Hi Hamid,
I didn't see any attachment but I think there is a solution. My first
question is, when you created the mempool, how much did you defined the
memory cache per CPU? In the example program this number is fairly small
(32) and I think that increasing it to something much bigger (e.g. 512)
w
Hi Konstantin,
On 05/07/2014 05:19 PM, Ananyev, Konstantin wrote:
> Just to clarify about mempool - I suppose you are talking about
> ability to place internal ring and mempool metadata inside externally
> allocated memory?
Yes, exactly.
> It is already possible to keep mempool elements inside e
Hi Anatoly
You guessed right...it doesn't
"show port stats all" always shows zeros.
Thanks
Tomasz
2014-05-07 17:08 GMT+02:00 Burakov, Anatoly :
> Hi Tomasz,
>
> > 2. dmesg messages appear only when I invoke "start tx_first" in testpmd
> app (so only when I try to send some packets)
>
> Does r
Hi Venky,
On 05/07/2014 04:01 PM, Venkatesan, Venky wrote:
> We should look at how to make the memseg capable of doing alloc/free
> (including re-assembly of fragments) after the 1.7 release. Is that
> something you are considering doing (or are there any other DPDKers
> considering this), or shou
Hi Anatoly
I'm using dpdk-1.6.0r2 on Ubuntu 12.04 LTS with kernel 3.11.0-20-generic
#35~precise1-Ubuntu SMP
As for further investigation:
1. It doesn't matter whether DPDK uses 1GB or 2MB hugepages.
2. dmesg messages appear only when I invoke "start tx_first" in testpmd app
(so only when I try to
It seems to be a good idea, thank you, Olivier!
But a few questions:
1. Will this changes affect performance?
2. In PATCH 2/2 you have a small bug:
In file rte_ring.h, in comments describing rte_ring_init function you have:
+ * @param name
+ * The size of the ring.
But it is name of the ring,
Hi Anatoly.
Yes I do have iommu=on set when booting kernel. This is one of
prerequisites to have SR-IOV running.
Below is the cmdline output
cat /proc/cmdline
BOOT_IMAGE=/boot/vmlinuz-3.11.0-20-generic
root=UUID=c70fa456-ee10-43e5-9f07-4dbb372dcee3 ro quiet splash iommu=pt
intel_iommu=on default_
Hi All
We're trying to run testpmd application on HP Proliant DL380P Gen 8 server.
We've enabled SR-IOV in BIOS and set appropriate flags when booting kernel
(iommu=pt intel_iommu=on)
The NIC we are using is 82599EB (2 ports, 10Gb SFP+)
When running testpmd application we always encouter DMAR err
Venky,
This also applies to mbuf pools. Inside of the openvswitch.org patches we
allocate mbuf pools for a port, but we are unable to free them back when
the port is removed.
One other request (maybe it is there, and I?m unaware), is the ability to
dynamically add / remove a physical port to DPD
Hi Tomasz,
> You guessed right...it doesn't
> "show port stats all" always shows zeros.
As I said earlier, such errors are usually related to errors in boot
parameters, but your kernel cmdline looks perfectly fine, so unless there's
something really odd happening, I can't see this being at faul
Hi Oliver,
Just to clarify about mempool - I suppose you are talking about ability to
place internal ring and mempool metadata inside externally allocated memory?
It is already possible to keep mempool elements inside externally allocated
memory (rte_mempool_xmem_create()).
Konstantin
-Orig
On 05/06/2014 04:33 PM, Konstantin Ananyev wrote:
> Signed-off-by: Konstantin Ananyev
> ---
> lib/librte_pmd_e1000/igb_rxtx.c |2 +-
> 1 files changed, 1 insertions(+), 1 deletions(-)
>
> diff --git a/lib/librte_pmd_e1000/igb_rxtx.c b/lib/librte_pmd_e1000/igb_rxtx.c
> index 6b454a5..7fe1780
On 05/06/2014 04:31 PM, Konstantin Ananyev wrote:
> When latest Linux ixgbe PF is used, and DPDK VF is used in DPDK application,
> jumbo frames are not received.
> Also - if Linux ixgbe PF has MTU set to 1500 (default),
> then normal sized packets can be received by DPDK VF.
> However, if Linux PF
Hi Tomasz,
> 2. dmesg messages appear only when I invoke "start tx_first" in testpmd app
> (so only when I try to send some packets)
Does receiving packets work? I would assume it doesn't, but just making sure.
Best regards,
Anatoly Burakov
DPDK SW Engineer
Hi Igor,
On 05/07/2014 02:42 PM, Igor Ryzhov wrote:
> But a few questions:
> 1. Will this changes affect performance?
It should not. If you have many rings, you may allocate them
in huge pages to avoid TLB misses.
> 2. In PATCH 2/2 you have a small bug:
>
> In file rte_ring.h, in comments descri
2014-05-05 17:50, Thomas Monjalon:
> 2014-04-15 11:03, Wang Sheng-Hui:
> > Parse args first, to resolve any invalid args and give out the usage
> > string. E.g './helloworld --invalid', the '--invalid' will be checked
> > before any init. After the options are checked, take any init actions.
> >
>
Hi Konstantin,
On 05/07/2014 02:35 PM, Ananyev, Konstantin wrote:
> 1. ssize_t rte_ring_get_memsize(unsigned count)
>
> Can you use usual syntax for functions definitions in DPDK:
>
> ssize_t
> rte_ring_get_memsize(unsigned count)
>
> 2. sz = (sz + CACHE_LINE_MASK) & (~CACHE_LINE_MASK);
>
> Use RT
David,
Sorry for the late response. Yes, your suggestion would work. Let?s implement
it ?
Regards,
-Venky
From: David Marchand [mailto:david.march...@6wind.com]
Sent: Monday, May 05, 2014 2:26 AM
To: Venkatesan, Venky
Cc: Burakov, Anatoly; dev at dpdk.org
Subject: Re: [dpdk-dev] [PATCH RFC] eal
Hi Tomasz,
>
> Here lies your mistake :-) Boot your kernel with iommu to "pt" (iommu=pt
> intel_iommu=on) and everything will work. Thje "pt" option enables IOMMU
> only for VM's while "on" sets up your whole system to work through IOMMU
> (including host devices). However, both of these options
Hi Tomasz,
Your words:
> We've enabled SR-IOV in BIOS and set appropriate flags when booting kernel
> (iommu=pt intel_iommu=on)
Your other words:
> Yes I do have iommu=on set when booting kernel.
Here lies your mistake :-) Boot your kernel with iommu to "pt" (iommu=pt
intel_iommu=on) and ever
Hi Tomasz
It looks like you have your kernel booted with iommu=on. Please check your
/proc/cmdline to make sure you didn't accidentally selected the wrong
bootloader entry.
> We're trying to run testpmd application on HP Proliant DL380P Gen 8 server.
> We've enabled SR-IOV in BIOS and set appro
Olivier,
We should look at how to make the memseg capable of doing alloc/free (including
re-assembly of fragments) after the 1.7 release. Is that something you are
considering doing (or are there any other DPDKers considering this), or should
I look at putting together a patch for that?
Rega
Hi Igor,
On 05/07/2014 09:54 AM, Igor Ryzhov wrote:
> I noticed that in Memzone realization there is a special global variable
> "free_memseg" containing pointers on free memory segments.
> An memzone reserve function just finst the best segment for allocation
> from this "free_memseg" variable.
>
Allow to initialize a ring in an already allocated memory. The rte_ring_create()
function that allocates a ring in a rte_memzone is still available and now uses
the new rte_ring_init() function in order to factorize the code.
Signed-off-by: Olivier Matz
---
lib/librte_ring/rte_ring.c | 63 ++
Add a function that returns the amount of memory occupied by a rte_ring
structure and its object table. This commit prepares the next one that
will allow to allocate a ring dynamically.
Signed-off-by: Olivier Matz
---
lib/librte_ring/rte_ring.c | 29 ++---
lib/librte_ring
These 2 patches adds 2 new functions that permits to initialize and use
a rte_ring anywhere in memory.
Before this patches, only rte_ring_create() was available. This function
allocates a rte_memzone (that cannot be freed) and initializes a ring
inside.
This series allows to do the following:
s
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Liu, Jijiang
> Sent: Wednesday, May 07, 2014 7:36 AM
> To: dev at dpdk.org
> Subject: Re: [dpdk-dev] could not l2fwd in DOM0
>
> Hi,
>
> I have checked source codes of xen_create_contiguous_region function in
>
Hi Oliver,
2 nits from me:
1. ssize_t rte_ring_get_memsize(unsigned count)
Can you use usual syntax for functions definitions in DPDK:
ssize_t
rte_ring_get_memsize(unsigned count)
2. sz = (sz + CACHE_LINE_MASK) & (~CACHE_LINE_MASK);
Use RTE_ALIGN(sz, CACHE_LINE_SIZE) instead?
Konstantin
---
Hello again.
I did some investigation on the code.
I learned that RTE Ring creation function uses functions related to RTE
Memzone to reserve memory (rte_memzone_reserve).
Documentation states that once reserved memzone can not be unreserved. I
decided to find out why it is so.
I noticed that i
On Tue, 6 May 2014 09:17:46 +
"Burakov, Anatoly" wrote:
> Hi Stephen,
>
> > When doing diagnostic function, it is useful to have a ability to iterate
> > over all
> > memzones.
> >
>
> You can already access all memzones through
> rte_eal_get_configuration()->mem_config.memzone[idx].
>
Hi,
I have checked source codes of xen_create_contiguous_region function in kernel
3.14, and found the dma_handle cannot be NULL.
int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
unsigned int address_bits,
31 matches
Mail list logo
