diff mbox

[28/33] libceph: switch ceph_calc_pg_acting() to new helpers

Message ID 1395944299-21970-29-git-send-email-ilya.dryomov@inktank.com (mailing list archive)
State New, archived
Headers show

Commit Message

Ilya Dryomov March 27, 2014, 6:18 p.m. UTC
Switch ceph_calc_pg_acting() to new helpers: pg_to_raw_osds(),
raw_to_up_osds() and apply_temps().

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
---
 include/linux/ceph/osdmap.h |    2 +-
 net/ceph/osdmap.c           |   51 ++++++++++++++++++++++++++++++++-----------
 2 files changed, 39 insertions(+), 14 deletions(-)

Comments

Alex Elder March 27, 2014, 8:49 p.m. UTC | #1
On 03/27/2014 01:18 PM, Ilya Dryomov wrote:
> Switch ceph_calc_pg_acting() to new helpers: pg_to_raw_osds(),
> raw_to_up_osds() and apply_temps().

So that's why you have a temp map in each osdmap.
The result is pretty clean and you eliminate the
local rawosds array.

Looks good.

Reviewed-by: Alex Elder <elder@linaro.org>

> Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
> ---
>  include/linux/ceph/osdmap.h |    2 +-
>  net/ceph/osdmap.c           |   51 ++++++++++++++++++++++++++++++++-----------
>  2 files changed, 39 insertions(+), 14 deletions(-)
> 
> diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
> index 4e28c1e5d62f..b0c8f8490663 100644
> --- a/include/linux/ceph/osdmap.h
> +++ b/include/linux/ceph/osdmap.h
> @@ -212,7 +212,7 @@ extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
>  
>  extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
>  			       struct ceph_pg pgid,
> -			       int *acting);
> +			       int *osds);
>  extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
>  				struct ceph_pg pgid);
>  
> diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
> index 6d418433d80d..1963623bd488 100644
> --- a/net/ceph/osdmap.c
> +++ b/net/ceph/osdmap.c
> @@ -1642,24 +1642,49 @@ static int apply_temps(struct ceph_osdmap *osdmap,
>  }
>  
>  /*
> - * Return acting set for given pgid.
> + * Calculate acting set for given pgid.
> + *
> + * Return acting set length, or error.
>   */
>  int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
> -			int *acting)
> +			int *osds)
>  {
> -	int rawosds[CEPH_PG_MAX_SIZE], *osds;
> -	int i, o, num = CEPH_PG_MAX_SIZE;
> +	struct ceph_pg_pool_info *pool;
> +	u32 pps;
> +	int len;
> +	int primary;
>  
> -	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
> -	if (!osds)
> -		return -1;
> +	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
> +	if (!pool)
> +		return 0;
>  
> -	/* primary is first up osd */
> -	o = 0;
> -	for (i = 0; i < num; i++)
> -		if (ceph_osd_is_up(osdmap, osds[i]))
> -			acting[o++] = osds[i];
> -	return o;
> +	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
> +		/* hash pool id and seed so that pool PGs do not overlap */
> +		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
> +				     ceph_stable_mod(pgid.seed, pool->pgp_num,
> +						     pool->pgp_num_mask),
> +				     pgid.pool);
> +	} else {
> +		/*
> +		 * legacy ehavior: add ps and pool together.  this is

Typo "behavior"

> +		 * not a great approach because the PGs from each pool
> +		 * will overlap on top of each other: 0.5 == 1.4 ==
> +		 * 2.3 == ...
> +		 */
> +		pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
> +				      pool->pgp_num_mask) +
> +			(unsigned)pgid.pool;
> +	}
> +
> +	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
> +	if (len < 0)
> +		return len;
> +
> +	len = raw_to_up_osds(osdmap, pool, osds, len, &primary);
> +
> +	len = apply_temps(osdmap, pool, pgid, osds, len, &primary);
> +
> +	return len;
>  }
>  
>  /*
> 

