From dmitry.kozliuk at gmail.com Mon Dec 1 10:20:51 2025 From: dmitry.kozliuk at gmail.com (Dmitry Kozlyuk) Date: Mon, 1 Dec 2025 12:20:51 +0300 Subject: Assistance with DPDK on Windows In-Reply-To: References: <85f9def5-7f88-47d1-9dc8-524b060c54e5@gmail.com> <2455856.MHSsGVy7CF@thomas> Message-ID: <49bc7ad0-89fa-4b47-9720-94e5c54cf72a@gmail.com> Hi Thenveer, virt2phys does not conflict with netuio, because virt2phys does not bind to any NIC. It is just loaded into the kernel for DPDK to make IOCTLs to get physical addresses. There are specific instruction for loading virt2phys: https://git.dpdk.org/dpdk-kmods/tree/windows/README.rst On 12/1/25 12:13, Thenveer Poolakkanni wrote: > Hi Team, > Additionally, I have one more query: how do I use the > *virt2phys*?driver when I have two network interfaces already bound to > *netuio*? > Thanks, > Thenveer From thenveer.poolakkanni at iwave-global.com Mon Dec 1 06:55:58 2025 From: thenveer.poolakkanni at iwave-global.com (Thenveer Poolakkanni) Date: Mon, 1 Dec 2025 05:55:58 +0000 Subject: Assistance with DPDK on Windows In-Reply-To: References: <85f9def5-7f88-47d1-9dc8-524b060c54e5@gmail.com> <2455856.MHSsGVy7CF@thomas> Message-ID: Hi Team, Just a quick reminder regarding my earlier email about the DPDK issue on Windows . Could you please advise on the cause and possible fix? Thanks, Thenveer ________________________________ From: Thenveer Poolakkanni Sent: Friday, November 14, 2025 3:42 PM To: Thomas Monjalon ; andremue at linux.microsoft.com ; Dmitry Kozlyuk Cc: dev at dpdk.org ; Chaturbhuja Nath Prabhu ; Ayshathul Thuhara ; users at dpdk.org Subject: Re: Assistance with DPDK on Windows Hi Team, I have successfully compiled and built DPDK on a Windows system and am using a custom driver in conjunction with DPDK. I am able to write to the registers, and the driver can also read from them. Additionally, I have successfully loaded the netuio driver onto my network interfaces (01:00.0 and 01:00.1). However, when running the DPDK application, I encounter the following error: "Invalid memory, No probed Ethernet devices." The issue is detailed further in the screenshot below. [cid:94365efe-78e5-4ef2-9d9a-b49188e35759] Could you please assist in identifying the cause of this error and advise on potential steps to resolve it? Thank you in advance for your support. Best regards, Thenveer ________________________________ From: Thomas Monjalon Sent: Wednesday, November 5, 2025 3:55 PM To: andremue at linux.microsoft.com ; Dmitry Kozlyuk Cc: Thenveer Poolakkanni ; dev at dpdk.org ; Chaturbhuja Nath Prabhu ; Ayshathul Thuhara Subject: Re: Assistance with DPDK on Windows 05/11/2025 08:36, Dmitry Kozlyuk: > Hi Thenveer, > > > On 11/5/25 10:18, Thenveer Poolakkanni wrote: > > 1. Is it possible to execute or use dpdk-devbind.py on Windows to > > verify the device binding status? > > No. Please use Device Manager for now. > > > 2. On Windows, the build generates .dll files (e.g., > > rte_net_driver.dll) instead of .so files (e.g., librte_net_driver.so > > in Linux). How can we use or execute these .dll files in the same way > > we use .so files when running DPDK applications? > > > The application must link the needed libraries and PMDs when building. > These files must be in PATH or in the working directory when running the > application. Loading additional PMDs with "-d" EAL option is not yet > implemented. If you have a custom PMD you have to build it as a part of > DPDK and link to your application. > > > P. S. Questions like these belong to users at dpdk.org. Keeping in dev@ to > avoid breaking threads. This question is probably showing a lack of documentation. Please can we have this gap solved with a patch? -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image.png Type: image/png Size: 24340 bytes Desc: image.png URL: From thenveer.poolakkanni at iwave-global.com Mon Dec 1 10:13:49 2025 From: thenveer.poolakkanni at iwave-global.com (Thenveer Poolakkanni) Date: Mon, 1 Dec 2025 09:13:49 +0000 Subject: Assistance with DPDK on Windows In-Reply-To: References: <85f9def5-7f88-47d1-9dc8-524b060c54e5@gmail.com> <2455856.MHSsGVy7CF@thomas> Message-ID: Hi Team, Additionally, I have one more query: how do I use the virt2phys driver when I have two network interfaces already bound to netuio? Thanks, Thenveer ________________________________ From: Thenveer Poolakkanni Sent: Monday, December 1, 2025 11:25 AM To: Thomas Monjalon ; andremue at linux.microsoft.com ; Dmitry Kozlyuk Cc: dev at dpdk.org ; Chaturbhuja Nath Prabhu ; Ayshathul Thuhara ; users at dpdk.org Subject: Re: Assistance with DPDK on Windows Hi Team, Just a quick reminder regarding my earlier email about the DPDK issue on Windows . Could you please advise on the cause and possible fix? Thanks, Thenveer ________________________________ From: Thenveer Poolakkanni Sent: Friday, November 14, 2025 3:42 PM To: Thomas Monjalon ; andremue at linux.microsoft.com ; Dmitry Kozlyuk Cc: dev at dpdk.org ; Chaturbhuja Nath Prabhu ; Ayshathul Thuhara ; users at dpdk.org Subject: Re: Assistance with DPDK on Windows Hi Team, I have successfully compiled and built DPDK on a Windows system and am using a custom driver in conjunction with DPDK. I am able to write to the registers, and the driver can also read from them. Additionally, I have successfully loaded the netuio driver onto my network interfaces (01:00.0 and 01:00.1). However, when running the DPDK application, I encounter the following error: "Invalid memory, No probed Ethernet devices." The issue is detailed further in the screenshot below. [cid:94365efe-78e5-4ef2-9d9a-b49188e35759] Could you please assist in identifying the cause of this error and advise on potential steps to resolve it? Thank you in advance for your support. Best regards, Thenveer ________________________________ From: Thomas Monjalon Sent: Wednesday, November 5, 2025 3:55 PM To: andremue at linux.microsoft.com ; Dmitry Kozlyuk Cc: Thenveer Poolakkanni ; dev at dpdk.org ; Chaturbhuja Nath Prabhu ; Ayshathul Thuhara Subject: Re: Assistance with DPDK on Windows 05/11/2025 08:36, Dmitry Kozlyuk: > Hi Thenveer, > > > On 11/5/25 10:18, Thenveer Poolakkanni wrote: > > 1. Is it possible to execute or use dpdk-devbind.py on Windows to > > verify the device binding status? > > No. Please use Device Manager for now. > > > 2. On Windows, the build generates .dll files (e.g., > > rte_net_driver.dll) instead of .so files (e.g., librte_net_driver.so > > in Linux). How can we use or execute these .dll files in the same way > > we use .so files when running DPDK applications? > > > The application must link the needed libraries and PMDs when building. > These files must be in PATH or in the working directory when running the > application. Loading additional PMDs with "-d" EAL option is not yet > implemented. If you have a custom PMD you have to build it as a part of > DPDK and link to your application. > > > P. S. Questions like these belong to users at dpdk.org. Keeping in dev@ to > avoid breaking threads. This question is probably showing a lack of documentation. Please can we have this gap solved with a patch? -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image.png Type: image/png Size: 24340 bytes Desc: image.png URL: From mgoralka4 at gmail.com Sun Dec 7 09:11:15 2025 From: mgoralka4 at gmail.com (Matt Goralka) Date: Sun, 7 Dec 2025 02:11:15 -0600 Subject: contributing to dpdk Message-ID: Hi, My name is Matt Goralka. I'm interested in contributing to dpdk and am wondering if you are taking people and have a few questions if someone can help get me started. I have a computer hardware engineering degree and experience in web dev so not totally starting from scratch. -How do you guys get newbies started? Can you kind of get me going? -I have a gaming laptop with a Ryzen 7 chip and NVIDIA GEFORCE RTX 5060 chip. Would it be enough to virtualize linux? Thanks guys, looking forward to hopefully