Re-implement the prefetcher using backpressure mechanism #980
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
The prefetcher now uses only one GetObject request to fetch data in advance. This request has a range of entire object but use backpressure mechanism to control how much data it wants to fetch into the part queue instead of spawning up to two requests in parallel. This should make the throughput more stable because previously the two request tasks could compete with each other when fetching data from S3. Also, it will be easier to control how much data we want to store in the part queue. Signed-off-by: Monthon Klongklaew <[email protected]>
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
passaro
reviewed
Aug 14, 2024
vladem
reviewed
Aug 14, 2024
monthonk
force-pushed
the
backpressure_prefetch
branch
from
65c7f26
to
a0d02d7
Compare
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR benchmarks
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR benchmarks
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR benchmarks
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR benchmarks
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR benchmarks
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
had a problem deploying
to
PR integration tests
GitHub Actions
Failure
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
passaro
reviewed
Aug 15, 2024
…st is already completed Signed-off-by: Monthon Klongklaew <[email protected]>
vladem
reviewed
Aug 15, 2024
Signed-off-by: Monthon Klongklaew <[email protected]>
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
monthonk
temporarily deployed
to
PR integration tests
GitHub Actions
Inactive
passaro
approved these changes
Aug 15, 2024
| // This should not block since the channel is unbounded | ||
| self.read_window_updater | ||
| let _ = self |
There was a problem hiding this comment.
nit: since we are not returning the error, I'd rather use an explicit if let Err.. to trace instead of inspect_err. Not blocking on this though.
vladem
approved these changes
Aug 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.
Description of change
The prefetcher now uses only one
GetObjectrequest to fetch data in advance. This request has a range of entire object but use backpressure mechanism to control how much data it wants to fetch into the part queue instead of spawning up to two requests in parallel.This should make the throughput more stable because previously the two request tasks could compete with each other when fetching data from S3. Also, it will be easier to control how much data we want to store in the part queue.
Related: #987
Does this change impact existing behavior?
No, the change only for internal interface.
Does this change need a changelog entry in any of the crates?
No
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license and I agree to the terms of the Developer Certificate of Origin (DCO).