From 48edbef5b4d9b204110c0542615dbd7084e5c767 Mon Sep 17 00:00:00 2001 From: Martin Czygan Date: Thu, 22 Oct 2020 00:45:45 +0200 Subject: add performance data point --- fuzzycat/cluster.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fuzzycat/cluster.py b/fuzzycat/cluster.py index 26615df..a28cf58 100644 --- a/fuzzycat/cluster.py +++ b/fuzzycat/cluster.py @@ -20,6 +20,12 @@ Example output: "c": "t" } +Performance data points: + +$ time zstdcat -T0 release_export_expanded.json.zst | pv -l | \ + parallel --roundrobin --pipe -j 16 fuzzycat-cluster /bigger/tmp -t title > cluster_title.json + +Takes 607 min (around 3800 docs/s). """ import argparse -- cgit v1.2.3