Redesign the caching layer

The original caching layer in cgit has no upper bound on the number of
concurrent cache entries, so when cgit is traversed by a spider (like the
googlebot), the cache might end up filling your disk. Also, if any error
occurs in the cache layer, no content is returned to the client.

This patch redesigns the caching layer to avoid these flaws by
* giving the cache a bound number of slots
* disabling the cache for the current request when errors occur

The cache size limit is implemented by hashing the querystring (the cache
lookup key) and generating a cache filename based on this hash modulo the
cache size. In order to detect hash collisions, the full lookup key (i.e.
the querystring) is stored in the cache file (separated from its associated
content by ascii 0).

The cache filename is the reversed 8-digit hexadecimal representation of

  hash(key) % cache_size

which should make the filesystem lookup pretty fast (if directory content
is indexed/sorted); reversing the representation avoids the problem where
all keys have equal prefix.

There is a new config option, cache-size, which sets the upper bound for
the cache. Default value for this option is 0, which has the same effect
as setting nocache=1 (hence nocache is now deprecated).

Included in this patch is also a new testfile which verifies that the
new option works as intended.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>

2 files changed, 68 insertions, 1 deletions

diff --git a/tests/setup.sh b/tests/setup.sh
index 66bf406..e37306e 100755
--- a/tests/setup.sh
+++ b/tests/setup.sh
@@ -1,116 +1,116 @@
 # This file should be sourced by all test-scripts
 #
 # Main functions:
 #   prepare_tests(description) - setup for testing, i.e. create repos+config
 #   run_test(description, script) - run one test, i.e. eval script
 #
 # Helper functions
 #   cgit_query(querystring) - call cgit with the specified querystring
 #   cgit_url(url) - call cgit with the specified virtual url
 #
 # Example script:
 #
 # . setup.sh
 # prepare_tests "html validation"
 # run_test 'repo index' 'cgit_url "/" | tidy -e'
 # run_test 'repo summary' 'cgit_url "/foo" | tidy -e'
 
 
 mkrepo() {
         name=$1
         count=$2
         dir=$PWD
         test -d $name && return
         printf "Creating testrepo %s\n" $name
         mkdir -p $name
         cd $name
         git init
         for ((n=1; n<=count; n++))
         do
                 echo $n >file-$n
                 git add file-$n
                 git commit -m "commit $n"
         done
         cd $dir
 }
 
 setup_repos()
 {
         rm -rf trash/cache
         mkdir -p trash/cache
         mkrepo trash/repos/foo 5 >/dev/null
         mkrepo trash/repos/bar 50 >/dev/null
         cat >trash/cgitrc <<EOF
 virtual-root=/
 cache-root=$PWD/trash/cache
 
-nocache=0
+cache-size=1021
 snapshots=tar.gz tar.bz zip
 enable-log-filecount=1
 enable-log-linecount=1
 summary-log=5
 summary-branches=5
 summary-tags=5
 
 repo.url=foo
 repo.path=$PWD/trash/repos/foo/.git
 # Do not specify a description for this repo, as it then will be assigned
 # the constant value "[no description]" (which actually used to cause a
 # segfault).
 
 repo.url=bar
 repo.path=$PWD/trash/repos/bar/.git
 repo.desc=the bar repo
 EOF
 }
 
 prepare_tests()
 {
         setup_repos
         rm -f test-output.log 2>/dev/null
         test_count=0
         test_failed=0
         echo "[$0]" "$@" >test-output.log
         echo "$@" "($0)"
 }
 
 tests_done()
 {
         printf "\n"
         if test $test_failed -gt 0
         then
                 printf "test: *** %s failure(s), logfile=%s\n" \
                         $test_failed "$(pwd)/test-output.log"
                 false
         fi
 }
 
 run_test()
 {
         desc=$1
         script=$2
         ((test_count++))
         printf "\ntest %d: name='%s'\n" $test_count "$desc" >>test-output.log
         printf "test %d: eval='%s'\n" $test_count "$2" >>test-output.log
         eval "$2" >>test-output.log 2>>test-output.log
         res=$?
         printf "test %d: exitcode=%d\n" $test_count $res >>test-output.log
         if test $res = 0
         then
                 printf " %2d) %-60s [ok]\n" $test_count "$desc"
         else
                 ((test_failed++))
                 printf " %2d) %-60s [failed]\n" $test_count "$desc"
         fi
 }
 
 cgit_query()
 {
         CGIT_CONFIG="$PWD/trash/cgitrc" QUERY_STRING="$1" "$PWD/../cgit"
 }
 
 cgit_url()
 {
         CGIT_CONFIG="$PWD/trash/cgitrc" QUERY_STRING="url=$1" "$PWD/../cgit"
 }
 
diff --git a/tests/t0020-validate-cache.sh b/tests/t0020-validate-cache.sh
new file mode 100755
index 0000000..53ec2eb
--- a/dev/null
+++ b/tests/t0020-validate-cache.sh
@@ -0,0 +1,67 @@
+#!/bin/sh
+
+. ./setup.sh
+
+prepare_tests 'Validate cache'
+
+run_test 'verify cache-size=0' '
+
+        rm -f trash/cache/* &&
+        sed -i -e "s/cache-size=1021$/cache-size=0/" trash/cgitrc &&
+        cgit_url "" &&
+        cgit_url "foo" &&
+        cgit_url "foo/refs" &&
+        cgit_url "foo/tree" &&
+        cgit_url "foo/log" &&
+        cgit_url "foo/diff" &&
+        cgit_url "foo/patch" &&
+        cgit_url "bar" &&
+        cgit_url "bar/refs" &&
+        cgit_url "bar/tree" &&
+        cgit_url "bar/log" &&
+        cgit_url "bar/diff" &&
+        cgit_url "bar/patch" &&
+        test 0 -eq $(ls trash/cache | wc -l)
+'
+
+run_test 'verify cache-size=1' '
+
+        rm -f trash/cache/* &&
+        sed -i -e "s/cache-size=0$/cache-size=1/" trash/cgitrc &&
+        cgit_url "" &&
+        cgit_url "foo" &&
+        cgit_url "foo/refs" &&
+        cgit_url "foo/tree" &&
+        cgit_url "foo/log" &&
+        cgit_url "foo/diff" &&
+        cgit_url "foo/patch" &&
+        cgit_url "bar" &&
+        cgit_url "bar/refs" &&
+        cgit_url "bar/tree" &&
+        cgit_url "bar/log" &&
+        cgit_url "bar/diff" &&
+        cgit_url "bar/patch" &&
+        test 1 -eq $(ls trash/cache | wc -l)
+'
+
+run_test 'verify cache-size=1021' '
+
+        rm -f trash/cache/* &&
+        sed -i -e "s/cache-size=1$/cache-size=1021/" trash/cgitrc &&
+        cgit_url "" &&
+        cgit_url "foo" &&
+        cgit_url "foo/refs" &&
+        cgit_url "foo/tree" &&
+        cgit_url "foo/log" &&
+        cgit_url "foo/diff" &&
+        cgit_url "foo/patch" &&
+        cgit_url "bar" &&
+        cgit_url "bar/refs" &&
+        cgit_url "bar/tree" &&
+        cgit_url "bar/log" &&
+        cgit_url "bar/diff" &&
+        cgit_url "bar/patch" &&
+        test 13 -eq $(ls trash/cache | wc -l)
+'
+
+tests_done