Skip to contentSkip to conversation

Unit for tx_rate in rte_eth_set_queue_rate_limit?

DISCUSSION Simon Kågström 2 participants 2 messages Oct 20, 2015

lore
Share & tools
lore
#0 lore raw

Hi!

What is the unit of the tx_rate parameter to the rte_eth_set_queue_rate_limit function? It's documented as

/**
* Set the rate limitation for a queue on an Ethernet device. *
* @param port_id
* The port identifier of the Ethernet device.
* @param queue_idx
* The queue id.
* @param tx_rate
* The tx rate allocated from the total link speed for this queue.
* @return

 *   - (0) if successful.
 *   - (-ENOTSUP) if hardware doesn't support this feature.
 *   - (-ENODEV) if *port_id* invalid.
 *   - (-EINVAL) if bad parameter.
 */
int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx,
			uint16_t tx_rate);

I parse this as meaning a percentage of total link speed, i.e., on a 10 Gbps link, 50 would mean 5Gbps, 10 means 1Gbps etc. Is this correct?

// Simon

#1 lore raw

2015-10-20 14:20, Simon Kågström:

Quoted 23 lines

Hi!

What is the unit of the tx_rate parameter to the rte_eth_set_queue_rate_limit function? It's documented as

/**
* Set the rate limitation for a queue on an Ethernet device. *
* @param port_id
* The port identifier of the Ethernet device.
* @param queue_idx
* The queue id.
* @param tx_rate
* The tx rate allocated from the total link speed for this queue.
* @return

 *   - (0) if successful.
 *   - (-ENOTSUP) if hardware doesn't support this feature.
 *   - (-ENODEV) if *port_id* invalid.
 *   - (-EINVAL) if bad parameter.
 */
int rte_eth_set_queue_rate_limit(uint8_t port_id, uint16_t queue_idx,
			uint16_t tx_rate);
Quoted 2 lines

I parse this as meaning a percentage of total link speed, i.e., on a 10 Gbps link, 50 would mean 5Gbps, 10 means 1Gbps etc. Is this correct?

It's implemented only in ixgbe:

        /* Calculate the rate factor values to set */
        rf_int = (uint32_t)link_speed / (uint32_t)tx_rate;
        rf_dec = (uint32_t)link_speed % (uint32_t)tx_rate;
        rf_dec = (rf_dec << IXGBE_RTTBCNRC_RF_INT_SHIFT) / tx_rate;

        bcnrc_val = IXGBE_RTTBCNRC_RS_ENA;
        bcnrc_val |= ((rf_int << IXGBE_RTTBCNRC_RF_INT_SHIFT) &
                IXGBE_RTTBCNRC_RF_INT_MASK_M);
        bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK);

So you just need to check the datasheet and send a patch to make it clear :) Thanks