summaryrefslogtreecommitdiff
path: root/codegen.py
diff options
context:
space:
mode:
authorMatthew Sackman <matthew@lshift.net>2010-04-18 11:58:35 +0100
committerMatthew Sackman <matthew@lshift.net>2010-04-18 11:58:35 +0100
commit28c6ed4a02943e19ce9c65f9a856f463f27a79d6 (patch)
tree290274a6f8780075213cbc626845fc919bec2c2d /codegen.py
parent3c5fb288e4fb9533da6143dd30770c2f7194fb70 (diff)
downloadrabbitmq-server-git-28c6ed4a02943e19ce9c65f9a856f463f27a79d6.tar.gz
Rewrote scanning of message files, to read in blocks of up to 4MB (hence bounded) but can still cope with variable sized files. The advantage here is vastly reduced number of OS calls to position and read. The results is that in tests, GC time is reduced from around 35 seconds to about 2. Code is also 7 lines shorter - and arguably simpler - the only tricky bit is reusing left over data from one block with the next read block, hence different read and scan offsets
Diffstat (limited to 'codegen.py')
0 files changed, 0 insertions, 0 deletions