[dpdk-users] IPv4 Fragmentation - indirect pool gets exhausted

[Vishal Mohan]

Hi,

I m trying to fragmentation an IPv4 packet using the below logic:

/

~after pkts ingress~

struct rte_port_ring_writer *p = port_out->h_port;

pool_direct = rte_mempool_lookup("MEMPOOL0");
pool_indirect = rte_mempool_lookup("MEMPOOL1");

printf("before frag mempool size d %d in 
%d\n",rte_mempool_avail_count(pool_direct),rte_mempool_avail_count(pool_indirect));

struct rte_mbuf *frag_pkts[MAX_FRAG_SIZE];
int out_pkts =rte_ipv4_fragment_packet (m, frag_pkts, n_frags, ip_mtu,

pool_direct, pool_indirect);

printf("after frag mempool size d %d in 
%d\n",rte_mempool_avail_count(pool_direct),rte_mempool_avail_count(pool_indirect));

if(out_pkts > 0)
port_out->ops.f_tx_bulk(port_out->h_port,frag_pkts,RTE_LEN2MASK(out_pkts, 
uint64_t));
else
printf("frag failed\n");

rte_pktmbuf_free(m);

/

Now the problem here is the indirect mempool gets exhausted. As a result after 
few burst of packets the fragmentation fails due to -ENOMEM. I quite cannot 
understand why the PMD doesn't free and put back the mempool obj back to 
MEMPOOL1. Please find the log below for the above snippet which prints the 
available slots in direct (d) and indirect (in) mempools:

before frag mempool size d 2060457 in 2095988
after frag mempool size d 2060344 in 2095952
before frag mempool size d 2060361 in 2095945
after frag mempool size d 2060215 in 2095913
.
.
.
before frag mempool size d 2045013 in 0
after frag mempool size d 2045013 in 0
before frag mempool size d 2045013 in 0
after frag mempool size d 2045013 in 0
before frag mempool size d 2045013 in 0

I can see the direct mempool reduce and increase as packets ingress and 
drop/egress as expected. I can also confirm I receive the initial burst of 
fragmented packets equal to MEMPOOL1 size. Any inputs towards understanding the 
cause of the problem is much appreciated.

P.S: We had the same problem in dpdk17.11. We had to refractor the 
rte_ipv4_fragment_packet() to not use indirect chaining of frags instead just 
generate them.

Thanks & Regards,
Vishal Mohan


Tata Communications - Public


Tata Communications - Public

[dpdk-users] the appending usage of pdump

[????????]

hello, the DPDK developer??
    I am a DPDK lover from asian,and i updated the dpdk-pdump during 
the study of dpdk,i added it on the function of ipv4-address filter,but when i 
am using it, the unexpected event happended, when the packets are lower than 
nearly 4, it filters accurately on a lot tests, but when the packets are 
more than 4,results are not accurate, there are missing packets, wrong 
packets occur;
    i spent a lot of time searching the reason, but failed, so i 
decide to ask for the ori developer,if you have any ideas,please reply on me 
,much thanks

Re: [dpdk-users] Question regarding DPDK on AWS

[Thomas Monjalon]

30/06/2021 16:40, Antonis Christodoulou:
> Hello all,

Hello,

> my name is Antonis Christodoulou, and I am a new user of DPDK. I am not sure 
> this is the right place to ask a usage question, so please feel free to 
> redirect me to someone more appropriate for such questions as needed.

Your question below looks related to the TCP stack in F-stack, not DPDK itself.
I would recommend to get in touch with the F-Stack project:
https://github.com/F-Stack/f-stack/issues


> I am working on AWS, and I have set up F-stack over DPDK, successfully 
> connecting to an address within my private VPC, using a client socket. On the 
> other side I am running a simple echo server with  ncat -l 2001 -k -c 'xargs 
> -n1 echo' -vvv. However, when I just change the address to some global IP, 
> like the one used by www.example.com, ie.  
> 93.184.216.34 (I used port 80), then I am not getting any socket connection.
> 
> Would you know why this is happening? I have not set up any veth0 interface 
> yet for the DPDK NIC, I am not sure this is needed for connectivity.
> 
> Regards,
> Antonis

[dpdk-users] Question regarding DPDK on AWS

[Antonis Christodoulou]

Hello all,

my name is Antonis Christodoulou, and I am a new user of DPDK. I am not sure 
this is the right place to ask a usage question, so please feel free to 
redirect me to someone more appropriate for such questions as needed.

I am working on AWS, and I have set up F-stack over DPDK, successfully 
connecting to an address within my private VPC, using a client socket. On the 
other side I am running a simple echo server with  ncat -l 2001 -k -c 'xargs 
-n1 echo' -vvv. However, when I just change the address to some global IP, like 
the one used by www.example.com, ie.  93.184.216.34 (I 
used port 80), then I am not getting any socket connection.

Would you know why this is happening? I have not set up any veth0 interface yet 
for the DPDK NIC, I am not sure this is needed for connectivity.

Regards,
Antonis

Re: [dpdk-users] Build on Windows not working: "ERROR: Program 'echo' not found"

[Rob Scheepens]

Hello Dmitry,

That works, thanks!

Is there an issue open for this? If not, should I create one?

\Rob


On 29/06/2021, 22:49, "Dmitry Kozlyuk"  wrote:

2021-06-22 15:39 (UTC+), Rob Scheepens:
> Hello All,
> 
> I’ve been trying to get the helloworld app built on Windows following 
instructions on 
https://urldefense.proofpoint.com/v2/url?u=https-3A__doc.dpdk.org_guides_windows-5Fgsg_build-5Fdpdk.html&d=DwIFaQ&c=s883GpUCOChKOHiocYtGcg&r=OMged-t_5I_fmfpUaT3vaA06lgLL_alYnDQJxHmXz64&m=bT-u34VRwfJXMWgvDg5dY_tdrVi2o7heSEOmmBp6nBo&s=JIqAR1lwhyW9xH5McZIJpbJ_EBi__53LaVMuaXtSI0g&e=
 , using option 1. It fails however and output ends with “doc\meson.build:14:0: 
ERROR: Program 'echo' not found”. Looking in the log I also see file not found 
errors for various header files under linux\*.h, for example:
> 
> Compiler stderr:
> C:\git\dpdk\build\meson-private\tmpdf9qrjqg\testfile.c:2:18: fatal error: 
'linux/tc_act/tc_bpf.h' file not found
> #include 
>  ^~~
> 1 error generated.
> 
> I came across the thread on 
https://urldefense.proofpoint.com/v2/url?u=https-3A__www.mail-2Darchive.com_dev-40dpdk.org_msg156490.html&d=DwIFaQ&c=s883GpUCOChKOHiocYtGcg&r=OMged-t_5I_fmfpUaT3vaA06lgLL_alYnDQJxHmXz64&m=bT-u34VRwfJXMWgvDg5dY_tdrVi2o7heSEOmmBp6nBo&s=hRh7Im-aP4eik7aOIzuGgJtI1u5FdOeKksZN35crSEI&e=
 , but it’s not exactly the same as far as I can see. Full log is attached. 
What am I missing?
> 
> \Rob
> -- next part --
> An embedded and charset-unspecified text was scrubbed...
> Name: meson-log.txt
> URL: 


Hello, Rob!

Try using Meson 0.53.2.
There seems to be an issue with Meson 0.58.1 on Windows.