v0.0.33: Merge pull request #49 from elandau/feature/error_supplier

Fix javadoc typo

v0.0.32: Merge pull request #48 from elandau/feature/error_supplier

Fix typo

Pluggable GRPC error and metadata

Merge pull request #47 from elandau/feature/error_supplier

Make the GRPC status and metadata generation pluggable

noload RTT smoothing

Merge pull request #46 from elandau/feature/noload_rtt_smoothing

feature: gradient noload rtt smoothing

v0.0.29: Merge pull request #44 from elandau/feature/vegas_slow_start

• Add probing to VegasLimit
• Simplify probing configuration
• TCP slow-start like behavior for VegasLimit

v0.0.28: Merge pull request #42 from elandau/bugfix/noload_rtt_probing

• Fix bug filtering sample window for high noload RTT
• Continue using the existing sample window when it fails the filter to avoid starving the algorithm
• Set limit to queueSize when probing for minRtt
• Add GRPC example

Fix precondition

Merge pull request #41 from elandau/bugfix/bad_precondition

Fix bad precondition check

v0.0.26

• Better tracking of RTT noLoad
• For the 'gradient' limiter allow for probing for an up to date noload RTT
• Less aggressive min rtt threshold of (1 us) now that we can probe for better RTT
• Make the sample window size relative to the last min RTT and not the absolute min RTT to get a more meaningful sample size
• Track metrics as distributions and not gauges for better visibility
• Capture data from sample window in a single immutable class
• Fix Vegas smoothing
• Fix Vegas smoothing and set default to 1.0
• Fix partitionByPathInfo

v0.0.25: Merge pull request #40 from elandau/bugfix/fix_javadocs

• Better tracking of RTT noLoad
• For the 'gradient' limiter allow for probing for an up to date noload RTT
• Less aggressive min rtt threshold of (1 us) now that we can probe for better RTT
• Make the sample window size relative to the last min RTT and not the absolute min RTT to get a more meaningful sample size
• Track metrics as distributions and not gauges for better visibility
• Capture data from sample window in a single immutable class
• Fix Vegas smoothing
• Fix Vegas smoothing and set default to 1.0
• Fix partitionByPathInfo

Better tracking of RTT noLoad

• For the 'gradient' limiter allow for probing for an up to date noload RTT
• Less aggressive min rtt threshold of (1 us) now that we can probe for better RTT
• Make the sample window size relative to the last min RTT and not the absolute min RTT to get a more meaningful sample size
• Track metrics as distributions and not gauges for better visibility