This PR adds EXPERIMENTAL support for accessing data in the
cloud using a variant of the Zarr protocol and storage
format. This enhancement is generically referred to as "NCZarr".
The data model supported by NCZarr is netcdf-4 minus the user-defined
types and the String type. In this sense it is similar to the CDF-5
data model.
More detailed information about enabling and using NCZarr is
described in the document NUG/nczarr.md and in a
[Unidata Developer's blog entry](https://www.unidata.ucar.edu/blogs/developer/en/entry/overview-of-zarr-support-in).
WARNING: this code has had limited testing, so do use this version
for production work. Also, performance improvements are ongoing.
Note especially the following platform matrix of successful tests:
Platform | Build System | S3 support
------------------------------------
Linux+gcc | Automake | yes
Linux+gcc | CMake | yes
Visual Studio | CMake | no
Additionally, and as a consequence of the addition of NCZarr,
major changes have been made to the Filter API. NOTE: NCZarr
does not yet support filters, but these changes are enablers for
that support in the future. Note that it is possible
(probable?) that there will be some accidental reversions if the
changes here did not correctly mimic the existing filter testing.
In any case, previously filter ids and parameters were of type
unsigned int. In order to support the more general zarr filter
model, this was all converted to char*. The old HDF5-specific,
unsigned int operations are still supported but they are
wrappers around the new, char* based nc_filterx_XXX functions.
This entailed at least the following changes:
1. Added the files libdispatch/dfilterx.c and include/ncfilter.h
2. Some filterx utilities have been moved to libdispatch/daux.c
3. A new entry, "filter_actions" was added to the NCDispatch table
and the version bumped.
4. An overly complex set of structs was created to support funnelling
all of the filterx operations thru a single dispatch
"filter_actions" entry.
5. Move common code to from libhdf5 to libsrc4 so that it is accessible
to nczarr.
Changes directly related to Zarr:
1. Modified CMakeList.txt and configure.ac to support both C and C++
-- this is in support of S3 support via the awd-sdk libraries.
2. Define a size64_t type to support nczarr.
3. More reworking of libdispatch/dinfermodel.c to
support zarr and to regularize the structure of the fragments
section of a URL.
Changes not directly related to Zarr:
1. Make client-side filter registration be conditional, with default off.
2. Hack include/nc4internal.h to make some flags added by Ed be unique:
e.g. NC_CREAT, NC_INDEF, etc.
3. cleanup include/nchttp.h and libdispatch/dhttp.c.
4. Misc. changes to support compiling under Visual Studio including:
* Better testing under windows for dirent.h and opendir and closedir.
5. Misc. changes to the oc2 code to support various libcurl CURLOPT flags
and to centralize error reporting.
6. By default, suppress the vlen tests that have unfixed memory leaks; add option to enable them.
7. Make part of the nc_test/test_byterange.sh test be contingent on remotetest.unidata.ucar.edu being accessible.
Changes Left TO-DO:
1. fix provenance code, it is too HDF5 specific.
