Created
April 18, 2023 20:16
-
-
Save blzzua/dd263f8ba81c6ae7d5e4b2e97f36ec54 to your computer and use it in GitHub Desktop.
elasticsearch count_size_by_index_pattern.py
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
#!/bin/python3 | |
import re | |
import requests | |
SIZE_SUFFIX = {'tb': 1024*1024*1024*1024,'gb': 1024*1024*1024, 'mb': 1024*1024, 'kb': 1024, 'b': 1} | |
def read_size_data(url='http://127.0.0.1:9200/_cat/indices?h=index,pri.store.size'): | |
response = requests.get(url) | |
if response.status_code == 200: | |
return response.text | |
else: | |
return '' | |
def sizeof_fmt(num, suffix="b"): | |
for unit in [" ", " k", " m", " g"]: | |
if abs(num) < 1024.0: | |
return f"{num:3.1f}{unit}{suffix}" | |
num /= 1024.0 | |
return '"{num:.1f}t{suffix}' | |
def print_formated_group_size(groups_size): | |
max_grp_name_len = max(map(len,groups_size.keys())) | |
for i, size in sorted(groups_size.items(), key=lambda x: x[1]): | |
ind_list = [t[1].strip(i+'-') for t in indices if t[0] == i] | |
cnt = len(ind_list) | |
if cnt >= 3: | |
short_ind_str = ind_list[0] + '..' + ind_list[-1] | |
elif cnt == 2: | |
short_ind_str = ind_list[0] + ' ' + ind_list[-1] | |
elif cnt == 1: | |
short_ind_str = ind_list[0] | |
else: | |
short_ind_str | |
f_indexname = i.rjust(max_grp_name_len) | |
f_size = sizeof_fmt(size).rjust(9) | |
print(f'{f_size}\t{f_indexname}\tcnt: {cnt}\t indices: {short_ind_str}') | |
if __name__ == '__main__': | |
groups_size = {} | |
indices = [] | |
for row in read_size_data('http://127.0.0.1:9200/_cat/indices?h=index,pri.store.size').split('\n'): | |
if row.strip() == '': | |
break # abort on empty rows | |
ind_name, size_h = re.split(' +', row) | |
m = re.match(r'([\w._\-]+)-\d{4}([-.])\d{2}(\1\d{2})?', ind_name) | |
if not m: | |
# skip non-patterned index | |
continue | |
ind_group = re.match(r'([\w._\-]+)-\d{4}([-.])\d{2}(\1\d{2})?', ind_name).group(1) | |
if size_h[-2:] in ('gb','mb','kb'): | |
size_b = int(float(size_h[:-2]) * SIZE_SUFFIX.get(size_h[-2:])) | |
elif size_h[-1:] == 'b': | |
size_b = int(float(size_h[:-1]) * SIZE_SUFFIX.get(size_h[-1:])) | |
else: | |
size_b = 0 | |
indices.append((ind_group, ind_name, size_b)) | |
if ind_group in groups_size: | |
groups_size[ind_group] += size_b | |
else: | |
groups_size[ind_group] = size_b | |
# default action: return as human readable text to stdout | |
print_formated_group_size(groups_size |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment