Name

ccache - a fast C/C++ compiler cache

Synopsis

ccache [ccache options]
ccache [KEY=VALUE …​] compiler [compiler options]
compiler [compiler options]

The first form takes options described in Command line options below. The second form invokes the compiler, optionally using configuration options as KEY=VALUE arguments. In the third form, ccache is masquerading as the compiler as described in Run modes.

Description

Ccache is a compiler cache that speeds up recompilation by storing the results of previous compilations and reusing them when the same compilation is performed again.

Ccache is designed to produce exactly the same compiler output as a normal compilation. The only difference you should notice is faster build times. Any known exceptions to this behavior are documented in the Caveats section. If you find a case where ccache produces different output than expected, please report it to us.

Run modes

There are two ways to use ccache to cache compilations:

  1. Prefix method: Add ccache before your compilation command. This is the simplest approach when you want to try ccache or use it for specific projects. Example:

    ccache gcc -c example.c

  2. Masquerade method: Make ccache appear as the compiler by creating a symbolic link to ccache with the compiler’s name. This is useful when you want to use ccache for all compilations. To set up ccache to masquerade as gcc and g++:

    cp ccache /usr/local/bin/
ln -s ccache /usr/local/bin/gcc
ln -s ccache /usr/local/bin/g++

    On systems that don’t support symbolic links, you can copy ccache instead:

    cp ccache /usr/local/bin/gcc
cp ccache /usr/local/bin/g++

    This works as long as the directory containing the symbolic links or ccache copies appears before the real compiler directory (typically /usr/bin) in your PATH.

    The masquerade method works well but may conflict with other tools that use the same technique. See Using ccache with other compiler wrappers for more information.

Command line options

These command line options apply only when you invoke ccache directly as “ccache”. When ccache masquerades as a compiler (as described in the previous section), you should use the normal compiler options and refer to your compiler’s documentation.

Common options

-c, --cleanup

Clean up the cache by removing not recently used cached files until the specified file number and cache size limits are not exceeded. This also recalculates the cache file count and size totals. Normally, there is no need to initiate cleanup manually as ccache keeps the cache below the specified limits at runtime and keeps statistics up to date on each compilation. Forcing a cleanup is mostly useful if you have modified the cache contents manually or believe that the cache size statistics may be inaccurate.

-C, --clear

Clear the entire cache, removing all cached files, but keeping the configuration file.

--config-path PATH

Let the command line options operate on configuration file PATH instead of the default. Using this option has the same effect as setting (overriding) the environment variable CCACHE_CONFIGPATH temporarily.

-d, --dir PATH

Let the command line options operate on cache directory PATH instead of the default. For example, to show statistics for a cache directory at /shared/ccache you can run ccache -d /shared/ccache -s. Using this option has the same effect as setting the environment variable CCACHE_DIR temporarily.

--evict-namespace NAMESPACE

Remove files created in the given namespace from the cache.

--evict-older-than AGE

Remove files used less recently than AGE from the cache. AGE should be an unsigned integer with a d (days) or s (seconds) suffix. If combined with --evict-namespace, only remove files within that namespace.

-h, --help

Print a summary of command line options.

-F NUM, --max-files NUM

Set the maximum number of files allowed in the cache to NUM. Use 0 for no limit. The value is stored in a configuration file in the cache directory and applies to all future compilations.

-M SIZE, --max-size SIZE

Set the maximum size of the files stored in the cache. SIZE should be a number followed by an optional suffix: kB, MB, GB, TB (decimal), KiB, MiB, GiB or TiB (binary). The default suffix is GiB. Use 0 for no limit. The value is stored in a configuration file in the cache directory and applies to all future compilations.

-X LEVEL, --recompress LEVEL

Recompress the cache to level LEVEL using the Zstandard algorithm. The level can be an integer, with the same semantics as the compression_level configuration option, or the special value uncompressed for no compression. See Cache compression for more information. This can potentially take a long time since all files in the cache need to be visited. Only files that are currently compressed with a different level than LEVEL will be recompressed.

-o KEY=VALUE, --set-config KEY=VALUE

Set configuration option KEY to VALUE in the configuration file. See Configuration for more information.

-x, --show-compression

Print cache compression statistics. See Cache compression for more information. This can potentially take a long time since all files in the cache need to be visited.

-p, --show-config

Print current configuration options and from where they originate (environment variable, configuration file or compile-time default) in human-readable format.

--show-log-stats

Print statistics counters from the stats log in human-readable format. See stats_log. Use -v/--verbose once or twice for more details.

-s, --show-stats

Print a summary of configuration and statistics counters in human-readable format. Use -v/--verbose once or twice for more details. See Cache statistics for more information.

--stop-storage-helpers

Storage helpers normally stop after a period of client inactivity, but this option can be used to stop any running helpers immediately.

--threads THREADS

Use up to THREADS threads for threaded operations. The default is to use one thread per CPU.

-v, --verbose

Increase verbosity. The option can be given multiple times.

-V, --version

Print version and copyright information.

-z, --zero-stats

Zero the cache statistics (but not the configuration options).

Options for remote file-based storage

--trim-dir PATH

Remove not recently used files from directory PATH until it is at most the size specified by --trim-max-size.

Don’t use this option to trim the local cache. To trim the local cache directory to a certain size, use CCACHE_MAXSIZE=SIZE ccache -c.
--trim-max-size SIZE

Specify the maximum size for --trim-dir. SIZE should be a number followed by an optional suffix: kB, MB, GB, TB (decimal), KiB, MiB, GiB or TiB (binary). The default suffix is GiB. Use 0 for no limit.

--trim-method METHOD

Specify the method to trim a directory with --trim-dir. Possible values are:

atime

LRU (least recently used) using the file access timestamp. This is the default.

mtime

LRU (least recently used) using the file modification timestamp.

--trim-recompress LEVEL

Recompress to level LEVEL using the Zstandard algorithm when using --trim-dir. The level can be an integer, with the same semantics as the compression_level configuration option, or the special value uncompressed for no compression. See Cache compression for more information. This can potentially take a long time since all files in the cache need to be visited. Only files that are currently compressed with a different level than LEVEL will be recompressed.

Options for scripting or debugging

--checksum-file PATH

Print the checksum (128 bit XXH3) of the file at PATH (- for standard input).

--extract-result PATH

Extract data stored in the result file at PATH (- for standard input). The data will be written to ccache-result.* files in to the current working directory. This option is only useful when debugging ccache and its behavior.

--format FORMAT

Specify format for --print-log-stats and --print-stats. Possible values are:

tab

Tab separated. This is the default.

json

JSON formatted.

-k KEY, --get-config KEY

Print the value of configuration option KEY. See Configuration for more information.

--hash-file PATH

Print the hash (160 bit BLAKE3) of the file at PATH (- for standard input). This is only useful when debugging ccache and its behavior.

--inspect PATH

Print the content of a result or manifest file at PATH (- for standard input) to standard output in human-readable format. File content embedded in a result file will however not be printed; use --extract-result to extract the file content. This option is only useful when debugging ccache and its behavior.

--print-log-stats

Print statistics counters from the stats log in machine-parsable (tab-separated or JSON) format. See stats_log and --format.

--print-stats

Print statistics counter IDs and corresponding values in machine-parsable (tab-separated or JSON) format. See --format.

--print-version

Print version and don’t do anything else.

Extra options

When run as a compiler, ccache usually just takes the same command line options as the compiler you are using. The only exception to this is the option --ccache-skip. That option can be used to tell ccache to avoid interpreting the next option in any way and to pass it along to the compiler as-is.

--ccache-skip currently only tells ccache not to interpret the next option as a special compiler option — the option will still be included in the direct mode hash.

The reason this can be important is that ccache does need to parse the command line and determine what is an input filename and what is a compiler option, as it needs the input filename to determine the name of the resulting object file (among other things). The heuristic ccache uses when parsing the command line is that any argument that exists as a file is treated as an input file name. By using --ccache-skip you can force an option to not be treated as an input file name and instead be passed along to the compiler as a command line option.

Another case where --ccache-skip can be useful is if ccache interprets an option specially but shouldn’t, since the option has another meaning for your compiler than what ccache thinks.

See also ignore_options.

Configuration

You can customize ccache’s behavior using configuration files and environment variables. Configuration options are processed in the following order of priority (highest first):

  1. Command line settings in KEY=VALUE form. Example:

    ccache debug=true compiler_check="%compiler% --version" gcc -c example.c

  2. Environment variables starting with CCACHE_.

  3. A directory-specific configuration file.

  4. The cache-specific configuration file.

  5. The system-wide configuration file <sysconfdir>/ccache.conf (typically /etc/ccache.conf or /usr/local/etc/ccache.conf).

  6. Compile-time defaults.

Exception: If the environment variable CCACHE_CONFIGPATH is set, it specifies the only configuration file that will be read (environment variables and command line settings still apply).

Cache-specific configuration file

The location of the cache-specific configuration file is determined like this on non-Windows systems:

  1. If CCACHE_CONFIGPATH is set, use that path.

  2. Otherwise, if the environment variable CCACHE_DIR is set then use $CCACHE_DIR/ccache.conf.

  3. Otherwise, if cache_dir is set in the system configuration file then use <cache_dir>/ccache.conf.

  4. Otherwise, if there is a legacy $HOME/.ccache directory then use $HOME/.ccache/ccache.conf.

  5. Otherwise, if XDG_CONFIG_HOME is set then use $XDG_CONFIG_HOME/ccache/ccache.conf.

  6. Otherwise, use $HOME/Library/Preferences/ccache/ccache.conf (macOS) or $HOME/.config/ccache/ccache.conf (other systems).

On Windows, this is the method used to find the configuration file:

  1. If CCACHE_CONFIGPATH is set, use that path.

  2. Otherwise, if the environment variable CCACHE_DIR is set then use %CCACHE_DIR%/ccache.conf.

  3. Otherwise, if cache_dir is set in the system configuration file then use <cache_dir>\ccache.conf. The system-wide configuration on Windows is %ALLUSERSPROFILE%\ccache\ccache.conf by default. The ALLUSERSPROFILE environment variable is usually C:\ProgramData.

  4. Otherwise, if there is a legacy %USERPROFILE%\.ccache directory then use %USERPROFILE%\.ccache\ccache.conf.

  5. Otherwise, use %LOCALAPPDATA%\ccache\ccache.conf if it exists.

  6. Otherwise, use %APPDATA%\ccache\ccache.conf.

See also the cache_dir configuration option for how the cache directory location is determined.

Directory-specific configuration file

Ccache searches for a ccache.conf file (separate from the cache-specific configuration file described above) in the current working directory or any parent directory. The found file must be owned by the effective user and must not be world-writable; otherwise ccache will abort with an error. The search stops when reaching:

  • a directory listed in a "ceiling directory" (by default the user’s home directory)

  • a directory that contains a "ceiling marker" (by default .git)

  • a directory owned by another user

  • a file system boundary (mount point)

By default, the file cannot set "unsafe options", i.e. those that affect which commands to execute, which files to write (except cache entries) and which remote storage to use. It is possible to allow unsafe options by adding an entry to safe_dirs.

Configuration value syntax

All configuration values support expansion of environment variables. The syntax is similar to POSIX shell syntax: $VAR or ${VAR}. Both variants will expand to the value of the environment variable VAR.

Two consecutive dollar signs ($$) will expand to a single dollar sign ($).

Configuration file syntax

Configuration files are in a simple “key = value” format, one option per line. Lines starting with a hash sign are comments. Blank lines are ignored, as is whitespace surrounding keys and values. Example:

# Set maximum cache size to 10 GB:
max_size = 10GB

Multi-line values

Values can span multiple lines using indentation-based continuation. Lines that start with whitespace (spaces or tabs) are treated as continuation lines and are joined to the previous value with a single space. Comments and blank lines within a multi-line value are skipped. For example:

ignore_options =
  -Wall
  -Wextra
  # This is a comment within the value
  -pedantic
# This ends the multi-line value
compiler = gcc

This is equivalent to:

ignore_options = -Wall -Wextra -pedantic
compiler = gcc

Multi-line values are particularly useful for options that accept multiple items.

Boolean values

Some configuration options are boolean values (i.e. truth values). In a configuration file, such values must be set to the string true or false. For the corresponding environment variables, the semantics are a bit different:

  • A set environment variable means “true” (even if set to the empty string).

  • The following case-insensitive negative values are considered an error (instead of surprising the user): 0, false, disable and no.

  • An unset environment variable means “false”.

Each boolean environment variable also has a negated form starting with CCACHE_NO. For example, CCACHE_COMPRESS can be set to force compression and CCACHE_NOCOMPRESS can be set to force no compression.

Configuration options

Below is a list of available configuration options. The corresponding environment variable name is indicated in parentheses after each configuration option key.

Options that define a list of paths have their entries separated by ; on Windows and : on other systems.

absolute_paths_in_stderr (CCACHE_ABSSTDERR)

This option specifies whether ccache should rewrite relative paths in the compiler’s textual output (standard error and standard output) to absolute paths. This can be useful if you use base_dir with a build system (e.g. CMake with the "Unix Makefiles" generator) that executes the compiler in a different working directory, which makes relative paths in compiler errors or warnings incorrect. The default is false.

base_dir (CCACHE_BASEDIR)

This option specifies a list of absolute paths. When set, ccache converts absolute paths to relative paths before hashing, but only for paths that start with one of the specified base directories.

This enables cache sharing between compilations in different directories, even when the project uses absolute paths. See Compiling in different directories_ for more details. When empty (the default), no path rewriting occurs.

Avoid using / as the base directory as this will also rewrite system header paths, which is usually counterproductive.

Example scenario: Alice works in /home/alice/project1/build and compiles like this:

ccache gcc -I/usr/include/example -I/home/alice/project2/include -c /home/alice/project1/src/example.c

Here is what ccache will actually execute for different base_dir settings:

# Current working directory: /home/alice/project1/build

# With base_dir = /:
gcc -I../../../../usr/include/example -I../../project2/include -c ../src/example.c

# With base_dir = /home or /home/alice:
gcc -I/usr/include/example -I../../project2/include -c ../src/example.c

# With base_dir = /home/alice/project1 or /home/alice/project1/src:
gcc -I/usr/include/example -I/home/alice/project2/include -c ../src/example.c

If Bob stores the same projects in /home/bob/stuff and both users set base_dir to /home or /home/$USER, they will share cache hits because the rewritten command lines will be identical:

# Current working directory: /home/bob/stuff/project1/build

# With base_dir = /home or /home/bob:
gcc -I/usr/include/example -I../../project2/include -c ../src/example.c

Without base_dir there will be a cache miss since the absolute paths will differ. With base_dir set to / there will be a cache miss since the relative path to /usr/include/example will be different. With base_dir set to /home/bob/stuff/project1 there will a cache miss since the path to project2 will be a different absolute path.

Rewriting absolute paths to relative is kind of a brittle hack. It works OK in many cases, but there might be cases where things break. One known issue is that absolute paths are not reproduced in dependency files, which can mess up dependency detection in tools like Make and Ninja. If possible, use relative paths in the first place instead of using base_dir.
cache_dir (CCACHE_DIR)

This option specifies where ccache will keep its cached compiler outputs.

On non-Windows systems, the default is $HOME/.ccache if such a directory exists, otherwise $XDG_CACHE_HOME/ccache if XDG_CACHE_HOME is set, otherwise $HOME/Library/Caches/ccache (macOS) or $HOME/.cache/ccache (other systems).

On Windows, the default is %USERPROFILE%\.ccache if such a directory exists, otherwise %LOCALAPPDATA%\ccache.

Previous ccache versions defaulted to storing the cache in %APPDATA%\ccache on Windows. This can result in large network file transfers of the cache in domain environments and similar problems. Please check this directory for cache directories and either delete them or the whole directory, or move them to the %LOCALAPPDATA%\ccache directory.

