IPoIB: Make send and receive queue sizes tunable
Make IPoIB's send and receive queue sizes tunable via module parameters ("send_queue_size" and "recv_queue_size"). This allows the queue sizes to be enlarged to fix disastrously bad performance on some platforms and workloads, without bloating memory usage when large queues aren't needed. Signed-off-by: Shirley Ma <xma@us.ibm.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
This commit is contained in:
parent
f2de3b0612
commit
0f4852513f
|
@ -65,6 +65,8 @@ enum {
|
|||
|
||||
IPOIB_RX_RING_SIZE = 128,
|
||||
IPOIB_TX_RING_SIZE = 64,
|
||||
IPOIB_MAX_QUEUE_SIZE = 8192,
|
||||
IPOIB_MIN_QUEUE_SIZE = 2,
|
||||
|
||||
IPOIB_NUM_WC = 4,
|
||||
|
||||
|
@ -332,6 +334,8 @@ static inline void ipoib_unregister_debugfs(void) { }
|
|||
#define ipoib_warn(priv, format, arg...) \
|
||||
ipoib_printk(KERN_WARNING, priv, format , ## arg)
|
||||
|
||||
extern int ipoib_sendq_size;
|
||||
extern int ipoib_recvq_size;
|
||||
|
||||
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
|
||||
extern int ipoib_debug_level;
|
||||
|
|
|
@ -161,7 +161,7 @@ static int ipoib_ib_post_receives(struct net_device *dev)
|
|||
struct ipoib_dev_priv *priv = netdev_priv(dev);
|
||||
int i;
|
||||
|
||||
for (i = 0; i < IPOIB_RX_RING_SIZE; ++i) {
|
||||
for (i = 0; i < ipoib_recvq_size; ++i) {
|
||||
if (ipoib_alloc_rx_skb(dev, i)) {
|
||||
ipoib_warn(priv, "failed to allocate receive buffer %d\n", i);
|
||||
return -ENOMEM;
|
||||
|
@ -187,7 +187,7 @@ static void ipoib_ib_handle_wc(struct net_device *dev,
|
|||
if (wr_id & IPOIB_OP_RECV) {
|
||||
wr_id &= ~IPOIB_OP_RECV;
|
||||
|
||||
if (wr_id < IPOIB_RX_RING_SIZE) {
|
||||
if (wr_id < ipoib_recvq_size) {
|
||||
struct sk_buff *skb = priv->rx_ring[wr_id].skb;
|
||||
dma_addr_t addr = priv->rx_ring[wr_id].mapping;
|
||||
|
||||
|
@ -252,9 +252,9 @@ static void ipoib_ib_handle_wc(struct net_device *dev,
|
|||
struct ipoib_tx_buf *tx_req;
|
||||
unsigned long flags;
|
||||
|
||||
if (wr_id >= IPOIB_TX_RING_SIZE) {
|
||||
if (wr_id >= ipoib_sendq_size) {
|
||||
ipoib_warn(priv, "completion event with wrid %d (> %d)\n",
|
||||
wr_id, IPOIB_TX_RING_SIZE);
|
||||
wr_id, ipoib_sendq_size);
|
||||
return;
|
||||
}
|
||||
|
||||
|
@ -275,7 +275,7 @@ static void ipoib_ib_handle_wc(struct net_device *dev,
|
|||
spin_lock_irqsave(&priv->tx_lock, flags);
|
||||
++priv->tx_tail;
|
||||
if (netif_queue_stopped(dev) &&
|
||||
priv->tx_head - priv->tx_tail <= IPOIB_TX_RING_SIZE / 2)
|
||||
priv->tx_head - priv->tx_tail <= ipoib_sendq_size >> 1)
|
||||
netif_wake_queue(dev);
|
||||
spin_unlock_irqrestore(&priv->tx_lock, flags);
|
||||
|
||||
|
@ -344,13 +344,13 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
|
|||
* means we have to make sure everything is properly recorded and
|
||||
* our state is consistent before we call post_send().
|
||||
*/
|
||||
tx_req = &priv->tx_ring[priv->tx_head & (IPOIB_TX_RING_SIZE - 1)];
|
||||
tx_req = &priv->tx_ring[priv->tx_head & (ipoib_sendq_size - 1)];
|
||||
tx_req->skb = skb;
|
||||
addr = dma_map_single(priv->ca->dma_device, skb->data, skb->len,
|
||||
DMA_TO_DEVICE);
|
||||
pci_unmap_addr_set(tx_req, mapping, addr);
|
||||
|
||||
if (unlikely(post_send(priv, priv->tx_head & (IPOIB_TX_RING_SIZE - 1),
|
||||
if (unlikely(post_send(priv, priv->tx_head & (ipoib_sendq_size - 1),
|
||||
address->ah, qpn, addr, skb->len))) {
|
||||
ipoib_warn(priv, "post_send failed\n");
|
||||
++priv->stats.tx_errors;
|
||||
|
@ -363,7 +363,7 @@ void ipoib_send(struct net_device *dev, struct sk_buff *skb,
|
|||
address->last_send = priv->tx_head;
|
||||
++priv->tx_head;
|
||||
|
||||
if (priv->tx_head - priv->tx_tail == IPOIB_TX_RING_SIZE) {
|
||||
if (priv->tx_head - priv->tx_tail == ipoib_sendq_size) {
|
||||
ipoib_dbg(priv, "TX ring full, stopping kernel net queue\n");
|
||||
netif_stop_queue(dev);
|
||||
}
|
||||
|
@ -488,7 +488,7 @@ static int recvs_pending(struct net_device *dev)
|
|||
int pending = 0;
|
||||
int i;
|
||||
|
||||
for (i = 0; i < IPOIB_RX_RING_SIZE; ++i)
|
||||
for (i = 0; i < ipoib_recvq_size; ++i)
|
||||
if (priv->rx_ring[i].skb)
|
||||
++pending;
|
||||
|
||||
|
@ -527,7 +527,7 @@ int ipoib_ib_dev_stop(struct net_device *dev)
|
|||
*/
|
||||
while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
|
||||
tx_req = &priv->tx_ring[priv->tx_tail &
|
||||
(IPOIB_TX_RING_SIZE - 1)];
|
||||
(ipoib_sendq_size - 1)];
|
||||
dma_unmap_single(priv->ca->dma_device,
|
||||
pci_unmap_addr(tx_req, mapping),
|
||||
tx_req->skb->len,
|
||||
|
@ -536,7 +536,7 @@ int ipoib_ib_dev_stop(struct net_device *dev)
|
|||
++priv->tx_tail;
|
||||
}
|
||||
|
||||
for (i = 0; i < IPOIB_RX_RING_SIZE; ++i)
|
||||
for (i = 0; i < ipoib_recvq_size; ++i)
|
||||
if (priv->rx_ring[i].skb) {
|
||||
dma_unmap_single(priv->ca->dma_device,
|
||||
pci_unmap_addr(&priv->rx_ring[i],
|
||||
|
|
|
@ -41,6 +41,7 @@
|
|||
#include <linux/init.h>
|
||||
#include <linux/slab.h>
|
||||
#include <linux/vmalloc.h>
|
||||
#include <linux/kernel.h>
|
||||
|
||||
#include <linux/if_arp.h> /* For ARPHRD_xxx */
|
||||
|
||||
|
@ -53,6 +54,14 @@ MODULE_AUTHOR("Roland Dreier");
|
|||
MODULE_DESCRIPTION("IP-over-InfiniBand net driver");
|
||||
MODULE_LICENSE("Dual BSD/GPL");
|
||||
|
||||
int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE;
|
||||
int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE;
|
||||
|
||||
module_param_named(send_queue_size, ipoib_sendq_size, int, 0444);
|
||||
MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue");
|
||||
module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444);
|
||||
MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue");
|
||||
|
||||
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
|
||||
int ipoib_debug_level;
|
||||
|
||||
|
@ -795,20 +804,19 @@ int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
|
|||
struct ipoib_dev_priv *priv = netdev_priv(dev);
|
||||
|
||||
/* Allocate RX/TX "rings" to hold queued skbs */
|
||||
|
||||
priv->rx_ring = kzalloc(IPOIB_RX_RING_SIZE * sizeof (struct ipoib_rx_buf),
|
||||
priv->rx_ring = kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
|
||||
GFP_KERNEL);
|
||||
if (!priv->rx_ring) {
|
||||
printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
|
||||
ca->name, IPOIB_RX_RING_SIZE);
|
||||
ca->name, ipoib_recvq_size);
|
||||
goto out;
|
||||
}
|
||||
|
||||
priv->tx_ring = kzalloc(IPOIB_TX_RING_SIZE * sizeof (struct ipoib_tx_buf),
|
||||
priv->tx_ring = kzalloc(ipoib_sendq_size * sizeof *priv->tx_ring,
|
||||
GFP_KERNEL);
|
||||
if (!priv->tx_ring) {
|
||||
printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n",
|
||||
ca->name, IPOIB_TX_RING_SIZE);
|
||||
ca->name, ipoib_sendq_size);
|
||||
goto out_rx_ring_cleanup;
|
||||
}
|
||||
|
||||
|
@ -876,7 +884,7 @@ static void ipoib_setup(struct net_device *dev)
|
|||
dev->hard_header_len = IPOIB_ENCAP_LEN + INFINIBAND_ALEN;
|
||||
dev->addr_len = INFINIBAND_ALEN;
|
||||
dev->type = ARPHRD_INFINIBAND;
|
||||
dev->tx_queue_len = IPOIB_TX_RING_SIZE * 2;
|
||||
dev->tx_queue_len = ipoib_sendq_size * 2;
|
||||
dev->features = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX;
|
||||
|
||||
/* MTU will be reset when mcast join happens */
|
||||
|
@ -1128,6 +1136,14 @@ static int __init ipoib_init_module(void)
|
|||
{
|
||||
int ret;
|
||||
|
||||
ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size);
|
||||
ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE);
|
||||
ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE);
|
||||
|
||||
ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size);
|
||||
ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE);
|
||||
ipoib_sendq_size = max(ipoib_sendq_size, IPOIB_MIN_QUEUE_SIZE);
|
||||
|
||||
ret = ipoib_register_debugfs();
|
||||
if (ret)
|
||||
return ret;
|
||||
|
|
|
@ -159,8 +159,8 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
|
|||
struct ipoib_dev_priv *priv = netdev_priv(dev);
|
||||
struct ib_qp_init_attr init_attr = {
|
||||
.cap = {
|
||||
.max_send_wr = IPOIB_TX_RING_SIZE,
|
||||
.max_recv_wr = IPOIB_RX_RING_SIZE,
|
||||
.max_send_wr = ipoib_sendq_size,
|
||||
.max_recv_wr = ipoib_recvq_size,
|
||||
.max_send_sge = 1,
|
||||
.max_recv_sge = 1
|
||||
},
|
||||
|
@ -175,7 +175,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
|
|||
}
|
||||
|
||||
priv->cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev,
|
||||
IPOIB_TX_RING_SIZE + IPOIB_RX_RING_SIZE + 1);
|
||||
ipoib_sendq_size + ipoib_recvq_size + 1);
|
||||
if (IS_ERR(priv->cq)) {
|
||||
printk(KERN_WARNING "%s: failed to create CQ\n", ca->name);
|
||||
goto out_free_pd;
|
||||
|
|
Loading…
Reference in New Issue