log-generator: add option to generate easily compressible data

This is useful to check that compression actually works, and how
compression influences file size in the best-case-scenario for
compression. (The answer is that not as much as one would hope:
there's still a big overhead of the indexing and since every field
is compressed separately, even fields that compress very well
contribute to the file size. This overhead becomes negligible only
for very big fields.)

diff --git a/src/journal-remote/log-generator.py b/src/journal-remote/log-generator.py
index 9a8fb07c7fde0c5a01f09fbe4229232c1c209c59..fd6964e758269177423fc28e1af2f8acb653d6db 100755 (executable)
--- a/src/journal-remote/log-generator.py
+++ b/src/journal-remote/log-generator.py
@@ -6,6 +6,8 @@ import argparse
 PARSER = argparse.ArgumentParser()
 PARSER.add_argument('n', type=int)
 PARSER.add_argument('--dots', action='store_true')
+PARSER.add_argument('--data-size', type=int, default=4000)
+PARSER.add_argument('--data-type', choices={'random', 'simple'})
 OPTIONS = PARSER.parse_args()
 
 template = """\
@@ -38,10 +40,16 @@ facility = 6
 src = open('/dev/urandom', 'rb')
 
 bytes = 0
+counter = 0
 
 for i in range(OPTIONS.n):
     message = repr(src.read(2000))
-    data = repr(src.read(4000))
+    if OPTIONS.data_type == 'random':
+        data = repr(src.read(OPTIONS.data_size))
+    else:
+        # keep the pattern non-repeating so we get a different blob every time
+        data = '{:0{}}'.format(counter, OPTIONS.data_size)
+        counter += 1
 
     entry = template.format(m=m,
                             realtime_ts=realtime_ts,