Commit Graph

368 Commits

Author SHA1 Message Date
David Anderson c3fe504e1d - client: add ATI support to job scheduling and work fetch
svn path=/trunk/boinc/; revision=18850
2009-08-17 16:50:40 +00:00
David Anderson 0a523d5f3f svn path=/trunk/boinc/; revision=18843 2009-08-14 17:10:52 +00:00
David Anderson e606170b14 - client: try to fix situations where the scheduler
runs GPU jobs in a seemingly random order,
        or preempts GPU jobs needlessly.
        The change has two parts:
        1) sort the "results" vector by received_time,
            so that the RR simulation processes GPU jobs FIFO.
        2) in the CPU scheduler (earliest_deadline_result())
            instead of choosing the earliest-deadline GPU job that
            misses its deadline,
            pick the earliest_deadline GPU from a project that
            has a deadline miss for that GPU type
            (this is what's done in the CPU case)
    - client: fix bug where if you have an exclusive app,
        then remove it from cc_config.xml and do "update config",
        it doesn't go away.
        Need to clear the list before parsing.

svn path=/trunk/boinc/; revision=18842
2009-08-14 16:54:45 +00:00
Rom Walton b932711a80 - client: refactor the CC startup process, move majority of the
windows code into sysmon_win.cpp, .h
        
    client/
        client_state.cpp, .h
        cpp.h
        http_curl.cpp
        main.cpp, .h
        net_stats.cpp
        sysmon_win.cpp, .h

svn path=/trunk/boinc/; revision=18803
2009-08-03 20:55:00 +00:00
David Anderson 2d058c5cb4 - GUI RPC: add active_only option to get_results() RPC
svn path=/trunk/boinc/; revision=18304
2009-06-04 17:59:04 +00:00
David Anderson f9222339e9 - client: simplify enforce_schedule(), and maybe fix bugs.
New approach: take the "ordered_schedule_results" list,
    add running jobs that haven't finished their time slice,
    and order the result appropriately.
    Then run jobs in order until CPUs are filled.
    Simpler and clearer than the old way.


svn path=/trunk/boinc/; revision=17992
2009-05-04 19:55:59 +00:00
David Anderson ed3e3b0063 - client: fix bug where if a GPU job is running,
and a 2nd GPU job with an earlier deadline arrives,
    neither job is executed ever.
    Reorganized things so that scheduling of GPU jobs is
    done independently of CPU jobs.
    The policy for GPU jobs:
    - always EDF
    - jobs are always removed from memory, regardless of checkpoint
    (GPU memory is not paged, so it's bad to leave an idle app in memory)

svn path=/trunk/boinc/; revision=17402
2009-02-26 21:36:41 +00:00
David Anderson feab684b3d - client: abort jobs that are unstarted and past deadline
- client: abort runaway jobs based on elapsed time instead of CPU time.
    Specifically, abort jobs for which
    elapsed time > WU.rsc_fpops_bound / app_version.flops
    This policy works for
    1) GPU jobs (which may use little CPU time)
    2) jobs that run but because of bugs use little CPU time
        (e.g., because they're sleeping)
    whereas the old policy didn't.

svn path=/trunk/boinc/; revision=17399
2009-02-26 17:51:38 +00:00
David Anderson 31e7127776 - client: make timeout values into #defines
svn path=/trunk/boinc/; revision=17396
2009-02-26 03:24:39 +00:00
David Anderson f7f2f85b79 - client: if a project is at max backoff for a resource,
stop accumulating debt if it's at or around zero.
        This prevents other projects from being driven unboundedly negative.
    - client: if the number of overworked projects exceeds the number
        of device instances, clear debts; this indicates that an earlier
        client was buggy and produced bad debt values.

svn path=/trunk/boinc/; revision=17325
2009-02-20 18:37:27 +00:00
David Anderson 3e98909ab6 - client: adjust debts at least every minute.
This fixes a bug that can cause debts to NEVER get updated.
- client: added "abort_jobs_on_exit" feature
    (available by --abort_jobs_on_exit cmdline
    or <abort_jobs_on_exit> in cc_config.xml).
    If set, when the client is exited by user request
    (this includes signals on Unix)
    it marks all pending jobs as aborted,
    and does a scheduler RPC to all projects with jobs.
    When these are completed the client exits.
    This is useful when BOINC is being used on grids
    where it is wiped clean after each run.

svn path=/trunk/boinc/; revision=17300
2009-02-18 19:47:02 +00:00
David Anderson af86d4326f - client: when accounting job elapsed time,
ignore intervals longer than 10 secs;
    that could only happen if the client or host was suspended/hibernated.
- client: in adjust_debts(), ignore intervals longer than
    2*work fetch period, not 2*CPU sched period.
    adjust_debts() is called from work fetch.

svn path=/trunk/boinc/; revision=17154
2009-02-05 20:16:28 +00:00
David Anderson 574d1fe087 - client: don't request work for a resource if it has no shortfall.
- client and server: get rid of coproc_cuda global.

svn path=/trunk/boinc/; revision=17019
2009-01-26 05:00:49 +00:00
David Anderson 0899975be5 - get_project_config: don't send error text if no terms_of_use.txt
- client: compute and store project work-fetch attributes

svn path=/trunk/boinc/; revision=16837
2009-01-08 00:41:15 +00:00
David Anderson 8c591e31df - client: first whack at new work-fetch logic. Very preliminary.
svn path=/trunk/boinc/; revision=16754
2008-12-31 23:07:59 +00:00
David Anderson cd4ca5fb17 - client: fix calculation of a job's FLOPS rate in round-robin simulation
svn path=/trunk/boinc/; revision=16662
2008-12-09 20:01:01 +00:00
David Anderson 0ded726fe7 - client: fix a long-standing error: if prefs say leave X GB free,
and BOINC is using Y GB, and there are Z GB free,
        the limit on BOINC is Y + Z - X (not Z - X).

svn path=/trunk/boinc/; revision=16388
2008-11-02 20:09:59 +00:00
David Anderson 51c993542e - client: cleaned up CPU scheduler logic somewhat
svn path=/trunk/boinc/; revision=16356
2008-10-29 22:13:04 +00:00
David Anderson 48ba503db3 - code shuffle
svn path=/trunk/boinc/; revision=16340
2008-10-28 22:38:00 +00:00
David Anderson 2d1d47de15 - client: move round-robin simulation to its own file
- web: check for profile existence before trying to show it
- file deleter: add some debugging msgs

svn path=/trunk/boinc/; revision=16338
2008-10-28 21:59:25 +00:00
David Anderson e43e8a408d - client: major changes to enforce_schedule() to handle GPUs
svn path=/trunk/boinc/; revision=16178
2008-10-09 22:44:45 +00:00
David Anderson f17c0879de - changed some comments for Doxygen
svn path=/trunk/boinc/; revision=16130
2008-10-04 23:44:24 +00:00
David Anderson 4f66bb4c95 - added copyright and license info to .C, .cpp, .h files
- scheduler: fix bug in adaptive replication:
    if send an unreplicated job to untrusted host,
    set both wu.target_nresults and wu.min_quorum to app.target_nresults.

svn path=/trunk/boinc/; revision=15762
2008-08-06 18:36:30 +00:00
David Anderson 884bad0975 - client: show proxy info in messages at startup and when changed
fixes 
- web: fix the am_set_info.php RPC
    (most args are optional, not mandatory)

svn path=/trunk/boinc/; revision=15716
2008-07-30 21:37:41 +00:00
David Anderson eeeb3b7951 - client: on startup, detect when the system clock has been set backwards,
and clear all timeout variables.
    This should fix the situation where, say:
    1) the user sets the system clock forward by a year;
    2) all projects get their min_rpc_time set;
    3) the user sets the system clock back to the correct time.
    Previously, BOINC would not do anything for a year.

    Note: a restart of BOINC is required to fix things.
    It would be harder to do this on the fly.

svn path=/trunk/boinc/; revision=15314
2008-05-28 19:15:44 +00:00
David Anderson c01e75ec4c - client: shuffle code to abstract coprocessor reservation
svn path=/trunk/boinc/; revision=15287
2008-05-23 21:24:36 +00:00
David Anderson 8294fba98f - client: print a message at startup if computation is suspended
svn path=/trunk/boinc/; revision=15279
2008-05-22 20:57:12 +00:00
David Anderson 9fa202d8f0 - client: add coprocessor support: i.e., parse the list of coprocs
in <app_version>s from the server,
    keep track of the number free of each type of coproc,
    and don't run an app that needs more than are available.
    (not quite working yet)

svn path=/trunk/boinc/; revision=14992
2008-04-01 15:08:47 +00:00
David Anderson 13400c9516 Changes for multithread app support:
- update_versions: use __ (not :) as separator for plan class
- client: add plan_class to APP_VERSION;
    an app version is now identified by platform/version/plan_class
- client CPU scheduler: don't assume apps use 1 CPU
- client: add avg_ncpus, max_cpus, flops, cmdline to RESULT
- scheduler: implement app planning scheme

Other changes:

- client: if symlink() fails, make a XML soft link instead
    (for Unix running off a FAT32 FS)
- client: don't accept nonpositive resource share from AMS
- daemons and DB: check for error returns from enumerations,
    and exit if so.  Thus, if the MySQL server goes down,
    all the daemons will soon exit.
    The cron script will restart them every 5 min,
    so when the DB server comes back up so will the project.
- web: show empty max CPU % as ---
- API: get rid of all_threads_cpu_time option (always the case now)


svn path=/trunk/boinc/; revision=14966
2008-03-27 18:25:29 +00:00
David Anderson c685f66384 - client: preliminary support for detecting and reporting coprocessors
(for now, CUDA devices)

svn path=/trunk/boinc/; revision=14876
2008-03-10 20:40:35 +00:00
David Anderson 35dab13859 - client code: my next-to-last checkin was flawed
svn path=/trunk/boinc/; revision=14725
2008-02-12 20:33:05 +00:00
David Anderson ee34cf3ab7 - client: removed sprawl
svn path=/trunk/boinc/; revision=14721
2008-02-12 15:04:27 +00:00
David Anderson 9b2998009f - client: add --start_delay cmdline option and <start_delay> config option.
Specifies an amount of time to delay starting apps
    (e.g. so that BOINC doesn't slow down boot process)

    Note: mechanisms that start BOINC at boot time
    need to figure out how to set this flag.

svn path=/trunk/boinc/; revision=14445
2007-12-27 21:40:20 +00:00
David Anderson f7c8bc5280 - client: fix bug that would falsely report DLL init errors
- client: don't crash when detach a project using anonymous platform
        (fixes )

svn path=/trunk/boinc/; revision=14348
2007-12-03 17:46:07 +00:00
David Anderson b3768ecc6f - client: removed -return_results_immediately cmdline option
(wasn't implemented anyway)
- client: added <report_results_immediately> configuration flag;
    causes results to be reported as soon as done.
    Needed for some WCG machines that are reformatted often.
    Should NOT be used in general, since it increases server load.

svn path=/trunk/boinc/; revision=14280
2007-11-21 19:57:40 +00:00
David Anderson cd9538589a - client: when starting an app, and an input/app file is not available,
show the file name and error code in the message
    that's appended to the job's stderr_out.

svn path=/trunk/boinc/; revision=14114
2007-11-07 19:32:32 +00:00
Frank Thomas 3bfc78b511 Updated the postal address of the Free Software Foundation in all license headers. See http://lists.ssl.berkeley.edu/pipermail/boinc_dev/2007-October/008939.html for reference.
svn path=/trunk/boinc/; revision=13804
2007-10-09 11:35:47 +00:00
David Anderson d302a5e107 - client/manager/API: code cleanup to disentangle sandbox code from lib/.
- move client sandbox-specific code to a new file, sandbox.C
    - remove g_use_sandbox from util.C; move to MainDocument.cpp (manager)
        and sandbox.C (client)
    - don't declare check_security() in util.h; it's not in util.C
    - don't call remove_project_owned_file_or_dir() in
        boinc_delete_file_aux() or boinc_rmdir();
        rather, at the points in the client that delete
        dirs that are usually owned by boinc_projects,
        call remove_project_owned_file_or_dir() first,
        then clean_out_dir().
    - rename boinc_exec() to switcher_exec() and move it to sandbox.C

Note: this change was sparked by needing to remove a call to getgrnam()
from boinclib, to avoid requiring the same version of glibc
on both compile and target hosts

svn path=/trunk/boinc/; revision=13784
2007-10-05 16:47:07 +00:00
David Anderson cbe14c89fa - finished up the above
svn path=/trunk/boinc/; revision=13693
2007-09-27 21:28:32 +00:00
David Anderson aadcc979cd - client: first pass at fixing a fundamental design flaw:
there's a single GUI_HTTP object,
    and it works only if used sequentially,
    i.e. an op is started only after the previous one ends.
    This breaks if a GUI RPC triggerse and op while
    a project-list fetch (initiated by the client itself) is in progress.
    Or if two managers are connected at the same time,
    and both do HTTP ops.
    The solution: have a separate GUI_HTTP object for each GUI_RPC_CONN,
    and an additional one for use by the client itself.

svn path=/trunk/boinc/; revision=13692
2007-09-27 21:03:15 +00:00
David Anderson f1f5930579 - client: removed everything related to screensaver
(deciding which app to use, implementing blanking interval, etc.)
    This logic is all now in the screensaver itself.
- GUI RPC: removed get/set screensaver mode RPCs
- API: added a "backwards_compatible_graphics" flag to BOINC_OPTIONS.
    V6 apps should set this.
    If set, the runtime library checks for graphics messages
    from the client, and launches/kills the graphics app (if any).
    The app will then work graphically with pre-V6 clients.
- removed some old files

svn path=/trunk/boinc/; revision=13651
2007-09-25 16:04:45 +00:00
David Anderson eaed993f4c - User web and client: added a new pref "suspend_if_no_recent_input"
that lets you suspend computation after a specified period of idleness.
        This is necessary to allow some machines to go into low-power mode
        when they're not being used.
    - Change the wording of some existing prefs; for example, changed
        "Do work while computer is in use?" to
        "Suspend work while computer is in use".
        The former is confusing - if you say yes, BOINC may in fact
        NOT do work while the computer is in use,
        due to other factors (time of day, etc.)
    TODO: HOST_INFO::users_idle() should be changed so that it
        returns the idle time
        (rather than telling you whether we've been idle for X)

