pipeline-manager: share an awc::Client instance instead of creating one per ingress/egress stream #1257
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ne per ingress/egress stream We've been seeing a repeatable issue with our deployments where demos generating high HTTP ingress/egress traffic load, eventually hit a 502 bad gateway error in the cloud form factor. Repeating such a workload against a local instance of the pipeline manager revealed the issue: we we were creating too many connections from the pipeline-manager when forwarding HTTP streams, which in turn led to resource exhaustion. This was because we were creating a new awc::Client instance per stream to forward HTTP streams to the pipeline. The awc::Client::new() documentation is clear that we should be creating at most one instance of the client per thread (and we were definitely not respecting that). This PR fixes this issue by sharing one instance of an awc::Client per actix server. Signed-off-by: Lalith Suresh <lalith@feldera.com>
lalithsuresh
force-pushed
the
http-perf
branch
from
18c48db
to
243de84
Compare
mihaibudiu
approved these changes
Jan 15, 2024
snkas
approved these changes
Jan 15, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We've been seeing a repeatable issue with our deployments where demos
generating high HTTP ingress/egress traffic load, eventually hit a 502
bad gateway error in the cloud form factor.
Repeating such a workload against a local instance of the pipeline
manager revealed the issue: we we were creating too many connections
from the pipeline-manager when forwarding HTTP streams, which in turn
led to resource exhaustion. This was because we were creating a new
awc::Client instance per stream to forward HTTP streams to the pipeline.
The awc::Client::new() documentation is clear that we should be
creating at most one instance of the client per thread (and we were
definitely not respecting that).
This PR fixes this issue by sharing one instance of an awc::Client
per actix server.
Signed-off-by: Lalith Suresh lalith@feldera.com
Is this a user-visible change (yes/no): yes