aboutsummaryrefslogtreecommitdiff
path: root/lib/sqfs/block_processor/common.c
AgeCommit message (Collapse)Author
2021-01-19libsqfs: block processor: backport exact fragment matchingDavid Oberhollenzer
This commit is an amalgamation of the commits on master that implement exact matching of fragment blocks during deduplication. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2021-01-19Fix: Move fragment consolidation back to block processor serial partDavid Oberhollenzer
Keeping a list of fragments stored away in the current fragment block and consolidating them in the thread pool takes them out of circulation. If we have a lot of tiny fragments, this can lead to a situation where all the limit is reached, but we cannot do anything, because we are waiting for a block to complete, but they are all attached to the current fragment block and the queue is empty. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-06-07Fix uninitialized error code in block processor error pathDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-06-07Move the fragment deduplication hash table back into the block processorDavid Oberhollenzer
Fragment deduplication really doesn't belong into the public API of the fragment table. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-06-07block processor: add an internal common cleanup functionDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Block processor: allow operation without a fragment tableDavid Oberhollenzer
This commit modifies the block processor to support operating without a fragment table. If that is the case, fragment deduplication is essentially disabled and fragment blocks aren't indexed anymore. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Block processor: Add a raw block submission functionDavid Oberhollenzer
This function allows submission of raw blocks to the block processor, completely bypassing the file API. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Block processor: add flags to manage hashing & sparse block detectionDavid Oberhollenzer
This commit adds 2 new user settable flags to the block processor: - A flag to ignore sparse blocks and treat them like normal data blocks. - A flag to disable checksum computation altogether. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Support associating a user pointer with data blocksDavid Oberhollenzer
This commit modifies the block processor to support associating a user data pointer with data blocks that it forwards to the block writer, which is modified to accept an optional user data pointer. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Block processor: turn internal functions into interface entry pointsDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Make the block processor inode management optionalDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29Turn the sqfs_block_writer_t into an interfaceDavid Oberhollenzer
This way, everything that could be done through the hooks (and more) can be done by simply providign a custom implementation. The result is a lot clener that the previous hook based version. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-29cleanup: libsqfs: eliminate block writer statisticsDavid Oberhollenzer
- the "bytes submitted" can be moved over to the block processor - the number of blocks submitted are already there (implcitily, by adding the data block count to the fragment block count) - actual data bytes written can be computed from the super block - the remaining block count can be changed to simple counter that can be obtained through a function. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-24Minor fixes/cleanups in the block processorDavid Oberhollenzer
- Move the inode modifications out of do_block. The inode may be reallocated in parallel by the process_completed_block function, so it is not safe to store the fragment location in the do_block function which is used from the worker threads. - Move the accounting of fragment blocks to the process_completed_block function. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-24Cleanup: split the block processor common.c againDavid Oberhollenzer
This commit breaks the common code up again by moving the data submission code to a separate file, making both a little bit more readable. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-24block processor: promote fragments to fragment blocksDavid Oberhollenzer
Instead of [potentially] allocating a new fragment block, take an existing fragment and promote it to the fragmenet block. This saves as a potential block allocation and a memcpy of the initial data. Also it *definitely* removes block allocation from the backend path of the block processor. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-23block processor: move the block consolidation to the worker threadDavid Oberhollenzer
Instead of merging fragments into the fragment block inside the process_completed_fragment function, store a linked list of fragments in the fragment block and do the actual merging (several memcpy calls totaling of up to 1M of data in worst case) in the worker thread instead of the locked, serial path. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-23block processor: recycle blocks to reduce allocation pressureDavid Oberhollenzer
Instead of freeing/allocating blocks all the time in the locked, serial path, use a free list to "recycle" blocks. Once a block is no longer used, throw it onto the free list. If a new block is, needed try to get one from the free list before calling malloc. After a few iterations, the block processor should stop allocating new blocks and only re-use the ones it already has. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-23block processor: don't zero initialize the block payload areaDavid Oberhollenzer
In the block processor, the payload area is only accessed up to the indicated size. Even the part that is accessed is initialized by copying data into the block before increasing the size, so there is no real point in zero-initializing hundres of kilobytes if not megabytes of payload area, especially since this is done in the locked, serial path of the block processor. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-05-04Fix: propperly set the last block flag if fragments are disabledDavid Oberhollenzer
If a file consisting of multiple blocks is produced, the last block is short and the don't fragment flag is set, the last block flag has to be set on the block when we flush it, so the processing pipeline does it's job correctly. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-03-01Add a "do not deduplicate" block flagDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-23Turn file inode management completely over to the block processorDavid Oberhollenzer
If the block processor allocates and dynamically resizes inodes on the fly, we can add data indefinitely without knowing the size of the file ahead of time. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-23Unify the payload counters in the sqfs_inode_generic_tDavid Oberhollenzer
Instead of having seperate counters for blocks, dir index bytes and having to fiddle out the link target size, simply use a single value that stores the number of payload bytes used. A seperate "payload bytes available" is used for dynamically growing inodes during processing. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-22Move inode size accounting completely to the block processorDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-20Restructure thread pool block processorDavid Oberhollenzer
Implement the io-queue based design as outline in doc/parallelism.txt Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-16block processor: merge rest of fileapi.c into common.cDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-16Replace crc32 with xxhash32David Oberhollenzer
On the one hand, benchmarking and profiling determined xxhash32 to be faster than the zlib implementation of crc32, on the other hand profiling determined that crc32 computation contributed signifficantly to the overall runtime. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-16Minor cleanupDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-16block processor: move sparse block detection into worker threadDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-15Move block block accounting to the other end of the block pipelineDavid Oberhollenzer
This commit moves all of the fragment/block accounting in the block processor over to the writing end of the pipeline. In order to do this, the sparse blocks are allowed to bubble through the pipeline. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-15Cleanup: block processor: move init/cleanup functions into implemenationsDavid Oberhollenzer
Again, the generic init/cleanup functions do way too many things that are specific to the thread pool implementation. Thanks to the splitting up of the block processor, they also have become quite trivial. This commit moves those functions into their respective implementations, allowing even further simplificiation. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-12Clenaup: remove useage of sqfs_block_t from block writerDavid Oberhollenzer
The sqfs_block_t structure has been written for the block processor and exposes way too many internals. This commit removes its usage from the block writer, cutting it down to the bare essentials, so the structure can be removed from the public API later on. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-10Cleanup: remove block hooks entirely from block processorDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-10Cleanup: remove the fragment store/discard and block discard hooksDavid Oberhollenzer
There is no obvious non-footgun use for those other than tallying statistics, which is now done by the data structures themselves. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-10Add run time statistics to the block writer and processorDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-09block processor: merge left overs of block.c/fragment.c into common.cDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-02-09Move block writer and fragment table management out of block processorDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-01-31Split the block writing/deduplication away from the block processorDavid Oberhollenzer
This commit moves the entire block writing and deduplication of data blocks over to a different data type named "block writer". For simplicity, the interfaces of the block processor are left as is and are turned into warppers. Likewise, most of the code in the block writer is just verbatim from the block processor, to be cleaned up in subsequent commits. Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>
2020-01-29Rename sqfs_data_writer_t back to sqfs_block_processor_tDavid Oberhollenzer
Signed-off-by: David Oberhollenzer <david.oberhollenzer@sigma-star.at>