tier/libgfdb: Replacing ASCII query file with binary

Earlier, when the database was queried we used to save
all the queried records in an ASCII format in the query file.
This caused issues like filename having ASCII delimiter and used
to take a lot of space. The tier.c file also had a lot of parsing code.

Here we changed the format of the query file to binary.
All the logic of serialization and formating of query record is done
by libgfdb. Libgfdb provides API,
gfdb_write_query_record() and gfdb_read_query_record(),
which the user i.e tier migrator and CTR xlator can use to
write to and read from query file.
With this binary format we save on disk space i.e reduce to 50% atleast
as we are saving GFID's in binary format 16 bytes and not the string format
which takes 36 bytes + We are not saving path of the file + we are also saving on
ASCII delimiters.

The on disk format of query record is as follows,

+---------------------------------------------------------------------------+
| Length of serialized query record |       Serialized Query Record         |
+---------------------------------------------------------------------------+
             4 bytes                     Length of serialized query record
                                                      |
                                                      |
     -------------------------------------------------|
     |
     |
     V
   Serialized Query Record Format:
   +---------------------------------------------------------------------------+
   | GFID |  Link count   |  <LINK INFO>  |.....                      | FOOTER |
   +---------------------------------------------------------------------------+
     16 B        4 B         Link Length                                  4 B
                                |                                          |
                                |                                          |
   -----------------------------|                                          |
   |                                                                       |
   |                                                                       |
   V                                                                       |
   Each <Link Info> will be serialized as                                  |
   +-----------------------------------------------+                       |
   | PGID | BASE_NAME_LENGTH |      BASE_NAME      |                       |
   +-----------------------------------------------+                       |
     16 B       4 B             BASE_NAME_LENGTH                           |
                                                                           |
                                                                           |
   ------------------------------------------------------------------------|
   |
   |
   V
   FOOTER is a magic number 0xBAADF00D indicating the end of the record.
   This also serves as a serialized schema validator.

Backport of http://review.gluster.org/#/c/12354/

> Change-Id: I9db7416fd421e118dd44eafab8b535caafe50d5a
> BUG: 1272207
> Signed-off-by: Joseph Fernandes <josferna@redhat.com>
> Reviewed-on: http://review.gluster.org/12354
> Reviewed-by: N Balachandran <nbalacha@redhat.com>
> Tested-by: Gluster Build System <jenkins@build.gluster.com>
> Reviewed-by: Dan Lambright <dlambrig@redhat.com>
> Tested-by: Dan Lambright <dlambrig@redhat.com>

Change-Id: I170c579027f2594a58706f826e3ddf89e34022f4
BUG: 1263619
Signed-off-by: Joseph Fernandes <josferna@redhat.com>
Reviewed-on: http://review.gluster.org/12535
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>

1 files changed, 125 insertions, 0 deletions

diff --git a/libglusterfs/src/gfdb/gfdb_data_store_helper.h b/libglusterfs/src/gfdb/gfdb_data_store_helper.h
new file mode 100644
index 00000000000..fe9fbba8795
--- /dev/null
+++ b/libglusterfs/src/gfdb/gfdb_data_store_helper.h
@@ -0,0 +1,125 @@
+/*
+   Copyright (c) 2015 Red Hat, Inc. <http://www.redhat.com>
+   This file is part of GlusterFS.
+
+   This file is licensed to you under your choice of the GNU Lesser
+   General Public License, version 3 or any later version (LGPLv3 or
+   later), or the GNU General Public License, version 2 (GPLv2), in all
+   cases as published by the Free Software Foundation.
+*/
+#ifndef __GFDB_DATA_STORE_HELPER_H
+#define __GFDB_DATA_STORE_HELPER_H
+
+#include <time.h>
+#include <sys/time.h>
+#include <string.h>
+
+#include "common-utils.h"
+#include "compat-uuid.h"
+#include "gfdb_mem-types.h"
+#include "dict.h"
+#include "byte-order.h"
+#include "libglusterfs-messages.h"
+
+
+#define GFDB_DATA_STORE               "gfdbdatastore"
+
+/*******************************************************************************
+ *
+ *                     Query related data structure and functions
+ *
+ * ****************************************************************************/
+
+#ifdef NAME_MAX
+#define GF_NAME_MAX NAME_MAX
+#else
+#define GF_NAME_MAX 255
+#endif
+
+/*Structure to hold the link information*/
+typedef struct gfdb_link_info {
+        uuid_t                          pargfid;
+        char                            file_name[GF_NAME_MAX];
+        struct list_head                list;
+} gfdb_link_info_t;
+
+
+/*Create a single link info structure*/
+gfdb_link_info_t *gfdb_link_info_new ();
+typedef gfdb_link_info_t *(*gfdb_link_info_new_t) ();
+
+/*Destroy a link info structure*/
+void
+gfdb_link_info_free (gfdb_link_info_t *gfdb_link_info);
+typedef void
+(*gfdb_link_info_free_t) (gfdb_link_info_t *gfdb_link_info);
+
+
+
+
+
+/*Structure used for querying purpose*/
+typedef struct gfdb_query_record {
+        uuid_t                          gfid;
+        /*This is the hardlink list*/
+        struct list_head                link_list;
+        int                             link_count;
+} gfdb_query_record_t;
+
+
+
+/* Function to create the query_record */
+gfdb_query_record_t *
+gfdb_query_record_new();
+typedef gfdb_query_record_t *
+(*gfdb_query_record_new_t)();
+
+
+
+
+/* Fuction to add linkinfo to query record */
+int
+gfdb_add_link_to_query_record (gfdb_query_record_t      *gfdb_query_record,
+                           uuid_t                   pgfid,
+                           char               *base_name);
+typedef int
+(*gfdb_add_link_to_query_record_t) (gfdb_query_record_t *, uuid_t, char *);
+
+
+
+
+/*Function to destroy query record*/
+void
+gfdb_query_record_free (gfdb_query_record_t *gfdb_query_record);
+typedef void
+(*gfdb_query_record_free_t) (gfdb_query_record_t *);
+
+
+
+
+
+
+/* Function to write query record to file */
+int
+gfdb_write_query_record (int fd,
+                        gfdb_query_record_t *gfdb_query_record);
+typedef int
+(*gfdb_write_query_record_t) (int, gfdb_query_record_t *);
+
+
+
+
+
+/* Function to read query record from file.
+ * Allocates memory to query record and return 0 when successful
+ * Return -1 when failed.
+ * Return 0 when EOF.
+ * */
+int
+gfdb_read_query_record (int fd,
+                        gfdb_query_record_t **gfdb_query_record);
+typedef int
+(*gfdb_read_query_record_t) (int, gfdb_query_record_t **);
+
+
+#endif
\ No newline at end of file