# 2009-11-5
# Notes on recoverying corrupted Berkeley DB files in PVFS
====================================================================

The pvfs2-server daemon uses Berkeley DB as the mechanism for storing file
system metadata.  There are 5 database files in total that can be found in
the following locations in the storage space:

./storage_attributes.db
./50a6d673/collection_attributes.db
./50a6d673/dataspace_attributes.db
./50a6d673/keyval.db
./collections.db

The dataspace_attributes.db and keyval.db are most frequently used by
the file system.  If one of these database files is corrupted for some
reason, then it may prevent the file system from operating correctly.

One common technique for repairing a Berkeley DB database is to dump its
contents using db_dump (possibly found in the db4-utils package) and then
reload it into a new .db file with db_load.  However, both the keyval.db and
dataspace_attributes.db use a custom function for sorting entries in order
to improve PVFS performance.  db_load must therefore be modified to use the
correct key order.

Here are the steps needed to build a db_load utility that will work on the
keyval.db or dataspace_attributes.db file:

- download the source code for Berkeley DB
- edit db_load/db_load.c
- find the section marked by #if 0 that indicates where to insert
  application specific btree comparison or hash functions
- insert the code listed at the end of this file (NOTE: there is different
  code depending on which .db file you are trying to recover)
- build Berkeley DB
- rename db_load binary to db_load_pvfs_keyval to avoid confusion

For keyval.db:
====================================================================
#include <stdint.h>

typedef uint64_t PVFS_handle;
typedef PVFS_handle                TROVE_handle;

#define PVFS_NAME_MAX            256
#define DBPF_MAX_KEY_LENGTH PVFS_NAME_MAX

struct dbpf_keyval_db_entry
{
    TROVE_handle handle;
    char key[DBPF_MAX_KEY_LENGTH];
};

#define DBPF_KEYVAL_DB_ENTRY_TOTAL_SIZE(_size) \
    (sizeof(TROVE_handle) + _size)

#define DBPF_KEYVAL_DB_ENTRY_KEY_SIZE(_size) \
    (_size - sizeof(TROVE_handle))

int PINT_trove_dbpf_keyval_compare(
    DB * dbp, const DBT * a, const DBT * b)
{
    const struct dbpf_keyval_db_entry * db_entry_a;
    const struct dbpf_keyval_db_entry * db_entry_b;

    db_entry_a = (const struct dbpf_keyval_db_entry *) a->data;
    db_entry_b = (const struct dbpf_keyval_db_entry *) b->data;

    if(db_entry_a->handle != db_entry_b->handle)
    {
        return (db_entry_a->handle < db_entry_b->handle) ? -1 : 1;
    }

    if(a->size > b->size)
    {
        return 1;
    }

    if(a->size < b->size)
    {
        return -1;
    }

    /* must be equal */
    return (memcmp(db_entry_a->key, db_entry_b->key,
                    DBPF_KEYVAL_DB_ENTRY_KEY_SIZE(a->size)));
}

if ((ret = dbp->set_bt_compare(dbp, PINT_trove_dbpf_keyval_compare)) != 0)

        dbp->err(dbp, ret, "DB->set_bt_compare");
        goto err;
}

====================================================================

For dataspace_attributes.db:
====================================================================

#include <stdint.h>

typedef uint64_t PVFS_handle;
typedef PVFS_handle                TROVE_handle;

int PINT_trove_dbpf_ds_attr_compare(DB * dbp, const DBT * a, const DBT * b)
{
    const TROVE_handle * handle_a;
    const TROVE_handle * handle_b;

    handle_a = (const TROVE_handle *) a->data;
    handle_b = (const TROVE_handle *) b->data;

    if(*handle_a == *handle_b)
    {
        return 0;
    }

    return (*handle_a > *handle_b) ? -1 : 1;
}

if ((ret = dbp->set_bt_compare(dbp, PINT_trove_dbpf_ds_attr_compare)) != 0) {
        dbp->err(dbp, ret, "DB->set_bt_compare");
        goto err;
}

====================================================================