Liking cljdoc? Tell your friends :D

qbits.alia.policy.speculative-execution


cluster-wide-percentile-trackerclj

(cluster-wide-percentile-tracker {:keys [highest-trackable-latency-millis]
                                  :as opts})

A PercentileTracker that aggregates all measurements into a single histogram.

This gives you global latency percentiles for the whole cluster, meaning that latencies of slower hosts will tend to appear in higher percentiles.

A `PercentileTracker` that aggregates all measurements into a single
histogram.

This gives you global latency percentiles for the whole cluster, meaning that
latencies of slower hosts will tend to appear in higher percentiles.
raw docstring

constant-speculative-execution-policyclj

(constant-speculative-execution-policy constant-delay-ms
                                       max-speculative-executions)

A SpeculativeExecutionPolicy that schedules a given number of speculative executions, separated by a fixed delay.

A SpeculativeExecutionPolicy that schedules a given number of
speculative executions, separated by a fixed delay.
raw docstring

makecljmultimethod


map->constant-speculative-execution-policyclj

(map->constant-speculative-execution-policy
  {:keys [constant-delay-millis max-speculative-executions]})

map->percentile-speculative-execution-policyclj

(map->percentile-speculative-execution-policy tracker
                                              {:keys [percentile
                                                      max-executions]})

no-speculative-execution-policyclj

(no-speculative-execution-policy)

A SpeculativeExecutionPolicy that never schedules speculative executions.

A SpeculativeExecutionPolicy that never schedules speculative executions.
raw docstring

per-host-percentile-trackerclj

(per-host-percentile-tracker {:keys [highest-trackable-latency-millis]
                              :as opts})

A PercentileTracker that maintains a separate histogram for each host.

This gives you per-host latency percentiles, meaning that each host will only be compared to itself.

A `PercentileTracker` that maintains a separate histogram for each host.

This gives you per-host latency percentiles, meaning that each host will
only be compared to itself.
raw docstring

percentile-speculative-execution-policyclj

(percentile-speculative-execution-policy percentile-tracker
                                         percentile
                                         max-speculative-executions)

A policy that triggers speculative executions when the request to the current host is above a given percentile. This class uses a PerHostPercentileTracker that must be registered with the cluster instance

A policy that triggers speculative executions when the request to
the current host is above a given percentile. This class uses a
PerHostPercentileTracker that must be registered with the cluster
instance
raw docstring

percentile-trackerclj

(percentile-tracker builder
                    {:keys [interval min-recorded-values
                            significant-value-digits]})

A LatencyTracker that records query latencies over a sliding time interval, and exposes an API to retrieve the latency at a given percentile.

It uses HdrHistogram to record latencies: for each category, there is a "live" histogram where current latencies are recorded, and a "cached", read-only histogram that is used when clients call getLatencyAtPercentile(Host, Statement, Exception, double). Each time the cached histogram becomes older than the interval, the two histograms are switched. Statistics will not be available during the first interval at cluster startup, since we don't have a cached histogram yet.

A `LatencyTracker` that records query latencies over a sliding time interval,
and exposes an API to retrieve the latency at a given percentile.

It uses `HdrHistogram` to record latencies: for each category, there is a
"live" histogram where current latencies are recorded, and a "cached",
read-only histogram that is used when clients call
`getLatencyAtPercentile(Host, Statement, Exception, double)`. Each time
the cached histogram becomes older than the interval, the two histograms
are switched. Statistics will not be available during the first interval
at cluster startup, since we don't have a cached histogram yet.
raw docstring

cljdoc is a website building & hosting documentation for Clojure/Script libraries

× close