<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"> <head> <meta http-equiv="Content-Type" content="text/html; charset=gb2312"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang="ZH-CN" link="#0563C1" vlink="#954F72" style="word-wrap:break-word;text-justify-trim:punctuation"> <div class="WordSection1"> Hi,<o:p></o:p> <o:p> </o:p> >> not unless you start polling those queues from some other thread<o:p></o:p> I don’t understand this point.<o:p></o:p> As the rx callback is per queue data, it seems to me only thing is we should not polling this queue while we are modify its callback. So only this queue should be in stopped state (maybe even this is not required? Because I see atomic operation is used (__atomic_store_n in rte_eth_add_rx_callback and __atomic_load_n in rte_eth_rx_burst)).<o:p></o:p> Anyway, polling other queues on some other thread should not affect, right? Or can you help to explain a bit more on this?<o:p></o:p> <o:p> </o:p> Thank you very much.<o:p></o:p> <o:p> </o:p> <div> Br, Xiaoping<o:p></o:p> </div> <o:p> </o:p> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Burakov, Anatoly <anatoly.burakov@intel.com> Sent: 2023年2月20日 21:59 To: Xiaoping Yan (NSB) <xiaoping.yan@nokia-sbell.com>; users@dpdk.org Subject: RE: why rte_power_ethdev_pmgmt_queue_enable need to check if other queues are stopped<o:p></o:p> </div> </div> <o:p> </o:p> Well, technically, no, you’re right, it wouldn’t – not unless you start polling those queues from some other thread. We can’t prevent that from happening, so we figured the best way would be to just disallow queue starts until we’re done configuring everything. So, yes, we could relax that restriction, it’s just a matter of specifying what’s allowed and what’s not vs. just doing a blanket “no” and keeping things simple.<o:p></o:p> <o:p> </o:p> <div style="border:none;border-left:solid blue 1.5pt;padding:0cm 0cm 0cm 4.0pt"> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Xiaoping Yan (NSB) <<a href="mailto:xiaoping.yan@nokia-sbell.com">xiaoping.yan@nokia-sbell.com</a>> Sent: Monday, February 20, 2023 1:41 PM To: Burakov, Anatoly <<a href="mailto:anatoly.burakov@intel.com">anatoly.burakov@intel.com</a>>; <a href="mailto:users@dpdk.org">users@dpdk.org</a> Subject: RE: why rte_power_ethdev_pmgmt_queue_enable need to check if other queues are stopped<o:p></o:p> </div> </div> <o:p> </o:p> Hi,<o:p></o:p> <o:p> </o:p> Thank you for the information.<o:p></o:p> I see from rte_eth_add_rx_callback, the callback is added to per queue data: rte_eth_devices[port_id].post_rx_burst_cbs[queue_id];<o:p></o:p> So it should not affect polling on other queues?<o:p></o:p> <o:p> </o:p> <o:p> </o:p> <div> Br, Xiaoping<o:p></o:p> </div> <o:p> </o:p> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Burakov, Anatoly <<a href="mailto:anatoly.burakov@intel.com">anatoly.burakov@intel.com</a>> Sent: 2023年2月20日 18:28 To: Xiaoping Yan (NSB) <<a href="mailto:xiaoping.yan@nokia-sbell.com">xiaoping.yan@nokia-sbell.com</a>>; <a href="mailto:users@dpdk.org">users@dpdk.org</a> Subject: RE: why rte_power_ethdev_pmgmt_queue_enable need to check if other queues are stopped<o:p></o:p> </div> </div> <o:p> </o:p> Hi,<o:p></o:p> <o:p> </o:p> It is mainly because we’re install callbacks, which is not thread-safe unless the PMD is stopped. Our PMD’s internal config structures are not thread-safe. You should only start these ports after you configure everything.<o:p></o:p> <o:p> </o:p> <div style="border:none;border-left:solid blue 1.5pt;padding:0cm 0cm 0cm 4.0pt"> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Xiaoping Yan (NSB) <<a href="mailto:xiaoping.yan@nokia-sbell.com">xiaoping.yan@nokia-sbell.com</a>> Sent: Monday, February 20, 2023 6:12 AM To: <a href="mailto:users@dpdk.org">users@dpdk.org</a>; Burakov, Anatoly <<a href="mailto:anatoly.burakov@intel.com">anatoly.burakov@intel.com</a>> Subject: RE: why rte_power_ethdev_pmgmt_queue_enable need to check if other queues are stopped<o:p></o:p> </div> </div> <o:p> </o:p> Hi Anatoly<o:p></o:p> <o:p> </o:p> I see this multiple queue support is added by you.<o:p></o:p> Could you kindly help me to understand why rte_power_ethdev_pmgmt_queue_enable need other queues to be in stopped state?<o:p></o:p> <o:p> </o:p> commit 5dff9a72b0efeab02a2b71e52c4871805b7e64cb<o:p></o:p> Author: Anatoly Burakov <a href="mailto:anatoly.burakov@intel.com"> anatoly.burakov@intel.com</a><o:p></o:p> Date: Fri Jul 9 16:08:15 2021 +0000<o:p></o:p> <o:p> </o:p> power: support callbacks for multiple Rx queues<o:p></o:p> <o:p> </o:p> <o:p> </o:p> Thank you.<o:p></o:p> <o:p> </o:p> <div> Br, Xiaoping<o:p></o:p> </div> <o:p> </o:p> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Xiaoping Yan (NSB) Sent: 2023年2月16日 21:00 To: <a href="mailto:users@dpdk.org">users@dpdk.org</a> Subject: why rte_power_ethdev_pmgmt_queue_enable need to check if other queues are stopped<o:p></o:p> </div> </div> <o:p> </o:p> Hi experts,<o:p></o:p> <o:p> </o:p> I’m trying to use dpdk power pmd management APIs in my dpdk application.<o:p></o:p> My application uses several ports, each have one rx queue, and it goes like this<o:p></o:p> <![if !supportLists]>1. <![endif]>Init first port, setup rx queue, call rte_power_ethdev_pmgmt_queue_enable, and start the first port<o:p></o:p> <![if !supportLists]>2. <![endif]>Init second port, setup rx queue, call rte_power_ethdev_pmgmt_queue_enable, and start the second port<o:p></o:p> <![if !supportLists]>3. <![endif]>…<o:p></o:p> Now for the first port & queue, rte_power_ethdev_pmgmt_queue_enable return success, but for the second port & queue, it returns -16<o:p></o:p> From rte_power_ethdev_pmgmt_queue_enable code, I think it fails when checking if other queues are stopped as well. <o:p></o:p> /* check if other queues are stopped as well */<o:p></o:p> ret = cfg_queues_stopped(lcore_cfg);<o:p></o:p> if (ret != 1) {<o:p></o:p> /* error means invalid queue, 0 means queue wasn't stopped */<o:p></o:p> ret = ret < 0 ? -EINVAL : -EBUSY;<o:p></o:p> goto end;<o:p></o:p> }<o:p></o:p> This seems quite strange for me, why other queues have to be in stopped state?<o:p></o:p> Can anyone help to explain?<o:p></o:p> <o:p> </o:p> Thank you.<o:p></o:p> <o:p> </o:p> <o:p> </o:p> Br, Xiaoping<o:p></o:p> <o:p> </o:p> </div> </div> </div> </body> </html>