From: Zoltan Kiss <zoltan.kiss@linaro.org>
To: "Venkatesan, Venky" <venky.venkatesan@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [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 [PATCH] ixgbe: fix checking for tx_free_thresh 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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.