git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v2 05/19] reftable: add blocksource, an abstraction for random access reads

From
Han-Wen Nienhuys via GitGitGadget <gitgitgadget@gmail.com>
Date
Sep 9, 2021, 18:47 UTC
Message-ID
<e9206532126ea165abb3ebd157ae3b0750e865cc.1631213265.git.gitgitgadget@gmail.com>
In-Reply-To
<pull.1081.v2.git.git.1631213264.gitgitgadget@gmail.com>
From: Han-Wen Nienhuys <hanwen@google.com>

The reftable format is usually used with files for storage. However, we abstract away this using the blocksource data structure. This has two advantages:

* log blocks are zlib compressed, and handling them is simplified if we can
  discard byte segments from within the block layer.
* for unittests, it is useful to read and write in-memory. The blocksource
  allows us to abstract the data away from on-disk files.
Signed-off-by: Han-Wen Nienhuys <hanwen@google.com>
---
 Makefile                        |   1 +
 reftable/blocksource.c          | 148 ++++++++++++++++++++++++++++++++
 reftable/blocksource.h          |  22 +++++
 reftable/reftable-blocksource.h |  49 +++++++++++
 4 files changed, 220 insertions(+)
 create mode 100644 reftable/blocksource.c
 create mode 100644 reftable/blocksource.h
 create mode 100644 reftable/reftable-blocksource.h
diff --git a/Makefile b/Makefile
index 0bf5e49aa61..c7ffc27a727 100644
--- a/Makefile
+++ b/Makefile
@@ -2451,6 +2451,7 @@ xdiff-objs: $(XDIFF_OBJS)
 
 REFTABLE_OBJS += reftable/basics.o
 REFTABLE_OBJS += reftable/error.o
+REFTABLE_OBJS += reftable/blocksource.o
 REFTABLE_OBJS += reftable/publicbasics.o
 
 REFTABLE_TEST_OBJS += reftable/test_framework.o
diff --git a/reftable/blocksource.c b/reftable/blocksource.c
new file mode 100644
index 00000000000..0044eecd9aa
--- /dev/null
+++ b/reftable/blocksource.c
@@ -0,0 +1,148 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#include "system.h"
+
+#include "basics.h"
+#include "blocksource.h"
+#include "reftable-blocksource.h"
+#include "reftable-error.h"
+
+static void strbuf_return_block(void *b, struct reftable_block *dest)
+{
+	memset(dest->data, 0xff, dest->len);
+	reftable_free(dest->data);
+}
+
+static void strbuf_close(void *b)
+{
+}
+
+static int strbuf_read_block(void *v, struct reftable_block *dest, uint64_t off,
+			     uint32_t size)
+{
+	struct strbuf *b = v;
+	assert(off + size <= b->len);
+	dest->data = reftable_calloc(size);
+	memcpy(dest->data, b->buf + off, size);
+	dest->len = size;
+	return size;
+}
+
+static uint64_t strbuf_size(void *b)
+{
+	return ((struct strbuf *)b)->len;
+}
+
+static struct reftable_block_source_vtable strbuf_vtable = {
+	.size = &strbuf_size,
+	.read_block = &strbuf_read_block,
+	.return_block = &strbuf_return_block,
+	.close = &strbuf_close,
+};
+
+void block_source_from_strbuf(struct reftable_block_source *bs,
+			      struct strbuf *buf)
+{
+	assert(!bs->ops);
+	bs->ops = &strbuf_vtable;
+	bs->arg = buf;
+}
+
+static void malloc_return_block(void *b, struct reftable_block *dest)
+{
+	memset(dest->data, 0xff, dest->len);
+	reftable_free(dest->data);
+}
+
+static struct reftable_block_source_vtable malloc_vtable = {
+	.return_block = &malloc_return_block,
+};
+
+static struct reftable_block_source malloc_block_source_instance = {
+	.ops = &malloc_vtable,
+};
+
+struct reftable_block_source malloc_block_source(void)
+{
+	return malloc_block_source_instance;
+}
+
+struct file_block_source {
+	int fd;
+	uint64_t size;
+};
+
+static uint64_t file_size(void *b)
+{
+	return ((struct file_block_source *)b)->size;
+}
+
+static void file_return_block(void *b, struct reftable_block *dest)
+{
+	memset(dest->data, 0xff, dest->len);
+	reftable_free(dest->data);
+}
+
+static void file_close(void *b)
+{
+	int fd = ((struct file_block_source *)b)->fd;
+	if (fd > 0) {
+		close(fd);
+		((struct file_block_source *)b)->fd = 0;
+	}
+
+	reftable_free(b);
+}
+
+static int file_read_block(void *v, struct reftable_block *dest, uint64_t off,
+			   uint32_t size)
+{
+	struct file_block_source *b = v;
+	assert(off + size <= b->size);
+	dest->data = reftable_malloc(size);
+	if (pread(b->fd, dest->data, size, off) != size)
+		return -1;
+	dest->len = size;
+	return size;
+}
+
+static struct reftable_block_source_vtable file_vtable = {
+	.size = &file_size,
+	.read_block = &file_read_block,
+	.return_block = &file_return_block,
+	.close = &file_close,
+};
+
+int reftable_block_source_from_file(struct reftable_block_source *bs,
+				    const char *name)
+{
+	struct stat st = { 0 };
+	int err = 0;
+	int fd = open(name, O_RDONLY);
+	struct file_block_source *p = NULL;
+	if (fd < 0) {
+		if (errno == ENOENT) {
+			return REFTABLE_NOT_EXIST_ERROR;
+		}
+		return -1;
+	}
+
+	err = fstat(fd, &st);
+	if (err < 0)
+		return -1;
+
+	p = reftable_calloc(sizeof(struct file_block_source));
+	p->size = st.st_size;
+	p->fd = fd;
+
+	assert(!bs->ops);
+	bs->ops = &file_vtable;
+	bs->arg = p;
+	return 0;
+}
diff --git a/reftable/blocksource.h b/reftable/blocksource.h
new file mode 100644
index 00000000000..072e2727ad2
--- /dev/null
+++ b/reftable/blocksource.h
@@ -0,0 +1,22 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#ifndef BLOCKSOURCE_H
+#define BLOCKSOURCE_H
+
+#include "system.h"
+
+struct reftable_block_source;
+
+/* Create an in-memory block source for reading reftables */
+void block_source_from_strbuf(struct reftable_block_source *bs,
+			      struct strbuf *buf);
+
+struct reftable_block_source malloc_block_source(void);
+
+#endif
diff --git a/reftable/reftable-blocksource.h b/reftable/reftable-blocksource.h
new file mode 100644
index 00000000000..5aa3990a573
--- /dev/null
+++ b/reftable/reftable-blocksource.h
@@ -0,0 +1,49 @@
+/*
+Copyright 2020 Google LLC
+
+Use of this source code is governed by a BSD-style
+license that can be found in the LICENSE file or at
+https://developers.google.com/open-source/licenses/bsd
+*/
+
+#ifndef REFTABLE_BLOCKSOURCE_H
+#define REFTABLE_BLOCKSOURCE_H
+
+#include <stdint.h>
+
+/* block_source is a generic wrapper for a seekable readable file.
+ */
+struct reftable_block_source {
+	struct reftable_block_source_vtable *ops;
+	void *arg;
+};
+
+/* a contiguous segment of bytes. It keeps track of its generating block_source
+ * so it can return itself into the pool. */
+struct reftable_block {
+	uint8_t *data;
+	int len;
+	struct reftable_block_source source;
+};
+
+/* block_source_vtable are the operations that make up block_source */
+struct reftable_block_source_vtable {
+	/* returns the size of a block source */
+	uint64_t (*size)(void *source);
+
+	/* reads a segment from the block source. It is an error to read
+	   beyond the end of the block */
+	int (*read_block)(void *source, struct reftable_block *dest,
+			  uint64_t off, uint32_t size);
+	/* mark the block as read; may return the data back to malloc */
+	void (*return_block)(void *source, struct reftable_block *blockp);
+
+	/* release all resources associated with the block source */
+	void (*close)(void *source);
+};
+
+/* opens a file on the file system as a block_source */
+int reftable_block_source_from_file(struct reftable_block_source *block_src,
+				    const char *name);
+
+#endif
-- 
gitgitgadget
Previous: Carlo ArenasNext: Han-Wen Nienhuys via GitGitGadget
Message 37 of 111 in “Adds reftable library code from https://github.com/hanwen/reftable.”