See also Cache-specific configuration file.

ceiling_dirs (CCACHE_CEILING_DIRS)

This option specifies absolute directories where ccache will stop searching for a directory-specific configuration file. You might want to set this if accessing files in parent directories is too slow, e.g. on network file systems. The default is to stop looking when reaching the user’s home directory.

ceiling_markers (CCACHE_CEILING_MARKERS)

This option specifies one or more file or directory names (separated by ; on Windows, : on other systems). When searching for a directory-specific configuration file, ccache will stop searching parent directories when it reaches a directory containing any of the specified names. The default is .git.

compiler (CCACHE_COMPILER or (deprecated) CCACHE_CC)

This option can be used to force the name of the compiler to use. If set to the empty string (which is the default), ccache works it out from the command line.

compiler_check (CCACHE_COMPILERCHECK)

By default, ccache includes the modification time (“mtime”) and size of the compiler in the hash to ensure that results retrieved from the cache are accurate. If compiler plugins are used, these plugins will also be added to the hash. This option can be used to select another strategy. Possible values are:

content

Hash the content of the compiler binary. This makes ccache very slightly slower compared to mtime, but makes it cope better with compiler upgrades during a build bootstrapping process.

mtime

Hash the compiler’s mtime and size, which is fast. This is the default.

none

Don’t hash anything. This may be good for situations where you can safely use the cached results even though the compiler’s mtime or size has changed (e.g. if the compiler is built as part of your build system and the compiler’s source has not changed, or if the compiler only has changes that don’t affect code generation). You should only use none if you know what you are doing.

string:value

Hash value. This can for instance be a compiler revision number or another string that the build system generates to identify the compiler.

a command string

Hash the standard output and standard error output of the specified command. The string will be split on whitespace to find out the command and arguments to run. No other interpretation of the command string will be done, except that the special word %compiler% will be replaced with the path to the compiler. Several commands can be specified with ; as the separator. Examples:

%compiler% -v
%compiler% -dumpmachine; %compiler% -dumpversion

You should make sure that the specified command is as fast as possible since it will be run once for each ccache invocation.

Identifying the compiler using a command is useful if you want to avoid cache misses when the compiler has been rebuilt but not changed.

Another case is when the compiler (as seen by ccache) actually isn’t the real compiler but another compiler wrapper — in that case, the default mtime method will hash the mtime and size of the other compiler wrapper, which means that ccache won’t be able to detect a compiler upgrade. Using a suitable command to identify the compiler is thus safer, but it’s also slower, so you should consider continue using the mtime method in combination with the prefix_command option if possible. See Using ccache with other compiler wrappers.

compiler_type (CCACHE_COMPILERTYPE)

Ccache normally guesses the compiler type based on the compiler name. The compiler_type option lets you force a compiler type. This can be useful if the compiler has a non-standard name but is actually one of the known compiler types. Possible values are:

auto

Guess one of the types below based on the compiler name (following symlinks). This is the default.

clang

Clang-based compiler.

clang-cl

clang-cl.

gcc

GCC-based compiler.

icl

Intel compiler on Windows.

icx

Intel LLVM-based compiler.

icx-cl

Intel LLVM-based MSVC-compatible compiler.

msvc

Microsoft Visual C++ (MSVC).

nvcc

NVCC (CUDA) compiler.

other

Any compiler other than the known types.

compression (CCACHE_COMPRESS or CCACHE_NOCOMPRESS, see Boolean values above)

If true, ccache will compress data it puts in the cache. However, this option has no effect on how files are retrieved from the cache; compressed and uncompressed results will still be usable regardless of this option. The default is true.

Compression is done using the Zstandard algorithm. The algorithm is fast enough that there should be little reason to turn off compression to gain performance. One exception is if the cache is located on a compressed file system, in which case the compression performed by ccache of course is redundant.

Compression will be disabled if file cloning (the file_clone option) or hard linking (the hard_link option) is enabled.

compression_level (CCACHE_COMPRESSLEVEL)

This option determines the level at which ccache will compress object files using the real-time compression algorithm Zstandard. It only has effect if compression is enabled (which it is by default). Zstandard is extremely fast for decompression and very fast for compression for lower compression levels. The default is 0.

Semantics of compression_level:

> 0

A positive value corresponds to normal Zstandard compression levels. Lower levels (e.g. 1) mean faster compression but worse compression ratio. Higher levels (e.g. 19) mean slower compression but better compression ratio. The maximum possible value depends on the libzstd version, but at least up to 19 is available for all versions. Decompression speed is essentially the same for all levels. As a rule of thumb, use level 5 or lower since higher levels may slow down compilations noticeably. Higher levels are however useful when recompressing the cache with command line option -X/--recompress.

< 0

A negative value corresponds to Zstandard’s “ultra-fast” compression levels, which are even faster than level 1 but with less good compression ratios. For instance, level -3 corresponds to --fast=3 for the zstd command line tool. In practice, there is little use for levels lower than -5 or so.

0 (default)

The value 0 means that ccache will choose a suitable level, currently 1.

See the Zstandard documentation for more information.

cpp_extension (CCACHE_EXTENSION)

This option can be used to force a certain extension for the intermediate preprocessed file. The default is to automatically determine the extension to use for intermediate preprocessor files based on the type of file being compiled, but that sometimes doesn’t work. For example, when using the “aCC” compiler on HP-UX, set the cpp extension to i.

debug (CCACHE_DEBUG or CCACHE_NODEBUG, see Boolean values above)

If true, enable the debug mode. The debug mode creates per-object debug files that are helpful when debugging unexpected cache misses. Note however that ccache performance will be reduced slightly. See Cache debugging for more information. The default is false.

debug_dir (CCACHE_DEBUGDIR)

Specifies where to write per-object debug files if the debug mode is enabled. If set to the empty string, the files will be written next to the object file. If set to a directory, the debug files will be written with full absolute paths in that directory, creating it if needed. The default is the empty string.

For example, if debug_dir is set to /example, the current working directory is /home/user and the object file is build/output.o then the debug log will be written to /example/home/user/build/output.o.ccache-log. See also Cache debugging.

debug_level (CCACHE_DEBUGLEVEL)

Specifies the amount of information that is written when the debug mode is enabled. See Cache debugging for more information. The default is 2.

depend_mode (CCACHE_DEPEND or CCACHE_NODEPEND, see Boolean values above)

If true, the depend mode will be used. The default is false. See The depend mode.

direct_mode (CCACHE_DIRECT or CCACHE_NODIRECT, see Boolean values above)

If true, the direct mode will be used. The default is true. See The direct mode.

disable (CCACHE_DISABLE or CCACHE_NODISABLE, see Boolean values above)

When true, ccache will just call the real compiler, bypassing the cache completely. The default is false.

It is also possible to disable ccache for a specific source code file by adding the string ccache:disable in a comment in the first 4096 bytes of the file.

extra_files_to_hash (CCACHE_EXTRAFILES)

This option is a list of paths to files that ccache will include in the hash sum that identifies the build.

file_clone (CCACHE_FILECLONE or CCACHE_NOFILECLONE, see Boolean values above)

If true, ccache will attempt to use file cloning (also known as “copy on write”, “CoW” or “reflinks”) to store and fetch cached compiler results. file_clone has priority over hard_link. The default is false.

Files stored by cloning cannot be compressed, so the cache size will likely be significantly larger if this option is enabled. However, performance may be improved depending on the use case.

Unlike the hard_link option, file_clone is completely safe to use, but not all file systems support the feature. For such file systems, ccache will fall back to use plain copying (or hard links if hard_link is enabled).

hash_dir (CCACHE_HASHDIR or CCACHE_NOHASHDIR, see Boolean values above)

If true (which is the default), ccache will include the current working directory (CWD) in the hash that is used to distinguish two compilations when generating debug info (compiler option -g with variations). Exception: The CWD will not be included in the hash if the compiler options -fdebug-prefix-map or -fdebug-compilation-dir are used appropriately. See also the discussion under Compiling in different directories.

The reason for including the CWD in the hash by default is to prevent a problem with the storage of the current working directory in the debug info of an object file, which can lead ccache to return a cached object file that has the working directory in the debug info set incorrectly.

You can disable this option to get cache hits when compiling the same source code in different directories if you don’t mind that CWD in the debug info might be incorrect.

ignore_headers_in_manifest (CCACHE_IGNOREHEADERS)

This option is a list of paths to files (or directories with headers) that ccache will not include in the manifest list that makes up the direct mode. Note that this can cause stale cache hits if those headers do indeed change.

ignore_options (CCACHE_IGNOREOPTIONS)

This option is a space-delimited list of compiler options that ccache will ignore. Entries in the list can optionally end with an asterisk (*) to matching any option suffix. For example, -fmessage-length=* will match both -fmessage-length=20 and -fmessage-length=70. A matching compiler option will neither be interpreted specially nor be part of the input hash. Ignoring a compiler option from the hash can be useful when you know it doesn’t affect the result (and ccache doesn’t know that), or when it does and you don’t care. See also Extra options.

inode_cache (CCACHE_INODECACHE or CCACHE_NOINODECACHE, see Boolean values above)

If true, ccache will cache source file hashes based on device, inode and timestamps. This reduces the time spent on hashing include files since the result can be reused between compilations. The default is true. The feature requires temporary_dir to be located on a local filesystem of a supported type.

Support for the inode cache feature on Windows is experimental. On Windows the default is false.
keep_comments_cpp (CCACHE_COMMENTS or CCACHE_NOCOMMENTS, see Boolean values above)

If true, ccache will not discard the comments before hashing preprocessor output. The default is false. This can be used to check documentation with -Wdocumentation.

libexec_dirs (CCACHE_LIBEXEC_DIRS)

If set, ccache will look for helper programs in these directories instead of the default.

log_file (CCACHE_LOGFILE)

If set to a file path, ccache will write information on what it is doing to the specified file. This is useful for tracking down problems.

If set to syslog, ccache will log using syslog() instead of to a file. If you use rsyslogd, you can add something like this to /etc/rsyslog.conf or a file in /etc/rsyslog.d:

# log ccache to file
:programname, isequal, "ccache"         /var/log/ccache
# remove from syslog
& ~
max_files (CCACHE_MAXFILES)

This option specifies the maximum number of files to keep in the cache. Use 0 for no limit (which is the default). See also Cache size management.

max_size (CCACHE_MAXSIZE)

This option specifies the maximum size of the cache. Use 0 for no limit. The default value is 5GiB. Available suffixes: kB, MB, GB, TB (decimal) and KiB, MiB, GiB, TiB (binary). The default suffix is GiB. See also Cache size management.

msvc_dep_prefix (CCACHE_MSVC_DEP_PREFIX)

This option specifies the prefix of included files output for MSVC compiler. The default prefix is “Note: including file:”. If you use a localized compiler, this should be set accordingly.

msvc_utf8 (CCACHE_MSVC_UTF8)

This option adds /utf-8 to the msvc command line when executing the preprocessor to ensure that filenames are not garbled for non-ascii characters. This implicitly enables /validate-charset and treats the source code as utf-8 which may cause compilation errors if comments in your code have characters in the [128, 255] range for a given Windows system codepage which results in an invalid utf-8 sequence. The default is true.

namespace (CCACHE_NAMESPACE)

If set, the namespace string will be added to the hashed data for each compilation. This will make the associated cache entries logically separate from cache entries with other namespaces, but they will still share the same storage space. Cache entries can also be selectively removed from the local cache with the command line option --evict-namespace, potentially in combination with --evict-older-than.

For instance, if you use the same local cache for several disparate projects, you can use a unique namespace string for each one. This allows you to remove cache entries that belong to a certain project if you stop working with that project.

path (CCACHE_PATH)

If set, ccache will search directories in this list when looking for the real compiler. If not set, ccache will look for the first executable matching the compiler name in the normal PATH that isn’t a symbolic link to ccache itself.

pch_external_checksum (CCACHE_PCH_EXTSUM or CCACHE_NOPCH_EXTSUM, see Boolean values above)

When this option is set, and ccache finds a precompiled header file, ccache will look for a file with the extension “.sum” added (e.g. “pre.h.gch.sum”), and if found, it will hash this file instead of the precompiled header itself to work around the performance penalty of hashing very large files.

prefix_command (CCACHE_PREFIX)

This option adds a list of prefixes (separated by space) to the command line that ccache uses when invoking the compiler. See also Using ccache with other compiler wrappers.

prefix_command_cpp (CCACHE_PREFIX_CPP)

This option adds a list of prefixes (separated by space) to the command line that ccache uses when invoking the preprocessor.

read_only (CCACHE_READONLY or CCACHE_NOREADONLY, see Boolean values above)

If true, ccache will attempt to use existing cached results, but it will not add new results to any cache backend. Statistics counters will still be updated, though, unless the stats option is set to false.

If you are using this because your ccache directory is read-only, you need to set temporary_dir since ccache will fail to create temporary files otherwise. You may also want to set stats to false make ccache not even try to update stats files.

read_only_direct (CCACHE_READONLY_DIRECT or CCACHE_NOREADONLY_DIRECT, see Boolean values above)

Just like read_only except that ccache will only try to retrieve results from the cache using the direct mode, not the preprocessor mode. See documentation for read_only regarding using a read-only ccache directory.

recache (CCACHE_RECACHE or CCACHE_NORECACHE, see Boolean values above)

If true, ccache will not use any previously stored result. New results will still be cached, possibly overwriting any pre-existing results.

remote_only (CCACHE_REMOTE_ONLY or CCACHE_NOREMOTE_ONLY, see Boolean values above)

If true, ccache will only use remote storage. The default is false. Note that cache statistics counters will still be kept in the local cache directory unless stats is false. See also Storage interaction.

remote_storage (CCACHE_REMOTE_STORAGE)

This option specifies one or several storage backends (separated by whitespace) to query after checking the local cache (unless remote_only is true). See Remote storage backends for documentation of syntax and available backends.

Examples:

remote_storage = file:/shared/nfs/directory+`
remote_storage =
  file:///shared/nfs/one read-only
  file:///shared/nfs/two
remote_storage = file:///Z:/example/windows/folder
remote_storage = http://example.com/cache
remote_storage = redis://example.com
In previous ccache versions this option was called secondary_storage (CCACHE_SECONDARY_STORAGE), which can still be used as an alias.
reshare (CCACHE_RESHARE or CCACHE_NORESHARE, see Boolean values above)

If true, ccache will write results to remote storage even for local storage cache hits. The default is false.

response_file_format (CCACHE_RESPONSE_FILE_FORMAT)

Ccache normally guesses the response file format based on the compiler type. The response_file_format option lets you force the response file quoting behavior. This can be useful if the compiler supports both POSIX and Windows response file quoting. Possible values are:

auto

Guess one of the formats below based on the compiler type. This is the default.

posix

POSIX quoting behavior.

windows

Windows quoting behavior.

safe_dirs (CCACHE_SAFE_DIRS)

List of trusted directories for which directory-specific configuration files are allowed to set "unsafe options" (see Directory-specific configuration file). The default is empty.

Allowed list values: * matches any directory. An absolute path ending with /* matches any subdirectory (at any depth) under that path. An absolute path not ending in /* matches only that directory.

sloppiness (CCACHE_SLOPPINESS)

By default, ccache tries to give as few false cache hits as possible. However, in certain situations it’s possible that you know things that ccache can’t take for granted. This option makes it possible to tell ccache to relax some checks in order to increase the hit rate. Available values (separated by whitespace or comma):

clang_index_store

Use case: Xcode projects with varying index store paths.
Effect: Ignores the -index-store-path and -index-unit-output-path options when hashing.
Trade-off: Index won’t update correctly on cache hits.

file_stat_matches

Use case: When file content checking is too slow.
Effect: Uses file timestamps instead of content for cache validation.
Trade-off: May miss content changes with identical timestamps.

file_stat_matches_ctime

Use case: When controlling file timestamps manually.
Effect: Ignores status change time when file_stat_matches is enabled.
Trade-off: May miss some file system changes.

gcno_cwd

Use case: Code coverage builds in different directories.
Effect: Ignores current directory when creating .gcno files (-ftest-coverage). Also disables hashing of the current working directory if -fprofile-abs-path is used.
Trade-off: Directory information in coverage files may be incorrect.

No effect with --coverage (it implies -fprofile-arcs).
incbin

Use case: Projects using assembly .incbin directives.
Effect: Allows caching files with .incbin directives.
Trade-off: Won’t detect changes to included binary files.

include_file_ctime

Use case: Build systems that modify file timestamps frequently.
Effect: Ignores file status change time when checking for recent modifications.
Trade-off: May miss recent changes to source files.

include_file_mtime

Use case: Build systems that modify file timestamps frequently.
Effect: Ignores file modification time when checking for recent changes.
Trade-off: May miss recent modifications to source files.

ivfsoverlay

Use case: Xcode projects mixing Objective-C and Swift.
Effect: Ignores -ivfsoverlay virtual filesystem option.
Trade-off: May not detect VFS-related changes.

locale

Use case: Builds in environments with varying locale settings.
Effect: Ignores locale environment variables (LANG, LC_ALL, LC_CTYPE, LC_MESSAGES).
Trade-off: Compiler warning messages may vary between cached and fresh builds.

modules

Use case: Clang builds using -fmodules.
Effect: Allows caching when C++ modules are used.
Trade-off: May not detect changes in module internal state.

See C++ modules for details.

pch_defines

Use case: Projects with precompiled headers.
Effect: Relaxes checking of #define directives in precompiled headers.
Trade-off: May not detect some macro definition changes.

See Precompiled headers for details.

random_seed

Use case: Builds with varying -frandom-seed values.
Effect: Ignores random seed values in compilation hash.
Trade-off: Builds may not be fully reproducible.

system_headers

Use case: Systems with frequently changing system headers.
Effect: Only tracks non-system headers in direct mode.
Trade-off: Won’t detect system header changes that affect compilation.
Limitations: Only supported for GCC-like compilers (not MSVC). System headers are still checked in preprocessor mode.

See also ignore_headers_in_manifest.

time_macros

Use case: Code using time macros but values don’t matter.
Effect: Ignores __DATE__, __TIME__, and __TIMESTAMP__ in source.
Trade-off: Time values in output will be from cached compilation.

stats (CCACHE_STATS or CCACHE_NOSTATS, see Boolean values above)

If true, ccache will update the statistics counters on each compilation. The default is true. If false, automatic cleanup will be disabled as well.

stats_log (CCACHE_STATSLOG)

If set to a file path, ccache will write statistics counter updates to the specified file. This is useful for getting statistics for individual builds. To show a summary of the current stats log, use ccache --show-log-stats.

Lines in the stats log starting with a hash sign (#) are comments.
temporary_dir (CCACHE_TEMPDIR)

This option specifies where ccache will put temporary files. The default is $XDG_RUNTIME_DIR/ccache-tmp (typically /run/user/<UID>/ccache-tmp) if XDG_RUNTIME_DIR is set and the directory exists, otherwise <cache_dir>/tmp.

In previous versions of ccache, CCACHE_TEMPDIR had to be on the same filesystem as the CCACHE_DIR path, but this requirement has been relaxed.
umask (CCACHE_UMASK)

This option (an octal integer) specifies the umask for files and directories in the cache directory. This is mostly useful when you wish to share your cache with other users.

Disabling ccache

To disable ccache completely for all invocations, set disable = true (CCACHE_DISABLE=1). You can also disable ccache for a certain source code file by adding the string ccache:disable in a comment in the first 4096 bytes of the file. In the latter case the Ccache disabled statistics counter will be increased.

Remote storage backends

The remote_storage option lets you configure ccache to use one or several remote storage backends. By default, the local cache directory located in cache_dir will be queried first and remote storage second, but remote_only can be set to true to disable local storage. Note that cache statistics counters will still be kept in the local cache directory — remote storage backends only store compilation results and manifests.

Storage helper process

ccache can spawn a long-lived local storage helper process (installed separately) to handle communication with the remote storage. Storage helpers keep remote connections up for efficiency and terminate after a while on inactivity.

The storage helper program is called ccache-storage-<scheme>, where <scheme> is the scheme part of a URL, e.g. https. The program can be placed in these locations (in priority order):

  1. In a location specified by the helper property (see below).

  2. In $PATH.

  3. Next to the ccache executable.

  4. In ccache’s libexec directory.

If the program is not found, ccache falls back to one of the builtin backends if available, otherwise ccache exits with an error.

Configuration syntax

A remote storage backend is specified by a URL and can be followed by a whitespace-separated list of properties (key=value) and custom attributes (@key=value). A missing =value is shorthand for setting the value to true. Values must be percent-encoded if they contain %, | or whitespace characters. For compatibility with older ccache versions, | characters are treated as spaces.

Properties

  • data-timeout: Timeout for send/receive data transfer. Resets whenever data is received or can be sent. Default: 1s.

  • helper: Override which storage helper to spawn (either a filename or a full path). This is mainly useful when developing or testing new helpers.

  • idle-timeout: Timeout for the helper process to wait before exiting after client inactivity (0s: stay up indefinitely). Default: 10m.

  • read-only: If true, only read from this backend, don’t write. The default is false.

  • request-timeout: Timeout for the whole request. Default: 10s.

  • shards: A comma-separated list of names for sharding (partitioning) the cache entries using Rendezvous hashing, typically to spread the cache over a server cluster. When set, the storage URL must contain an asterisk (*), which will be replaced by one of the shard names to form a real URL. A shard name can optionally have an appended weight within parentheses to indicate how much of the key space should be associated with that shard. A shard with weight w will contain w/S of the cache, where S is the sum of all shard weights. A weight could for instance be set to represent the available memory for a memory cache on a specific server. The default weight is 1.

    Timeouts can be specified with an ms (milliseconds), s (seconds), m (minutes), h (hours) or d (days) suffix.

    Examples:

    • http://cache-*.example.com shards=a(3),b(1),c(1.5) will put 55% (3/5.5) of the cache on http://cache-a.example.com, 18% (1/5.5) on http://cache-b.example.com and 27% (1.5/5.5) on http://cache-c.example.com.

    • http://example.com/* shards=alpha,beta will put 50% of the cache on http://example.com/alpha and 50% on http://example.com/beta.

Custom attributes

Custom attributes on the form @key=value are specific to each storage helper implementation. See the backend’s documentation for which attributes are available. Examples:

  • file:///example/directory @umask=002 @update-mtime=true

  • https://example.com/path @bearer-token=deadbeef

Storage interaction

The table below describes the interaction between local and remote storage on cache hits and misses if remote_only is false (which is the default):

Local storage Remote storage What happens

miss

miss

Compile, write to local, write to remote[1]

miss

hit

Read from remote, write to local

hit

-

Read from local, don’t write to remote[2]

[1] Unless remote storage has property read-only=true.
[2] Unless local storage is set to share its cache hits with the reshare option.

If remote_only is true:

Local storage Remote storage What happens

-

miss

Compile, write to remote, don’t write to local

-

hit

Read from remote, don’t write to local

File storage backend

URL format: file:DIRECTORY or file://[HOST]DIRECTORY

This backend stores data as separate files in a directory structure below DIRECTORY, similar (but not identical) to the local cache storage. A typical use case for this backend would be sharing a cache on an NFS directory. DIRECTORY must start with a slash. HOST can be the empty string or localhost. On Windows, HOST can also be the name of a server hosting a shared folder.

ccache will not perform any cleanup of the storage — that has to be done by other means, for instance by running ccache --trim-dir periodically.

Examples:

  • file:/shared/nfs/directory

  • file:///shared/nfs/directory @umask=002 @update-mtime=true

  • file:///Z:/example/windows/folder

  • file://example.com/shared/ccache%20folder

Optional attributes:

  • @layout: How to store file under the cache directory. Available values:

    • flat: Store all files directly under the cache directory.

    • subdirs: Store files in 256 subdirectories of the cache directory.

    The default is subdirs.

  • @umask: This attribute (an octal integer) overrides the umask to use for files and directories in the cache directory.

  • @update-mtime: If true, update the modification time (mtime) of cache entries that are read. The default is false.

CRSH storage backend

URL format: crsh:IPC_ENDPOINT

This backend connects to an already running ccache storage helper (CRSH) process listening on IPC_ENDPOINT (Unix socket path or Windows named pipe). The use case for this is mainly when developing or debugging a storage helper, or in special setups where the helper program is started and managed externally.

Examples:

  • crsh:/path/to/your.sock (Unix socket)

  • crsh:name-of-your-pipe (Windows named pipe)

HTTP storage backend

Built-in support for the HTTP protocol will likely be removed in a future ccache release.

URL format: http://HOST[:PORT][/PATH]

This backend stores data in an HTTP-compatible server. The required HTTP methods are GET, PUT and DELETE.

ccache will not perform any cleanup of the storage — that has to be done by other means, for instance by running ccache --trim-dir periodically.
HTTPS is not supported.
See How to set up HTTP storage for hints on how to set up an HTTP server for use with ccache.

Examples:

  • http://localhost

  • http://someusername:p4ssw0rd@example.com/cache/

  • http://localhost:8080 @layout=bazel

Optional attributes:

  • @bearer-token: Bearer token used to authorize the HTTP requests.

  • @keep-alive: If true, keep the HTTP connection to the storage server open to avoid reconnects. The default is true.

  • @layout: How to map key names to the path part of the URL. Available values:

    • bazel: Store values in a format compatible with the Bazel HTTP caching protocol. More specifically, the entries will be stored as 64 hex digits under the /ac/ part of the cache.

      You may have to disable verification of action cache values in the server for this to work since ccache entries are not valid action result metadata values.

    • flat: Append the key directly to the path part of the URL (with a leading slash if needed).

    • subdirs: Append the first two characters of the key to the URL (with a leading slash if needed), followed by a slash and the rest of the key. This divides the entries into 256 buckets.

    The default is subdirs.

  • @header: Add the key=value pair to the HTTP headers of the request. For example: @header=Content-Type=application/octet-stream adds "Content-Type: application/octet-stream" to the HTTP headers of the request.

Redis storage backend

Built-in support for the Redis protocol will likely be removed in a future ccache release.

URL formats:

redis://[[USERNAME:]PASSWORD@]HOST[:PORT][/DBNUMBER]
redis+unix:SOCKET_PATH[?db=DBNUMBER]
redis+unix://[[USERNAME:]PASSWORD@localhost]SOCKET_PATH[?db=DBNUMBER]

This backend stores data in a Redis (or Redis-compatible) server. There are implementations for both memory-based and disk-based storage. PORT defaults to 6379 and DBNUMBER defaults to 0.

ccache will not perform any cleanup of the Redis storage, but you can configure LRU eviction.
See How to set up Redis storage for hints on setting up a Redis server for use with ccache.
You can set up a cluster of Redis servers using the shards property described in Remote storage backends.

Examples:

  • redis://localhost

  • redis://p4ssw0rd@cache.example.com:6379/0

  • redis+unix:/run/redis.sock

  • redis+unix:///run/redis.sock

  • redis+unix://p4ssw0rd@localhost/run/redis.sock?db=0

Cache size management

By default, ccache has a 5 GB limit on the total size of files in the cache and no limit on the number of files. You can set different limits using the command line options -M/--max-size and -F/--max-files. Use the -s/--show-stats option to see the cache size and the currently configured limits (in addition to other various statistics).

Cleanup can be triggered in two different ways: automatic and manual.

Automatic cleanup

After a new compilation result has been stored in the local cache, ccache will trigger an automatic cleanup if max_size or max_files is exceeded. The cleanup removes cache entries in approximate LRU (least recently used) order based on the modification time (mtime) of files in the cache. For this reason, ccache updates mtime of the cache files read on a cache hit to mark them as recently used.

For performance reasons only entries in a subset of the cache are considered when automatic cleanup is triggered, so the oldest entries aren’t always removed first but the overall behavior approximates LRU over time.

Manual cleanup

Run ccache --cleanup to force cleanup of the whole cache. This will recalculate the cache size information and make sure that the cache size does not exceed max_size and max_files.

Note that there is no guarantee that only the oldest entries are evicted, as discussed in Automatic cleanup above. To evict based on age use ccache --evict-older-than AGE.

Cache compression

By default, ccache compresses all cached data using the Zstandard (zstd) algorithm at compression level 1. This algorithm is fast enough that compression rarely impacts performance. You might want to disable compression only if your cache is stored on an already-compressed filesystem, where ccache’s compression would be redundant.

For configuration details, see compression and compression_level.

Use ccache --show-compression to display compression information. Example output:

Total data:           14.8 GB (16.0 GB disk blocks)
Compressed data:      11.3 GB (30.6% of original size)
  Original size:      36.9 GB
  Compression ratio: 3.267 x  (69.4% space savings)
Incompressible data:   3.5 GB

Notes:

  • Disk blocks: The actual cache size accounting for filesystem block size. This should match the "Cache size" from ccache --show-stats.

  • Compressed data: Result and manifest files stored in the cache.

  • Incompressible data: Files stored without compression (due to file_clone or hard_link settings) or legacy files from older ccache versions.

  • Compression ratio: Affected by compression_level.

You can recompress cached data to different compression levels using ccache --recompress. Only files with different compression levels than the target will be recompressed.

Cache statistics

ccache --show-stats shows a summary of statistics, including cache size, cleanups (number of performed cleanups, either implicitly due to a cache size limit being reached or due to explicit ccache -c calls), overall hit rate, hit rate for direct/preprocessed modes and hit rate for local and remote storage.

The statistics counters are not used by ccache itself during builds. This means that you can safely reset them at any time using ccache --zero-stats without affecting the build process. For example, you might reset them before a build so that ccache --show-stats will only summarize the results from that specific build. Alternatively, you can set stats_log before starting the build and then run ccache --show-log-stats afterward to view build-specific statistics. This approach allows the statistics counters to continue tracking the entire lifetime of the cache while still giving you detailed information for individual builds. Another advantage of stats_log is that it collects statistics without interference from other concurrent builds that access the same cache.

The summary also includes counters called “Errors” and “Uncacheable”, which are sums of more detailed counters. To see those detailed counters, use the -v/--verbose flag. The verbose mode can show the following counters:

Counter Description

Autoconf compile/link

Uncacheable compilation or linking by an Autoconf test.

Bad compiler arguments

Malformed compiler argument, e.g. missing a value for a compiler option that requires an argument or failure to read a file specified by a compiler option argument.

Called for linking

The compiler was called for linking, not compiling. Ccache only supports compilation of a single file, i.e. calling the compiler with the -c option to produce a single object file from a single source file.

Called for preprocessing

The compiler was called for preprocessing, not compiling.

Ccache disabled

Ccache was disabled by a ccache:disable string in the source code file.

Could not use modules

Preconditions for using C++ modules were not fulfilled.

Could not use precompiled header

Preconditions for using precompiled headers were not fulfilled.

Could not read or parse input file

An input file could not be read or parsed (see the debug log for details).

Could not write to output file

The output path specified with -o could not be written to.

Compilation failed

The compilation failed. No result stored in the cache.

Compiler check failed

A compiler check program specified by compiler_check (CCACHE_COMPILERCHECK) failed.

Compiler output file missing

One of the files expected to be produced by the compiler was missing after compilation.

Compiler produced empty output

The compiler’s output file (typically an object file) was empty after compilation.

Could not find the compiler

The compiler to execute could not be found.

Error hashing extra file

Failure reading a file specified by extra_files_to_hash (CCACHE_EXTRAFILES).

Forced recache

CCACHE_RECACHE was used to overwrite an existing result.

Input file modified during compilation

An input file was modified during compilation.

Internal error

Unexpected failure, e.g. due to problems reading/writing the cache.