--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Ilya Dryomov March 28, 2014, 3:02 p.m. UTC | #2
On Thu, Mar 27, 2014 at 10:49 PM, Alex Elder <elder@ieee.org> wrote:
> On 03/27/2014 01:18 PM, Ilya Dryomov wrote:
>> Switch ceph_calc_pg_acting() to new helpers: pg_to_raw_osds(),
>> raw_to_up_osds() and apply_temps().
>
> So that's why you have a temp map in each osdmap.
> The result is pretty clean and you eliminate the
> local rawosds array.
>
> Looks good.
>
> Reviewed-by: Alex Elder <elder@linaro.org>
>
>> Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
>> ---
>>  include/linux/ceph/osdmap.h |    2 +-
>>  net/ceph/osdmap.c           |   51 ++++++++++++++++++++++++++++++++-----------
>>  2 files changed, 39 insertions(+), 14 deletions(-)
>>
>> diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
>> index 4e28c1e5d62f..b0c8f8490663 100644
>> --- a/include/linux/ceph/osdmap.h
>> +++ b/include/linux/ceph/osdmap.h
>> @@ -212,7 +212,7 @@ extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
>>
>>  extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
>>                              struct ceph_pg pgid,
>> -                            int *acting);
>> +                            int *osds);
>>  extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
>>                               struct ceph_pg pgid);
>>
>> diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
>> index 6d418433d80d..1963623bd488 100644
>> --- a/net/ceph/osdmap.c
>> +++ b/net/ceph/osdmap.c
>> @@ -1642,24 +1642,49 @@ static int apply_temps(struct ceph_osdmap *osdmap,
>>  }
>>
>>  /*
>> - * Return acting set for given pgid.
>> + * Calculate acting set for given pgid.
>> + *
>> + * Return acting set length, or error.
>>   */
>>  int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
>> -                     int *acting)
>> +                     int *osds)
>>  {
>> -     int rawosds[CEPH_PG_MAX_SIZE], *osds;
>> -     int i, o, num = CEPH_PG_MAX_SIZE;
>> +     struct ceph_pg_pool_info *pool;
>> +     u32 pps;
>> +     int len;
>> +     int primary;
>>
>> -     osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
>> -     if (!osds)
>> -             return -1;
>> +     pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
>> +     if (!pool)
>> +             return 0;
>>
>> -     /* primary is first up osd */
>> -     o = 0;
>> -     for (i = 0; i < num; i++)
>> -             if (ceph_osd_is_up(osdmap, osds[i]))
>> -                     acting[o++] = osds[i];
>> -     return o;
>> +     if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
>> +             /* hash pool id and seed so that pool PGs do not overlap */
>> +             pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
>> +                                  ceph_stable_mod(pgid.seed, pool->pgp_num,
>> +                                                  pool->pgp_num_mask),
>> +                                  pgid.pool);
>> +     } else {
>> +             /*
>> +              * legacy ehavior: add ps and pool together.  this is
>
> Typo "behavior"

Fixed.

Thanks,

                Ilya
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 4e28c1e5d62f..b0c8f8490663 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -212,7 +212,7 @@  extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 
 extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
 			       struct ceph_pg pgid,
-			       int *acting);
+			       int *osds);
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 6d418433d80d..1963623bd488 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1642,24 +1642,49 @@  static int apply_temps(struct ceph_osdmap *osdmap,
 }
 
 /*
- * Return acting set for given pgid.
+ * Calculate acting set for given pgid.
+ *
+ * Return acting set length, or error.
  */
 int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
-			int *acting)
+			int *osds)
 {
-	int rawosds[CEPH_PG_MAX_SIZE], *osds;
-	int i, o, num = CEPH_PG_MAX_SIZE;
+	struct ceph_pg_pool_info *pool;
+	u32 pps;
+	int len;
+	int primary;
 
-	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
-	if (!osds)
-		return -1;
+	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
+	if (!pool)
+		return 0;
 
-	/* primary is first up osd */
-	o = 0;
-	for (i = 0; i < num; i++)
-		if (ceph_osd_is_up(osdmap, osds[i]))
-			acting[o++] = osds[i];
-	return o;
+	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
+		/* hash pool id and seed so that pool PGs do not overlap */
+		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
+				     ceph_stable_mod(pgid.seed, pool->pgp_num,
+						     pool->pgp_num_mask),
+				     pgid.pool);
+	} else {
+		/*
+		 * legacy ehavior: add ps and pool together.  this is
+		 * not a great approach because the PGs from each pool
+		 * will overlap on top of each other: 0.5 == 1.4 ==
+		 * 2.3 == ...
+		 */
+		pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
+				      pool->pgp_num_mask) +
+			(unsigned)pgid.pool;
+	}
+
+	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
+	if (len < 0)
+		return len;
+
+	len = raw_to_up_osds(osdmap, pool, osds, len, &primary);
+
+	len = apply_temps(osdmap, pool, pgid, osds, len, &primary);
+
+	return len;
 }
 
 /*