`hdr_value_at_percentile()` is part of the Hdr_Histogram library
used when generating `latencystats` report.
There's a pending optimization for this function which greatly
affects the performance of `info latencystats`.
https://github.com/HdrHistogram/HdrHistogram_c/pull/107
This PR:
1. Upgrades the sources in _deps/hdr_histogram_ to the latest Hdr_Histogram
version 0.11.5
2. Applies the referenced optimization.
3. Adds minor documentation about the hdr_histogram dependency which was
missing under _deps/README.md_.
benchmark on my machine:
running: `redis-benchmark -n 100000 info latencystats` on a clean build with no data.
| benchmark | RPS |
| ---- | ---- |
| before upgrade to v0.11.05 | 7,681 |
| before optimization | 12,474 |
| after optimization | 52,606 |
Co-authored-by: filipe oliveira <filipecosta.90@gmail.com>
# Short description
The Redis extended latency stats track per command latencies and enables:
- exporting the per-command percentile distribution via the `INFO LATENCYSTATS` command.
**( percentile distribution is not mergeable between cluster nodes ).**
- exporting the per-command cumulative latency distributions via the `LATENCY HISTOGRAM` command.
Using the cumulative distribution of latencies we can merge several stats from different cluster nodes
to calculate aggregate metrics .
By default, the extended latency monitoring is enabled since the overhead of keeping track of the
command latency is very small.
If you don't want to track extended latency metrics, you can easily disable it at runtime using the command:
- `CONFIG SET latency-tracking no`
By default, the exported latency percentiles are the p50, p99, and p999.
You can alter them at runtime using the command:
- `CONFIG SET latency-tracking-info-percentiles "0.0 50.0 100.0"`
## Some details:
- The total size per histogram should sit around 40 KiB. We only allocate those 40KiB when a command
was called for the first time.
- With regards to the WRITE overhead As seen below, there is no measurable overhead on the achievable
ops/sec or full latency spectrum on the client. Including also the measured redis-benchmark for unstable
vs this branch.
- We track from 1 nanosecond to 1 second ( everything above 1 second is considered +Inf )
## `INFO LATENCYSTATS` exposition format
- Format: `latency_percentiles_usec_<CMDNAME>:p0=XX,p50....`
## `LATENCY HISTOGRAM [command ...]` exposition format
Return a cumulative distribution of latencies in the format of a histogram for the specified command names.
The histogram is composed of a map of time buckets:
- Each representing a latency range, between 1 nanosecond and roughly 1 second.
- Each bucket covers twice the previous bucket's range.
- Empty buckets are not printed.
- Everything above 1 sec is considered +Inf.
- At max there will be log2(1000000000)=30 buckets
We reply a map for each command in the format:
`<command name> : { `calls`: <total command calls> , `histogram` : { <bucket 1> : latency , < bucket 2> : latency, ... } }`
Co-authored-by: Oran Agra <oran@redislabs.com>
A first step to enable a consistent full percentile analysis on query latency so that we can fully understand the performance and stability characteristics of the redis-server system we are measuring. It also improves the instantaneous reported metrics, and the csv output format.
