Skip to content

Add proxy/dequeuer CPU and memory requests #2252

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
Jun 17, 2021
Merged

Add proxy/dequeuer CPU and memory requests #2252

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
afecf50
Add proxy/dequeuer resource requests
deliahu Jun 16, 2021
c5ebb86
Update docs
deliahu Jun 16, 2021
0ba24c4
Fix lint
deliahu Jun 16, 2021
954535a
Improve formatting
deliahu Jun 17, 2021
030efb2
Improve formatting
deliahu Jun 17, 2021
5625980
Use power of 2 resource requests in examples
deliahu Jun 17, 2021
58e4949
Address PR comments
deliahu Jun 17, 2021
a17e31a
Merge branch 'master' of github.com:cortexlabs/cortex into proxy-reso…
deliahu Jun 17, 2021
2ae3dca
Merge branch 'master' into proxy-resource-request
deliahu Jun 17, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update docs
  • Loading branch information
@deliahu
deliahu committed Jun 16, 2021
commit c5ebb86cb91a4d1ede288df15777b595291fbabe
4 changes: 4 additions & 0 deletions docs/workloads/async/containers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,10 @@ Your API pod can contain multiple containers, only one of which can be listening

The `/mnt` directory is mounted to each container's filesystem, and is shared across all containers.

## Resource requests

Each container in the pod requests its own amount of CPU, memory, GPU, and Inferentia resources. In addition, Cortex's dequeuer sidecar container (which is automatically added to the pod) requests 100m CPU and 100Mi memory.

## Observability

See docs for [logging](../../clusters/observability/logging.md), [metrics](../../clusters/observability/metrics.md), and [alerting](../../clusters/observability/metrics.md).
Expand Down
4 changes: 4 additions & 0 deletions docs/workloads/batch/containers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,10 @@ Your API pod can contain multiple containers, only one of which can be listening

The `/mnt` directory is mounted to each container's filesystem, and is shared across all containers.

## Resource requests

Each container in the pod requests its own amount of CPU, memory, GPU, and Inferentia resources. In addition, Cortex's dequeuer sidecar container (which is automatically added to the pod) requests 100m CPU and 100Mi memory.

## Observability

See docs for [logging](../../clusters/observability/logging.md), [metrics](../../clusters/observability/metrics.md), and [alerting](../../clusters/observability/metrics.md).
Expand Down
4 changes: 4 additions & 0 deletions docs/workloads/realtime/containers.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,10 @@ Your API pod can contain multiple containers, only one of which can be listening

The `/mnt` directory is mounted to each container's file system, and is shared across all containers.

## Resource requests

Each container in the pod requests its own amount of CPU, memory, GPU, and Inferentia resources. In addition, Cortex's proxy sidecar container (which is automatically added to the pod) requests 100m CPU and 100Mi memory.

## Observability

See docs for [logging](../../clusters/observability/logging.md), [metrics](../../clusters/observability/metrics.md), and [alerting](../../clusters/observability/metrics.md).
Expand Down