Missing cache file

A file was unexpectedly missing from the cache. This only happens in rare situations, e.g. if one ccache instance is about to get a file from the cache while another instance removed the file as part of cache cleanup.

Multiple source files

The compiler was called to compile multiple source files in one go. This is not supported by ccache.

No input file

No input file was specified to the compiler.

Output to stdout

The compiler was instructed to write its output to standard output using -o -. This is not supported by ccache.

Preprocessing failed

Preprocessing the source code using the compiler’s -E option failed.

Unsupported code directive

Code like the assembler .incbin directive was found. This is not supported by ccache.

Unsupported compiler option

A compiler option not supported by ccache was found.

Unsupported environment variable

An environment variable not supported by ccache was set.

Unsupported source encoding

Source file (or an included header) has unsupported encoding. ccache currently requires UTF-8-encoded source code for MSVC when msvc_utf8 is true.

Unsupported source language

A source language e.g. specified with -x was unsupported by ccache.

How ccache works

Ccache detects when you’re compiling the same code and reuses previously stored output. It works by creating a unique hash (the “input hash”) from various information that affects the compilation. When the same hash is encountered again, ccache can supply all the correct compiler outputs from the cache.

For hashing, ccache uses BLAKE3, a fast cryptographic hash algorithm. For data integrity, cached data is protected with XXH3 checksums to detect corruption.

Ccache has two strategies for gathering the information used to create cache lookup keys:

  • Preprocessor mode: Ccache runs the preprocessor on the source code and hashes the result.

  • Direct mode: Ccache hashes the source code and include files directly.

Direct mode is generally faster because it avoids the overhead of running the preprocessor.

When direct mode doesn’t find a cached result (cache miss), ccache falls back to preprocessor mode unless depend mode is enabled. In depend mode, ccache never runs the preprocessor, even on cache misses. See The depend mode for details.

Common hashed information

The following information is always included in the hash:

  • the extension used by the compiler for a file with preprocessor output (normally .i for C code and .ii for C++ code)

  • the compiler’s size and modification time (or other compiler-specific information specified by compiler_check)

  • the name of the compiler

  • the current directory (if hash_dir is enabled)

  • contents of files specified by extra_files_to_hash (if any)

The preprocessor mode

In the preprocessor mode, the hash is formed of the common information and:

  • the preprocessor output from running the compiler with -E

  • the command line options except those that affect include files (-I, -include, -D, etc; the theory is that these command line options will change the preprocessor output if they have any effect at all)

  • any standard error output generated by the preprocessor

Based on the hash, the cached compilation result can be looked up directly in the cache.

The direct mode

In the direct mode, the hash is formed of the common information and:

  • the input source file

  • the compiler options

Based on the hash, a data structure called “manifest” is looked up in the cache. The manifest contains:

  • references to cached compilation results (object file, dependency file, etc) that were produced by previous compilations that matched the hash

  • paths to the include files that were read at the time the compilation results were stored in the cache

  • hash sums of the include files at the time the compilation results were stored in the cache

The current contents of the include files are then hashed and compared to the information in the manifest. If there is a match, ccache knows the result of the compilation. If there is no match, ccache falls back to running the preprocessor. The output from the preprocessor is parsed to find the include files that were read. The paths and hash sums of those include files are then stored in the manifest along with information about the produced compilation result.

There is a catch with the direct mode: header files that were used by the compiler are recorded, but header files that were not used, but would have been used if they existed, are not. To mitigate this problem, ccache records whether directories specified with -I and similar exist at the time of compilation, which handles most cases. Still, when ccache checks if a result can be taken from the cache, it currently can’t check with 100% accuracy if the existence of a new header file should invalidate the result. In practice, the direct mode is safe to use in the absolute majority of cases.

The direct mode will be disabled if any of the following holds:

  • direct_mode is false

  • a modification time of one of the include files is too new (needed to avoid a race condition)

  • a compiler option not supported by the direct mode is used, for example:

    • a -Wp,* compiler option other than -Wp,-MD,<path>, -Wp,-MMD,<path>, -Wp,-D<macro[=defn]> or -Wp,-U<macro>

    • most uses of -Xpreprocessor

  • the string __TIME__ is present in the source code

The depend mode

If the depend mode is enabled, ccache will not use the preprocessor at all. The hash used to identify results in the cache will be based on the direct mode hash described above plus information about include files read from the dependency list generated by MSVC with /showIncludes, or the dependency file generated by other compilers with -MD or -MMD.

Advantages:

  • The ccache overhead of a cache miss will be much smaller.

  • Not running the preprocessor at all can be good if compilation is performed remotely, for instance when using distcc or similar; ccache then won’t make potentially costly preprocessor calls on the local machine.

Disadvantages:

  • The cache hit rate will likely be lower since any change to compiler options or source code will make the hash different. Compare this with the default setup where ccache will fall back to the preprocessor mode, which is tolerant to some types of changes of compiler options and source code changes.

  • If -MD is used, the manifest entries will include system header files as well, thus slowing down cache hits slightly, just as using -MD slows down make. This is also the case for MSVC with /showIncludes.

  • If -MMD is used, the manifest entries will not include system header files, which means ccache will ignore changes in them.

The depend mode will be disabled if any of the following holds:

  • depend_mode is false.

  • The compiler is not generating dependencies using -MD or -MMD (for MSVC, /showIncludes is added automatically if not specified by the user).

Handling of newly created source files

If modification time (mtime) or status change time (ctime) of the source file or one of the include files is equal to (or newer than) the time that ccache was invoked, ccache disables caching completely. This is done as a safety measure to avoid a race condition (see below). In practice, this is only a problem when using file systems with very low timestamp granularity. You can set sloppiness to include_file_ctime,include_file_mtime to opt out of the safety measure.

For reference, the race condition mentioned above consists of these events:

  1. A source code file is read by ccache and added to the input hash.

  2. The source code file is modified.

  3. The compiler is executed and reads the modified source code.

  4. Ccache stores the compiler output in the cache associated with the incorrect key (based on the unmodified source code).

Cache debugging

To find out what information ccache actually is hashing, you can enable the debug mode via the configuration option debug or by setting CCACHE_DEBUG in the environment. This can be useful if you are investigating why you don’t get cache hits. Note that performance will be reduced slightly.

When the debug mode is enabled, ccache will create up to five additional files next to the object file:

Filename Debug level Description

<objectfile>.<timestamp>.ccache-input-c

2

Binary input hashed by both the direct mode and the preprocessor mode.

<objectfile>.<timestamp>.ccache-input-d

2

Binary input only hashed by the direct mode.

<objectfile>.<timestamp>.ccache-input-p

2

Binary input only hashed by the preprocessor mode.

<objectfile>.<timestamp>.ccache-input-text

2

Human-readable combined diffable text version of the three files above.

<objectfile>.<timestamp>.ccache-log

1

Log for this object file.

The timestamp format is <year><month><day>_<hour><minute><second>_<microsecond>.

If you only need the log file, set debug_level (environment variable CCACHE_DEBUGLEVEL) to 1.

If debug_dir (environment variable CCACHE_DEBUGDIR) is set, the files above will be written to that directory with full absolute paths instead of next to the object file.

In the direct mode, ccache uses the 160 bit BLAKE3 hash of the “ccache-input-c” + “ccache-input-d” data (where + means concatenation), while the “ccache-input-c” + “ccache-input-p” data is used in the preprocessor mode.

The “ccache-input-text” file is a combined text version of the three binary input files. It has three sections (“COMMON”, “DIRECT MODE” and “PREPROCESSOR MODE”), which is turn contain annotations that say what kind of data comes next.

To debug why you don’t get an expected cache hit for an object file, you can do something like this:

  1. Enable debug (CCACHE_DEBUG).

  2. Build.

  3. Clean and build again.

  4. Compare the <objectfile>.<timestamp>.ccache-input-text files for the two builds. This together with the <objectfile>.<timestamp>.ccache-log files should give you some clues about what is happening.

Compiling in different directories

When compiling the same source code in different directories, ccache often can’t share cached results if absolute paths become part of the input hash. These paths appear in:

  • preprocessed source code (when using -g for debug info or absolute paths in -I options)

  • command-line arguments (absolute paths to source files or include directories)

  • macro expansions (__FILE__ macros and preprocessor warnings)

To enable cache sharing across different build directories for debug builds (using -g), normalize debug paths e.g. with GCC option -fdebug-prefix-map=$PWD=. (map current directory to relative) or -fdebug-compilation-dir=. (set compilation directory). Alternatively, set hash_dir to false (disables directory hashing).

For builds with absolute paths, set base_dir to a common parent directory. Ccache will convert absolute paths under this directory to relative paths before hashing.

For example, if projects are in /home/user/projects, set base_dir to /home/user/projects or just /home/user.

Precompiled headers

Ccache has limited support for precompiled headers (PCH) with GCC and Clang.

Required configuration:

  1. Set sloppiness to pch_defines,time_macros

    • This is needed because ccache can’t detect time macro usage or #define changes when using PCH.

    • Consider adding include_file_mtime,include_file_ctime for newly created files (see Handling of newly created source files).

  2. One of:

    • GCC/Clang: Use -include header (don’t use #include in source; the filename must be sufficient to find the header).

    • Clang only: Use -include-pch with the generated PCH file.

    • GCC only: Add -fpch-preprocess when compiling.

  3. For Clang, add -fno-pch-timestamp to disable timestamp checks.

Troubleshooting:

  • Without proper setup, ccache falls back to the non-precompiled header (if available).

  • If no fallback exists, you’ll see “Preprocessing failed” in statistics.

  • Files using #pragma once instead of include guards may cause issues.

C++ modules

Ccache does currently not support standard C++20 modules.

There is however limited support for “Clang modules” (the -fmodules option) with these requirements:

This is how it works:

  • Ccache hashes module.modulemap files but ignores Clang’s binary module cache.

  • This works because identical module.modulemap files should produce compatible cached results.

The preprocessor mode doesn’t provide enough information for module support depend mode. When using the preprocessor mode Clang does not provide enough information to allow hashing of module.modulemap files.

Sharing a local cache

A group of developers can increase the cache hit rate by sharing a local cache directory. To share a local cache without unpleasant side effects, the following conditions should to be met:

  • Use the same cache directory.

  • Make sure that the configuration option hard_link is false (which is the default).

  • Make sure that all users are in the same group.

  • Set the configuration option umask to 002. This ensures that cached files are accessible to everyone in the group.

  • Make sure that all users have write permission in the entire cache directory (and that you trust all users of the shared cache).

  • Make sure that the setgid bit is set on all directories in the cache. This tells the filesystem to inherit group ownership for new directories. The following command might be useful for this:

    find $CCACHE_DIR -type d | xargs chmod g+s

The reason to avoid the hard link mode is that the hard links cause unwanted side effects, as all links to a cached file share the file’s modification timestamp. This results in false dependencies to be triggered by timestamp-based build systems whenever another user links to an existing file. Typically, users will see that their libraries and binaries are relinked without reason.

You may also want to make sure that a base directory is set appropriately, as discussed in a previous section.

Sharing a cache on NFS

It is possible to put the cache directory on an NFS filesystem (or similar filesystems), but keep in mind that:

  • Having the cache on NFS may slow down compilation. Make sure to do some benchmarking to see if it’s worth it.

  • Ccache hasn’t been tested very thoroughly on NFS.

A tip is to set temporary_dir to a directory on the local host to avoid NFS traffic for temporary files.

It is recommended to use the same operating system version when using a shared cache. If operating system versions are different then system include files will likely be different and there will be few or no cache hits between the systems. One way of improving cache hit rate in that case is to set sloppiness to system_headers to ignore system headers.

An alternative to putting the main cache directory on NFS is to set up a remote storage file cache.

Using ccache with other compiler wrappers

The recommended way of combining ccache with another compiler wrapper (such as “distcc”) is by letting ccache execute the compiler wrapper. This is accomplished by defining prefix_command, for example by setting the environment variable CCACHE_PREFIX to the name of the wrapper (e.g. distcc). Ccache will then prefix the command line with the specified command when running the compiler. To specify several prefix commands, set prefix_command to a space-separated list of commands.

Unless you set compiler_check to a suitable command (see the description of that configuration option), it is not recommended to use the form ccache anotherwrapper compiler args as the compilation command. It’s also not recommended to use the masquerading technique for the other compiler wrapper. The reason is that by default, ccache will in both cases hash the mtime and size of the other wrapper instead of the real compiler, which means that:

  • Compiler upgrades will not be detected properly.

  • The cached results will not be shared between compilations with and without the other wrapper.

Another minor thing is that if prefix_command is used, ccache will not invoke the other wrapper when running the preprocessor, which increases performance. You can use prefix_command_cpp if you also want to invoke the other wrapper when doing preprocessing (normally by adding -E).

Caveats

  • The direct mode fails to pick up new header files in some rare scenarios. See The direct mode above.

Troubleshooting

General

To understand what ccache is doing you can enable debug logging by setting debug to true or using the environment variable CCACHE_DEBUG=1. See Cache debugging for details.

You can also use ccache -s to view cache hit rates, miss reasons and other performance metrics.

Performance

Ccache is designed to work well with minimal configuration, but you can optimize performance further:

  • Place the cache directory on fast storage (SSD preferred).

  • Ensure sufficient RAM so cached files stay in the filesystem cache.

  • Consider using remote storage for sharing the cache.

To monitor cache effectiveness, compare ccache -s output before and after builds to identify issues.

If “preprocessed cache hits” increases instead of “direct cache hits”, ccache is falling back to the slower preprocessor mode. Causes include:

  • source code changes that don’t affect preprocessor output

  • changes to include-related options (-I, -include, -D) that don’t change the actual preprocessed code

  • using unsupported preprocessor options like -Xpreprocessor or -Wp,* (except -Wp,-MD,<path>, -Wp,-MMD,<path>, -Wp,-D<define>)

  • first compilation after changing base_dir

  • include files with timestamps newer than ccache startup (see Handling of newly created source files)

  • code containing __TIME__, __DATE__, or __TIMESTAMP__ forces preprocessor mode (if these macros aren’t actually used or you don’t need current values, set sloppiness to time_macros)

  • input file path changes (affects __FILE__ macro expansion)

If identical code doesn’t produce cache hits these are some possible causes:

  • time/date macros or generated code with timestamps/build counters

  • cache cleanup due to size limits

  • environment differences affecting compilation

Common error counters:

  • “Multiple source files”: The compiler was called with multiple source files at once (not supported by ccache).

  • “Unsupported compiler option”: Enable debug logging to see which option was rejected.

  • “Preprocessing failed”: Could indicate precompiled header issues (see Precompiled headers).

  • “Could not use precompiled header”: See Precompiled headers for setup requirements.

  • “Could not use modules”: See C++ modules for configuration needs and check which compiler option was rejected.

Corrupt object files

It should be noted that ccache is susceptible to general storage problems. If a bad object file sneaks into the cache for some reason, it will of course stay bad. Some possible reasons for erroneous object files are bad hardware (disk drive, disk controller, memory, etc), buggy drivers or file systems, a bad prefix_command or compiler wrapper. If this happens, the easiest way of fixing it is this:

  1. Build so that the bad object file ends up in the build tree.

  2. Remove the bad object file from the build tree.

  3. Rebuild with CCACHE_RECACHE set.

An alternative is to clear the whole cache with ccache -C if you don’t mind losing other cached results.

There are no reported issues about ccache producing broken object files reproducibly. That doesn’t mean it can’t happen, so if you find a repeatable case, please report it.

More information

Credits, mailing list information, bug reporting instructions, source code, etc, can be found on ccache’s web site: https://ccache.dev.

Author

Ccache was originally written by Andrew Tridgell and is currently developed and maintained by Joel Rosdahl. See AUTHORS.txt or AUTHORS.html and https://ccache.dev/credits.html for a list of contributors.