From: "Qiu, Michael" <michael.qiu@intel.com>
To: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v2] librte_ether: release memory in uninit function.
Date: Mon, 6 Jul 2015 11:35:16 +0000 [thread overview]
Message-ID: <533710CFB86FA344BFBF2D6802E60286046AE60D@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <533710CFB86FA344BFBF2D6802E60286046A75A4@SHSMSX101.ccr.corp.intel.com>
Hi, all
As we has gap on the memory release action to be done in which step, I
appreciate all your comments on this patch.
Currently, the correct quit sequence for testpmd is stop() --->
port_stop() --> port_close() --> quit(). This will lead lots of memory
not released by default, like queues.
We have 3 potential proposals(normal case means without hotplug):
1. Those memory release in close() other left in uninit()
This will work fine for both hotplug case and normal case.
2. leave close() just as the same before, all be done in uninit()
This will works fine for hotplug, for normal case maybe has
issue(memory not released?).
3. Combine close() and uninit(), only one will be left.
This will work fine for both hotplug case and normal case. But it
may change a lot, such as logic.
4. other.
For more details, you could go though this thread.
Thanks,
Michael
On 6/30/2015 9:32 AM, Qiu, Michael wrote:
> On 6/30/2015 12:42 AM, Iremonger, Bernard wrote:
>>> -----Original Message-----
>>> From: Qiu, Michael
>>> Sent: Monday, June 29, 2015 4:22 PM
>>> To: Iremonger, Bernard; dev@dpdk.org
>>> Cc: Zhang, Helin; Ananyev, Konstantin; mukawa@igel.co.jp; Stephen
>>> Hemminger
>>> Subject: Re: [PATCH v2] librte_ether: release memory in uninit function.
>>>
>>> On 2015/6/29 18:20, Iremonger, Bernard wrote:
>>>>> -----Original Message-----
>>>>> From: Qiu, Michael
>>>>> Sent: Monday, June 29, 2015 9:55 AM
>>>>> To: Iremonger, Bernard; dev@dpdk.org
>>>>> Cc: Zhang, Helin; Ananyev, Konstantin; mukawa@igel.co.jp; Stephen
>>>>> Hemminger
>>>>> Subject: Re: [PATCH v2] librte_ether: release memory in uninit function.
>>>>>
>>>>> On 6/26/2015 5:32 PM, Iremonger, Bernard wrote:
>>>>>> Changes in v2:
>>>>>> do not free mac_addrs and hash_mac_addrs here.
>>>>>>
>>>>>> Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
>>>>>> ---
>>>>>> lib/librte_ether/rte_ethdev.c | 6 +++++-
>>>>>> 1 files changed, 5 insertions(+), 1 deletions(-)
>>>>>>
>>>>>> diff --git a/lib/librte_ether/rte_ethdev.c
>>>>>> b/lib/librte_ether/rte_ethdev.c index e13fde5..7ae101a 100644
>>>>>> --- a/lib/librte_ether/rte_ethdev.c
>>>>>> +++ b/lib/librte_ether/rte_ethdev.c
>>>>>> @@ -369,8 +369,12 @@ rte_eth_dev_uninit(struct rte_pci_device
>>>>> *pci_dev)
>>>>>> /* free ether device */
>>>>>> rte_eth_dev_release_port(eth_dev);
>>>>>>
>>>>>> - if (rte_eal_process_type() == RTE_PROC_PRIMARY)
>>>>>> + if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
>>>>>> + rte_free(eth_dev->data->rx_queues);
>>>>>> + rte_free(eth_dev->data->tx_queues);
>>>>>> rte_free(eth_dev->data->dev_private);
>>>>>> + memset(eth_dev->data, 0, sizeof(struct
>>>>> rte_eth_dev_data));
>>>>>> + }
>>>>>>
>>>>>> eth_dev->pci_dev = NULL;
>>>>>> eth_dev->driver = NULL;
>>>>> Actually, This could be put in rte_eth_dev_close() becasue queues
>>>>> should be released when closed.
>>>>>
>>>>> Also before free dev->data->rx_queues you should make sure
>>>>> dev->data->rx_queues[i] has been freed in PMD close() function, So
>>>>> dev->data->this
>>>>> two should be better done at the same time, ether in
>>>>> rte_eth_dev_close() or in PMD close() function. For hotplug in fm10k,
>>>>> I put it in PMD close() function.
>>>>>
>>>>> Thanks,
>>>>> Michael
>>>> Hi Michael,
>>>>
>>>> The consensus is that the rx_queue and tx_queue memory should not be
>>> released in the PMD as it is not allocated by the PMD. The memory is
>>> allocated in rte_eth_dev_rx_queue_config() and
>>> rte_eth_dev_tx_queue_config(), which are both called from
>>> rte_eth_dev_configure() which is called by the application (for example
>>> test_pmd). So it seems to make sense to free this memory in
>>> rte_eth_dev_uninit().
>>>
>>> It really make sense to free memory in rte_ether level, but when close a port
>>> with out detached? just as stop --> close() --> quit(), the memory will not be
>>> released :)
>>>
>> In the above scenario lots of memory will not be released.
>>
>> This is why the detach() and the underlying dev_uninit() functions were introduced.
> First detach is only for hotplug, for *users do not use hotplug*, that
> scenario is the right action. So "lots of memory will not be released"
> is issue need be fixed, actually, in fm10k driver, lots of memory has
> been released.
>
>> The dev_uninit() functions currently call dev_close() which in turn calls dev_stop() which calls dev_clear_queues().
> Users do hotplug then must call stop() --> close() --> dev_uninit(), it
> works fine. But do you think it make sense to release memory when
> close() it?
>
>> The dev_clear_queues() function does not release the queue_memory or the queue array memory. The queue memory is now released in the dev_uninit() and the queue array memory is released in the rte_eth_dev_uninit() function.
> That's your implementation, make sure not all users will detach a
> device, but the right action must include close(), do you agree?
>
>> If the queue array memory is released in rte_eth_dev_close() then the release of the queue_memory will have to be moved to the dev_close() functions from the dev_uninit() functions. This will impact all the existing PMD hotplug patches. It will also change the existing dev_close() functionality.
> Why impact?? Actually it works fine with fm10k driver. What I concern is
> *when user do not use hotplug*, it will lead lots of memory not
> released, that unacceptable, to move release action to
> rte_eth_dev_close() is just a suggestion by me, I think *the solution
> should cover both scenario*, am I right?
>
>
>> My preference is to leave the existing dev_close() functions unchanged as far as possible and to do what needs to be done in the dev_uninit() functions.
>>
>> We probably need the view of the maintainers as to whether this should be done in the close() or uninit() functions.
>>
>> Regards,
>>
>> Bernard.
>>
>>
>>
>>
>>
>>
>
next prev parent reply other threads:[~2015-07-06 11:35 UTC|newest]
Thread overview: 270+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <PATCH>
2014-12-08 17:18 ` [dpdk-dev] [PATCH] doc: add bsd license to svg file Bernard Iremonger
2014-12-11 13:42 ` De Lara Guarch, Pablo
2015-06-10 15:12 ` [dpdk-dev] [PATCH 0/2] doc: kni command line fixes Bernard Iremonger
2015-06-10 15:12 ` [dpdk-dev] [PATCH 1/2] doc: correct kni command line in virtio chapter Bernard Iremonger
2015-06-15 2:29 ` Zhang, Helin
2015-06-10 15:12 ` [dpdk-dev] [PATCH 2/2] doc: fix kni command line in Kernel NIC Interface chapter Bernard Iremonger
2015-06-15 2:30 ` Zhang, Helin
2015-06-10 17:13 ` [dpdk-dev] [PATCH 0/2] doc: kni command line fixes Mcnamara, John
2015-07-27 21:45 ` Thomas Monjalon
2015-06-11 14:33 ` [dpdk-dev] [PATCH] doc: update port attach and detach in Testpmd Runtime Functions chapter Bernard Iremonger
2015-06-16 2:45 ` Tetsuya Mukawa
2015-07-28 10:22 ` Thomas Monjalon
2015-06-12 16:21 ` [dpdk-dev] [PATCH v3 0/2] bonding PCI Port Hotplug Bernard Iremonger
2015-06-12 16:21 ` [dpdk-dev] [PATCH v3 1/2] bonding: add support for " Bernard Iremonger
2015-06-12 16:21 ` [dpdk-dev] [PATCH v3 2/2] test-pmd: modified testpmd for link_bonding Bernard Iremonger
2015-06-19 16:33 ` [dpdk-dev] [PATCH v3 0/2] bonding PCI Port Hotplug Declan Doherty
2015-06-16 11:30 ` [dpdk-dev] [PATCH v2 0/2] virtio: " Bernard Iremonger
2015-06-16 11:30 ` [dpdk-dev] [PATCH v3 1/2] virtio: add support for " Bernard Iremonger
2015-06-17 1:27 ` Ouyang, Changchun
2015-06-16 11:30 ` [dpdk-dev] [PATCH v3 2/2] virtio: check vq parameter Bernard Iremonger
2015-06-17 1:27 ` Ouyang, Changchun
2015-06-17 11:38 ` [dpdk-dev] [PATCH v4 0/6] i40e: PCI Port Hotplug Changes Bernard Iremonger
2015-06-17 11:38 ` [dpdk-dev] [PATCH v4 1/6] i40e: changes to support PCI Port Hotplug Bernard Iremonger
2015-06-17 11:38 ` [dpdk-dev] [PATCH v4 2/6] i40e: release vmdq vsi's in dev_close Bernard Iremonger
2015-06-17 11:38 ` [dpdk-dev] [PATCH v4 3/6] i40e: increase ASQ_DELAY_MS to 100 in i40evf_wait_cmd_done() Bernard Iremonger
2015-06-17 11:39 ` [dpdk-dev] [PATCH v4 4/6] i40e: call _clear_cmd() when error occurs Bernard Iremonger
2015-06-17 11:39 ` [dpdk-dev] [PATCH v4 5/6] i40e: clear queues in i40evf_dev_stop Bernard Iremonger
2015-06-17 11:39 ` [dpdk-dev] [PATCH v4 6/6] i40e: check rxq parameter in i40e_reset_rx_queue Bernard Iremonger
2015-06-18 12:44 ` [dpdk-dev] [PATCH v5] e1000: igb and em1000 PCI Port Hotplug changes Bernard Iremonger
2015-06-19 17:03 ` [dpdk-dev] [PATCH v5 0/6] i40e: PCI Port Hotplug Changes Bernard Iremonger
2015-06-19 17:03 ` [dpdk-dev] [PATCH v5 1/6] i40e: changes to support PCI Port Hotplug Bernard Iremonger
2015-06-19 17:03 ` [dpdk-dev] [PATCH v5 2/6] i40e: release vmdq vsi's in dev_close Bernard Iremonger
2015-06-19 17:03 ` [dpdk-dev] [PATCH v5 3/6] i40e: increase ASQ_DELAY_MS to 100 and MAX_TRY_TIMES to 20 in i40evf_wait_cmd_done() Bernard Iremonger
2015-06-19 17:04 ` [dpdk-dev] [PATCH v5 4/6] i40e: call _clear_cmd() when error occurs Bernard Iremonger
2015-06-19 17:04 ` [dpdk-dev] [PATCH v5 5/6] i40e: clear queues in i40evf_dev_stop Bernard Iremonger
2015-06-19 17:04 ` [dpdk-dev] [PATCH v5 6/6] i40e: check rxq parameter in i40e_reset_rx_queue Bernard Iremonger
2015-06-25 2:28 ` [dpdk-dev] [PATCH v5 0/6] i40e: PCI Port Hotplug Changes Zhang, Helin
2015-06-22 10:44 ` [dpdk-dev] [PATCH v6] e1000: igb and em1000 PCI Port Hotplug changes Bernard Iremonger
2015-06-25 2:33 ` Zhang, Helin
2015-06-25 9:04 ` Iremonger, Bernard
2015-06-26 8:56 ` Zhang, Helin
2015-06-24 15:08 ` [dpdk-dev] [PATCH v5] ixgbe: changes to support PCI Port Hotplug Bernard Iremonger
2015-06-25 11:41 ` Ananyev, Konstantin
2015-06-25 14:30 ` [dpdk-dev] [PATCH] librte_ether: release memory in uninit function Bernard Iremonger
2015-06-25 14:41 ` Stephen Hemminger
2015-06-25 18:32 ` Ananyev, Konstantin
2015-06-26 8:17 ` Iremonger, Bernard
2015-06-26 9:32 ` [dpdk-dev] [PATCH v2] " Bernard Iremonger
2015-06-26 9:55 ` Ananyev, Konstantin
2015-06-29 8:54 ` Qiu, Michael
2015-06-29 10:20 ` Iremonger, Bernard
2015-06-29 15:22 ` Qiu, Michael
2015-06-29 16:42 ` Iremonger, Bernard
2015-06-30 1:31 ` Qiu, Michael
2015-07-06 11:35 ` Qiu, Michael [this message]
2015-07-07 3:38 ` Tetsuya Mukawa
2015-07-07 10:53 ` Iremonger, Bernard
2015-07-08 3:47 ` Tetsuya Mukawa
2015-07-08 9:49 ` Iremonger, Bernard
2015-07-08 9:59 ` Thomas Monjalon
2015-07-09 3:32 ` Tetsuya Mukawa
2015-07-14 5:15 ` Qiu, Michael
2015-07-09 5:46 ` [dpdk-dev] [PATCH] doc: Fix doxygen comments of rte_eth_dev_close() and rte_eth_dev_detach() Tetsuya Mukawa
2015-07-09 7:28 ` Thomas Monjalon
2015-07-09 8:10 ` Tetsuya Mukawa
2015-07-09 8:19 ` [dpdk-dev] [PATCH v2] " Tetsuya Mukawa
2015-07-10 22:31 ` Thomas Monjalon
2015-07-02 14:36 ` [dpdk-dev] [PATCH v6 0/2] PCI Port Hotplug Bernard Iremonger
2015-07-02 14:36 ` [dpdk-dev] [PATCH v6 1/2] ixgbe: changes to support " Bernard Iremonger
2015-07-02 14:36 ` [dpdk-dev] [PATCH v2] librte_ether: release memory in uninit function Bernard Iremonger
2015-07-02 14:36 ` [dpdk-dev] [PATCH v6 2/2] ixgbe: release queue memory in close functions Bernard Iremonger
2015-07-02 14:59 ` [dpdk-dev] [PATCH v6 0/2] PCI Port Hotplug Ananyev, Konstantin
2015-07-19 15:42 ` Thomas Monjalon
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 0/7] i40e: PCI Port Hotplug Changes Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 1/7] i40e: changes to support PCI Port Hotplug Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 2/7] i40e: release vmdq vsi's in dev_close Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 3/7] i40e: increase ASQ_DELAY_MS to 100 and MAX_TRY_TIMES to 20 in i40evf_wait_cmd_done() Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 4/7] i40e: call _clear_cmd() when error occurs Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 5/7] i40e: clear queues in i40evf_dev_stop Bernard Iremonger
2015-07-03 14:03 ` [dpdk-dev] [PATCH v6 6/7] i40e: check rxq parameter in i40e_reset_rx_queue Bernard Iremonger
2015-07-03 14:04 ` [dpdk-dev] [PATCH v6 7/7] i40e: release queue memory in close functions Bernard Iremonger
2015-07-10 20:44 ` [dpdk-dev] [PATCH v6 0/7] i40e: PCI Port Hotplug Changes Zhang, Helin
2015-07-19 19:39 ` Thomas Monjalon
2015-07-03 14:38 ` [dpdk-dev] [PATCH v7 0/2] e1000: PCI Port Hotplug changes Bernard Iremonger
2015-07-03 14:38 ` [dpdk-dev] [PATCH v7 1/2] e1000: igb and em1000 " Bernard Iremonger
2015-07-13 15:53 ` Zhang, Helin
2015-07-03 14:38 ` [dpdk-dev] [PATCH v7 2/2] e1000: free queue memory in close functions Bernard Iremonger
2015-07-13 15:54 ` Zhang, Helin
2015-07-19 15:26 ` [dpdk-dev] [PATCH v7 0/2] e1000: PCI Port Hotplug changes Thomas Monjalon
2015-07-07 9:18 ` [dpdk-dev] [PATCH v4 0/4] virtio: PCI Port Hotplug Bernard Iremonger
2015-07-07 9:18 ` [dpdk-dev] [PATCH v4 1/4] virtio: add support for " Bernard Iremonger
2015-07-07 9:18 ` [dpdk-dev] [PATCH v4 2/4] virtio: check vq parameter in virtqueue_detatch_unused() function Bernard Iremonger
2015-07-07 9:18 ` [dpdk-dev] [PATCH v4 3/4] virtio: free queue memory in virtio_dev_close() Bernard Iremonger
2015-07-07 18:04 ` Stephen Hemminger
2015-07-07 9:18 ` [dpdk-dev] [PATCH v4 4/4] test-pmd: remove call to rte_eth_promiscuous_disable() from detach_port() Bernard Iremonger
2015-07-08 0:42 ` Ouyang, Changchun
2015-07-09 2:04 ` Tetsuya Mukawa
2015-07-07 10:21 ` [dpdk-dev] [PATCH v4 0/3] bonding PCI Port Hotplug Bernard Iremonger
2015-07-07 10:21 ` [dpdk-dev] [PATCH v4 1/3] bonding: add support for " Bernard Iremonger
2015-07-15 10:22 ` Declan Doherty
2015-07-07 10:21 ` [dpdk-dev] [PATCH v4 2/3] test-pmd: modified testpmd for link_bonding Bernard Iremonger
2015-07-07 10:21 ` [dpdk-dev] [PATCH v4 3/3] bonding: free queue memory in stop function Bernard Iremonger
2015-07-07 13:09 ` [dpdk-dev] [PATCH v4 0/1] ring PCI Port Hotplug Bernard Iremonger
2015-07-07 13:09 ` [dpdk-dev] [PATCH v4 1/1] ring: changes to support " Bernard Iremonger
2015-07-18 20:27 ` Thomas Monjalon
2015-07-21 15:36 ` Iremonger, Bernard
2015-07-27 2:52 ` Thomas Monjalon
2015-07-13 13:04 ` [dpdk-dev] [PATCH v3 0/2] librte_ether release memory Bernard Iremonger
2015-07-13 13:04 ` [dpdk-dev] [PATCH v3 1/2] librte_ether: release memory in uninit function Bernard Iremonger
2015-07-17 13:55 ` Thomas Monjalon
2015-07-13 13:04 ` [dpdk-dev] [PATCH v3 2/2] librte_ether: release queue array memory in close function Bernard Iremonger
2015-07-19 21:37 ` Thomas Monjalon
2015-07-14 4:51 ` [dpdk-dev] [PATCH v3 0/2] librte_ether release memory Qiu, Michael
2015-07-14 13:10 ` [dpdk-dev] [PATCH v5 0/4] virtio PCI Port Hotplug Bernard Iremonger
2015-07-14 13:10 ` [dpdk-dev] [PATCH 1/5] virtio: add support for " Bernard Iremonger
2015-07-14 13:10 ` [dpdk-dev] [PATCH 2/5] virtio: check vq parameter in virtqueue_detatch_unused() function Bernard Iremonger
2015-07-14 13:10 ` [dpdk-dev] [PATCH 3/5] virtio: add proper queue release Bernard Iremonger
2015-07-14 13:10 ` [dpdk-dev] [PATCH 4/5] virtio: free queue memory in virtio_dev_close() Bernard Iremonger
2015-07-14 18:28 ` Stephen Hemminger
2015-07-15 8:27 ` Iremonger, Bernard
2015-07-15 8:38 ` Ouyang, Changchun
2015-07-15 8:50 ` Iremonger, Bernard
2015-07-15 1:36 ` Ouyang, Changchun
2015-07-15 8:01 ` Iremonger, Bernard
2015-07-15 8:36 ` Ouyang, Changchun
2015-07-14 13:10 ` [dpdk-dev] [PATCH v5 5/5] test-pmd: remove call to rte_eth_promiscuous_disable() from detach_port() Bernard Iremonger
2015-07-15 13:50 ` [dpdk-dev] [PATCH v6 0/6] virtio PCI Port Hotplug Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 1/6] virtio: add support for " Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 2/6] virtio: check vq parameter in virtqueue_detatch_unused() function Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 3/6] virtio: add proper queue release Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 4/6] virtio: free queue memory in virtio_dev_close() Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 5/6] virtio: use queue_release in dev_uninit Bernard Iremonger
2015-07-15 13:51 ` [dpdk-dev] [PATCH v6 6/6] test-pmd: remove call to rte_eth_promiscuous_disable() from detach_port() Bernard Iremonger
2015-07-17 9:23 ` Xu, Qian Q
2015-07-17 0:53 ` [dpdk-dev] [PATCH v6 0/6] virtio PCI Port Hotplug Stephen Hemminger
2015-07-19 20:12 ` Thomas Monjalon
2015-07-15 15:32 ` [dpdk-dev] [PATCH v5 0/3] bonding " Bernard Iremonger
2015-07-15 15:32 ` [dpdk-dev] [PATCH v5 1/3] bonding: add support for " Bernard Iremonger
2015-07-18 20:39 ` Thomas Monjalon
2015-07-21 10:18 ` Iremonger, Bernard
2015-07-15 15:32 ` [dpdk-dev] [PATCH v5 2/3] test-pmd: modified testpmd for link_bonding Bernard Iremonger
2015-07-15 15:32 ` [dpdk-dev] [PATCH v5 3/3] bonding: free queue memory in stop function Bernard Iremonger
2015-07-21 15:16 ` [dpdk-dev] [PATCH v6 0/3] bonding PCI Port Hotplug Bernard Iremonger
2015-07-21 15:16 ` [dpdk-dev] [PATCH v6 1/3] bonding: add support for " Bernard Iremonger
2015-07-21 15:16 ` [dpdk-dev] [PATCH v6 2/3] test-pmd: modified testpmd for link_bonding Bernard Iremonger
2015-07-21 15:16 ` [dpdk-dev] [PATCH v6 3/3] bonding: free queue memory in stop function Bernard Iremonger
2015-07-27 2:48 ` Thomas Monjalon
2015-07-27 8:31 ` Iremonger, Bernard
2015-07-27 9:55 ` Thomas Monjalon
2015-07-27 15:54 ` [dpdk-dev] [PATCH v7 0/4] bonding PCI Port Hotplug Bernard Iremonger
2015-07-27 15:54 ` [dpdk-dev] [PATCH v7 1/4] bonding: add support for " Bernard Iremonger
2015-07-27 17:14 ` Thomas Monjalon
2015-07-27 15:54 ` [dpdk-dev] [PATCH v7 2/4] test-pmd: modified testpmd for link_bonding Bernard Iremonger
2015-07-27 17:15 ` Thomas Monjalon
2015-07-27 15:54 ` [dpdk-dev] [PATCH v7 3/4] bonding: free queue memory in close function Bernard Iremonger
2015-07-27 15:54 ` [dpdk-dev] [PATCH v7 4/4] testpmd_app_ug: add example of re-attaching bonded port Bernard Iremonger
2015-07-27 17:38 ` [dpdk-dev] [PATCH v7 0/4] bonding PCI Port Hotplug Thomas Monjalon
2015-08-04 15:26 ` [dpdk-dev] [PATCH 1/1] bonding: fix error handling in rte_eth_bond_create() Bernard Iremonger
2015-08-04 15:52 ` Thomas Monjalon
2015-08-05 12:28 ` Iremonger, Bernard
2015-08-05 12:36 ` [dpdk-dev] [PATCH v2 " Bernard Iremonger
2015-08-05 12:48 ` Liu, Yong
2015-08-05 13:15 ` Thomas Monjalon
2015-08-05 13:19 ` Iremonger, Bernard
2015-08-05 13:35 ` Thomas Monjalon
2015-08-05 13:39 ` Iremonger, Bernard
2015-08-05 14:04 ` [dpdk-dev] [PATCH v3 1/1] bonding: fix device initialisation error handling Bernard Iremonger
2015-08-06 8:19 ` Jastrzebski, MichalX K
2015-08-10 0:06 ` Thomas Monjalon
2015-09-28 13:03 ` [dpdk-dev] [PATCH 00/20] remove pci driver from vdevs Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 01/20] librte_eal: add RTE_KDRV_NONE for vdevs Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 02/20] librte_ether: add fields from rte_pci_driver to rte_eth_dev_data Bernard Iremonger
2015-09-29 19:08 ` Neil Horman
2015-09-30 9:56 ` Bruce Richardson
2015-09-30 13:14 ` Neil Horman
2015-09-30 13:21 ` Bruce Richardson
2015-09-30 16:33 ` Iremonger, Bernard
2015-09-30 13:18 ` Neil Horman
2015-09-30 13:23 ` Bruce Richardson
2015-09-28 13:03 ` [dpdk-dev] [PATCH 03/20] librte_ether: add function rte_eth_copy_dev_info() Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 04/20] null: remove pci device driver Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 05/20] ring: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 06/20] bonding: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 07/20] pcap: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 08/20] af_packet: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 09/20] xenvirt: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 10/20] mpipe: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 11/20] ixgbe: copy pci device info to eth_dev data Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 12/20] e1000: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 13/20] i40e: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 14/20] fm10k: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 15/20] bnx2x: " Bernard Iremonger
2015-09-28 19:55 ` Stephen Hemminger
2015-09-29 8:43 ` Iremonger, Bernard
2015-09-28 13:03 ` [dpdk-dev] [PATCH 16/20] cxgbe: " Bernard Iremonger
2015-09-28 18:53 ` Rahul Lakkireddy
2015-09-29 8:41 ` Iremonger, Bernard
2015-09-28 13:03 ` [dpdk-dev] [PATCH 17/20] enic: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 18/20] mlx4: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 19/20] virtio: " Bernard Iremonger
2015-09-28 13:03 ` [dpdk-dev] [PATCH 20/20] vmxnet3: " Bernard Iremonger
2015-10-01 15:16 ` [dpdk-dev] [PATCH 0/1] vmxnet3 hotplug support Bernard Iremonger
2015-10-01 15:16 ` [dpdk-dev] [PATCH 1/1] vmxnet3: add PCI Port Hotplug support Bernard Iremonger
2015-10-02 9:08 ` [dpdk-dev] [PATCH 1/2] xenvirt: add support for PCI Port Hotplug Bernard Iremonger
2015-10-02 9:08 ` [dpdk-dev] [PATCH 2/2] xenvirt: free queues in dev_close Bernard Iremonger
2015-10-02 9:09 ` [dpdk-dev] [PATCH] vhost_xen: fix compile error in main.c Bernard Iremonger
2015-10-02 9:20 ` [dpdk-dev] [PATCH 0/2] xenvirt hotplug support Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 00/20] remove pci driver from vdevs Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 01/20] librte_eal: add RTE_KDRV_NONE for vdevs Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 02/20] librte_ether: add fields from rte_pci_driver to rte_eth_dev_data Bernard Iremonger
2015-10-14 16:28 ` Mcnamara, John
2015-10-16 10:34 ` Iremonger, Bernard
2015-10-20 8:57 ` Qiu, Michael
2015-10-20 11:18 ` Iremonger, Bernard
2015-10-20 9:18 ` Qiu, Michael
2015-10-20 10:35 ` Iremonger, Bernard
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 03/20] librte_ether: add function rte_eth_copy_dev_info() Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 04/20] null: remove pci device driver Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 05/20] ring: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 06/20] bonding: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 07/20] pcap: " Bernard Iremonger
2015-10-14 16:31 ` Mcnamara, John
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 08/20] af_packet: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 09/20] xenvirt: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 10/20] mpipe: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 11/20] ixgbe: copy pci device info to eth_dev data Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 12/20] e1000: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 13/20] i40e: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 14/20] fm10k: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 15/20] bnx2x: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 16/20] cxgbe: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 17/20] enic: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 18/20] mlx4: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 19/20] virtio: " Bernard Iremonger
2015-10-12 16:25 ` [dpdk-dev] [PATCH v3 20/20] vmxnet3: " Bernard Iremonger
2015-10-20 15:37 ` [dpdk-dev] [PATCH 1/2] virtio: fixed segmentation fault in queue_release Bernard Iremonger
2015-10-20 15:37 ` [dpdk-dev] [PATCH 2/2] rel_notes: update for fix for virtio segmentation fault Bernard Iremonger
2015-10-20 18:44 ` [dpdk-dev] [PATCH 1/2] virtio: fixed segmentation fault in queue_release Stephen Hemminger
2015-10-20 21:32 ` Thomas Monjalon
2015-11-06 16:30 ` [dpdk-dev] [PATCH 1/1] librte_ether: fix coverity errors in rte_eth_copy_pci_info Bernard Iremonger
2015-11-06 16:39 ` Thomas Monjalon
2015-11-06 16:54 ` Iremonger, Bernard
2015-11-06 17:20 ` [dpdk-dev] [v2 0/1] librte_ether: fix coverity errors Bernard Iremonger
2015-11-06 17:20 ` [dpdk-dev] [v2 1/1] librte_ether: fix coverity errors in rte_eth_copy_pci_info Bernard Iremonger
2015-11-10 15:40 ` Thomas Monjalon
2015-11-23 15:20 ` [dpdk-dev] [PATCH 1/1] app/test: create ring and ethdevs in pmd_ring_autotest Bernard Iremonger
2015-11-24 16:14 ` Bruce Richardson
2015-11-24 16:29 ` Iremonger, Bernard
2015-11-24 16:30 ` Richardson, Bruce
2015-11-24 17:33 ` [dpdk-dev] [PATCH v2 0/2] ring pmd autotest Bernard Iremonger
2015-11-24 17:33 ` [dpdk-dev] [PATCH v2 1/2] app/test: create ring and ethdevs in pmd_ring_autotest Bernard Iremonger
2015-11-24 17:33 ` [dpdk-dev] [PATCH v2 2/2] doc: revise ring-based PMD to match latest ring PMD code Bernard Iremonger
2015-11-27 16:07 ` [dpdk-dev] [PATCH v3 0/2] ring pmd autotest Bernard Iremonger
2015-11-27 16:07 ` [dpdk-dev] [PATCH v3 1/2] app/test: fix failures in the ring_pmd_autotest program Bernard Iremonger
2015-11-27 16:14 ` Bruce Richardson
2015-11-27 16:40 ` Iremonger, Bernard
2015-11-27 18:20 ` Thomas Monjalon
2015-11-27 16:07 ` [dpdk-dev] [PATCH v3 2/2] doc: correct Rings-based PMD section in the NIC Drivers guides Bernard Iremonger
2015-11-27 16:17 ` Bruce Richardson
2015-11-28 11:01 ` Iremonger, Bernard
2015-11-28 11:01 ` [dpdk-dev] [PATCH v4 0/2] ring pmd autotest Bernard Iremonger
2015-11-28 11:01 ` [dpdk-dev] [PATCH v4 1/2] app/test: fix failures in the ring_pmd_autotest program Bernard Iremonger
2015-11-28 11:01 ` [dpdk-dev] [PATCH v4 2/2] doc: correct Rings-based PMD section in the NIC Drivers guides Bernard Iremonger
2015-12-01 11:24 ` Mcnamara, John
2015-12-07 2:55 ` [dpdk-dev] [PATCH v4 0/2] ring pmd autotest Thomas Monjalon
2015-12-04 14:05 ` [dpdk-dev] [PATCH] bonding: use eth_dev link state interrupt flag Bernard Iremonger
2015-12-04 16:45 ` Declan Doherty
2015-12-06 23:12 ` Thomas Monjalon
2015-12-04 15:14 ` [dpdk-dev] [PATCH 1/1] virtio: call rte_eth_copy_pci_info() later Bernard Iremonger
2015-12-06 22:37 ` Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=533710CFB86FA344BFBF2D6802E60286046AE60D@SHSMSX101.ccr.corp.intel.com \
--to=michael.qiu@intel.com \
--cc=dev@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).