luxolus
/
open-nomad
2
0
Fork 0
Code Issues 1 Pull Requests Packages Releases Wiki Activity

Added info about scheduler fail and success cases

This commit is contained in:
Charlie Voiselle 2019-05-09 14:53:45 -04:00
parent 0d572b7cbe
commit 7ca1a9cee2
1 changed files with 26 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
website/source/docs/schedulers.html.md
View File

@ -6,6 +6,11 @@ description: |-
Learn about Nomad's various schedulers.
---
[Borg]: https://research.google.com/pubs/pub43438.html
[preemption]: /docs/internals/scheduling/preemption.html
[restart]: /docs/job-specification/restart.html
[reschedule]: /docs/job-specification/reschedule.html
# Schedulers
Nomad has three scheduler types that can be used when creating your job:
@ -17,10 +22,15 @@ each of these schedulers.
The `service` scheduler is designed for scheduling long lived services that
should never go down. As such, the `service` scheduler ranks a large portion
of the nodes that meet the job's constraints and selects the optimal node to
place a task group on. The `service` scheduler uses a best fit scoring algorithm influenced by Google's work on
[Borg](https://research.google.com/pubs/pub43438.html). Ranking this larger set of candidate nodes
increases scheduling time but provides greater guarantees about the optimality
of a job placement, which given the service workload is highly desirable.
place a task group on. The `service` scheduler uses a best fit scoring algorithm
influenced by Google's work on [Borg]. Ranking this larger set of candidate
nodes increases scheduling time but provides greater guarantees about the
optimality of a job placement, which given the service workload is highly
desirable.
Service jobs will be considered failed by Nomad upon failure or exit
regardless of exit code and and handled according to the job's [restart]
and [reschedule] stanzas.
## Batch
@ -28,9 +38,13 @@ Batch jobs are much less sensitive to short term performance fluctuations and
are short lived, finishing in a few minutes to a few days. Although the `batch`
scheduler is very similar to the `service` scheduler, it makes certain
optimizations for the batch workload. The main distinction is that after finding
the set of nodes that meet the job's constraints it uses the power of two choices
described in Berkeley's Sparrow scheduler to limit the number of nodes that are
ranked.
the set of nodes that meet the job's constraints it uses the power of two
choices described in Berkeley's Sparrow scheduler to limit the number of nodes
that are ranked.
Successful Batch jobs–having an exit code of 0–will not be restarted/rescheduled
by Nomad. All other cases will be considered failures and handled
according to the job's [restart] and [reschedule] stanzas.
## System
@ -47,5 +61,8 @@ service discovery and more.
Since Nomad 0.9, the system scheduler will preempt eligible lower priority
tasks running on a node if there isn't enough capacity to place a system job.
See [preemption](/docs/internals/scheduling/preemption.html) for details on how
tasks that get preempted are chosen.
See [preemption] for details on how tasks that get preempted are chosen.
Service jobs will be considered failed by Nomad upon failure or exit, **except
when preempted**, regardless of exit code and and handled according to the
job's [restart] and [reschedule] stanzas.