working with you! -Matt -------------- next part -------------- An HTML attachment was scrubbed... URL: From bruce.richardson at intel.com Tue Dec 9 09:55:38 2025 From: bruce.richardson at intel.com (Bruce Richardson) Date: Tue, 9 Dec 2025 08:55:38 +0000 Subject: contributing to dpdk In-Reply-To: References: Message-ID: On Sun, Dec 07, 2025 at 02:11:15AM -0600, Matt Goralka wrote: > Hi, > My name is Matt Goralka. I'm interested in contributing to dpdk and am > wondering if you are taking people and have a few questions if someone > can help get me started. I have a computer hardware engineering degree > and experience in web dev so not totally starting from scratch. > -How do you guys get newbies started? Can you kind of get me going? > -I have a gaming laptop with a Ryzen 7 chip and NVIDIA GEFORCE RTX 5060 > chip. Would it be enough to virtualize linux? > Thanks guys, looking forward to hopefully working with you! > -Matt Hi Matt, new contributions and contributors always welcome! To get started, I'd suggest getting linux up and running on whatever hardware you have and then build DPDK as described in our linux getting-started-guide doc[1]. Beyond that, for questions I'd recommend joining the DPDK slack channel as linked on our contribute page [2]. Regards, /Bruce [1] http://doc.dpdk.org/guides/linux_gsg/index.html [2] https://core.dpdk.org/contribute/ From coolwilled at gmail.com Tue Dec 9 10:44:55 2025 From: coolwilled at gmail.com (coolwilled) Date: Tue, 9 Dec 2025 17:44:55 +0800 Subject: Ask help for DPAA_SEC: test_pdcp almost all cases failed Message-ID: Hi, NXP and dpdk.org users and developers Did anyone run test_pdcp on DPAA_SEC ? I have a NXP LS1046A board. I have configured DPAA sec and 4 dpaa_sec crypto_dev can be found in rte_eal_init(). I run dpdk-test from dpdk.org git commit = b287e404643a (24.11.3) and almost all cases execpt one PDCP status report case failed. I also run app/dpdk-test-crypto-perf throughput test with dpaa_sec. It only measures throughput and doesn't check correctness. I find the session is created with rte_security_session_create() in app/test-crypto-perf/cperfops.c for CPERF_PDCP. And session is created with rte_cryptodev_sym_session_create() in lib/pdcp/pdcp_crypto.c . Which type of session should be created ? How the test_pdcp can succeed in LS1046A DPAA_SEC ? Thanks a lot. -------------- next part -------------- An HTML attachment was scrubbed... URL: From pnarsimharaj at gmail.com Tue Dec 9 17:41:11 2025 From: pnarsimharaj at gmail.com (narsimharaj pentam) Date: Tue, 9 Dec 2025 22:11:11 +0530 Subject: Indirect mbuf handling Message-ID: Hi I have a query related to ip fragmentation handling in DPDK. The DPDK application is trying to send a larger packet than the configured MTU on the interface, before sending the packet to the i40e PMD the packet will undergo fragmentation . The DPDK library function *"rte_ipv4_fragment_packet"* is used for fragmentation. Function *rte_ipv4_fragment_packet* will create direct and indirect mbuf's for a fragment , *the indirect buffers will have reference to the mbuf of the actual packet (zero copy).* The application will call function rte_eth_tx_burst to transmit fragments , which internally invokes *i40e_xmit_pkts *, the question here is when should main application mbuf should be freed , can It be freed immediately after i40e_xmit_pkts returns success, not sure because the mbuf's are queued up in software ring before actual transmit, I am worried about the fragments holding references to the main application buffer. Thanks. BR Narsimha -------------- next part -------------- An HTML attachment was scrubbed... URL: From pnarsimharaj at gmail.com Tue Dec 9 18:05:17 2025 From: pnarsimharaj at gmail.com (narsimharaj pentam) Date: Tue, 9 Dec 2025 22:35:17 +0530 Subject: Indirect mbuf handling In-Reply-To: References: Message-ID: Added dev group. On Tue, Dec 9, 2025 at 10:11?PM narsimharaj pentam wrote: > Hi > > I have a query related to ip fragmentation handling in DPDK. > > The DPDK application is trying to send a larger packet than the configured > MTU on the interface, before sending the packet to the i40e PMD the packet > will > undergo fragmentation . The DPDK library function > *"rte_ipv4_fragment_packet"* is used for fragmentation. Function > *rte_ipv4_fragment_packet* will create > direct and indirect mbuf's for a fragment , *the indirect buffers will > have reference to the mbuf of the actual packet (zero copy).* > > The application will call function rte_eth_tx_burst to transmit fragments > , which internally invokes *i40e_xmit_pkts *, the question here is when > should main application > mbuf should be freed , can It be freed immediately after i40e_xmit_pkts > returns success, not sure because the mbuf's are queued up in software ring > before actual transmit, > I am worried about the fragments holding references to the main > application buffer. > > Thanks. > > BR > Narsimha > -------------- next part -------------- An HTML attachment was scrubbed... URL: From mb at smartsharesystems.com Wed Dec 10 10:44:06 2025 From: mb at smartsharesystems.com (=?UTF-8?B?TW9ydGVuIEJyw7hydXA=?=) Date: Wed, 10 Dec 2025 10:44:06 +0100 Subject: Indirect mbuf handling In-Reply-To: References: Message-ID: <98CBD80474FA8B44BF855DF32C47DC35F655D0@smartserver.smartshare.dk> > From: narsimharaj pentam [mailto:pnarsimharaj at gmail.com] > Sent: Tuesday, 9 December 2025 18.05 > > Added dev group. > > On Tue, Dec 9, 2025 at 10:11?PM narsimharaj pentam wrote: > Hi > > I have a query related to ip fragmentation handling in DPDK. > > The DPDK application is trying to send a larger packet than the configured MTU on the interface, before sending the packet to the i40e PMD the packet will > undergo fragmentation . The DPDK library function "rte_ipv4_fragment_packet" is used for fragmentation. Function rte_ipv4_fragment_packet will create > direct and indirect mbuf's for a fragment , the indirect buffers will have reference to the mbuf of the actual packet (zero copy). > > The application will call function rte_eth_tx_burst to transmit fragments , which internally invokes i40e_xmit_pkts , the question here is when should main application > mbuf should be freed , can It be freed immediately after i40e_xmit_pkts returns success, not sure because the mbuf's are queued up in software ring before actual transmit, > I am worried about the fragments holding references to the main application buffer. The original packet can be freed immediately when then fragments have been created. This is what the fragmentation example does: https://elixir.bootlin.com/dpdk/v25.11/source/examples/ip_fragmentation/main.c#L289 This is what happens: The original packet has a reference counter (which was incremented for each of the indirect mbufs referring to it), so freeing it at that point doesn't put it back in the pool. When the last of the indirect mbufs is freed (by the driver called by rte_eth_tx_burst()), the original packet's reference counter reaches zero, and then the original mbuf is put back in the pool. > > Thanks. > > BR > Narsimha From pnarsimharaj at gmail.com Wed Dec 10 12:41:55 2025 From: pnarsimharaj at gmail.com (narsimharaj pentam) Date: Wed, 10 Dec 2025 17:11:55 +0530 Subject: Indirect mbuf handling In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35F655D0@smartserver.smartshare.dk> References: <98CBD80474FA8B44BF855DF32C47DC35F655D0@smartserver.smartshare.dk> Message-ID: Thanks for your response, got it. BR Narsimha On Wed, Dec 10, 2025 at 3:14?PM Morten Br?rup wrote: > > From: narsimharaj pentam [mailto:pnarsimharaj at gmail.com] > > Sent: Tuesday, 9 December 2025 18.05 > > > > Added dev group. > > > > On Tue, Dec 9, 2025 at 10:11?PM narsimharaj pentam < > pnarsimharaj at gmail.com> wrote: > > Hi > > > > I have a query related to ip fragmentation handling in DPDK. > > > > The DPDK application is trying to send a larger packet than the > configured MTU on the interface, before sending the packet to the i40e PMD > the packet will > > undergo fragmentation . The DPDK library function > "rte_ipv4_fragment_packet" is used for fragmentation. Function > rte_ipv4_fragment_packet will create > > direct and indirect mbuf's for a fragment , the indirect buffers will > have reference to the mbuf of the actual packet (zero copy). > > > > The application will call function rte_eth_tx_burst to transmit > fragments , which internally invokes i40e_xmit_pkts , the question here is > when should main application > > mbuf should be freed , can It be freed immediately after i40e_xmit_pkts > returns success, not sure because the mbuf's are queued up in software ring > before actual transmit, > > I am worried about the fragments holding references to the main > application buffer. > > The original packet can be freed immediately when then fragments have been > created. > > This is what the fragmentation example does: > > https://elixir.bootlin.com/dpdk/v25.11/source/examples/ip_fragmentation/main.c#L289 > > This is what happens: > The original packet has a reference counter (which was incremented for > each of the indirect mbufs referring to it), so freeing it at that point > doesn't put it back in the pool. > When the last of the indirect mbufs is freed (by the driver called by > rte_eth_tx_burst()), the original packet's reference counter reaches zero, > and then the original mbuf is put back in the pool. > > > > > Thanks. > > > > BR > > Narsimha > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From nagurvalisayyad at bel.co.in Wed Dec 10 12:44:50 2025 From: nagurvalisayyad at bel.co.in (nagurvalisayyad) Date: Wed, 10 Dec 2025 17:14:50 +0530 Subject: DPDK Qos scheduler TC's misbehaviour within a Pipe Message-ID: <0816e6ae903d089cebeea389f4c564e6@bel.co.in> Hi, We are using dpdk-stable-22.11.6 version in our project. We are facing an issue in our DPDK QoS scheduler example application, we notice that lower priority traffic (TC2) starves higher priority traffic if the packet size of the lower priority traffic is smaller than the packet size of the higher priority traffic. If the packet size of the lower priority traffic (TC2) is same or larger than the higher priority (TC0 or TC1), we dont see the problem. Using q-index within the TC: Pipe 0 size is 20Mbps - Q0 (TC0), 1500 byte packets, 5Mbps configured and - Q1 (TC2), 1400 byte packets, 20Mbps configured - Total two pipes are configured and traffic is mapped to Pipe 0 TC0 and TC2 - Only on subport configured. - TC period is set to 50ms (to support lower rates of around 256Kbps) In this scenario TC2 consumes all the 20Mbps bandwidth, but as per priority, TC0 should get 5Mbps and TC2 should get 15Mbps. If we pump the same size byte packets, then TC0 is getting 5Mbps and TC1 is getting 15Mbps as per priority. If we stop the TC0 traffic, then the unused 5Mbps from TC0 is getting used by TC1 and is getting 20Mbps.(as expected). To further debug, we found in the qos scheduler documentation section 57.2.4.6.3. Traffic Shaping " * Full accuracy can be achieved by selecting the value for _tb_period_ for which _tb_credits_per_period = 1_. * When full accuracy is not required, better performance is achieved by setting _tb_credits_ to a larger value. " In rte_sched.c file, rte_sched_pipe_profile_convert(), the _tb_credits_per_period _is set to 1 and accordingly _tb_period _is set according to the rate. We have increased the _tb_credits_per_period _and_ tb_period _by 10000 times. So that 10000 credis are updated in the token bucket at a time. With this, TC0 and TC2 are working but not as much accurate as earlier. And we are having the doubt of how this change will behave for different rates and different packet sizes. Can you please help us in setting the optimal value for _tb_credits_per_period and tb_period, _so that it works well for different traffic rates and different packet sizes. Please