[dpdk-stable] [PATCH v2] examples/multi_process: fix buffer underrun

[Yongseok Koh]

> On Apr 11, 2019, at 12:18 AM, Yongseok Koh <yskoh at mellanox.com> wrote:
> 
>> On Apr 10, 2019, at 12:41 PM, Yongseok Koh <yskoh at mellanox.com> wrote:
>> 
>> For client_server_mp, the total number of buffers for the mbuf mempool
>> should be correctly calculated. Otherwise, having more clients will stop
>> traffic.
>> 
>> Fixes: af75078fece3 ("first public release")
>> Cc: stable at dpdk.org
>> 
>> Signed-off-by: Yongseok Koh <yskoh at mellanox.com>
>> ---
>> 
>> v2:
>> * split up the calculation
> 
> Sorry, I forgot to specify 'v2' in the title of this email.

No ack? No merge?

Yongseok

> 
>> examples/multi_process/client_server_mp/mp_server/init.c | 13 +++++++++----
>> 1 file changed, 9 insertions(+), 4 deletions(-)
>> 
>> diff --git a/examples/multi_process/client_server_mp/mp_server/init.c b/examples/multi_process/client_server_mp/mp_server/init.c
>> index 30c8e44bc0..3af5dc6994 100644
>> --- a/examples/multi_process/client_server_mp/mp_server/init.c
>> +++ b/examples/multi_process/client_server_mp/mp_server/init.c
>> @@ -37,8 +37,6 @@
>> #include "args.h"
>> #include "init.h"
>> 
>> -#define MBUFS_PER_CLIENT 1536
>> -#define MBUFS_PER_PORT 1536
>> #define MBUF_CACHE_SIZE 512
>> 
>> #define RTE_MP_RX_DESC_DEFAULT 1024
>> @@ -63,8 +61,15 @@ struct port_info *ports;
>> static int
>> init_mbuf_pools(void)
>> {
>> -	const unsigned num_mbufs = (num_clients * MBUFS_PER_CLIENT) \
>> -			+ (ports->num_ports * MBUFS_PER_PORT);
>> +	const unsigned int num_mbufs_server =
>> +		RTE_MP_RX_DESC_DEFAULT * ports->num_ports;
>> +	const unsigned int num_mbufs_client =
>> +		num_clients * (CLIENT_QUEUE_RINGSIZE +
>> +			       RTE_MP_TX_DESC_DEFAULT * ports->num_ports);
>> +	const unsigned int num_mbufs_mp_cache =
>> +		(num_clients + 1) * MBUF_CACHE_SIZE;
>> +	const unsigned int num_mbufs =
>> +		num_mbufs_server + num_mbufs_client + num_mbufs_mp_cache;
>> 
>> 	/* don't pass single-producer/single-consumer flags to mbuf create as it
>> 	 * seems faster to use a cache instead */
>> -- 
>> 2.11.0
>> 
>