2020-06-29 08:02:47 +08:00
|
|
|
/*********************************************************************
|
|
|
|
* Copyright 2018, UCAR/Unidata
|
|
|
|
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
|
|
|
|
*********************************************************************/
|
|
|
|
|
|
|
|
#ifndef GENERATE_H
|
|
|
|
#define GENERATE_H 1
|
|
|
|
|
|
|
|
typedef struct Generator Generator;
|
|
|
|
|
|
|
|
void alignbuffer(struct NCConstant* prim, Bytebuffer* buf);
|
|
|
|
|
|
|
|
/* Code dump support procedures */
|
|
|
|
void bbindent(Bytebuffer*,const int);
|
|
|
|
void bbprintf(Bytebuffer*,const char *fmt, ...); /* append */
|
|
|
|
void bbprintf0(Bytebuffer*,const char *fmt, ...); /* clear, then append*/
|
|
|
|
/* Following dump to codebuffer */
|
|
|
|
void codeprintf(const char *fmt, ...);
|
|
|
|
void codedump(Bytebuffer*);
|
|
|
|
void codepartial(const char*);
|
|
|
|
void codeline(const char*);
|
|
|
|
void codelined(int n,const char*);
|
|
|
|
void codeflush(void); /* flush codebuffer to stdout */
|
|
|
|
|
|
|
|
void commify(Bytebuffer* buf);
|
|
|
|
char* word(char* p, Bytebuffer* buf);
|
|
|
|
|
|
|
|
/* Provide buffers for language based generators */
|
|
|
|
extern Bytebuffer* codebuffer; /* buffer over the std output */
|
|
|
|
extern Bytebuffer* stmt; /* single stmt text generation */
|
|
|
|
|
|
|
|
/* From genchar.c */
|
|
|
|
void gen_charattr(Datalist*, Bytebuffer*);
|
|
|
|
void gen_charseq(Datalist*, Bytebuffer*);
|
|
|
|
void gen_chararray(Dimset*, int, Datalist*, Bytebuffer*, Datalist*);
|
|
|
|
|
|
|
|
typedef enum ListClass {
|
|
|
|
LISTDATA, LISTATTR, LISTVLEN, LISTCOMPOUND, LISTFIELDARRAY
|
|
|
|
} ListClass;
|
|
|
|
|
|
|
|
struct Generator {
|
|
|
|
void* globalstate; /* per-generator; per list state is in the method args where needed */
|
|
|
|
int (*charconstant)(Generator*,struct Symbol*,Bytebuffer*,...);
|
|
|
|
int (*constant)(Generator*,struct Symbol*,NCConstant*,Bytebuffer*,...);
|
|
|
|
int (*listbegin)(Generator*,struct Symbol*,void*,ListClass,size_t,Bytebuffer*,int*,...);
|
|
|
|
int (*list)(Generator*,struct Symbol*,void*,ListClass,int,size_t,Bytebuffer*,...);
|
|
|
|
int (*listend)(Generator*,struct Symbol*,void*,ListClass,int,size_t,Bytebuffer*,...);
|
|
|
|
int (*vlendecl)(Generator*,struct Symbol*,Bytebuffer*,int,size_t,...);
|
|
|
|
int (*vlenstring)(Generator*,struct Symbol*,Bytebuffer*,int*,size_t*,...);
|
|
|
|
};
|
|
|
|
|
|
|
|
extern int generator_getstate(Generator*,void**);
|
|
|
|
extern int generator_reset(Generator*,void*);
|
|
|
|
|
|
|
|
typedef int (*Writer)(Generator*,struct Symbol*,Bytebuffer*,int,const size_t*,const size_t*);
|
|
|
|
|
|
|
|
extern void generate_attrdata(struct Symbol*, Generator*, Writer writer, Bytebuffer*);
|
Improve performance of the nc_reclaim_data and nc_copy_data functions.
re: Issue https://github.com/Unidata/netcdf-c/issues/2685
re: PR https://github.com/Unidata/netcdf-c/pull/2179
As noted in PR https://github.com/Unidata/netcdf-c/pull/2179,
the old code did not allow for reclaiming instances of types,
nor for properly copying them. That PR provided new functions
capable of reclaiming/copying instances of arbitrary types.
However, as noted by Issue https://github.com/Unidata/netcdf-c/issues/2685, using these
most general functions resulted in a significant performance
degradation, even for common cases.
This PR attempts to mitigate the cost of using the general
reclaim/copy functions in two ways.
First, the previous functions operating at the top level by
using ncid and typeid arguments. These functions were augmented
with equivalent versions that used the netcdf-c library internal
data structures to allow direct access to needed information.
These new functions are used internally to the library.
The second mitigation involves optimizing the internal functions
by providing early tests for common cases. This avoids
unnecessary recursive function calls.
The overall result is a significant improvement in speed by a
factor of roughly twenty -- your mileage may vary. These
optimized functions are still not as fast as the original (more
limited) functions, but they are getting close. Additional optimizations are
possible. But the cost is a significant "uglification" of the
code that I deemed a step too far, at least for now.
## Misc. Changes
1. Added a test case to check the proper reclamation/copy of complex types.
2. Found and fixed some places where nc_reclaim/copy should have been used.
3. Replaced, in the netcdf-c library, (almost all) occurrences of nc_reclaim_copy with calls to NC_reclaim/copy. This plus the optimizations is the primary speed-up mechanism.
4. In DAP4, the metadata is held in a substrate in-memory file; this required some changes so that the reclaim/copy code accessed that substrate dispatcher rather than the DAP4 dispatcher.
5. Re-factored and isolated the code that computes if a type is (transitively) variable-sized or not.
6. Clean up the reclamation code in ncgen; adding the use of nc_reclaim exposed some memory problems.
2023-05-21 07:11:25 +08:00
|
|
|
extern void generate_vardata(struct Symbol*, Generator*, Writer writer, Bytebuffer*);
|
This PR adds EXPERIMENTAL support for accessing data in the
cloud using a variant of the Zarr protocol and storage
format. This enhancement is generically referred to as "NCZarr".
The data model supported by NCZarr is netcdf-4 minus the user-defined
types and the String type. In this sense it is similar to the CDF-5
data model.
More detailed information about enabling and using NCZarr is
described in the document NUG/nczarr.md and in a
[Unidata Developer's blog entry](https://www.unidata.ucar.edu/blogs/developer/en/entry/overview-of-zarr-support-in).
WARNING: this code has had limited testing, so do use this version
for production work. Also, performance improvements are ongoing.
Note especially the following platform matrix of successful tests:
Platform | Build System | S3 support
------------------------------------
Linux+gcc | Automake | yes
Linux+gcc | CMake | yes
Visual Studio | CMake | no
Additionally, and as a consequence of the addition of NCZarr,
major changes have been made to the Filter API. NOTE: NCZarr
does not yet support filters, but these changes are enablers for
that support in the future. Note that it is possible
(probable?) that there will be some accidental reversions if the
changes here did not correctly mimic the existing filter testing.
In any case, previously filter ids and parameters were of type
unsigned int. In order to support the more general zarr filter
model, this was all converted to char*. The old HDF5-specific,
unsigned int operations are still supported but they are
wrappers around the new, char* based nc_filterx_XXX functions.
This entailed at least the following changes:
1. Added the files libdispatch/dfilterx.c and include/ncfilter.h
2. Some filterx utilities have been moved to libdispatch/daux.c
3. A new entry, "filter_actions" was added to the NCDispatch table
and the version bumped.
4. An overly complex set of structs was created to support funnelling
all of the filterx operations thru a single dispatch
"filter_actions" entry.
5. Move common code to from libhdf5 to libsrc4 so that it is accessible
to nczarr.
Changes directly related to Zarr:
1. Modified CMakeList.txt and configure.ac to support both C and C++
-- this is in support of S3 support via the awd-sdk libraries.
2. Define a size64_t type to support nczarr.
3. More reworking of libdispatch/dinfermodel.c to
support zarr and to regularize the structure of the fragments
section of a URL.
Changes not directly related to Zarr:
1. Make client-side filter registration be conditional, with default off.
2. Hack include/nc4internal.h to make some flags added by Ed be unique:
e.g. NC_CREAT, NC_INDEF, etc.
3. cleanup include/nchttp.h and libdispatch/dhttp.c.
4. Misc. changes to support compiling under Visual Studio including:
* Better testing under windows for dirent.h and opendir and closedir.
5. Misc. changes to the oc2 code to support various libcurl CURLOPT flags
and to centralize error reporting.
6. By default, suppress the vlen tests that have unfixed memory leaks; add option to enable them.
7. Make part of the nc_test/test_byterange.sh test be contingent on remotetest.unidata.ucar.edu being accessible.
Changes Left TO-DO:
1. fix provenance code, it is too HDF5 specific.
2020-06-29 08:02:47 +08:00
|
|
|
extern void generate_basetype(struct Symbol*,NCConstant*,Bytebuffer*,Datalist*,Generator*);
|
|
|
|
|
|
|
|
#endif /*DATA_H*/
|
|
|
|
|