help us in resolving this issue. -- Thanks & Regards Nagurvali Sayyad. -------------- next part -------------- An HTML attachment was scrubbed... URL: From nagurvalisayyad at bel.co.in Thu Dec 11 05:51:10 2025 From: nagurvalisayyad at bel.co.in (nagurvalisayyad) Date: Thu, 11 Dec 2025 10:21:10 +0530 Subject: DPDK Qos scheduler TC's misbehaviour within a Pipe Message-ID: Hi, We are using dpdk-stable-22.11.6 version in our project. We are facing an issue in our DPDK QoS scheduler example application, we notice that lower priority traffic (TC2) starves higher priority traffic if the packet size of the lower priority traffic is smaller than the packet size of the higher priority traffic. If the packet size of the lower priority traffic (TC2) is same or larger than the higher priority (TC0 or TC1), we dont see the problem. Using q-index within the TC: Pipe 0 size is 20Mbps - Q0 (TC0), 1500 byte packets, 5Mbps configured and - Q1 (TC2), 1400 byte packets, 20Mbps configured - Total two pipes are configured and traffic is mapped to Pipe 0 TC0 and TC2 - Only on subport configured. - TC period is set to 50ms (to support lower rates of around 256Kbps) In this scenario TC2 consumes all the 20Mbps bandwidth, but as per priority, TC0 should get 5Mbps and TC2 should get 15Mbps. If we pump the same size byte packets, then TC0 is getting 5Mbps and TC1 is getting 15Mbps as per priority. If we stop the TC0 traffic, then the unused 5Mbps from TC0 is getting used by TC1 and is getting 20Mbps.(as expected). To further debug, we found in the qos scheduler documentation section 57.2.4.6.3. Traffic Shaping " * Full accuracy can be achieved by selecting the value for _tb_period_ for which _tb_credits_per_period = 1_. * When full accuracy is not required, better performance is achieved by setting _tb_credits_ to a larger value. " In rte_sched.c file, rte_sched_pipe_profile_convert(), the _tb_credits_per_period _is set to 1 and accordingly _tb_period _is set according to the rate. We have increased the _tb_credits_per_period _and_ tb_period _by 10000 times. So that 10000 credis are updated in the token bucket at a time. With this, TC0 and TC2 are working but not as much accurate as earlier. And we are having the doubt of how this change will behave for different rates and different packet sizes. Can you please help us in setting the optimal value for _tb_credits_per_period and tb_period, _so that it works well for different traffic rates and different packet sizes. Please help us in resolving this issue. -- Thanks & Regards Nagurvali sayyad -------------- next part -------------- An HTML attachment was scrubbed... URL: From G.Singh at nxp.com Thu Dec 11 07:34:26 2025 From: G.Singh at nxp.com (Gagandeep Singh) Date: Thu, 11 Dec 2025 06:34:26 +0000 Subject: Ask help for DPAA_SEC: test_pdcp almost all cases failed In-Reply-To: References: Message-ID: Hi, The PDCP test is working on DPDK 25.11 on LS1046A with "dpdk-test" application. However, some of the other crypto/IPsec cases are failing with seg fault during cleanup. If you want to test PDCP only, please comment out the other cases to proceed with PDCP testing. We are also working to resolve the failing cases. " --- a/app/test/test_cryptodev.c +++ b/app/test/test_cryptodev.c @@ -19898,11 +19898,7 @@ run_cryptodev_testsuite(const char *pmd_name) &cryptodev_negative_aes_gcm_testsuite, &cryptodev_negative_aes_gmac_testsuite, &cryptodev_mixed_cipher_hash_testsuite, - &cryptodev_negative_hmac_sha1_testsuite, - &cryptodev_gen_testsuite, - &cryptodev_sm4_gcm_testsuite, #ifdef RTE_LIB_SECURITY - &ipsec_proto_testsuite, &pdcp_proto_testsuite, &docsis_proto_testsuite, &tls12_record_proto_testsuite, " Use the config/arm/arm64_dpaa_linux_gcc configuration file for compilation. Attaching the logs of the PDCP test on version 25.11 for reference. Regards, Gagan From: coolwilled Sent: Tuesday, December 9, 2025 3:15 PM To: Hemant Agrawal ; Sachin Saxena (OSS) ; Gagandeep Singh ; dev at dpdk.org; users at dpdk.org Subject: Ask help for DPAA_SEC: test_pdcp almost all cases failed You don't often get email from coolwilled at gmail.com. Learn why this is important Hi, NXP and dpdk.org users and developers Did anyone run test_pdcp on DPAA_SEC ? I have a NXP LS1046A board. I have configured DPAA sec and 4 dpaa_sec crypto_dev can be found in rte_eal_init(). I run dpdk-test from dpdk.org git commit = b287e404643a (24.11.3) and almost all cases execpt one PDCP status report case failed. I also run app/dpdk-test-crypto-perf throughput test with dpaa_sec. It only measures throughput and doesn't check correctness. I find the session is created with rte_security_session_create() in app/test-crypto-perf/cperfops.c for CPERF_PDCP. And session is created with rte_cryptodev_sym_session_create() in lib/pdcp/pdcp_crypto.c . Which type of session should be created ? How the test_pdcp can succeed in LS1046A DPAA_SEC ? Thanks a lot. -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: pdcp_logs_25.11.txt URL: From mgoralka4 at gmail.com Tue Dec 9 17:40:35 2025 From: mgoralka4 at gmail.com (Matt Goralka) Date: Tue, 9 Dec 2025 10:40:35 -0600 Subject: contributing to dpdk In-Reply-To: References: Message-ID: Thanks Bruce! I have a few things to figure out but I will lyk! Best, Matt On Tue, Dec 9, 2025, 2:55?AM Bruce Richardson wrote: > On Sun, Dec 07, 2025 at 02:11:15AM -0600, Matt Goralka wrote: > > Hi, > > My name is Matt Goralka. I'm interested in contributing to dpdk and > am > > wondering if you are taking people and have a few questions if someone > > can help get me started. I have a computer hardware engineering > degree > > and experience in web dev so not totally starting from scratch. > > -How do you guys get newbies started? Can you kind of get me going? > > -I have a gaming laptop with a Ryzen 7 chip and NVIDIA GEFORCE RTX > 5060 > > chip. Would it be enough to virtualize linux? > > Thanks guys, looking forward to hopefully working with you! > > -Matt > > Hi Matt, > > new contributions and contributors always welcome! To get started, I'd > suggest getting linux up and running on whatever hardware you have and then > build DPDK as described in our linux getting-started-guide doc[1]. Beyond > that, for questions I'd recommend joining the DPDK slack channel as linked > on our contribute page [2]. > > Regards, > /Bruce > > [1] http://doc.dpdk.org/guides/linux_gsg/index.html > [2] https://core.dpdk.org/contribute/ > -------------- next part -------------- An HTML attachment was scrubbed... URL: From coolwilled at gmail.com Tue Dec 30 15:05:22 2025 From: coolwilled at gmail.com (coolwilled) Date: Tue, 30 Dec 2025 22:05:22 +0800 Subject: Is it a Bug? DPAA_SEC-test_cryptodev : output packet length is wrong ! Message-ID: Hi, I run command "cryptodev_dpaa_sec_autotest" in app/test/test_cryptodev.c in DPDK v25.11. The output mbuf->pkt_len is wrong in the case : TEST_PDCP_COUNT(uplane_encap_with_integrity(18, UPLINK, SNOW_ENC, AES_AUTH)); from test_PDCP_PROTO_uplane_encap_all() from test_PDCP_PROTO_all(). In this case, in test_pdcp_proto(), the output ut_params->ibuf->data_len/pkt_len = 73. The pkt_len is wrong, it should be 71. Thanks a lot ! -------------- next part -------------- An HTML attachment was scrubbed... URL: From 455434913 at qq.com Fri Dec 19 18:10:56 2025 From: 455434913 at qq.com (=?utf-8?B?NDU1NDM0OTEz?=) Date: Fri, 19 Dec 2025 17:10:56 -0000 Subject: Question about kni performance Message-ID: Hello, I ran the KNI example from DPDK version 19.11 and performed a ping latency test from another machine. I found that after running KNI, the latency increased by over 100 times?from the original 0.05 ms to 7 ms, which is unacceptable for my use case. My network card is an mlx5 with a specification of 1000 Gbps. Is this performance degradation within normal parameters? What methods can be used to optimize it? -------------- next part -------------- An HTML attachment was scrubbed... URL: