| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1336127716-20383-5-git-send-email-jeffrey.t.kirsher@intel.com>
Date: Fri, 4 May 2012 03:35:12 -0700
From: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
To: davem@...emloft.net
Cc: Alexander Duyck <alexander.h.duyck@...el.com>,
netdev@...r.kernel.org, gospo@...hat.com, sassmann@...hat.com,
Jeff Kirsher <jeffrey.t.kirsher@...el.com>
Subject: [net-next 4/8] ixgbe: Reorder the ring to q_vector mapping to improve performance
From: Alexander Duyck <alexander.h.duyck@...el.com>
This change reorders the mapping of rings to q_vectors in the case that the
number of rings exceeds the number of q_vectors. Previously we would
allocate the first R/N queues to the first q_vector where R is the number
of rings and N is the number of q_vectors. Instead of doing this we can do
a better job of interleaving the rings to the CPUs by assigning every Nth
ring to the q_vector.
The below tables illustrate this change for the R = 16 N = 4 case.
Before patch After patch
q_vector: 0 1 2 3 0 1 2 3
Rings: 0 4 8 12 0 1 2 3
1 5 9 13 4 5 6 7
3 6 10 14 8 9 10 11
4 7 11 15 12 13 14 15
This should improve the performance for both DCB or ATR when the number of
rings exceeds the number of q_vectors allocated by the adapter.
Signed-off-by: Alexander Duyck <alexander.h.duyck@...el.com>
Tested-by: Ross Brattain <ross.b.brattain@...el.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 35 ++++++++++++++-----------
1 files changed, 20 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index ed1b47d..af1a531 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -523,11 +523,17 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring,
/**
* ixgbe_alloc_q_vector - Allocate memory for a single interrupt vector
* @adapter: board private structure to initialize
+ * @v_count: q_vectors allocated on adapter, used for ring interleaving
* @v_idx: index of vector in adapter struct
+ * @txr_count: total number of Tx rings to allocate
+ * @txr_idx: index of first Tx ring to allocate
+ * @rxr_count: total number of Rx rings to allocate
+ * @rxr_idx: index of first Rx ring to allocate
*
* We allocate one q_vector. If allocation fails we return -ENOMEM.
**/
-static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, int v_idx,
+static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
+ int v_count, int v_idx,
int txr_count, int txr_idx,
int rxr_count, int rxr_idx)
{
@@ -598,7 +604,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, int v_idx,
/* update count and index */
txr_count--;
- txr_idx++;
+ txr_idx += v_count;
/* push pointer to next ring */
ring++;
@@ -641,7 +647,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, int v_idx,
/* update count and index */
rxr_count--;
- rxr_idx++;
+ rxr_idx += v_count;
/* push pointer to next ring */
ring++;
@@ -700,24 +706,23 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
q_vectors = 1;
if (q_vectors >= (rxr_remaining + txr_remaining)) {
- for (; rxr_remaining; v_idx++, q_vectors--) {
- int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors);
- err = ixgbe_alloc_q_vector(adapter, v_idx,
- 0, 0, rqpv, rxr_idx);
+ for (; rxr_remaining; v_idx++) {
+ err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
+ 0, 0, 1, rxr_idx);
if (err)
goto err_out;
/* update counts and index */
- rxr_remaining -= rqpv;
- rxr_idx += rqpv;
+ rxr_remaining--;
+ rxr_idx++;
}
}
- for (; q_vectors; v_idx++, q_vectors--) {
- int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors);
- int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors);
- err = ixgbe_alloc_q_vector(adapter, v_idx,
+ for (; v_idx < q_vectors; v_idx++) {
+ int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
+ int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+ err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx,
tqpv, txr_idx,
rqpv, rxr_idx);
@@ -726,9 +731,9 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter)
/* update counts and index */
rxr_remaining -= rqpv;
- rxr_idx += rqpv;
txr_remaining -= tqpv;
- txr_idx += tqpv;
+ rxr_idx++;
+ txr_idx++;
}
return 0;
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists