You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When futures are spawned on a worker (called source worker), all but 1 (or until time < highwatermark) are sent to the broker. However, if there was a previously running job on this source worker, there would also be a pending task request from this worker at the broker queue. This means that of the spawned futures, it is highly likely (especially if #jobs = #workers) that 2 are executed on the source worker even when they could have been executed separately. for simulations that are small and numerous, this makes little difference, but for simulations that are long, this doubles the execution time.
I propose the following fix (will be implemented in pull request #67):
Send ALL futures spawned to the broker
Maintain an explicit one-one correspondence between requests sent and futures received. i.e. do not spam future requests.
The text was updated successfully, but these errors were encountered:
maharjun
added a commit
to IGITUGraz/scoop
that referenced
this issue
Jun 16, 2017
Made the following changes
1. Added a new function append_init which is used by futures.submit.
This function adds newly spawned futures to the broker's task
queue.
2. Added new state variable request_in_process to the FutureQueue
object in order to track the state of the future request. This is
used to track the state of a future request so that a future
request is sent iff the previous future request has been answered
3. Also, replaced function recvFutures with recvIncoming which passes
the received incoming messages back to updateQueue where they are
processed. Changed _recv to only perform preprocessing of the
messages.
When futures are spawned on a worker (called source worker), all but 1 (or until time < highwatermark) are sent to the broker. However, if there was a previously running job on this source worker, there would also be a pending task request from this worker at the broker queue. This means that of the spawned futures, it is highly likely (especially if #jobs = #workers) that 2 are executed on the source worker even when they could have been executed separately. for simulations that are small and numerous, this makes little difference, but for simulations that are long, this doubles the execution time.
I propose the following fix (will be implemented in pull request #67):
The text was updated successfully, but these errors were encountered: