lost and out-of-order packets at high traffic loads.

Storage System and Multimedia: Classification and Extensions

With the increasing processing speeds, there is a shift away from the paradigm of centralized, sequential storage systems towards distributed and network based storage systems. Further, with the new imaging and real time multimedia applications, it is becoming more than ever important to design powerful, efficient and scaleable I/O systems. In this paper, the requirements of storage subsystems in multimedia environment were presented. The storage system components relating to those requirements were analyzed. Current solutions were surveyed and classified. Then we proposed approaches to improve storage subsystem performance for multimedia. The first approach applies constrained layout currently used for single disk model to multi-disk system. The second calls for using a stripping unit that meets both media and storage system optimization criteria. The third uses a pool of buffers instead of single buffer per stream.

Stabilization of acid phosphatase in DDDACl/n-butyl acetate reverse micelles

Storage stability of acid phosphatase entrapped in reverse micelles was studied. Supramolecular systems were prepared with a cationic twin chain surfactant, didodecyldimethylammonium chloride (DDDAC1), n-butyl acetate as an organic solvent and different water percentages. The rate of enzyme deactivation was monitored in the temperature interval from 20 to 45 °C, at bulk pH from 4.8 to 6.4, either unstirred conditions or under convective mixing from 250 to 750 rev min−1, water-to-surfactant molar ratio (w0) equal to 11.4, 12.7, 14.2 and with the following buffers, Na-citrate, Li-citrate, K-citrate, Na-propionate. Acid phosphatase entrapped in buffer pools of reverse micelles exhibited enhanced stability in comparison with the enzyme in the pure aqueous phase. Half-life was up to 4 times larger. Both the chemicals used for buffer preparation and buffer pH change, within one unit, were found to influence the rate of acid phosphatase deactivation. The activation energy of enzyme deactivation process in micellar systems was slightly increasing with w0 but the values were not very different from the one in aqueous phase (145.3 kJ mol−1). The rate of deactivation of enzyme confined in the micelles when shear stress was applied was reduced in comparison with that of the free protein, even though the percentage loss was greater.

Indexing for multiversion locking: alternatives and performance evaluation

Multiversion two phase locking (MV2PL) provides online serializable queries without introducing the long blocking delays that can occur with conventional two phase locking (2PL). MV2PL requires indexing structures, however, that are capable of supporting multiple versions of data. We present several options for extending single version indexing schemes for use with MV2PL. These basic approaches are largely orthogonal to the underlying indexing structure (e.g., hashing or B+ trees). The options considered differ in where they place version selection information (i.e., references to individual versions); this information is placed either with the data or with the index entries of one or more of the indices. We also present the results from a performance study that show that placing the version selection information with the data is usually the best option, since it keeps the indices smaller and thus enables a larger fraction of the index pages to remain cached in the buffer pool.

An incremental memory allocation method for mixed workloads

This paper proposes and investigates an incremental memory allocation method for mixed database workloads of simple hash-join queries and short read transactions. Traditionally, a DBMS allocates all memory reserved for a query at the beginning of the query execution. However, there may be a prolonged period from the time the query begins to the time that all reserved memory is actually consumed by the query process. We propose to allocate reserved memory to the query incrementally by smaller portions when the query process is actually ready to utilize this memory. Memory that was reserved but not yet allocated to the query can be used temporarily as a shared buffer pool by other components of the workload. Through a series of simulation experiments we demonstrate that the incremental memory allocation for hash-join queries improves the performance of read transactions without penalizing queries.

Buffer management in shared-memory Time Warp systems

Mechanisms for managing message buffers in Time Warp parallel simulations executing on cache-coherent shared-memory multiprocessors are studied. Two simple buffer management strategies called the sender pool and receiver pool mechanisms are examined with respect to their efficiency, and in particular, their interaction with multiprocessor cache-coherence protocols. Measurements of implementations on a Kendall Square Research KSR-2 machine using both synthetic workloads and benchmark applications demonstrate that sender pools offer significant performance advantages over receiver pools. However, it is also observed that both schemes, especially the sender pool mechanism, are prone to severe performance degradations due to poor locality of reference in large simulations using substantial amounts of message buffer memory. A third strategy called the partitioned buffer pool approach is proposed that exploits the advantages of sender pools, but exhibits much better locality. Measurements of this approach indicate that the partitioned pool mechanism yields substantially better performance than both the sender and receiver pool schemes for large-scale, small-granularity parallel simulation applications. The central conclusions from this study are: (1) buffer management strategies play an important role in determining the overall efficiency of multiprocessor-based parallel simulators, and (2) the partitioned buffer pool organization offers significantly better performance than the sender and receiver pool schemes. These studies demonstrate that poor performance may result if proper attention is not paid to realizing an efficient buffer management mechanism.

Approximate analysis of buffer sharing scheme in arbitrary configurations of queueing networks

Arbitrary configurations of open queueing networks under the Sharing with a Maximum Queue and Minimum Allocation (SMQMA) scheme are analyzed. In this scheme, a minimum number of buffers are reserved for each node in addition to a common pool of buffers shared among all nodes. There is also a limit on the number of buffers that each node can use. Owing to blocking, this queueing network does not have a product form solution. We present an approximation algorithm for the performance analysis of the network. Comparisons with exact numerical solutions are given to illustrate that the approximation algorithm has an acceptable error-level.

The SPIFFI scalable video-on-demand system

This paper presents a simulation study of a video-on-demand system. We present video server algorithms for real-time disk scheduling, prefetching, and buffer pool management. The performance of these algorithms is compared against the performance of simpler algorithms such as elevator and round-robin disk scheduling and global LRU buffer pool management. Finally, we show that the SPIFFI video-on-demand system scales nearly linearly as the number of disks, videos, and terminals is increased.

Credit-based flow control for ATM networks

This paper presents three new results concerning credit-based flow control for ATM networks: (1) a simple and robust credit update protocol (CUP) suited for relatively inexpensive hardware/software implementation; (2) automatic adaptation of credit buffer allocation for virtual circuits (VCs) sharing the same buffer pool; (3) use of credit-based flow control to improve the effectiveness of statistical multiplexing in minimizing switch memory. These results have been substantiated by analysis, simulation and implementation.

ARIES/CSA

This paper presents an algorithm, called ARIES/CSA ( Algorithm for Recovery and Isolation Exploiting Semantics for Client-Server Architectures ), for performing recovery correctly in client-server (CS) architectures. In CS, the server manages the disk version of the database. The clients, after obtaining database pages from the server, cache them in their buffer pools. Clients perform their updates on the cached pages and produce log records. The log records are buffered locally in virtual storage and later sent to the single log at the server. ARIES/CSA supports a write-ahead logging (WAL), fine-granularity (e.g., record) locking, partial rollbacks and flexible buffer management policies like steal and no-force . It does not require that the clocks on the clients and the server be synchronized. Checkpointing by the server and the clients allows for flexible and easier recovery.

An adaptive memory management protocol for Time Warp parallel simulation

It is widely believed that Time Warp is prone to two potential problems: an excessive amount of wasted, rolled back computation resulting from “rollback thrashing” behaviors, and inefficient use of memory, leading to poor performance of virtual memory and/or multiprocessor cache systems. An adaptive mechanism is proposed based on the Cancelback memory management protocol that dynamically controls the amount of memory used in the simulation in order to maximize performance. The proposed mechanism is adaptive in the sense that it monitors the execution of the Time Warp program, automatically adjusts the amount of memory used to reduce Time Warp overheads (fossil collection, Cancelback, the amount of rolled back computation, etc.) to a manageable level. The mechanism is based on a model that characterizes the behavior of Time Warp programs in terms of the flow of memory buffers among different buffer pools. We demonstrate that an implementation of the adaptive mechanism on a Kendall Square Research KSR-1 multiprocessor is effective in automatically maximizing performance while minimizing memory utilization of Time Warp programs, even for dynamically changing simulation models.

An efficient and flexible method for archiving a data base

We describe an efficient method for supporting incremental and full archiving of data bases (e.g., individual files). Customers archive their data bases quite frequently to minimize the duration of data outage. Because of the growing sizes of data bases and the ever increasing need for high availability of data, the efficiency of the archive copy utility is very important. The method presented here minimizes interferences with concurrent transactions by not acquiring any locks on the data being copied. It significantly reduces disk I/Os by not keeping on data pages any extra tracking information in connection with archiving. These features make the archive copy operation be more efficient in terms of resource consumption compared to other methods. The method is also flexible in that it optionally supports direct copying of data from disks, bypassing the DBMS's buffer pool. This reduces buffer pool pollution and processing overheads, and allows the utility to take advantage of device geometries for efficiently retrieving data. We also describe extensions to the method to accommodate the multisystem shared disks transaction environment. The method tolerates gracefully system failures during the archive copy operation.

The LRU-K page replacement algorithm for database disk buffering

This paper introduces a new approach to database disk buffering, called the LRU-K method. The basic idea of LRU-K is to keep track of the times of the last K references to popular database pages, using this information to statistically estimate the interarrival times of references on a page by page basis. Although the LRU-K approach performs optimal statistical inference under relatively standard assumptions, it is fairly simple and incurs little bookkeeping overhead. As we demonstrate with simulation experiments, the LRU-K algorithm surpasses conventional buffering algorithms in discriminating between frequently and infrequently referenced pages. In fact, LRU-K can approach the behavior of buffering algorithms in which page sets with known access frequencies are manually assigned to different buffer pools of specifically tuned sizes. Unlike such customized buffering algorithms however, the LRU-K method is self-tuning, and does not rely on external hints about workload characteristics. Furthermore, the LRU-K algorithm adapts in real time to changing patterns of access.

Characterization of database access skew in a transaction processing environment

The knowledge of access skew (non-uniform access) in each database relation is useful for both workload management (buffer pool allocation, transaction routing, etc.), as well as capacity planning for changing workload mix. However, it is a challenging problem to characterize the access skew of a real database workload in a simple manner that can easily be used to compute the buffer hit probability under the LRU replacement policy. A concise way to characterize the access skew is proposed by assuming that the large number of data pages may be logically grouped into a small number of partitions such that the frequency of accessing each page within a partition can be treated as equal. Based on this approach, a recursive binary partitioning algorithm is presented that can infer the access skew from the buffer hit probabilities for a subset of the buffer sizes. This avoids explicit estimation of individual access frequencies for the large number of database pages. The method is validated of its ability to predict buffer hit from the skew characterization using production database traces.