CASTOR CERNs data management system Data and storage

  • Slides: 14
Download presentation
CASTOR: CERN’s data management system Data and storage mgmt workshop 17/3/2003 Ben Couturier, Jean-Damien

CASTOR: CERN’s data management system Data and storage mgmt workshop 17/3/2003 Ben Couturier, Jean-Damien Durand, CERN IT-ADC 17/3/2003 CASTOR: CERN's data management system

Introduction • CERN Advanced STORage Manager – Hierarchical Storage Manager used to store user

Introduction • CERN Advanced STORage Manager – Hierarchical Storage Manager used to store user and physics files – Manages the secondary and tertiary storage • History – Development started in 1999 based on SHIFT, CERN's tape and disk management system since beginning of 1990 s (SHIFT was awarded the 21 st Century Achievement Award by Computerworld in 2001) – In production since the beginning of 2001 • Currently holds more than 9 million files and 2000 TB of data 17/3/2003 CASTOR: CERN's data management system 2

Main Characteristics (1) • CASTOR Namespace – All files belong to the “/castor” hierarchy

Main Characteristics (1) • CASTOR Namespace – All files belong to the “/castor” hierarchy – The rights are standard UNIX rights • POSIX Interface – The files are accessible through a standard POSIX interface, all calls are rfio_xxx (e. g. rfio_open, rfio_close…) • RFIO Protocol – All remote file access done using the Remote File IO protocol, developed at CERN. 17/3/2003 CASTOR: CERN's data management system 3

Main Characteristics (2) • Modularity – The components in CASTOR have well defined roles

Main Characteristics (2) • Modularity – The components in CASTOR have well defined roles and interfaces, it is possible to change a component without affecting the whole system • Highly Distributed System – CERN uses a very distributed configuration with many disk servers/tape servers. – Can also run in more limited environment • Scalability – The number of disk servers, tape servers, name servers… is not limited – Use of RDBMS (Oracle, My. SQL) to improve the scalability of some critical components 17/3/2003 CASTOR: CERN's data management system 4

Main Characteristics (3) • Tape drive sharing – A large number of drives can

Main Characteristics (3) • Tape drive sharing – A large number of drives can be shared between users or dedicated to some users/experiments – Drives can be shared with other applications: with TSM, for example • High Performance Tape Mover – Use of threads and circular buffers – Overlaid device and network I/O • Grid Interfaces – A Grid. FTP daemon interfaced with CASTOR is currently in test – A SRM Interface (V 1. 0) for CASTOR has been developed 17/3/2003 CASTOR: CERN's data management system 5

Hardware Compatibility • CASTOR runs on: – Linux, Solaris, AIX, HP-UX, Digital UNIX, IRIX

Hardware Compatibility • CASTOR runs on: – Linux, Solaris, AIX, HP-UX, Digital UNIX, IRIX – The clients and some of the servers run on Windows NT/2 K • Supported drives – DLT/SDLT, LTO, IBM 3590, STK 9840, STK 9940 A/B (and old drives already supported by SHIFT) • Libraries – SCSI Libraries – ADIC Scalar, IBM 3494, IBM 3584, Odetics, Sony DMS 24, STK Powderhorn 17/3/2003 CASTOR: CERN's data management system 6

CASTOR Components • Central servers – Name Server – Volume Manager – Volume and

CASTOR Components • Central servers – Name Server – Volume Manager – Volume and Drive Queue Manager (Manages the volume and drive queues per device group) – UPV (Authorization daemon) • “Disk” subsystem – RFIO (Disk Mover) – Stager (Disk Pool Manager and Hierarchical Resource Manager) • “Tape” Subsystem – RTCOPY daemon (Tape Mover) – Tpdaemon (PVR) 17/3/2003 CASTOR: CERN's data management system 7

CASTOR Architecture CUPV VDQM server NAME server RFIO Client STAGER RTCPD (TAPE MOVER) RFIOD

CASTOR Architecture CUPV VDQM server NAME server RFIO Client STAGER RTCPD (TAPE MOVER) RFIOD (DISK MOVER) DISK POOL 17/3/2003 TPDAEMON (PVR) VOLUME manager CASTOR: CERN's data management system MSGD 8

CASTOR Setup at CERN • Disk servers – ~ 140 disk servers – ~

CASTOR Setup at CERN • Disk servers – ~ 140 disk servers – ~ 70 TB of staging pools – ~ 40 stagers • Tape drives and servers Model Nb Drives Nb Servers 9940 B 21 20 9940 A 28 10 9840 15 5 3590 4 2 DLT 7000 6 2 LTO 6 3 SDLT 2 1 • Libraries – 2 sets of 5 Powderhorn silos (2 x 27500 cartridges) – 1 Timberwolf (1 x 600 cartridges) – 1 L 700 (1 x 600 cartridges) 17/3/2003 CASTOR: CERN's data management system 9

Evolution of Data in CASTOR 17/3/2003 CASTOR: CERN's data management system 10

Evolution of Data in CASTOR 17/3/2003 CASTOR: CERN's data management system 10

Tape Mounts per group 17/3/2003 CASTOR: CERN's data management system 11

Tape Mounts per group 17/3/2003 CASTOR: CERN's data management system 11

Tape Mounts per drive type 17/3/2003 CASTOR: CERN's data management system 13

Tape Mounts per drive type 17/3/2003 CASTOR: CERN's data management system 13

ALICE Data Challenge • Migration rate of 300 MB/s sustained for a week –

ALICE Data Challenge • Migration rate of 300 MB/s sustained for a week – Using 18 STK T 9940 B drives – ~ 20 disk servers managed by 1 stager – A separate name server was used for the data challenge 17/3/2003 CASTOR: CERN's data management system 14

17/3/2003 CASTOR: CERN's data management system 15

17/3/2003 CASTOR: CERN's data management system 15