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
If set, the scheduler will use EDF simulation,
together with the in-progress workload reported by the client,
to avoid sending results that
1) will miss their deadline, or
2) will cause an in-progress result to miss its deadline, or
3) will make an in-progress result miss its deadline
by more than is already predicted.
If this option is not set, or if the client request doesn't
include a workload description (i.e. the client is old)
use the existing approach, which assumes there's no workload.
NOTE: this is experimental. Production projects should not use it.
- EDF sim: write debug stuff to stderr instead of stdout
- Account manager:
- if an account is detach_when_done, set dont_request_more_work
- check done_request_more_work even for first-time projects
- update_uotd: generate a file for use by Google gadget
- user_links(): use full URLs (so can use in Google gadget)
client/
acct_mgr.C
work_fetch.C
html/
inc/
uotd.inc
util.inc
user/
uotd_gadget.php (new)
sched/
Makefile.am
edf_sim.C
sched_config.C,h
sched_resend.C
sched_send.C,h
server_types.C,h
svn path=/trunk/boinc/; revision=12639
- scheduler: accept elements of the form
<alt_platform>
<name>windows_x86</name>
</alt_platform>
in request messages.
These are platforms that the client can handle,
other than its main one,
listed in order of decreasing preferences.
fixes#81.
sched/
handle_request.C
server_types.C,h
svn path=/trunk/boinc/; revision=12423
WU, I need to separate two types of 'sticky/report on RPC' files.
One type is used for WU names of the form FILE__ and the others
are auxilliary. David, after I've talked with you I'll either
generalize this notion or we can eliminate it.
svn path=/trunk/boinc/; revision=9131
running for a given host. This works by creating a file called
CGI_<HOSTID> in the cgi-bin/ directory, and using Posix advisory file
locking. I have been testing this code for three days and am seeing
*some* invocations of this. David, I'll send details to the dev mailing
list or talk with you about it later this week. Note: this code probably
can be removed in the future, when the core client problems are fixed.
Also note: I don't know if this is compatible with the fast cgi sched.
svn path=/trunk/boinc/; revision=6172
scheduler, and fails to get work because there are N secs
of pending work, then send a delay request of min(3600, N/5) secs.
Otherwise the same host was coming back every hour, without being able
to get additional work.
Implemented by adding a method set_delay() to
SCHEDULER_REQUEST. This sets the delay to the maximum of the
previous requested delay or the current requested delay. The
delay is NEVER set longer than two days.
svn path=/trunk/boinc/; revision=5437
- Ignore CPU limitations and resource share entirely, IF
a host:
(1) has no work for this project
(2) has no results in this sched reply
This ensures that any host that wants to do work will at least
get *something*. It liberalizes slightly David A's approach
from 14 Feb 2005. Eliminate use_time_stats from wreq structure.
- Scheduler changes (locality scheduling only):
- Improve return value info for some functions.
- Modify send_old_work() to accept a t_min < t < t_max time range
- New sched locality algorithm to send work to hosts with no files.
Send oldest result in the time range A < t < B where
B = locality_scheduling_timeout/2
A = B - rand*locality_scheduling_timeout/2
Here rand is a uniformly distributed random number in [0,1].
- When an unsent result is older than locality_scheduling_timeout, no
longer send it to the FIRST host that requests work. Instead send
it to the first host which has a connection speed > 100kb/s.
- Fix file deletion. Previously we were deleting files from hosts
when they got no work for that file. But this might have been
because the work was infeasible (cpu time). Now delete files
from host ONLY if there is no work remaining for that file.
svn path=/trunk/boinc/; revision=5434
Frank Thomas