]> git.ipfire.org Git - thirdparty/squid.git/commit
projects / thirdparty / squid.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: f1162d0) | patch
Optimization: Faster response headers packing (#230) M-staged-PR230
authorEduard Bagdasaryan <eduard.bagdasaryan@measurement-factory.com>
Thu, 26 Jul 2018 17:44:14 +0000 (17:44 +0000)
committerSquid Anubis <squid-anubis@squid-cache.org>
Thu, 26 Jul 2018 19:38:52 +0000 (19:38 +0000)
commitf8432432a77535cd4ec0d34fff716e4bf7f467b2
treefa6c38440cf5b4a49ae66bcb2b0873e35150b714tree
parentf1162d09c91281aec88d34ccaa8b5d126ed1cf02commit | diff
Optimization: Faster response headers packing (#230)

Packing reply headers into StoreEntry/ShmWriter directly means numerous
tiny append() calls which involve expensive mem_node/slice searches. For
example, every two-byte ": " and CRLF delimiter is packed separately.
src/HttpReply.cc diff | blob | blame | history
src/HttpReply.h diff | blob | blame | history
src/MemStore.cc diff | blob | blame | history
src/store.cc diff | blob | blame | history
src/tests/stub_HttpReply.cc diff | blob | blame | history
src/tests/testRock.cc diff | blob | blame | history
src/tests/testUfs.cc diff | blob | blame | history
Mirror of https://github.com/squid-cache/squid.git