[sheepdog] [PATCH 1/2 v2] sheep : add new strage type "tree"

[Saeki Masaki]

On 2015/03/18 11:50, Saeki Masaki wrote:
> On 2015/03/18 10:44, Liu Yuan wrote:
>> On Tue, Mar 17, 2015 at 06:03:26PM +0900, Saeki Masaki wrote:
>>> Current sheepdog stores whole objects in single directory like "/var/lib/sheepdog/obj"
>>> This mechanism is difficult to handle massive files when increasing cluster volume.
>>>
>>> In particular, inode object having special informations about VDI,
>>> so it is preferable to divide.
>>>
>>> new storage type named "tree"
>>> It separates the inode object and data object.
>>>
>>> How to use ,
>>> specify the --store option at the time format
>>>
>>> dog cluster format --store tree
>>>
>>> v2: refactor using common functions for store driver
>>>      use check_store_type to identify tree store_driver
>>>
>>> Signed-off-by: Masaki Saeki <saeki.masaki at po.ntts.co.jp>
>>> ---
>>>   sheep/Makefile.am         |    2 +-
>>>   sheep/sheep_priv.h        |   21 ++
>>>   sheep/store/common.c      |    5 +
>>>   sheep/store/md.c          |   14 +
>>>   sheep/store/plain_store.c |    1 +
>>>   sheep/store/tree_store.c  |  757 +++++++++++++++++++++++++++++++++++++++++++++
>>>   6 files changed, 799 insertions(+), 1 deletions(-)
>>>   create mode 100644 sheep/store/tree_store.c
>>>
>>> diff --git a/sheep/Makefile.am b/sheep/Makefile.am
>>> index 3ddd761..9dedb03 100644
>>> --- a/sheep/Makefile.am
>>> +++ b/sheep/Makefile.am
>>> @@ -28,7 +28,7 @@ sheep_SOURCES        = sheep.c group.c request.c gateway.c vdi.c \
>>>                 journal.c ops.c recovery.c cluster/local.c \
>>>                 object_cache.c object_list_cache.c \
>>>                 store/common.c store/md.c \
>>> -              store/plain_store.c \
>>> +              store/plain_store.c store/tree_store.c \
>>>                 config.c migrate.c
>>>
>>>   if BUILD_HTTP
>>> diff --git a/sheep/sheep_priv.h b/sheep/sheep_priv.h
>>> index e58901f..51e686f 100644
>>> --- a/sheep/sheep_priv.h
>>> +++ b/sheep/sheep_priv.h
>>> @@ -84,6 +84,11 @@ enum REQUST_STATUS {
>>>       REQUEST_DROPPED
>>>   };
>>>
>>> +enum store_id {
>>> +    PLAIN_STORE,
>>> +    TREE_STORE
>>> +};
>>> +
>>>   struct request_iocb {
>>>       uint32_t count;
>>>       int efd;
>>> @@ -235,6 +240,7 @@ struct vdi_info {
>>>
>>>   struct store_driver {
>>>       struct list_node list;
>>> +    enum store_id id;
>>>       const char *name;
>>>       int (*init)(void);
>>>       bool (*exist)(uint64_t oid, uint8_t ec_index);
>>> @@ -269,6 +275,20 @@ int default_format(void);
>>>   int default_remove_object(uint64_t oid, uint8_t ec_index);
>>>   int default_get_hash(uint64_t oid, uint32_t epoch, uint8_t *sha1);
>>>   int default_purge_obj(void);
>>> +
>>> +int tree_init(void);
>>> +bool tree_exist(uint64_t oid, uint8_t ec_index);
>>> +int tree_create_and_write(uint64_t oid, const struct siocb *iocb);
>>> +int tree_write(uint64_t oid, const struct siocb *iocb);
>>> +int tree_read(uint64_t oid, const struct siocb *iocb);
>>> +int tree_link(uint64_t oid, uint32_t tgt_epoch);
>>> +int tree_update_epoch(uint32_t epoch);
>>> +int tree_cleanup(void);
>>> +int tree_format(void);
>>> +int tree_remove_object(uint64_t oid, uint8_t ec_index);
>>> +int tree_get_hash(uint64_t oid, uint32_t epoch, uint8_t *sha1);
>>> +int tree_purge_obj(void);
>>> +
>>>   int for_each_object_in_wd(int (*func)(uint64_t, const char *, uint32_t,
>>>                         uint8_t, struct vnode_info *, void *),
>>>                 bool, void *);
>>> @@ -404,6 +424,7 @@ void queue_cluster_request(struct request *req);
>>>   int prepare_iocb(uint64_t oid, const struct siocb *iocb, bool create);
>>>   int err_to_sderr(const char *path, uint64_t oid, int err);
>>>   int discard(int fd, uint64_t start, uint32_t end);
>>> +bool check_store_type(enum store_id id);
>>
>> Better rename check_store_type as store_id_match(enum store_id)
>>
>>>
>>>   int update_epoch_log(uint32_t epoch, struct sd_node *nodes, size_t nr_nodes);
>>>   int inc_and_log_epoch(void);
>>> diff --git a/sheep/store/common.c b/sheep/store/common.c
>>> index 8959392..aa2858d 100644
>>> --- a/sheep/store/common.c
>>> +++ b/sheep/store/common.c
>>> @@ -102,6 +102,11 @@ int discard(int fd, uint64_t start, uint32_t end)
>>>       return ret;
>>>   }
>>>
>>> +bool check_store_type(enum store_id id)
>>> +{
>>> +    return (sd_store->id == id);
>>> +}
>>> +
>>>   int update_epoch_log(uint32_t epoch, struct sd_node *nodes, size_t nr_nodes)
>>>   {
>>>       int ret, len, nodes_len;
>>> diff --git a/sheep/store/md.c b/sheep/store/md.c
>>> index 87ab759..ed95c98 100644
>>> --- a/sheep/store/md.c
>>> +++ b/sheep/store/md.c
>>> @@ -212,6 +212,20 @@ static int for_each_object_in_path(const char *path,
>>>           if (unlikely(!strncmp(d->d_name, ".", 1)))
>>>               continue;
>>
>> I think for_each_object_in_path family might be moved to common.c
>>

I try to check the code for the above comments,
for_each_object_in_wd and for_each_object_in_stale use "md.lock"
So it is not suitable for moving to common.c.

Although I think there is room to improve in the future,
But I think that we should step on the stage.

Regards, Saeki.

(snip)
>>
>> It seems that tree.c and plain.c still share a great portion of lines. It is
>> okay to keep them for fast development, but I hope later we can drag as many
>> lines as possible to common.c.
>>
>> Thanks,
>> Yuan
>>
>
> Thank for your advice.
> I'll make patch reflecting the noted.
>
> Thanks,Saeki.
>
>