  1. 00/19 Adds reftable library code from https://github.com/hanwen/reftable.Han-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  2. 01/19 hash.h: provide constants for the hash IDsHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  3. 03/19 reftable: add error related functionalityHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  4. 02/19 reftable: RFC: add LICENSEHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  5. 04/19 reftable: utility functionsHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  6. 05/19 reftable: add blocksource, an abstraction for random access readsHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  7. 07/19 Provide zlib's uncompress2 from compat/zlib-compat.cHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  8. fixup! Provide zlib's uncompress2 from compat/zlib-compat.cCarlo Marcelo Arenas Belón, Sep 2, 2021
  9. 06/19 reftable: (de)serialization for the polymorphic record type.Han-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  10. 09/19 reftable: a generic binary tree implementationHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  11. 08/19 reftable: reading/writing blocksHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  12. 11/19 reftable: generic interface to tablesHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  13. 14/19 reftable: add a heap-based priority queue for reftable recordsHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  14. 10/19 reftable: write reftable filesHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  15. 13/19 reftable: reftable file level testsHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  16. 12/19 reftable: read reftable filesHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  17. 15/19 reftable: add merged table viewHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  18. 16/19 reftable: implement refname validationHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  19. 18/19 reftable: add dump utilityHan-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  20. 19/19 Add "test-tool dump-reftable" command.Han-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  21. 17/19 reftable: implement stack, a mutable database of reftable files.Han-Wen Nienhuys via GitGitGadget, Aug 30, 2021
  22. Han-Wen NienhuysAug 30, 2021
  23. 0/4 fixup for hn/reftableCarlo Marcelo Arenas Belón, Sep 8, 2021
  24. 1/4 fixup! reftable: reading/writing blocksCarlo Marcelo Arenas Belón, Sep 8, 2021
  25. 2/4 fixup! reftable: utility functionsCarlo Marcelo Arenas Belón, Sep 8, 2021
  26. 3/4 fixup! Provide zlib's uncompress2 from compat/zlib-compat.cCarlo Marcelo Arenas Belón, Sep 8, 2021
  27. 4/4 fixup! reftable: utility functionsCarlo Marcelo Arenas Belón, Sep 8, 2021
  28. Junio C HamanoSep 8, 2021
  29. 00/19 Adds reftable library code from https://github.com/hanwen/reftable.Han-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  30. 01/19 hash.h: provide constants for the hash IDsHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  31. 02/19 reftable: RFC: add LICENSEHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  32. 03/19 reftable: add error related functionalityHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  33. 04/19 reftable: utility functionsHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  34. 06/19 reftable: (de)serialization for the polymorphic record type.Han-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  35. 07/19 Provide zlib's uncompress2 from compat/zlib-compat.cHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  36. Carlo ArenasSep 15, 2021
  37. 05/19 reftable: add blocksource, an abstraction for random access readsHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  38. 08/19 reftable: reading/writing blocksHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  39. Ævar Arnfjörð BjarmasonSep 24, 2021
  40. 09/19 reftable: a generic binary tree implementationHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  41. 10/19 reftable: write reftable filesHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  42. 11/19 reftable: generic interface to tablesHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  43. 12/19 reftable: read reftable filesHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  44. 14/19 reftable: add a heap-based priority queue for reftable recordsHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  45. 13/19 reftable: reftable file level testsHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  46. 16/19 reftable: implement refname validationHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  47. 15/19 reftable: add merged table viewHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  48. 17/19 reftable: implement stack, a mutable database of reftable files.Han-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  49. 18/19 reftable: add dump utilityHan-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  50. 19/19 Add "test-tool dump-reftable" command.Han-Wen Nienhuys via GitGitGadget, Sep 9, 2021
  51. Junio C HamanoSep 9, 2021
  52. Junio C HamanoSep 9, 2021
  53. Han-Wen NienhuysSep 13, 2021
  54. Junio C HamanoSep 13, 2021
  55. Carlo ArenasSep 13, 2021
  56. Junio C HamanoSep 13, 2021
