pointers to dynamically allocated COPROC-derived objects,
just have the objects themselves.
Dynamic allocation should be avoided at all costs.
svn path=/trunk/boinc/; revision=21564
Add more info to "project in-progress job list".
Old: entries included only job name and app plan class;
this was used to resend lost jobs,
and to count the # of CPU and GPU jobs.
But it's not usable e.g. for per-app in-progress limits.
New: send the client's app versions (including usage info)
and for each in-progress job, which app version it uses.
(This reduces request-message size compared with sending
usage info and app name per job).
- client and scheduler RPC:
Add more info to "all in-progress job list", and make it optional.
This list is used by schedulers that do deadline checks
using EDF workload simulation.
Old: the list is always sent, and it contains no info
about job resource usage
New: the list is sent only if the scheduler asked for it
in a previous reply,
and each entry now contains resource usage (CPU, GPUs)
Note: the scheduler's EDF simulator is outdated;
it doesn't know about GPU jobs.
But we may as well get the info in place.
svn path=/trunk/boinc/; revision=21513
and <ati_backoff> elements to scheduler reply.
These specify backoffs for the resource types,
overriding the existing backoff mechanism.
Projects can supply these if they don't have apps of a particular type
and don't want to get periodic requests for them.
svn path=/trunk/boinc/; revision=19059
e.g. the Milkyway@home ATI app, of which we can typically run
2 or 3 instances at once on a GPU.
Changes include:
- In APP_VERSION, don't use a COPROCS to represent the GPU
requirements; just use doubles ncudas and natis.
- sufficient_coprocs() etc. are no longer members of COPROCS
- in HOST_USAGE, ncudas and natis are doubles
- in scheduler request, req_instances is now a double
This checkin doesn't include the job scheduling logic,
i.e. assigning jobs to GPUs. That will follow.
svn path=/trunk/boinc/; revision=18868
- client: show times correctly in rr_sim debug msgs
- client: in "requesting new tasks" msg,
say what resources we're requesting (if there's more than CPU)
- client: estimated delay was possibly being calculated incorrectly
because of roundoff error
svn path=/trunk/boinc/; revision=18269
Instead, write the info into a file in the slot directory,
and check for these files on startup.
This should reduce the overhead of state-file writing
on machines with lots of cores.
There will still be a flurry of writes each time a job finishes,
but reducing that overhead would be a larger job.
- client: make sure we write the state file after a failed RPC
svn path=/trunk/boinc/; revision=17814
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=17503
to ask for work inappropriately,
and tell user that it wasn't asking for work.
Here's what was going on:
There are two different structures with work request fields
(req_secs, req_instances, estimated_delay):
COPROC_CUDA *coproc_cuda
and
RSC_WORK_FETCH cuda_work_fetch.
WORK_FETCH::choose_project() copied from cuda_work_fetch to coproc_cuda,
but only if a project was selected.
WORK_FETCH::clear_request() clears cuda_work_fetch but not coproc_cuda.
Scenario:
- a scheduler op is made to project A requesting X>0 secs of CUDA
- later, a scheduler op is made to project B for reason
other than work fetch (e.g., user request)
- choose_project() doesn't choose anything,
so the value of coproc_cuda->req_secs remains X
- clear_request() is called but that doesn't change *coproc_cuda
Solution: work-fetch code no longer knows about internals of
COPROC_CUDA and is not responsible for settings its request fields.
The copying of request fields from RSC_WORK_FETCH to COPROC
is done at a higher level,
in CLIENT_STATE::make_scheduler_request()
Additional bug fix: estimated_delay wasn't being cleared in some cases.
svn path=/trunk/boinc/; revision=17411
this gets called when the op fails, either at initialization or later on;
it clears the project's sched_rpc_pending flag if needed.
This fixes a bug that caused user-requested RPCs to retry every 10 seconds
when the network is down.
- client: if debt-adjust period is too long, reset accounting.
Otherwise we'll get this infinitely.
- API: all optional alpha argument to TEXTURE_DESC::draw()
svn path=/trunk/boinc/; revision=17195
- client: if a project-requested RPC doesn't return work,
don't do resource backoff.
- client: if a user-requested scheduler RPC errors out, clear the request
svn path=/trunk/boinc/; revision=17191
David Anderson