dho-qa: disentangle file generation from uploading

Static load test script now provides separate functions for generating a
list of random-file pointers and uploading those files to an S3 store.  When
run as a script it still does both, but you can call each function
individually from a different script after loading the module.

generate_objects.py

@@ -17,11 +17,7 @@ import sys
 def parse_opts():
     parser = OptionParser();
     parser.add_option('-O' , '--outfile', help='write output to FILE. Defaults to STDOUT', metavar='FILE')
-    parser.add_option('-a' , '--access-key', dest='access_key', help='use S3 access key KEY', metavar='KEY')
-    parser.add_option('-s' , '--secret-key', dest='secret_key', help='use S3 secret key KEY', metavar='KEY')
     parser.add_option('-b' , '--bucket', dest='bucket', help='push objects to BUCKET', metavar='BUCKET')
-    parser.add_option('--checksum', dest='checksum', action='store_true', help='include the md5 checksum with the object urls')
-    parser.add_option('--host', dest='host', help='use S3 gateway at HOST', metavar='HOST')
     parser.add_option('--seed', dest='seed', help='optional seed for the random number generator')
 
     return parser.parse_args()
@@ -38,63 +34,67 @@ def connect_s3(host, access_key, secret_key):
     return conn
 
 
-def generate_objects(bucket, quantity, mean, stddev, seed, checksum=False, name_seed=None):
+def get_random_files(quantity, mean, stddev, seed):
-    """Generate random objects with sizes across a normal distribution
+    """Create file-like objects with pseudorandom contents.
-       specified by mean and standard deviation and write them to bucket.
        IN:
-         boto S3 bucket object
+           number of files to create
-         Number of files
            mean file size in bytes
            standard deviation from mean file size
-         seed for RNG
+           seed for PRNG
-         flag to tell the method to append md5 checksums to the output
-         seed to use for the file names. defaults to use the other seed
        OUT:
-         list of urls (strings) to objects valid for 1 hour.
+           list of file handles
-         If "checksum" is true, each output string consists of the url
-         followed by the md5 checksum.
     """
-    if name_seed == None:
-        name_seed = seed
-
-    urls = []
     file_generator = realistic.files(mean, stddev, seed)
-    name_generator = realistic.names(15, 4,seed=name_seed)
+    return [file_generator.next() for _ in xrange(quantity)]
-    for _ in xrange(quantity):
+
-        fp = file_generator.next()
+
+def upload_objects(bucket, files, seed):
+    """Upload a bunch of files to an S3 bucket
+       IN:
+         boto S3 bucket object
+         list of file handles to upload
+         seed for PRNG
+       OUT:
+         list of boto S3 key objects
+    """
+    keys = []
+    name_generator = realistic.names(15, 4,seed=seed)
+
+    for fp in files:
         print >> sys.stderr, 'sending file with size %dB' % fp.size
         key = Key(bucket)
         key.key = name_generator.next()
         key.set_contents_from_file(fp)
-        url = key.generate_url(30758400) #valid for 1 year
+        keys.append(key)
-        if checksum:
-            url += ' %s' % key.md5
-        urls.append(url)
 
-    return urls
+    return keys
 
 
 def main():
     '''To run the static content load test, make sure you've bootstrapped your
        test environment and set up your config.yml file, then run the following:
-          S3TEST_CONF=config.yml virtualenv/bin/python generate_objects.py -a S3_ACCESS_KEY -s S3_SECRET_KEY -O urls.txt --seed 1234 && siege -rc ./siege.conf -r 5
+          S3TEST_CONF=config.yml virtualenv/bin/python generate_objects.py -O urls.txt --seed 1234
 
-        This creates a bucket with your S3 credentials and fills it with
+        This creates a bucket with your S3 credentials (from config.yml) and
-        garbage objects as described in generate_objects.conf. It writes a
+        fills it with garbage objects as described in generate_objects.conf.
-        list of URLS to those objects to ./urls.txt.  siege then reads the
+        It writes a list of URLS to those objects to ./urls.txt.
-        ./siege.conf config file which tells it to read from ./urls.txt and
+
-        log to ./siege.log and hammers each url in urls.txt 5 times (-r flag).
+        Once you have objcts in your bucket, run the siege benchmarking program:
+            siege -rc ./siege.conf -r 5
+
+        This tells siege to read the ./siege.conf config file which tells it to
+        use the urls in ./urls.txt and log to ./siege.log. It hits each url in
+        urls.txt 5 times (-r flag).
 
         Results are printed to the terminal and written in CSV format to
         ./siege.log
-
-        S3 credentials and output file may also be specified in config.yml
-        under s3.main and file_generation.url_file
     '''
     (options, args) = parse_opts();
 
     #SETUP
     random.seed(options.seed if options.seed else None)
+    conn = common.s3.main
+
     if options.outfile:
         OUTFILE = open(options.outfile, 'w')
     elif common.config.file_generation.url_file:
@@ -102,31 +102,23 @@ def main():
     else:
         OUTFILE = sys.stdout
 
-    if options.access_key and options.secret_key:
-        host = options.host if options.host else common.config.s3.defaults.host
-        conn = connect_s3(host, options.access_key, options.secret_key)
-    else:
-        conn = common.s3.main
-
     if options.bucket:
-        bucket = get_bucket(conn, options.bucket)
+        bucket = conn.create_bucket(options.bucket)
     else:
         bucket = common.get_new_bucket()
 
-    urls = []
+    keys = []
-
     print >> OUTFILE, 'bucket: %s' % bucket.name
     print >> sys.stderr, 'setup complete, generating files'
     for profile in common.config.file_generation.groups:
         seed = random.random()
-        urls += generate_objects(bucket, profile[0], profile[1], profile[2], seed, options.checksum)
+        files = get_random_files(profile[0], profile[1], profile[2], seed)
-    print >> sys.stderr, 'finished sending files. generating  urls and sending to S3'
+        keys += upload_objects(bucket, files, seed)
+
+    print >> sys.stderr, 'finished sending files. generating urls'
+    for key in keys:
+        print >> OUTFILE, key.generate_url(30758400) #valid for 1 year
 
-    url_string = '\n'.join(urls)
-    url_key = Key(bucket)
-    url_key.key = 'urls'
-    url_key.set_contents_from_string(url_string)
-    print >> OUTFILE, url_string
     print >> sys.stderr, 'done'