  57. 00/19 Adds reftable library code from https://github.com/hanwen/reftable.Han-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  58. 02/19 reftable: RFC: add LICENSEHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  59. 03/19 reftable: add error related functionalityHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  60. 01/19 hash.h: provide constants for the hash IDsHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  61. 04/19 reftable: utility functionsHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  62. 05/19 reftable: add blocksource, an abstraction for random access readsHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  63. 06/19 reftable: (de)serialization for the polymorphic record type.Han-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  64. 07/19 Provide zlib's uncompress2 from compat/zlib-compat.cHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  65. 09/19 reftable: a generic binary tree implementationHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  66. 08/19 reftable: reading/writing blocksHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  67. squash! reftable: reading/writing blocksCarlo Marcelo Arenas Belón, Sep 30, 2021
  68. Han-Wen NienhuysOct 7, 2021
  69. 10/19 reftable: write reftable filesHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  70. 11/19 reftable: generic interface to tablesHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  71. 12/19 reftable: read reftable filesHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  72. 15/19 reftable: add merged table viewHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  73. 13/19 reftable: reftable file level testsHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  74. 14/19 reftable: add a heap-based priority queue for reftable recordsHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  75. 16/19 reftable: implement refname validationHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  76. 17/19 reftable: implement stack, a mutable database of reftable files.Han-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  77. 18/19 reftable: add dump utilityHan-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  78. 19/19 Add "test-tool dump-reftable" command.Han-Wen Nienhuys via GitGitGadget, Sep 28, 2021
  79. Junio C HamanoSep 28, 2021
  80. Ævar Arnfjörð BjarmasonOct 2, 2021
  81. hn/reftable "fixes"Carlo Marcelo Arenas Belón, Sep 30, 2021
  82. 1/4 fixup! reftable: add a heap-based priority queue for reftable recordsCarlo Marcelo Arenas Belón, Sep 30, 2021
  83. 2/4 fixup! reftable: implement stack, a mutable database of reftable files.Carlo Marcelo Arenas Belón, Sep 30, 2021
  84. C++(C99)-style comments in git.gitÆvar Arnfjörð Bjarmason, Oct 1, 2021
  85. 3/4 config.mak.uname: last release and snapshots of Minix still use zlib 1.2.3Carlo Marcelo Arenas Belón, Sep 30, 2021
  86. 4/4 reftable: avoid non portable compile time pointer to functionCarlo Marcelo Arenas Belón, Sep 30, 2021
  87. Junio C HamanoSep 30, 2021
  88. 00/19 Adds reftable library code from https://github.com/hanwen/reftable.Han-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  89. 01/19 hash.h: provide constants for the hash IDsHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  90. 02/19 reftable: add LICENSEHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  91. 03/19 reftable: add error related functionalityHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  92. 04/19 reftable: utility functionsHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  93. 05/19 reftable: add blocksource, an abstraction for random access readsHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  94. 09/19 reftable: a generic binary tree implementationHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  95. 10/19 reftable: write reftable filesHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  96. 11/19 reftable: generic interface to tablesHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  97. 08/19 reftable: reading/writing blocksHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  98. 12/19 reftable: read reftable filesHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  99. 06/19 reftable: (de)serialization for the polymorphic record type.Han-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  100. 07/19 Provide zlib's uncompress2 from compat/zlib-compat.cHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  101. 13/19 reftable: reftable file level testsHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  102. 14/19 reftable: add a heap-based priority queue for reftable recordsHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  103. 15/19 reftable: add merged table viewHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  104. reftable tests: use C syntax compatible with old xlcÆvar Arnfjörð Bjarmason, Jan 13, 2022
  105. Han-Wen NienhuysJan 13, 2022
  106. Ævar Arnfjörð BjarmasonJan 13, 2022
  107. Junio C HamanoJan 13, 2022
  108. 16/19 reftable: implement refname validationHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  109. 18/19 reftable: add dump utilityHan-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  110. 17/19 reftable: implement stack, a mutable database of reftable files.Han-Wen Nienhuys via GitGitGadget, Oct 7, 2021
  111. 19/19 Add "test-tool dump-reftable" command.Han-Wen Nienhuys via GitGitGadget, Oct 7, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.