diff mbox

[dpdk-dev] mutli process C/S model example init failed on xen dom0 with dpdk-16.07 rc2 package

Message ID 5784D4DF.6070204@6wind.com (mailing list archive)
State Not Applicable, archived
Headers

Commit Message

Olivier Matz July 12, 2016, 11:30 a.m. UTC 
  Hi Huilong,


On 07/12/2016 11:22 AM, Xu, HuilongX wrote:
> Hi all,
>
> I run mutli procee C/S model example failed on xen dom0. Does anyone
> give me some suggest how to debug it?
>
> Thanks a lot
>
> test environment:
>
>        OS&kernel: 3.17.4-301.fc21.x86_64
>
> Gcc version: gcc version 4.9.2 20141101 (Red Hat 4.9.2-1) (GCC)
>
> Package :dpdk.16.07-rc1.tar.gz
>
> Target: x86_64-native-linuxapp-gcc
>
> Compile switch: enable CONFIG_RTE_LIBRTE_XEN_DOM0
>
> Xen version:4.4.1
>
> Test cmdline and result:
>
> /examples/multi_process/client_server_mp/mp_server/mp_server/x86_64-native-linuxapp-gcc/mp_server
> -c f -n 4 --xen-dom0 -- -p 0x3 -n 2
> EAL: Detected 72 lcore(s)
> EAL: Probing VFIO support...
> PMD: bnxt_rte_pmd_init() called for (null)
> EAL: PCI device 0000:01:00.0 on NUMA socket 0
> EAL: probe driver: 8086:1521 rte_igb_pmd
> EAL: PCI device 0000:01:00.1 on NUMA socket 0
> EAL: probe driver: 8086:1521 rte_igb_pmd
> EAL: PCI device 0000:04:00.0 on NUMA socket 0
> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
> EAL: PCI device 0000:04:00.1 on NUMA socket 0
> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
> Creating mbuf pool 'MProc_pktmbuf_pool' [6144 mbufs] ...
> Port 0 init ... Segmentation fault (core dumped)
>

I reproduced the issue on my platform. In my case, the crash occurs in 
rx_queue_setup():

         /* Free memory prior to re-allocation if needed. */
         if (dev->data->rx_queues[queue_idx] != NULL) {
=>              em_rx_queue_release(dev->data->rx_queues[queue_idx]);
                 dev->data->rx_queues[queue_idx] = NULL;
         }

I don't this we should go in that area for the first rx queue 
initialization. I suspect it could be related to this commit:
http://dpdk.org/browse/dpdk/commit/?id=ea0bddbd14e68f

I think we cannot expect that memory is initialized at 0 when using Xen 
dom0. If I add the following (dirty) patch, I don't see a crash anymore:


  /*


Sergio, could you have a look at it?

Regards,
Olivier

Comments

Sergio Gonzalez Monroy July 18, 2016, 11:33 a.m. UTC | #1 
Hi,

On 12/07/2016 12:30, Olivier MATZ wrote:
> Hi Huilong,
>
>
> On 07/12/2016 11:22 AM, Xu, HuilongX wrote:
>> Hi all,
>>
>> I run mutli procee C/S model example failed on xen dom0. Does anyone
>> give me some suggest how to debug it?
>>
>> Thanks a lot
>>
>> test environment:
>>
>>        OS&kernel: 3.17.4-301.fc21.x86_64
>>
>> Gcc version: gcc version 4.9.2 20141101 (Red Hat 4.9.2-1) (GCC)
>>
>> Package :dpdk.16.07-rc1.tar.gz
>>
>> Target: x86_64-native-linuxapp-gcc
>>
>> Compile switch: enable CONFIG_RTE_LIBRTE_XEN_DOM0
>>
>> Xen version:4.4.1
>>
>> Test cmdline and result:
>>
>> /examples/multi_process/client_server_mp/mp_server/mp_server/x86_64-native-linuxapp-gcc/mp_server 
>>
>> -c f -n 4 --xen-dom0 -- -p 0x3 -n 2
>> EAL: Detected 72 lcore(s)
>> EAL: Probing VFIO support...
>> PMD: bnxt_rte_pmd_init() called for (null)
>> EAL: PCI device 0000:01:00.0 on NUMA socket 0
>> EAL: probe driver: 8086:1521 rte_igb_pmd
>> EAL: PCI device 0000:01:00.1 on NUMA socket 0
>> EAL: probe driver: 8086:1521 rte_igb_pmd
>> EAL: PCI device 0000:04:00.0 on NUMA socket 0
>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>> EAL: PCI device 0000:04:00.1 on NUMA socket 0
>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>> Creating mbuf pool 'MProc_pktmbuf_pool' [6144 mbufs] ...
>> Port 0 init ... Segmentation fault (core dumped)
>>
>
> I reproduced the issue on my platform. In my case, the crash occurs in 
> rx_queue_setup():
>
>         /* Free memory prior to re-allocation if needed. */
>         if (dev->data->rx_queues[queue_idx] != NULL) {
> => em_rx_queue_release(dev->data->rx_queues[queue_idx]);
>                 dev->data->rx_queues[queue_idx] = NULL;
>         }
>
> I don't this we should go in that area for the first rx queue 
> initialization. I suspect it could be related to this commit:
> http://dpdk.org/browse/dpdk/commit/?id=ea0bddbd14e68f
>
> I think we cannot expect that memory is initialized at 0 when using 
> Xen dom0. If I add the following (dirty) patch, I don't see a crash 
> anymore:

I don't have a Xen system available right now, but I'm not sure I follow 
here.
Are you saying that when we allocate pages/hugepages from Xen they are 
not zeroed?

>
> --- a/lib/librte_eal/common/eal_common_memzone.c
> +++ b/lib/librte_eal/common/eal_common_memzone.c
> @@ -258,6 +258,8 @@ memzone_reserve_aligned_thread_unsafe(const char 
> *name, size_t len,
>         mz->flags = 0;
>         mz->memseg_id = elem->ms - 
> rte_eal_get_configuration()->mem_config->memseg;
>
> +       memset(mz->addr, 0, mz->len);
> +
>         return mz;
>  }
>

The commit you are referring to does not touch the memzone reserve APIs, 
only changes zmalloc and related APIs.

> --- a/lib/librte_eal/common/rte_malloc.c
> +++ b/lib/librte_eal/common/rte_malloc.c
> @@ -123,7 +123,13 @@ rte_malloc(const char *type, size_t size, 
> unsigned align)
>  void *
>  rte_zmalloc_socket(const char *type, size_t size, unsigned align, int 
> socket)
>  {
> -       return rte_malloc_socket(type, size, align, socket);
> +       void *x = rte_malloc_socket(type, size, align, socket);
> +
> +       if (x == NULL)
> +               return NULL;
> +
> +       memset(x, 0, size);
> +       return x;
>  }
>
>  /*
>
>
> Sergio, could you have a look at it?
>
> Regards,
> Olivier
Olivier Matz July 18, 2016, 11:49 a.m. UTC | #2 
Hi Sergio,

