Displaying 11 results from an estimated 11 matches for "ifla_txqlen".
2016 Jun 30
2
[PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...Fastabend <john.r.fastabend at intel.com>
Great timing I was just looking into this because I need it for the
qdisc side.
It looks like this covers the sysfs change but the tx_queue_len can
also be changed via rtnetlink as well. So we need another patch for
that path right?
if (tb[IFLA_TXQLEN]) {
unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
if (dev->tx_queue_len ^ value)
status |= DO_SETLINK_NOTIFY;
dev->tx_queue_len = value;
}
Thanks,
John
2016 Jun 30
2
[PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...Fastabend <john.r.fastabend at intel.com>
Great timing I was just looking into this because I need it for the
qdisc side.
It looks like this covers the sysfs change but the tx_queue_len can
also be changed via rtnetlink as well. So we need another patch for
that path right?
if (tb[IFLA_TXQLEN]) {
unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
if (dev->tx_queue_len ^ value)
status |= DO_SETLINK_NOTIFY;
dev->tx_queue_len = value;
}
Thanks,
John
2016 Jun 30
1
[PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...I was just looking into this because I need it for the
>> qdisc side.
>>
>> It looks like this covers the sysfs change but the tx_queue_len can
>> also be changed via rtnetlink as well. So we need another patch for
>> that path right?
>>
>> if (tb[IFLA_TXQLEN]) {
>> unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
>>
>> if (dev->tx_queue_len ^ value)
>> status |= DO_SETLINK_NOTIFY;
>>
>> dev->tx_queue_len = value;
>> }...
2016 Jun 30
1
[PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...I was just looking into this because I need it for the
>> qdisc side.
>>
>> It looks like this covers the sysfs change but the tx_queue_len can
>> also be changed via rtnetlink as well. So we need another patch for
>> that path right?
>>
>> if (tb[IFLA_TXQLEN]) {
>> unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
>>
>> if (dev->tx_queue_len ^ value)
>> status |= DO_SETLINK_NOTIFY;
>>
>> dev->tx_queue_len = value;
>> }...
2016 Jun 30
0
[PATCH net-next V3 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...m>
>
> Great timing I was just looking into this because I need it for the
> qdisc side.
>
> It looks like this covers the sysfs change but the tx_queue_len can
> also be changed via rtnetlink as well. So we need another patch for
> that path right?
>
> if (tb[IFLA_TXQLEN]) {
> unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
>
> if (dev->tx_queue_len ^ value)
> status |= DO_SETLINK_NOTIFY;
>
> dev->tx_queue_len = value;
> }
>
> Thanks,
> John...
2016 Jun 30
0
[PATCH net-next V4 5/6] net: introduce NETDEV_CHANGE_TX_QUEUE_LEN
...t;tx_queue_len = orig_len;
+ return -EFAULT;
+ }
+ }
+
return 0;
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index eb49ca2..b16b779 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1927,11 +1927,19 @@ static int do_setlink(const struct sk_buff *skb,
if (tb[IFLA_TXQLEN]) {
unsigned long value = nla_get_u32(tb[IFLA_TXQLEN]);
-
- if (dev->tx_queue_len ^ value)
+ unsigned long orig_len = dev->tx_queue_len;
+
+ if (dev->tx_queue_len ^ value) {
+ dev->tx_queue_len = value;
+ err = call_netdevice_notifiers(
+ NETDEV_CHANGE_TX_QUEUE_LEN, de...
2016 Jun 30
10
[PATCH net-next V4 0/6] switch to use tx skb array in tun
...notifier which was triggered when tx_queue_len was
changed for a netdev.
- resize all queues during the tx_queue_len changing.
Tests shows about 15% improvement on guest rx pps:
Before: ~1300000pps
After : ~1500000pps
Changes from V3:
- fix kbuild warnings
- call NETDEV_CHANGE_TX_QUEUE_LEN on IFLA_TXQLEN
Changes from V2:
- add multiple rings resizing support for ptr_ring/skb_array
- add zero length ring support
- introdce a NETDEV_CHANGE_TX_QUEUE_LEN
- drop new flags
Changes from V1:
- switch to use skb array instead of a customized circular buffer
- add non-blocking support
- rename .peek to .pe...
2016 Jun 30
10
[PATCH net-next V4 0/6] switch to use tx skb array in tun
...notifier which was triggered when tx_queue_len was
changed for a netdev.
- resize all queues during the tx_queue_len changing.
Tests shows about 15% improvement on guest rx pps:
Before: ~1300000pps
After : ~1500000pps
Changes from V3:
- fix kbuild warnings
- call NETDEV_CHANGE_TX_QUEUE_LEN on IFLA_TXQLEN
Changes from V2:
- add multiple rings resizing support for ptr_ring/skb_array
- add zero length ring support
- introdce a NETDEV_CHANGE_TX_QUEUE_LEN
- drop new flags
Changes from V1:
- switch to use skb array instead of a customized circular buffer
- add non-blocking support
- rename .peek to .pe...
2016 Jun 30
0
[PATCH net-next V4 0/6] switch to use tx skb array in tun
...gt;
> Tests shows about 15% improvement on guest rx pps:
>
> Before: ~1300000pps
> After : ~1500000pps
Acked-by: Michael S. Tsirkin <mst at redhat.com>
Acked-from-altitude: 34697 feet.
> Changes from V3:
> - fix kbuild warnings
> - call NETDEV_CHANGE_TX_QUEUE_LEN on IFLA_TXQLEN
>
> Changes from V2:
> - add multiple rings resizing support for ptr_ring/skb_array
> - add zero length ring support
> - introdce a NETDEV_CHANGE_TX_QUEUE_LEN
> - drop new flags
>
> Changes from V1:
> - switch to use skb array instead of a customized circular buffer
>...
2016 Jun 30
9
[PATCH net-next V3 0/6] switch to use tx skb array in tun
Hi all:
This series tries to switch to use skb array in tun. This is used to
eliminate the spinlock contention between producer and consumer. The
conversion was straightforward: just introdce a tx skb array and use
it instead of sk_receive_queue.
A minor issue is to keep the tx_queue_len behaviour, since tun used to
use it for the length of sk_receive_queue. This is done through:
- add the
2016 Jun 30
9
[PATCH net-next V3 0/6] switch to use tx skb array in tun
Hi all:
This series tries to switch to use skb array in tun. This is used to
eliminate the spinlock contention between producer and consumer. The
conversion was straightforward: just introdce a tx skb array and use
it instead of sk_receive_queue.
A minor issue is to keep the tx_queue_len behaviour, since tun used to
use it for the length of sk_receive_queue. This is done through:
- add the