IHEP DIRAC Set-Up and Services Overview
Discover the setup details and services offered by IHEP DIRAC, including server configurations, extension versions, and a range of services related to accounting, data management, framework, monitoring, workload management, and more. Dive into the world of IHEP DIRAC through detailed information and images provided in this overview.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
IHEP DIRAC set-up and some info from DIRAC Xiaomei Zhang Oct 27
IHEP DIRAC set-up One server with all the services and agents, including DB server Hardware Intel(R) Xeon(R) CPU Silver 4116 @ 2.10GHz with 24 cores, 128GB Mem with 4TB disk DIRAC Set-up Setup: CAS_Production DIRAC version: v6r22p3 Extension Set-up WebApp version v4r0p7 VM version v2r4-pre2 IHEPDIRAC Set-up IHEPDIRAC version: v0r18
Services in set-up (1) 'Accounting': ['DataStore', 'ReportGenerator'] 'Configuration': ['Server'] 'DataManagement': ['FTS3Manager','StorageElement', 'FileCatalog', 'StorageElementProxy'] 'Framework': ['SystemAdministrator , 'ComponentMonitoring', 'SystemLoggingReport', 'Monitoring', 'Notification', 'SecurityLogging', 'UserProfileManager', 'ProxyManager', 'SystemLogging', 'Plotting', 'BundleDelivery']
Services in set-up (2) 'Monitoring': ['Monitoring'] 'RequestManagement': ['ReqManager', 'ReqProxy'] 'ResourceStatus': ['ResourceStatus', 'ResourceManagement', 'Publisher', 'PublisherIHEP', 'ResourceManagementIHEP'] 'Transfer': ['Dataset', 'TransferRequest'] 'Transformation': ['TransformationManager'] 'WorkloadManagement': ['SandboxStore', 'Matcher', 'JobMonitoring', 'JobManager , 'JobStateUpdate', 'WMSAdministrator , 'OptimizationMind', VirtualMachineManager', 'TaskManager', 'PilotManager']
Agents in set-up (1) 'Configuration': ['Bdii2CSAgent', 'VOMS2CSAgent'], 'DataManagement': ['FTS3Agent'], 'Framework': ['SystemLoggingDBCleaner', 'TopErrorMessagesReporter'], 'RequestManagement': ['RequestExecutingAgent'], 'ResourceStatus': ['CacheFeederAgent', 'EmailAgent', 'SiteInspectorAgent', 'CacheFeederIHEPAgent', 'SAMTestAgent'], 'Transfer': ['TransferAgent']
Agents in set-up (2) 'Transformation': ['InputDataAgent', 'MCExtensionAgent', 'RequestTaskAgent', 'TransformationAgent', 'TransformationCleaningAgent', 'ValidateOutputDataAgent', 'WorkflowTaskAgent', 'WorkflowTaskAgent- JUNO', 'WorkflowTaskAgent-CEPC , 'RequestTaskAgent- JUNO', 'RequestTaskAgent-CEPC'], 'WorkloadManagement': ['PilotStatusAgent', 'JobCleaningAgent', 'StalledJobAgent', 'StatesAccountingAgent', 'StatesMonitoringAgent', 'TaskAgent', 'CloudDirectorJUNO', 'SiteDirectorJUNO', 'SiteDirectorBOINC', 'CloudDirectorAWS']
DIRAC duplications (1) Not all the components can be duplicated, which means we can t have a full DIRAC mirror somewhere For services, most of they can be duplicated For agents, instead, this probably means that they can not be duplicated DIRAC redundancy can aim for sharing loads and scaling, not for avoiding single-point failure More details: https://dirac.readthedocs.io/en/latest/AdministratorGuid e/ServerInstallations/scalingAndLimitations.html
DIRAC duplications (2) Even some services can be duplicated, but they have to interact with one DB, so the efficiency of replicating the services and agents?
Case in LHCb LHCb has some redundant services on 5 VMs in 5 different sites (most of our Tier1s) This VMs all install at a minimum: - SystemAdministration - Configuration - ReqProxy
Redundancy server in JINR JINR has done the same as what LHCb T1 has done Igor will have more details on that There are two servers appeared in IHEP CS Other sites will do the same?
Discussions Machines or VMs needed? How to set up redundancy servers in data centers? How do we know it is working or failing? Pilots use server info from CS when they are setting up local environment, what about clients? Randomly choose one from servers info in CS? Look like it only can be seen from the site CS log? Monitoring? From LHCb, no monitoring needed, look like DIRAC can ignore the problematic servers if exists But need to something watch on the healthy of redundancy server?