On 07/18/2016 01:33 PM, Sergio Gonzalez Monroy wrote:
> On 12/07/2016 12:30, Olivier MATZ wrote:
>> On 07/12/2016 11:22 AM, Xu, HuilongX wrote:
>>> /examples/multi_process/client_server_mp/mp_server/mp_server/x86_64-native-linuxapp-gcc/mp_server
>>>
>>> -c f -n 4 --xen-dom0 -- -p 0x3 -n 2
>>> EAL: Detected 72 lcore(s)
>>> EAL: Probing VFIO support...
>>> PMD: bnxt_rte_pmd_init() called for (null)
>>> EAL: PCI device 0000:01:00.0 on NUMA socket 0
>>> EAL: probe driver: 8086:1521 rte_igb_pmd
>>> EAL: PCI device 0000:01:00.1 on NUMA socket 0
>>> EAL: probe driver: 8086:1521 rte_igb_pmd
>>> EAL: PCI device 0000:04:00.0 on NUMA socket 0
>>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>>> EAL: PCI device 0000:04:00.1 on NUMA socket 0
>>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>>> Creating mbuf pool 'MProc_pktmbuf_pool' [6144 mbufs] ...
>>> Port 0 init ... Segmentation fault (core dumped)
>>>
>>
>> I reproduced the issue on my platform. In my case, the crash occurs in
>> rx_queue_setup():
>>
>>         /* Free memory prior to re-allocation if needed. */
>>         if (dev->data->rx_queues[queue_idx] != NULL) {
>> => em_rx_queue_release(dev->data->rx_queues[queue_idx]);
>>                 dev->data->rx_queues[queue_idx] = NULL;
>>         }
>>
>> I don't this we should go in that area for the first rx queue
>> initialization. I suspect it could be related to this commit:
>> http://dpdk.org/browse/dpdk/commit/?id=ea0bddbd14e68f
>>
>> I think we cannot expect that memory is initialized at 0 when using
>> Xen dom0. If I add the following (dirty) patch, I don't see a crash
>> anymore:
> 
> I don't have a Xen system available right now, but I'm not sure I follow
> here.
> Are you saying that when we allocate pages/hugepages from Xen they are
> not zeroed?

I did not check it, but from the tests I've done, I suppose they're not.


>> --- a/lib/librte_eal/common/eal_common_memzone.c
>> +++ b/lib/librte_eal/common/eal_common_memzone.c
>> @@ -258,6 +258,8 @@ memzone_reserve_aligned_thread_unsafe(const char
>> *name, size_t len,
>>         mz->flags = 0;
>>         mz->memseg_id = elem->ms -
>> rte_eal_get_configuration()->mem_config->memseg;
>>
>> +       memset(mz->addr, 0, mz->len);
>> +
>>         return mz;
>>  }
>>
> 
> The commit you are referring to does not touch the memzone reserve APIs,
> only changes zmalloc and related APIs.

I just did a quick test, adding the memset() at the places where I
thought it could be required. Maybe the patch is a bit overkill and only
the zmalloc part fixes the issue.


Regards,
Olivier
Sergio Gonzalez Monroy July 18, 2016, 1:15 p.m. UTC | #3 
On 18/07/2016 12:49, Olivier Matz wrote:
> Hi Sergio,
>
> On 07/18/2016 01:33 PM, Sergio Gonzalez Monroy wrote:
>> On 12/07/2016 12:30, Olivier MATZ wrote:
>>> On 07/12/2016 11:22 AM, Xu, HuilongX wrote:
>>>> /examples/multi_process/client_server_mp/mp_server/mp_server/x86_64-native-linuxapp-gcc/mp_server
>>>>
>>>> -c f -n 4 --xen-dom0 -- -p 0x3 -n 2
>>>> EAL: Detected 72 lcore(s)
>>>> EAL: Probing VFIO support...
>>>> PMD: bnxt_rte_pmd_init() called for (null)
>>>> EAL: PCI device 0000:01:00.0 on NUMA socket 0
>>>> EAL: probe driver: 8086:1521 rte_igb_pmd
>>>> EAL: PCI device 0000:01:00.1 on NUMA socket 0
>>>> EAL: probe driver: 8086:1521 rte_igb_pmd
>>>> EAL: PCI device 0000:04:00.0 on NUMA socket 0
>>>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>>>> EAL: PCI device 0000:04:00.1 on NUMA socket 0
>>>> EAL: probe driver: 8086:10fb rte_ixgbe_pmd
>>>> Creating mbuf pool 'MProc_pktmbuf_pool' [6144 mbufs] ...
>>>> Port 0 init ... Segmentation fault (core dumped)
>>>>
>>> I reproduced the issue on my platform. In my case, the crash occurs in
>>> rx_queue_setup():
>>>
>>>          /* Free memory prior to re-allocation if needed. */
>>>          if (dev->data->rx_queues[queue_idx] != NULL) {
>>> => em_rx_queue_release(dev->data->rx_queues[queue_idx]);
>>>                  dev->data->rx_queues[queue_idx] = NULL;
>>>          }
>>>
>>> I don't this we should go in that area for the first rx queue
>>> initialization. I suspect it could be related to this commit:
>>> http://dpdk.org/browse/dpdk/commit/?id=ea0bddbd14e68f
>>>
>>> I think we cannot expect that memory is initialized at 0 when using
>>> Xen dom0. If I add the following (dirty) patch, I don't see a crash
>>> anymore:
>> I don't have a Xen system available right now, but I'm not sure I follow
>> here.
>> Are you saying that when we allocate pages/hugepages from Xen they are
>> not zeroed?
> I did not check it, but from the tests I've done, I suppose they're not.

If that is the case then I would suggest to zero all memory on EAL init 
(only for Xen) so
all memory is zeroed after init for both Linux and Xen.

What do you think about that?

Regards,
Sergio

>
>>> --- a/lib/librte_eal/common/eal_common_memzone.c
>>> +++ b/lib/librte_eal/common/eal_common_memzone.c
>>> @@ -258,6 +258,8 @@ memzone_reserve_aligned_thread_unsafe(const char
>>> *name, size_t len,
>>>          mz->flags = 0;
>>>          mz->memseg_id = elem->ms -
>>> rte_eal_get_configuration()->mem_config->memseg;
>>>
>>> +       memset(mz->addr, 0, mz->len);
>>> +
>>>          return mz;
>>>   }
>>>
>> The commit you are referring to does not touch the memzone reserve APIs,
>> only changes zmalloc and related APIs.
> I just did a quick test, adding the memset() at the places where I
> thought it could be required. Maybe the patch is a bit overkill and only
> the zmalloc part fixes the issue.
>
>
> Regards,
> Olivier
Thomas Monjalon July 18, 2016, 1:34 p.m. UTC | #4 
2016-07-18 14:15, Sergio Gonzalez Monroy:
> On 18/07/2016 12:49, Olivier Matz wrote:
> > On 07/18/2016 01:33 PM, Sergio Gonzalez Monroy wrote:
> >> On 12/07/2016 12:30, Olivier MATZ wrote:
> >>> I think we cannot expect that memory is initialized at 0 when using
> >>> Xen dom0. If I add the following (dirty) patch, I don't see a crash
> >>> anymore:
> >> I don't have a Xen system available right now, but I'm not sure I follow
> >> here.
> >> Are you saying that when we allocate pages/hugepages from Xen they are
> >> not zeroed?
> > I did not check it, but from the tests I've done, I suppose they're not.
> 
> If that is the case then I would suggest to zero all memory on EAL init 
> (only for Xen) so
> all memory is zeroed after init for both Linux and Xen.
> 
> What do you think about that?

It is an idea.
It is probable that you won't have any answer as the Xen support is
unmaintained:
	http://dpdk.org/ml/archives/dev/2016-July/043875.html
Feel free to make a patch to try fixing it or we can remove this
whole dead code.
diff mbox

Patch

--- a/lib/librte_eal/common/eal_common_memzone.c
+++ b/lib/librte_eal/common/eal_common_memzone.c
@@ -258,6 +258,8 @@  memzone_reserve_aligned_thread_unsafe(const char 
*name, size_t len,
         mz->flags = 0;
         mz->memseg_id = elem->ms - 
rte_eal_get_configuration()->mem_config->memseg;

+       memset(mz->addr, 0, mz->len);
+
         return mz;
  }

--- a/lib/librte_eal/common/rte_malloc.c
+++ b/lib/librte_eal/common/rte_malloc.c
@@ -123,7 +123,13 @@  rte_malloc(const char *type, size_t size, unsigned 
align)
  void *
  rte_zmalloc_socket(const char *type, size_t size, unsigned align, int 
socket)
  {
-       return rte_malloc_socket(type, size, align, socket);
+       void *x = rte_malloc_socket(type, size, align, socket);
+
+       if (x == NULL)
+               return NULL;
+
+       memset(x, 0, size);
+       return x;
  }