The limit on jobs in progress is now
max_wus_in_progress * NCPUS
+ max_wus_in_progress * NGPUS
where NCPUS and NGPUS reflect prefs and are capped.
Furthermore: if the client reports plan class for in-progress jobs
(see checkin of 31 May 2009)
then these limits are enforced separately;
i.e. the # of in-progress CPU jobs is <= max_wus_in_progress*NCPUS,
and the # of in-progress GPU jobs is <= max_wus_in_progress_gpu*NGPUS
- scheduler config: rename <cuda_multiplier> to <gpu_multiplier>
- scheduler: <max_wus_to_send> is now scaled by
(NCPUS + gpu_multiplier*NGPUS)
- scheduler: don't keep scanning array if !work_needed()
- scheduler: moved array-scan logic from sched_send.cpp to sched_array.cpp
- scheduler: don't say "no work available" if jobs are available
but work_needed() is initially false
svn path=/trunk/boinc/; revision=18255
Otherwise, if an app version has a platform different from
the client's primary platform, the client won't find it.
svn path=/trunk/boinc/; revision=17508
Old: although the request message contained all info
about the app version (flops, coproc usage etc.)
the server ignored this info,
and assumed that all anonymous platform apps where CPU.
With 6.6 client, this could produce infinite work fetch:
- client uses anon platform, has coproc app
- client has idle CPU, requests CPU work
- scheduler sends it jobs, thinking they will be done by CPU app
- client asks for more work etc.
New: scheduler parses full info on anon platform app versions:
plan class, FLOPS, coprocs.
It uses this info to make scheduling decisions;
in particular, if the request is for CUDA work,
if will only send jobs that use a CUDA app version.
The <result> records it returns contain info
(plan_class) that tells the client which app_version to use.
This will work correctly even if the client has multiple app versions
for the same app (e.g., a CPU version and a GPU version)
svn path=/trunk/boinc/; revision=17506
when to do a scheduler RPC:
if user request or acct mgr request, ignore backoff and suspend via GUI;
in all other cases honor both of these.
svn path=/trunk/boinc/; revision=17504
There are two mechanisms to prevent the scheduler from
sending jobs that won't finish by their deadline.
Simple mechanism:
The client sends the interval x for which CPUs are projected
to be saturated.
Given a job with estimated duration y,
the scheduler doesn't send it if x + y exceeds the delay bound.
If it does send it, x is incremented by y.
Complex mechanism:
Client sends workload description.
Scheduler does EDF simulation, sees if deadlines are missed.
The only project using this AFAIK is BOINC alpha test.
Neither of these mechanisms takes coprocessors into account,
and as a result jobs could be sent that are doomed to
miss their deadline.
This checkin adds coprocessor awareness to the Simple mechanism.
Changes:
Client:
compute estimated delay (i.e. time until non-saturation)
for coprocessors as well as CPU.
Send them in scheduler request as part of coproc descriptor.
Scheduler:
Keep track of estimated delays separately for different resources
- client: fixed bug that computed CPU estimated delay incorrectly
- client: the work request (req_secs) for a resource is the min
of the project's share and the shortfall.
svn path=/trunk/boinc/; revision=17086
and add <cuda_multiplier>.
The latter is used in calculating max jobs/day for a host;
namely, it's host.max_results_day * (NCPUS + NCUDA*cuda_multiplier).
Set it to 10 or so if you have CUDA apps.
- scheduler: don't overload effective_ncpus();
instead, add two new functions,
max_results_day_multiplier() and max_wus_in_progress_multiplier()
- scheduler: don't reduce max_results_day if we get an aborted job
(it might have been aborted by the project;
not appopriate to punish host in this case)
svn path=/trunk/boinc/; revision=16959
- parse new request message elements
(CPU and coproc requested seconds and instances)
- decide how many jobs to send based on these params
- select app version based on these params
(may send both CPU and CUDA app versions for the same app!)
svn path=/trunk/boinc/; revision=16861
for the selected APP_VERSION, rather than on the CPU benchmarks.
Otherwise estimates are wrong for GPU or multi-thread apps.
- scheduler: start switching from having SCHED_REQUEST and
SCHED_REPLY as globals instead of passing them around as args;
to be continued.
svn path=/trunk/boinc/; revision=16691
because we don't have any (matchmaker only).
- back end programs: for programs that do enumerations,
check for error returns and exit
(otherwise we'll get stuck forever if DB fails)
NOTE: In the course of researching this I came across a bug
in the transitioner: if there's a WU with more than 1000 results,
the enumeration will always return ERR_DB_NOT_FOUND,
and the transitioner won't ever do anything again.
Fixing this is a little tricky, so I'm not going to do it right now.
svn path=/trunk/boinc/; revision=16324
If set the "effective NCPUS" (which is used to scale
daily_result_quota and max_wus_in_progress)
is max'd with the # of CUDA GPUs.
svn path=/trunk/boinc/; revision=16246
saying "no work was available for the apps you requested"
with locality scheduling (i.e. Einstein@home)
even if the user hasn't select apps.
Note: the logic for printing these messages won't work
for matchmaker scheduling.
svn path=/trunk/boinc/; revision=15847
- 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
set the timestamp of the thread to the timetamp of
the latest non-hidden post (rather than to now).
Same thing for forum timestamp.
- scheduler: return more informative message to user in case of
request message parse error
svn path=/trunk/boinc/; revision=15526
Keep track of the "easiest" job that has been rejected by EDF sim.
Any jobs harder than this one can be rejected without doing the sim.
svn path=/trunk/boinc/; revision=15171
Merge redundant messages.
Condition various messages on config flags.
- client (Unix) fix to CUDA detection if LD_LIBRARY_PATH is ""
svn path=/trunk/boinc/; revision=15122
send <client_cap_plan_class/> if client understands
app version plan class.
The server checks for this instead of version > 6.11.
- clean up unix_util: .h files declare only (extern) interfaces;
no reason for daemon() to be C
svn path=/trunk/boinc/; revision=15006
and change the correspending structure field from 64KB to 256KB
(could increase this if needed).
This is needed to handle app versions with lots (> 100) of files
- change LARGE_BLOB_SIZE to BLOB_SIZE a bunch of places
- Change COPROCS from vector<COPROC> to vector<COPROC*>.
Otherwise the right virtual functions of COPROCs don't get called
svn path=/trunk/boinc/; revision=14986
- 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
- DB code: remove "is_high_priority" stuff.
- scheduler: merge find_app_version() into get_app_version().
Have the latter memoize its results (both positive and negative).
Have it call app_plan() for apps with nonempty plan_class.
- scheduler: first steps towards improved selectability of log messages.
It will eventually be like the client,
where you can select among various types of messages.
- feeder: if can't unlink the reread_db trigger file, exit
(else we'd go into an infinite loop)
svn path=/trunk/boinc/; revision=14940
to allow validator to assign different credit
to different instances of a job
- Scheduler: if can't open DB, return <project_is_down/>
(fixes#578)
- clean up logic of modify_claimed_credit
- feeder: for -priority_order_create_time, use workunitid
rather than create time (faster for the DB)
from Kevin Reed
svn path=/trunk/boinc/; revision=14908
and apps that use coprocessors.
There now can be several app_versions for the same
(app, platform, version_num) combination.
This changes a number of things.
- Added app_version.plan_class field to DB
- update_versions now looks for a :plan-class in the
file or directory name, and puts it in the app_version's DB record
- Change uniqueness constraint to include plan_class
- Feeder: the feeder was putting non-deprecated app_versions
in shared mem, and leaving it to the scheduler to
find the latest version for a given platform.
This is dumb.
Instead, for each app/platform pair the feeder now
finds the highest version number of a non-deprecated app version,
and enumerates all non-deprecated app_versions with that
app/platform/version
- Scheduler: add a BEST_APP_VERSION data structure that keeps track,
for each app, what the best app_version is for this host.
This saves the work of recomputing it for each job.
svn path=/trunk/boinc/; revision=14906
The design has been changed to constant #threads per app version
Various changes from Kevin Reed/WCG:
- server: add workunit.rsc_bandwidth_bound: if nonzero,
send this WU only to hosts with that much download bandwidth
- assimilators: if a handler returns DEFER_ASSIMILATION,
the WU remains in INIT state and will be handled when the
next instance completes.
Useful if you want the assimilator to see all instances.
- scheduler: when setting result.outcome = DETACHED,
set received_time to now
- scheduler: removed the reliable_time and reliable_min_avg_credit
options
- scheduler/web: add optional <allow_non_preferred_projects>
in project preferences.
If present, user will accept work from non-selected apps
if no work is available for selected apps
- scheduler: improved messages for projects with multiple apps
- scheduler: added config options
<granted_credit_weight> and <granted_credit_ramp_up>.
Used in calculating host.claimed_credit_per_cpu_sec,
but I'm not sure how.
- Added two new credit-granting formulas (validate_util.C):
stddev_credit() and two_credit()
- server DB: add rollback_transaction() and affected_rows() to DB_CONN
NOTE: DB update required
svn path=/trunk/boinc/; revision=14870
into a #define's symbol (ASSIGNED_WU_STR)
- scheduler: when send client command to abort a WU,
include a reason code in the scheduler log
svn path=/trunk/boinc/; revision=14798
Lets you assign a WU to a particular host,
to one or all hosts belonging to a user or team, or to all hosts.
See http://boinc.berkeley.edu/trac/wiki/AssignedWork
Disabled unless you include <enable_assignment> in config.xml
Uses a new DB table.
Tested but only a little.
- Server: code cleanup; moved result-handling to a new file,
and removed the PLATFORM_LIST arg to everything
(put it in SCHEDULER_REQUEST instead)
svn path=/trunk/boinc/; revision=14767
- server: limit global prefs mod time to now
These changes address the situation where a server
sends out prefs with mod time far in the future,
and there's no way to undo them
svn path=/trunk/boinc/; revision=14664
This is for debugging apps (currently works only in Unix).
What it does: when running an app,
the client does everything except actually fork/exec the app,
i.e. it sets up the slot dir, creates shared mem segment etc.
It then continues as if the app were actually running,
and you can then manually run your app under a debugger
in the slot directory.
Note: the client won't notice the termination of your app.
- API, Unix: in situations where the timer thread wants to exit
(e.g. it notices a missing heartbeat).
don't directly call boinc_exit(),
since this touches data structures that the worker thread
may be using concurrently.
Instead, set a flag telling the worker thread to call boinc_exit()
(which it will do from its signal handler)
This is an attempt to fix problems reported by Bernd;
I haven't tested it.
- scheduler: add config flag for uploading usage data
- web: show account key and weak account key on user page
- added some code for multithread support (not finished)
api/
boinc_api.C
svn path=/trunk/boinc/; revision=14542
tells the client to use this as the data directory
- scheduler: improve the message telling the client that
more disk or memory is needed;
tell them the minimum amount needed to
send any of the jobs rejected,
rather than the amount needed for the first job rejected
- manager: fix text in "connect now" dialog
svn path=/trunk/boinc/; revision=13387
To do this, set host.max_results_day to -1.
If you do this, scheduler requests from that host
will get an error message, and will otherwise be ignored
(no jobs in or out, no trickles).
- Scheduler: send_message() should be called ONLY if you're
not going to call handle_request();
otherwise we'll write two separate replies.
To fix this, I added a separate function (send_error_message())
that can be called within handle_request()
to deal with error situations.
- Scheduler: moved debug_sched() to main.C
- Scheduler: moved logic to send "delete file" commands
out of handle_request() into a separate function,
send_file_deletes() in sched_locality.C.
Remove #ifdef EINSTEIN_AT_HOMEs; maybe someday another project
will use locality scheduling!
svn path=/trunk/boinc/; revision=13108
"resend_lost_results" option was used also
(because the count of in-progress results was
based from the DB query used by resend_lost_results).
Fix: initialize the count of in-progress results to
the list provided in the scheduler request.
- scheduler: add "--mark_jobs_done" flag; if set, all jobs
sent are marked as done, and their WUs enabled for transition.
This is used for simulation purposes,
in conjunction with sched_driver.
- scheduler: if --batch option is set, don't check RPC seqnos
(for simulation purposes)
svn path=/trunk/boinc/; revision=13101
Limits total # of in-progress results per host
(independently of #CPUs)
sched/
sched_config.C,h
sched_resend.C
sched_send.C
server_types.h
svn path=/trunk/boinc/; revision=12661
David Anderson