mirror of
https://github.com/Unidata/netcdf-c.git
synced 2024-11-21 03:13:42 +08:00
df3636b959
This PR started as an attempt to add unlimited dimensions to NCZarr. It did that, but this exposed significant problems with test interference. So this PR is mostly about fixing -- well mitigating anyway -- test interference. The problem of test interference is now documented in the document docs/internal.md. The solutions implemented here are also describe in that document. The solution is somewhat fragile but multiple cleanup mechanisms are provided. Note that this feature requires that the AWS command line utility must be installed. ## Unlimited Dimensions. The existing NCZarr extensions to Zarr are modified to support unlimited dimensions. NCzarr extends the Zarr meta-data for the ".zgroup" object to include netcdf-4 model extensions. This information is stored in ".zgroup" as dictionary named "_nczarr_group". Inside "_nczarr_group", there is a key named "dims" that stores information about netcdf-4 named dimensions. The value of "dims" is a dictionary whose keys are the named dimensions. The value associated with each dimension name has one of two forms Form 1 is a special case of form 2, and is kept for backward compatibility. Whenever a new file is written, it uses format 1 if possible, otherwise format 2. * Form 1: An integer representing the size of the dimension, which is used for simple named dimensions. * Form 2: A dictionary with the following keys and values" - "size" with an integer value representing the (current) size of the dimension. - "unlimited" with a value of either "1" or "0" to indicate if this dimension is an unlimited dimension. For Unlimited dimensions, the size is initially zero, and as variables extend the length of that dimension, the size value for the dimension increases. That dimension size is shared by all arrays referencing that dimension, so if one array extends an unlimited dimension, it is implicitly extended for all other arrays that reference that dimension. This is the standard semantics for unlimited dimensions. Adding unlimited dimensions required a number of other changes to the NCZarr code-base. These included the following. * Did a partial refactor of the slice handling code in zwalk.c to clean it up. * Added a number of tests for unlimited dimensions derived from the same test in nc_test4. * Added several NCZarr specific unlimited tests; more are needed. * Add test of endianness. ## Misc. Other Changes * Modify libdispatch/ncs3sdk_aws.cpp to optionally support use of the AWS Transfer Utility mechanism. This is controlled by the ```#define TRANSFER```` command in that file. It defaults to being disabled. * Parameterize both the standard Unidata S3 bucket (S3TESTBUCKET) and the netcdf-c test data prefix (S3TESTSUBTREE). * Fixed an obscure memory leak in ncdump. * Removed some obsolete unit testing code and test cases. * Uncovered a bug in the netcdf-c handling of big-endian floats and doubles. Have not fixed yet. See tst_h5_endians.c. * Renamed some nczarr_tests testcases to avoid name conflicts with nc_test4. * Modify the semantics of zmap\#ncsmap_write to only allow total rewrite of objects. * Modify the semantics of zodom to properly handle stride > 1. * Add a truncate operation to the libnczarr zmap code.
73 lines
3.0 KiB
C
73 lines
3.0 KiB
C
/*********************************************************************
|
|
* Copyright 2018, UCAR/Unidata
|
|
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
|
|
*********************************************************************/
|
|
|
|
#ifndef ZCACHE_H
|
|
#define ZCACHE_H
|
|
|
|
/* This holds all the fields
|
|
to support either impl of cache
|
|
*/
|
|
|
|
struct NCxcache;
|
|
|
|
/* Note in the following: the term "real"
|
|
refers to the unfiltered/uncompressed data
|
|
The term filtered refers to the result of running
|
|
the real data through the filter chain. Note that the
|
|
sizeof the filtered data might be larger than the size of
|
|
the real data.
|
|
The term "raw" is used to refer to the data on disk and it may either
|
|
be real or filtered.
|
|
*/
|
|
|
|
typedef struct NCZCacheEntry {
|
|
struct List {void* next; void* prev; void* unused;} list;
|
|
int modified;
|
|
size64_t indices[NC_MAX_VAR_DIMS];
|
|
struct ChunkKey {
|
|
char* varkey; /* key to the containing variable */
|
|
char* chunkkey; /* name of the chunk */
|
|
} key;
|
|
size64_t hashkey;
|
|
int isfiltered; /* 1=>data contains filtered data else real data */
|
|
int isfixedstring; /* 1 => data contains the fixed strings, 0 => data contains pointers to strings */
|
|
size64_t size; /* |data| */
|
|
void* data; /* contains either filtered or real data */
|
|
} NCZCacheEntry;
|
|
|
|
typedef struct NCZChunkCache {
|
|
int valid; /* 0 => following fields need to be re-calculated */
|
|
NC_VAR_INFO_T* var; /* backlink */
|
|
size64_t ndims; /* true ndims == var->ndims + scalar */
|
|
size64_t chunksize; /* for real data */
|
|
size64_t chunkcount; /* cross product of chunksizes */
|
|
void* fillchunk; /* enough fillvalues to fill a real chunk */
|
|
struct ChunkCache params;
|
|
size_t used; /* How much total space is being used */
|
|
NClist* mru; /* NClist<NCZCacheEntry> all cache entries in mru order */
|
|
struct NCxcache* xcache;
|
|
char dimension_separator;
|
|
} NCZChunkCache;
|
|
|
|
/**************************************************/
|
|
|
|
#define FILTERED(cache) (nclistlength((NClist*)(cache)->var->filters))
|
|
|
|
extern int NCZ_set_var_chunk_cache(int ncid, int varid, size_t size, size_t nelems, float preemption);
|
|
extern int NCZ_adjust_var_cache(NC_VAR_INFO_T *var);
|
|
extern int NCZ_create_chunk_cache(NC_VAR_INFO_T* var, size64_t, char dimsep, NCZChunkCache** cachep);
|
|
extern void NCZ_free_chunk_cache(NCZChunkCache* cache);
|
|
extern int NCZ_read_cache_chunk(NCZChunkCache* cache, const size64_t* indices, void** datap);
|
|
extern int NCZ_flush_chunk_cache(NCZChunkCache* cache);
|
|
extern size64_t NCZ_cache_entrysize(NCZChunkCache* cache);
|
|
extern NCZCacheEntry* NCZ_cache_entry(NCZChunkCache* cache, const size64_t* indices);
|
|
extern size64_t NCZ_cache_size(NCZChunkCache* cache);
|
|
extern int NCZ_buildchunkpath(NCZChunkCache* cache, const size64_t* chunkindices, struct ChunkKey* key);
|
|
extern int NCZ_ensure_fill_chunk(NCZChunkCache* cache);
|
|
extern int NCZ_reclaim_fill_chunk(NCZChunkCache* cache);
|
|
extern int NCZ_chunk_cache_modify(NCZChunkCache* cache, const size64_t* indices);
|
|
|
|
#endif /*ZCACHE_H*/
|