# Configuration of libucw modules ######## Memory Mapped Access to Files ########################################## # Whenever you specify 0 for I/O buffer size, memory mapping is used instead. FBMMap { # Map this many bytes at once (needs to be a multiple of CPU page size) WindowSize 1M # When in need to extend a file, grow it by so many bytes (>= page size) ExtendSize 1M } ######## Direct Streamed I/O on Files ########################################### FBDirect { # Debug: Cheat by turning off O_DIRECT #Cheat 1 } ######## Parametrized I/O on Files ############################################## FBParam { Defaults { # Access type (std|direct|mmap). Type std # Size of I/O buffer. Something of the order of megabytes for fast disks is recommended for direct I/O. BufSize 64K # Optimize for mixed forward/backward reading (standard I/O only) KeepBackBuf 0 # Perform read-ahead (direct I/O only) ReadAhead 1 # Maximum number of write-back requests queued (direct I/O only) WriteBack 1 } } ######## Temporary files ######################################################## Tempfiles { # Filename prefix for temporary files ("pid(-tid)-counter" is appended) # The directory should not be writeable by malicious users. Prefix tmp/temp } ######## Threads ################################################################ Threads { # Default thread stack size DefaultStackSize 64K } ######## Sorter ################################################################# Sorter { # Trace sorting (1=basic statistics, 2=more stats, 3 and more for debugging) Trace 2 # Trace array sorting (internal sorters) TraceArray 0 # How much memory is the sorter allowed to use SortBuffer 4M # File access used by the sorter (see FBParam section for details) FileAccess std 256K # Use a different file access method for small inputs (less than the specified size) SmallFileAccess std 64K SmallInput 64M # Min-/Maximum number of bits to use in the external radix-sort (beware, we will open # 1+2^this files and require a stream buffer for each of them; however, while we are # doing that, the sort buffer is not allocated). Set both to zero to disable radix-sorting. MinRadixBits 2 MaxRadixBits 4 # The same for multi-way merging. The memory requirements are also the same, # but please keep in mind that this can create lots of SortBuffer-sized files, # so it is probably better to keep it disabled if you have a small SortBuffer. MinMultiwayBits 2 MaxMultiwayBits 4 # If we did not use radix-sorter to the full width, we still might add some more # bits to the width to get chunks which are even smaller than SortBuffer, because # it can speed up internal sorting later. However, we also want to avoid small # files, so we add only a little. AddRadixBits 2 # Number of threads used for sorting (0=disable threading) Threads 0 # Minimum size of input (in bytes) to consider multi-threaded internal sorting ThreadThreshold 1M # Chunks smaller than ThreadThreshold are sorted by a sequential algorithm, but # if they are at least of the following size, different chunks are sorted in # parallel. There is a slight space penalty for setting up the parallel process, # so better avoid setting this number too small. ThreadChunk 256 # Internal radix-sort stops at this size and switches to QuickSort (must be >0) RadixThreshold 4K # Debugging switches (see the source) Debug 0 } ######## URL processing ######################################################### URL { # Ignore spaces at the start/end of a URL IgnoreSpaces 1 # Ignore underflows in relative paths (/../ from root) IgnoreUnderflow 1 # Some URL's with many repeated components are filtered out to avoid infinite # URL's (e.g. http://czech.recoder.cz/win/iso/win/iso/file.html, or # http://a.com/?a=b&a=b&a=b, ...). # The URL is split to components divided by any of the specified separators. # Then the separators are forgotten and the components between them are # examined. ComponentSeparators /&? # URL is filtered out if there's a sequence of components in a row with at most # MaxRepeatLength components and the sequence is repeated more than MinRepeatCount # times. Default values are high MinRepeatCount and low MaxRepeatLength, so the # mechanism is disabled. MinRepeatCount 4 MaxRepeatLength 4 # Maximum number of occurences of a single component in the entire URL (possibly interleaved # by different components). The detector is disabled by default. MaxOccurences 4 }