svn path=/trunk/boinc/; revision=13193
2007-07-19 23:22:19 +00:00
David Anderson 79adf59f98 - client: if can't write state file, don't immediately exit,
but don't do anything other than handle GUI RPCs.
    After 50 secs, print an "about to exit" message.
    After 60 seconds, exit

svn path=/trunk/boinc/; revision=13162
2007-07-16 20:30:21 +00:00
David Anderson b9d7ecdc1a - client: run_if_user_active pref applies to both
network transfers and CPU usage.
    (Note: maybe we should have a separate pref for this).

svn path=/trunk/boinc/; revision=13131
2007-07-10 17:49:51 +00:00
David Anderson cdc65cd283 - Manager: if a job is running EDF, show "high priority" in status
- compile fixes for Charlie's next-to-last checkin
    
    client/
        client_state.h
        cpu_sched.C
        sim.h
        sim_util.C
    clientgui/
        ViewWork.cpp
        ViewWorkGrid.cpp

svn path=/trunk/boinc/; revision=13021
2007-06-25 19:05:29 +00:00
Charlie Fenton 7bb1b1a0d4 CC: Add logic to scheduler, etc. for systems which limit the number of shared memory segments per process and / or system-wide.
svn path=/trunk/boinc/; revision=13015
2007-06-25 11:46:15 +00:00
David Anderson 1e7e58875a - client: add cmdline options --exit_before_start and --exit_after_finish.
This cause the core client to exit immediately before or after
    running a job,
    letting you examine the contents of the slot directory.
- scheduler: changed max # of CPUs used in daily_result_quota
    limit from 4 to 8, and make it a compile-time parameter
- feeder/scheduler: make the number of work items in shared
    memory configurable (in config.xml).
    The element is <shmem_work_items>
- feeder: make the size of the work item query configurable
    (<feeder_query_size)
- feeder: remove code related to removing infeasible results
    from shared mem.
    This mechanism was never needed,
    and I think a timeout would accomplish the same effect.

client/
    app.C
    app_start.C
    client_state.C,h
    cs_cmdline.C
sched/
    feeder.C
    sched_array.C
    sched_config.C,h
    sched_send.C
    sched_shmem.C,h
    sched_util.C
    show_shmem.C

svn path=/trunk/boinc/; revision=12771
2007-05-29 21:45:01 +00:00
David Anderson 5bbcc6b3b6 - client: fix bug where:
1) client wakes up from hibernate
    2) one or more network ops start (e.g. because backoff expired)
    3) ops fail because DNS system isn't up yet
    4) connect to reference site fails too
    5) user sees "please create physical connection",
        even though there's been a physical connection the whole time.
    Solution:
    - keep track of "last wakeup time": the last time the
        time of day (measured in poll_slow_events())            increased by more than 10 times the polling interval.
        This must be either coming out of hibernation,
        or the user resetting the system clock.
    - When a network operation fails, try to contact the reference site
        only if it's more than 30 seconds after the last wakeup time.

client/
    client_state.C,h
    net_stats.C

svn path=/trunk/boinc/; revision=12665
2007-05-14 21:45:02 +00:00
David Anderson bd8b0aed41 - core client: on attach to project,
if the initial sched request failed,
		the manager would show "communicating" for 60 sec,
		then time out and show "failed to attach".
		But the project would actually be attached.
		This was due to a logic error,
		but I fixed it in a more fundamental way:
		by considering an attach to be complete immediately,
		without waiting for a successful scheduler RPC.

		This was originally done to ensure that the URL and account key were valid.
		But when using the BOINC Manager, we've already verified
		both of these before doing the attach project RPC.

		When using boinc_cmd, you now have to check for messages
		indicating a bad URL or account key.
		I changed things to print these messages on every sched RPC.

		Implementation: the notion of "tentative project" no longer exists.

	client/
		client_state.C,h
		client_types.C,h
		cs_account.C
		cs_benchmarks.C
		cs_scheduler.C
		gui_rpc_server_ops.C
		scheduler_op.C
		sim.C
		sim_util.C

svn path=/trunk/boinc/; revision=12663
2007-05-14 19:18:45 +00:00
David Anderson 2853649d28 - core client: add <no_alt_platform> config option;
eliminates use of alternate platforms.

    client/
        client_state.h
        cs_platforms.C
        cs_statefile.C
        log_flags.C,h

svn path=/trunk/boinc/; revision=12600
2007-05-07 19:38:27 +00:00