[dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Xutao Sun]

Macro MAX_QUEUES was defined to 128, only allow 16 mem_pools in theory.
When running vmdq_app with more than 34 mem_pools,
it will cause the core_dump issue.
Change MAX_QUEUES to 1024 will solve this issue.

Signed-off-by: Xutao Sun <xutao.sun@intel.com>
---
 examples/vmdq/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
index a142d49..b463cfb 100644
--- a/examples/vmdq/main.c
+++ b/examples/vmdq/main.c
@@ -69,7 +69,7 @@
 #include <rte_mbuf.h>
 #include <rte_memcpy.h>
 
-#define MAX_QUEUES 128
+#define MAX_QUEUES 1024
 /*
  * For 10 GbE, 128 queues require roughly
  * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
-- 
1.9.3

Re: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[De Lara Guarch, Pablo]

Hi Xutao,

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xutao Sun
> Sent: Tuesday, October 13, 2015 8:29 AM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when
> mem_pool is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 mem_pools in
> theory.
> When running vmdq_app with more than 34 mem_pools,
> it will cause the core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> ---
>  examples/vmdq/main.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
> index a142d49..b463cfb 100644
> --- a/examples/vmdq/main.c
> +++ b/examples/vmdq/main.c
> @@ -69,7 +69,7 @@
>  #include <rte_mbuf.h>
>  #include <rte_memcpy.h>
> 
> -#define MAX_QUEUES 128
> +#define MAX_QUEUES 1024
>  /*
>   * For 10 GbE, 128 queues require roughly
>   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> --
> 1.9.3

Just for clarification, when you say mem_pools, do you mean vmdq pools?
Also, if you are going to increase MAX_QUEUES, shouldn't you increase the NUM_MBUFS_PER_PORT?
Looking at the comment below, looks like there is a calculation of number of mbufs based on number of queues.
Plus, I assume 128 is the maximum number of queues per port, and as far as I know,
only Fortville supports 256 as maximum.

Thanks,
Pablo

Re: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Sun, Xutao]

> -----Original Message-----
> From: De Lara Guarch, Pablo
> Sent: Tuesday, October 13, 2015 3:59 PM
> To: Sun, Xutao; dev@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue
> when mem_pool is more than 34
> 
> Hi Xutao,
> 
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xutao Sun
> > Sent: Tuesday, October 13, 2015 8:29 AM
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue
> > when mem_pool is more than 34
> >
> > Macro MAX_QUEUES was defined to 128, only allow 16 mem_pools in
> > theory.
> > When running vmdq_app with more than 34 mem_pools, it will cause the
> > core_dump issue.
> > Change MAX_QUEUES to 1024 will solve this issue.
> >
> > Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> > ---
> >  examples/vmdq/main.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c index
> > a142d49..b463cfb 100644
> > --- a/examples/vmdq/main.c
> > +++ b/examples/vmdq/main.c
> > @@ -69,7 +69,7 @@
> >  #include <rte_mbuf.h>
> >  #include <rte_memcpy.h>
> >
> > -#define MAX_QUEUES 128
> > +#define MAX_QUEUES 1024
> >  /*
> >   * For 10 GbE, 128 queues require roughly
> >   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> > --
> > 1.9.3
> 
> Just for clarification, when you say mem_pools, do you mean vmdq pools?
> Also, if you are going to increase MAX_QUEUES, shouldn't you increase the
> NUM_MBUFS_PER_PORT?
> Looking at the comment below, looks like there is a calculation of number of
> mbufs based on number of queues.
> Plus, I assume 128 is the maximum number of queues per port, and as far as I
> know, only Fortville supports 256 as maximum.
> 
> Thanks,
> Pablo


Hi Pablo,

I mean vmdq pools when I say mem_pools.
And as you say, NUM_MBUFS_PER_PORT should be increased actually. 
I may use macro to replace the old expression. 
#define NUM_MBUFS_PER_PORT (MAX_QUEUES * max(RTE_TEST_RX_DESC_DEFAULT,RTE_TEST_TX_DESC_DEFAULT))
And this patch is to fix the issue about running VMDQ on  Fortville, so the maximum number of queues is larger than 128.
Thank you very much for your advice!

Thanks,
Xutao

[dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Xutao Sun]

Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in theory.
When running vmdq_app with more than 34 vmdq_pools, it will cause the
core_dump issue.
Change MAX_QUEUES to 1024 will solve this issue.

Signed-off-by: Xutao Sun <xutao.sun@intel.com>
---
v2:
 - rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been changed

 examples/vmdq/main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
index a142d49..bba5164 100644
--- a/examples/vmdq/main.c
+++ b/examples/vmdq/main.c
@@ -69,12 +69,13 @@
 #include <rte_mbuf.h>
 #include <rte_memcpy.h>
 
-#define MAX_QUEUES 128
+#define MAX_QUEUES 1024
 /*
  * For 10 GbE, 128 queues require roughly
  * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
  */
-#define NUM_MBUFS_PER_PORT (128*512)
+#define NUM_MBUFS_PER_PORT (MAX_QUEUES * RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, \
+						RTE_TEST_TX_DESC_DEFAULT))
 #define MBUF_CACHE_SIZE 64
 
 #define MAX_PKT_BURST 32
-- 
1.9.3

Re: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[De Lara Guarch, Pablo]

Hi Xutao,

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xutao Sun
> Sent: Tuesday, October 27, 2015 5:11 AM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue
> when mem_pool is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in
> theory.
> When running vmdq_app with more than 34 vmdq_pools, it will cause the
> core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> ---
> v2:
>  - rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been
> changed
> 
>  examples/vmdq/main.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
> index a142d49..bba5164 100644
> --- a/examples/vmdq/main.c
> +++ b/examples/vmdq/main.c
> @@ -69,12 +69,13 @@
>  #include <rte_mbuf.h>
>  #include <rte_memcpy.h>
> 
> -#define MAX_QUEUES 128
> +#define MAX_QUEUES 1024
>  /*
>   * For 10 GbE, 128 queues require roughly
>   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
>   */
> -#define NUM_MBUFS_PER_PORT (128*512)
> +#define NUM_MBUFS_PER_PORT (MAX_QUEUES *
> RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, \
> +
> 	RTE_TEST_TX_DESC_DEFAULT))
>  #define MBUF_CACHE_SIZE 64
> 
>  #define MAX_PKT_BURST 32
> --
> 1.9.3

Please, change the comment above, as you have change code related to it,
i.e. it is not 128*512 anymore.

Pablo

Re: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Sun, Xutao]

> -----Original Message-----
> From: De Lara Guarch, Pablo
> Sent: Tuesday, October 27, 2015 3:55 PM
> To: Sun, Xutao; dev@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue
> when mem_pool is more than 34
> 
> Hi Xutao,
> 
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xutao Sun
> > Sent: Tuesday, October 27, 2015 5:11 AM
> > To: dev@dpdk.org
> > Subject: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue
> > when mem_pool is more than 34
> >
> > Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in
> > theory.
> > When running vmdq_app with more than 34 vmdq_pools, it will cause the
> > core_dump issue.
> > Change MAX_QUEUES to 1024 will solve this issue.
> >
> > Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> > ---
> > v2:
> >  - rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been
> changed
> >
> >  examples/vmdq/main.c | 5 +++--
> >  1 file changed, 3 insertions(+), 2 deletions(-)
> >
> > diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c index
> > a142d49..bba5164 100644
> > --- a/examples/vmdq/main.c
> > +++ b/examples/vmdq/main.c
> > @@ -69,12 +69,13 @@
> >  #include <rte_mbuf.h>
> >  #include <rte_memcpy.h>
> >
> > -#define MAX_QUEUES 128
> > +#define MAX_QUEUES 1024
> >  /*
> >   * For 10 GbE, 128 queues require roughly
> >   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> >   */
> > -#define NUM_MBUFS_PER_PORT (128*512)
> > +#define NUM_MBUFS_PER_PORT (MAX_QUEUES *
> > RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, \
> > +
> > 	RTE_TEST_TX_DESC_DEFAULT))
> >  #define MBUF_CACHE_SIZE 64
> >
> >  #define MAX_PKT_BURST 32
> > --
> > 1.9.3
> 
> Please, change the comment above, as you have change code related to it,
> i.e. it is not 128*512 anymore.
> 
> Pablo

Hi, Pablo

I described how I changed code in version 2 below "v2".
And I think the main feature of the patch to is modify the number of MAX_QUEUES.
So I just described the other features briefly.

Thanks,
Xutao

[dpdk-dev] [PATCH v3] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Xutao Sun]

Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in theory.
When running vmdq_app with more than 34 vmdq_pools, it will cause the
core_dump issue.
Change MAX_QUEUES to 1024 will solve this issue.

Signed-off-by: Xutao Sun <xutao.sun@intel.com>
---
v2:
 - Rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been changed

v3:
 - Change the comments above the relevant code.
 
 examples/vmdq/main.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
index a142d49..178af2f 100644
--- a/examples/vmdq/main.c
+++ b/examples/vmdq/main.c
@@ -69,12 +69,13 @@
 #include <rte_mbuf.h>
 #include <rte_memcpy.h>
 
-#define MAX_QUEUES 128
+#define MAX_QUEUES 1024
 /*
- * For 10 GbE, 128 queues require roughly
- * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
+ * 1024 queues require to meet the needs of a large number of vmdq_pools.
+ * (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
  */
-#define NUM_MBUFS_PER_PORT (128*512)
+#define NUM_MBUFS_PER_PORT (MAX_QUEUES * RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, \
+						RTE_TEST_TX_DESC_DEFAULT))
 #define MBUF_CACHE_SIZE 64
 
 #define MAX_PKT_BURST 32
-- 
1.9.3

Re: [dpdk-dev] [PATCH v3] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[De Lara Guarch, Pablo]

> -----Original Message-----
> From: Sun, Xutao
> Sent: Tuesday, October 27, 2015 8:59 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo; Wu, Jingjing; Zhang, Helin; Sun, Xutao
> Subject: [PATCH v3] examples/vmdq: Fix the core dump issue when
> mem_pool is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in
> theory.
> When running vmdq_app with more than 34 vmdq_pools, it will cause the
> core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> ---
> v2:
>  - Rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been
> changed
> 
> v3:
>  - Change the comments above the relevant code.
> 
>  examples/vmdq/main.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c
> index a142d49..178af2f 100644
> --- a/examples/vmdq/main.c
> +++ b/examples/vmdq/main.c
> @@ -69,12 +69,13 @@
>  #include <rte_mbuf.h>
>  #include <rte_memcpy.h>
> 
> -#define MAX_QUEUES 128
> +#define MAX_QUEUES 1024
>  /*
> - * For 10 GbE, 128 queues require roughly
> - * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> + * 1024 queues require to meet the needs of a large number of
> vmdq_pools.
> + * (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
>   */
> -#define NUM_MBUFS_PER_PORT (128*512)
> +#define NUM_MBUFS_PER_PORT (MAX_QUEUES *
> RTE_MAX(RTE_TEST_RX_DESC_DEFAULT, \
> +
> 	RTE_TEST_TX_DESC_DEFAULT))
>  #define MBUF_CACHE_SIZE 64
> 
>  #define MAX_PKT_BURST 32
> --
> 1.9.3

Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

Re: [dpdk-dev] [PATCH v2] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Wu, Jingjing]

> -----Original Message-----
> From: Sun, Xutao
> Sent: Tuesday, October 27, 2015 1:11 PM
> To: dev@dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Sun, Xutao
> Subject: [PATCH v2] examples/vmdq: Fix the core dump issue when
> mem_pool is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in
> theory.
> When running vmdq_app with more than 34 vmdq_pools, it will cause the
> core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>

Acked-by: Jingjing Wu <jingjing.wu@intel.com>

> ---
> v2:
>  - rectify the NUM_MBUFS_PER_PORT since MAX_QUEUES has been
> changed
> 
>  examples/vmdq/main.c | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> 1.9.3

Re: [dpdk-dev] [PATCH v3] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Thomas Monjalon]

> > Macro MAX_QUEUES was defined to 128, only allow 16 vmdq_pools in
> > theory.
> > When running vmdq_app with more than 34 vmdq_pools, it will cause the
> > core_dump issue.
> > Change MAX_QUEUES to 1024 will solve this issue.
> > 
> > Signed-off-by: Xutao Sun <xutao.sun@intel.com>
> 
> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>

Applied, thanks

Re: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Xu, Qian Q]

Tested-by: Qian Xu<qian.q.xu@intel.com>
Commit: c36a82f045ae362b76af4f2a53af10a2a4d2d20f
Test platform: HSW server
OS: Fedora 20
Kernel : 3.18
1. Bind 2ports to igb_uio
2. Run vmdq sample : ./examples/vmdq/build/vmdq_app -n 4 -c 0x1e -- -p 0x3 --nb-pools 63
3. Send 63 flows with different MAC/VLAN and see the output.
4. No crash at the app, before the app will be core dumped due to the queue number is too small. 
Test result: Pass


Thanks
Qian


-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Wu, Jingjing
Sent: Monday, September 21, 2015 2:43 PM
To: Sun, Xutao; dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34



> -----Original Message-----
> From: Sun, Xutao
> Sent: Monday, September 21, 2015 1:45 PM
> To: dev@dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Sun, Xutao
> Subject: [PATCH] examples/vmdq: Fix the core dump issue when mem_pool 
> is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 mem_pools in theory.
> When running vmdq_app with more than 34 mem_pools, it will cause the 
> core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
> ---
>  examples/vmdq/main.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c index 
> a142d49..b463cfb 100644
> --- a/examples/vmdq/main.c
> +++ b/examples/vmdq/main.c
> @@ -69,7 +69,7 @@
>  #include <rte_mbuf.h>
>  #include <rte_memcpy.h>
> 
> -#define MAX_QUEUES 128
> +#define MAX_QUEUES 1024
>  /*
>   * For 10 GbE, 128 queues require roughly
>   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> --
> 1.9.3

Re: [dpdk-dev] [PATCH] examples/vmdq: Fix the core dump issue when mem_pool is more than 34

[Wu, Jingjing]

> -----Original Message-----
> From: Sun, Xutao
> Sent: Monday, September 21, 2015 1:45 PM
> To: dev@dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Sun, Xutao
> Subject: [PATCH] examples/vmdq: Fix the core dump issue when mem_pool
> is more than 34
> 
> Macro MAX_QUEUES was defined to 128, only allow 16 mem_pools in theory.
> When running vmdq_app with more than 34 mem_pools, it will cause the
> core_dump issue.
> Change MAX_QUEUES to 1024 will solve this issue.
> 
> Signed-off-by: Xutao Sun <xutao.sun@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
> ---
>  examples/vmdq/main.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/examples/vmdq/main.c b/examples/vmdq/main.c index
> a142d49..b463cfb 100644
> --- a/examples/vmdq/main.c
> +++ b/examples/vmdq/main.c
> @@ -69,7 +69,7 @@
>  #include <rte_mbuf.h>
>  #include <rte_memcpy.h>
> 
> -#define MAX_QUEUES 128
> +#define MAX_QUEUES 1024
>  /*
>   * For 10 GbE, 128 queues require roughly
>   * 128*512 (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port.
> --
> 1.9.3