D. Lomet, R. Anderson, T.K. Rengarajan, and P. Spiro. How the Rdb#VMS data sharing system became fast. Technical Report CRL 92#4, Digital Equipment Corporation Cambridge Research Lab, 1992. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Client-Based Logging for High Performance Distributed Architectures - Biliris (1996) (10 citations) (Correct)
....system executing on a VAXcluster. Earlier versions of Rdb VMS employed an undo no redo recovery protocol that required, at transaction commit, the forcing to disk of all the pages updated by the committing transaction. More recent versions offer both an undo noredo and an undo redo recovery scheme [12]. In addition, a variation of the callback locking algorithm, referred to as lock carry over , is used for reducing the number of messages sent across the nodes for locking purposes. However, Rdb VMS does not allow multiple outstanding updates belonging to different nodes to be present on a ....
D. Lomet, R. Anderson, T. K. Rengarajan, and P. Spiro. How the Rdb/VMS data sharing system became fast. Technical Report CRL 92/4, Digital Equipment Corporation Cambridge Research Lab, 1992.
A High Performance Configurable Storage Manager - Biliris, Panagos (1995) (10 citations) (Correct)
....to every application process accessing them. BeSS uses latches (atomic test and set) for synchronizing concurrent accesses and implementing atomic read write operations on the cached objects. Cleanup of shared structures from process failures is handled by keeping track of process actions as in [20]. BeSS insures the validity of the shared pointers by treating them in a uniform way as offsets from the beginning of a fictitious virtual address space as outlined below and illustrated in Figure 4. Each process P maps the shared cache in a number of frames each having size equal to database ....
D. Lomet, R. Anderson, Rengarajan T.K., and P. Spiro. How the Rdb/VMS data sharing system became fast. Technical Report CRL 92/4, Digital Equipment Corporation, Cambridge Research Lab, May 1992.
Fine-granularity Locking and Client-Based Logging.. - Panagos, Biliris.. (1996) (3 citations) (Correct)
....executing on a VAXcluster. Earlier versions of Rdb VMS employed an undo no redo recovery protocol that required, at transaction commit, the forcing to disk of all the pages updated by the committing transaction. More recent versions offer both an undo noredo and an undo redo recovery scheme [15]. In addition, a variation of the callback locking algorithm, referred to as lock carry over , is used for reducing the number of messages sent across the nodes for locking purposes. However, Rdb VMS does not allow multiple outstanding updates belonging to different nodes to be present on a ....
D. Lomet, R. Anderson, T.K. Rengarajan, and P. Spiro. How the Rdb/VMS data sharing system became fast. Technical Report CRL 92/4, Digital Equipment Corporation Cambridge Research Lab, 1992.
Fine-granularity Locking and Client-Based Logging.. - Panagos, Biliris.. (1996) (3 citations) (Correct)
No context found.
D. Lomet, R. Anderson, T.K. Rengarajan, and P. Spiro. How the Rdb#VMS data sharing system became fast. Technical Report CRL 92#4, Digital Equipment Corporation Cambridge Research Lab, 1992.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC