From: Zoltan Kiss <zoltan.kiss@linaro.org>
To: "Venkatesan, Venky" <venky.venkatesan@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] ixgbe: fix checking for tx_free_thresh
Date: Thu, 28 May 2015 12:12:45 +0100 [thread overview]
Message-ID: <5566F82D.3070608@linaro.org> (raw)
In-Reply-To: <65CC0274-0B2A-460C-B381-59EB8CE9F970@intel.com>
The requirements for rte_eth_tx_burst(), which calls a driver specific
function, in case of ixgbe, these two:
"It is the responsibility of the rte_eth_tx_burst() function to
transparently free the memory buffers of packets previously sent. This
feature is driven by the *tx_free_thresh* value supplied to the
rte_eth_dev_configure() function at device configuration time. When the
number of previously sent packets reached the "minimum transmit packets
to free" threshold, the rte_eth_tx_burst() function must [attempt to]
free the *rte_mbuf* buffers of those packets whose transmission was
effectively completed."
Also rte_eth_tx_queue_setup() uses the same description for tx_free_thresh:
"The *tx_free_thresh* value indicates the [minimum] number of network
buffers that must be pending in the transmit ring to trigger their
[implicit] freeing by the driver transmit function."
And all the other poll mode drivers are using this formula. Plus I've
described a possible hang situation in the commit message.
On 28/05/15 11:50, Venkatesan, Venky wrote:
> NAK. This causes more (unsuccessful) cleanup attempts on the descriptor ring. What is motivating this change?
>
> Regards,
> Venky
>
>
>> On May 28, 2015, at 1:42 AM, Zoltan Kiss <zoltan.kiss@linaro.org> wrote:
>>
>> This check doesn't do what's required by rte_eth_tx_burst:
>> "When the number of previously sent packets reached the "minimum transmit
>> packets to free" threshold"
>>
>> This can cause problems when txq->tx_free_thresh + [number of elements in the
>> pool] < txq->nb_tx_desc.
>>
>> Signed-off-by: Zoltan Kiss <zoltan.kiss@linaro.org>
>> ---
>> drivers/net/ixgbe/ixgbe_rxtx.c | 4 ++--
>> drivers/net/ixgbe/ixgbe_rxtx_vec.c | 2 +-
>> 2 files changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
>> index 4f9ab22..b70ed8c 100644
>> --- a/drivers/net/ixgbe/ixgbe_rxtx.c
>> +++ b/drivers/net/ixgbe/ixgbe_rxtx.c
>> @@ -250,10 +250,10 @@ tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
>>
>> /*
>> * Begin scanning the H/W ring for done descriptors when the
>> - * number of available descriptors drops below tx_free_thresh. For
>> + * number of in flight descriptors reaches tx_free_thresh. For
>> * each done descriptor, free the associated buffer.
>> */
>> - if (txq->nb_tx_free < txq->tx_free_thresh)
>> + if ((txq->nb_tx_desc - txq->nb_tx_free) > txq->tx_free_thresh)
>> ixgbe_tx_free_bufs(txq);
>>
>> /* Only use descriptors that are available */
>> diff --git a/drivers/net/ixgbe/ixgbe_rxtx_vec.c b/drivers/net/ixgbe/ixgbe_rxtx_vec.c
>> index abd10f6..f91c698 100644
>> --- a/drivers/net/ixgbe/ixgbe_rxtx_vec.c
>> +++ b/drivers/net/ixgbe/ixgbe_rxtx_vec.c
>> @@ -598,7 +598,7 @@ ixgbe_xmit_pkts_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
>> if (unlikely(nb_pkts > RTE_IXGBE_VPMD_TX_BURST))
>> nb_pkts = RTE_IXGBE_VPMD_TX_BURST;
>>
>> - if (txq->nb_tx_free < txq->tx_free_thresh)
>> + if ((txq->nb_tx_desc - txq->nb_tx_free) > txq->tx_free_thresh)
>> ixgbe_tx_free_bufs(txq);
>>
>> nb_commit = nb_pkts = (uint16_t)RTE_MIN(txq->nb_tx_free, nb_pkts);
>> --
>> 1.9.1
>>
next prev parent reply other threads:[~2015-05-28 11:12 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-05-27 20:12 Zoltan Kiss
2015-05-28 10:50 ` Venkatesan, Venky
2015-05-28 11:12 ` Zoltan Kiss [this message]
2015-06-01 16:15 ` Zoltan Kiss
2015-06-02 13:31 ` Ananyev, Konstantin
2015-06-02 15:08 ` Zoltan Kiss
2015-06-02 17:35 ` Ananyev, Konstantin
2015-06-03 17:46 ` Zoltan Kiss
2015-06-09 11:18 ` Ananyev, Konstantin
2015-06-09 15:08 ` Zoltan Kiss
2015-06-09 15:44 ` Ananyev, Konstantin
2015-06-09 17:46 ` Zoltan Kiss
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=5566F82D.3070608@linaro.org \
--to=zoltan.kiss@linaro.org \
--cc=dev@dpdk.org \
--cc=venky.venkatesan@intel.com \
/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).