Memoizing/caching command line output
I just got nerd-sniped into writing a rather complete script for this; latest version is at https://gist.github.com/akorn/51ee2fe7d36fa139723c851d87e56096.
Advantages over sivann's shell implementation:
- also takes envvars into account when computing cache key;
- completely avoids race conditions using locking instead of relying on a random wait
- better performance when called in tight loop due to fewer forks
- also caches stderr
- completely transparent: prints nothing; doesn't prevent parallel execution of same command; just runs command uncached if there is a problem with the cache
- configurable via envvars and command line switches
- can prune its cache (remove all obsolete entries)
Disadvantage: written in zsh, not bash.
#!/bin/zsh
#
# Purpose: run speficied command with specified arguments and cache result. If cache is fresh enough, don't run command again but return cached output.
# Also cache exit status and stderr.
# Copyright (c) 2019-2020 András Korn; License: GPLv3
# Use silly long variable names to avoid clashing with whatever the invoked program might use
RUNCACHED_MAX_AGE=${RUNCACHED_MAX_AGE:-300}
RUNCACHED_IGNORE_ENV=${RUNCACHED_IGNORE_ENV:-0}
RUNCACHED_IGNORE_PWD=${RUNCACHED_IGNORE_PWD:-0}
[[ -n "$HOME" ]] && RUNCACHED_CACHE_DIR=${RUNCACHED_CACHE_DIR:-$HOME/.runcached}
RUNCACHED_CACHE_DIR=${RUNCACHED_CACHE_DIR:-/var/cache/runcached}
function usage() {
echo "Usage: runcached [--ttl <max cache age>] [--cache-dir <cache directory>]"
echo " [--ignore-env] [--ignore-pwd] [--help] [--prune-cache]"
echo " [--] command [arg1 [arg2 ...]]"
echo
echo "Run 'command' with the specified args and cache stdout, stderr and exit"
echo "status. If you run the same command again and the cache is fresh, cached"
echo "data is returned and the command is not actually run."
echo
echo "Normally, all exported environment variables as well as the current working"
echo "directory are included in the cache key. The --ignore options disable this."
echo "The OLDPWD variable is always ignored."
echo
echo "--prune-cache deletes all cache entries older than the maximum age. There is"
echo "no other mechanism to prevent the cache growing without bounds."
echo
echo "The default cache directory is ${RUNCACHED_CACHE_DIR}."
echo "Maximum cache age defaults to ${RUNCACHED_MAX_AGE}."
echo
echo "CAVEATS:"
echo
echo "Side effects of 'command' are obviously not cached."
echo
echo "There is no cache invalidation logic except cache age (specified in seconds)."
echo
echo "If the cache can't be created, the command is run uncached."
echo
echo "This script is always silent; any output comes from the invoked command. You"
echo "may thus not notice errors creating the cache and such."
echo
echo "stdout and stderr streams are saved separately. When both are written to a"
echo "terminal from cache, they will almost certainly be interleaved differently"
echo "than originally. Ordering of messages within the two streams is preserved."
exit 0
}
while [[ -n "$1" ]]; do
case "$1" in
--ttl) RUNCACHED_MAX_AGE="$2"; shift 2;;
--cache-dir) RUNCACHED_CACHE_DIR="$2"; shift 2;;
--ignore-env) RUNCACHED_IGNORE_ENV=1; shift;;
--ignore-pwd) RUNCACHED_IGNORE_PWD=1; shift;;
--prune-cache) RUNCACHED_PRUNE=1; shift;;
--help) usage;;
--) shift; break;;
*) break;;
esac
done
zmodload zsh/datetime
zmodload zsh/stat
zmodload zsh/system
zmodload zsh/files
# the built-in mv doesn't fall back to copy if renaming fails due to EXDEV;
# since the cache directory is likely on a different fs than the tmp
# directory, this is an important limitation, so we use /bin/mv instead
disable mv
mkdir -p "$RUNCACHED_CACHE_DIR" >/dev/null 2>/dev/null
((RUNCACHED_PRUNE)) && find "$RUNCACHED_CACHE_DIR/." -maxdepth 1 -type f \! -newermt @$[EPOCHSECONDS-RUNCACHED_MAX_AGE] -delete 2>/dev/null
[[ -n "$@" ]] || exit 0 # if no command specified, exit silently
(
# Almost(?) nothing uses OLDPWD, but taking it into account potentially reduces cache efficency.
# Thus, we ignore it for the purpose of coming up with a cache key.
unset OLDPWD
((RUNCACHED_IGNORE_PWD)) && unset PWD
((RUNCACHED_IGNORE_ENV)) || env
echo -E "$@"
) | md5sum | read RUNCACHED_CACHE_KEY RUNCACHED__crap__
# make the cache dir hashed unless a cache file already exists (created by a previous version that didn't use hashed dirs)
if ! [[ -f $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.exitstatus ]]; then
RUNCACHED_CACHE_KEY=$RUNCACHED_CACHE_KEY[1,2]/$RUNCACHED_CACHE_KEY[3,4]/$RUNCACHED_CACHE_KEY[5,$]
mkdir -p "$RUNCACHED_CACHE_DIR/${RUNCACHED_CACHE_KEY:h}" >/dev/null 2>/dev/null
fi
# If we can't obtain a lock, we want to run uncached; otherwise
# 'runcached' wouldn't be transparent because it would prevent
# parallel execution of several instances of the same command.
# Locking is necessary to avoid races between the mv(1) command
# below replacing stderr with a newer version and another instance
# of runcached using a newer stdout with the older stderr.
: >>$RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.lock 2>/dev/null
if zsystem flock -t 0 $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.lock 2>/dev/null; then
if [[ -f $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.stdout ]]; then
if [[ $[EPOCHSECONDS-$(zstat +mtime $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.stdout)] -le $RUNCACHED_MAX_AGE ]]; then
cat $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.stdout &
cat $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.stderr >&2 &
wait
exit $(<$RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.exitstatus)
else
rm -f $RUNCACHED_CACHE_DIR/$RUNCACHED_CACHE_KEY.{stdout,stderr,exitstatus} 2>/dev/null
fi
fi
# only reached if cache didn't exist or was too old
if [[ -d $RUNCACHED_CACHE_DIR/. ]]; then
RUNCACHED_tempdir=$(mktemp -d 2>/dev/null)
if [[ -d $RUNCACHED_tempdir/. ]]; then
$@ >&1 >$RUNCACHED_tempdir/${RUNCACHED_CACHE_KEY:t}.stdout 2>&2 2>$RUNCACHED_tempdir/${RUNCACHED_CACHE_KEY:t}.stderr
RUNCACHED_ret=$?
echo $RUNCACHED_ret >$RUNCACHED_tempdir/${RUNCACHED_CACHE_KEY:t}.exitstatus 2>/dev/null
mv $RUNCACHED_tempdir/${RUNCACHED_CACHE_KEY:t}.{stdout,stderr,exitstatus} $RUNCACHED_CACHE_DIR/${RUNCACHED_CACHE_KEY:h} 2>/dev/null
rmdir $RUNCACHED_tempdir 2>/dev/null
exit $RUNCACHED_ret
fi
fi
fi
# only reached if cache not created successfully or lock couldn't be obtained
exec $@
An implementation exists here: https://bitbucket.org/sivann/runcached/src Caches executable path, output, exit code, remembers arguments. Configurable expiration. Implemented in bash, C, python, choose whatever suits you.