boinc/client/rr_sim.h

26 lines
923 B
C
Raw Normal View History

// This file is part of BOINC.
// http://boinc.berkeley.edu
// Copyright (C) 2018 University of California
//
// BOINC is free software; you can redistribute it and/or modify it
// under the terms of the GNU Lesser General Public License
// as published by the Free Software Foundation,
// either version 3 of the License, or (at your option) any later version.
//
// BOINC is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
// See the GNU Lesser General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public License
// along with BOINC. If not, see <http://www.gnu.org/licenses/>.
#ifndef BOINC_RR_SIM_H
#define BOINC_RR_SIM_H
Avoid starvation when max_concurrent is used, and related fixes. Synopsis: max concurrent was being enforced in the last stage of CPU sched, but not in earlier stages, or in work fetch. This caused starvation in some cases. Fix this by modeling max concurrent in RR sim and make_run_list(). - CPU sched: model and enforce max concurrent limits in building run list for CPU jobs; otherwise the list has jobs we can't actually run - RR simulation: model and enforce max concurrent limits - RR sim: fix bug in calculation of # idle instances - RR sim: model unavailability of GPUs e.g. if we can't run GPU jobs we can potentially run more CPU jobs - work fetch: if a project is at a max concurrent limit, don't fetch work from it. The jobs we get (possibly) wouldn't be runnable. NOTE: we currently provide max concurrent limits at both project and app level. The problem with app level is that apps can have versions that use different resources. It would be better to have limits at the resource level instead. - In many cases (e.g. job completion) CPU sched and work fetch are both done back to back. Each of them does RR simulation. Only need to do this once (efficiency). - Show max concurrent settings in startup messages - Make max runnable jobs (1000) into a #define - Fix removal of "can't fetch work" notices - Make "can't fetch work" notices resource-specific; the reasons may differ between resources - Get rid of WF_DEBUG macro; just print everything if log_flags.work_fetch_debug is set. - Change project- and resource-level work-fetch reason codes (DONT_FETCH_PREFS etc.) from #defines to enums, and give them prefixes RSC_REASON and PROJECT_REASON - Fix bug where the return of compute_project_reason() wasn't actually being stored in project.work_fetch. - Add work-fetch reason MAX_CONCURRENT (project is at max concurrent limit)
2018-12-28 20:55:05 +00:00
extern void rr_simulation(const char* why);
extern void print_deadline_misses();
extern int n_idle_resources();
#endif