diff options
| author | Matthias Tafelmeier <matthias.tafelmeier@gmx.net> | 2016-12-29 21:37:21 +0100 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2016-12-29 15:38:35 -0500 |
| commit | 3d48b53fb2ae37158e700ffef3f45461ff15c965 (patch) | |
| tree | 453c287c28359dfbee7671207a44a23286496aa7 /net/core | |
| parent | afbb167415843ef23546f5bfaf2a06c86750c2f0 (diff) | |
| download | linux-next-3d48b53fb2ae37158e700ffef3f45461ff15c965.tar.gz | |
net: dev_weight: TX/RX orthogonality
Oftenly, introducing side effects on packet processing on the other half
of the stack by adjusting one of TX/RX via sysctl is not desirable.
There are cases of demand for asymmetric, orthogonal configurability.
This holds true especially for nodes where RPS for RFS usage on top is
configured and therefore use the 'old dev_weight'. This is quite a
common base configuration setup nowadays, even with NICs of superior processing
support (e.g. aRFS).
A good example use case are nodes acting as noSQL data bases with a
large number of tiny requests and rather fewer but large packets as responses.
It's affordable to have large budget and rx dev_weights for the
requests. But as a side effect having this large a number on TX
processed in one run can overwhelm drivers.
This patch therefore introduces an independent configurability via sysctl to
userland.
Signed-off-by: Matthias Tafelmeier <matthias.tafelmeier@gmx.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/dev.c | 8 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 31 |
2 files changed, 36 insertions, 3 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 8db5a0b4b520..56818f7eab2b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3427,7 +3427,11 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -int weight_p __read_mostly = 64; /* old backlog weight */ +int weight_p __read_mostly = 64; /* old backlog weight */ +int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ +int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ +int dev_rx_weight __read_mostly = 64; +int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4833,7 +4837,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = weight_p; + napi->weight = dev_rx_weight; while (again) { struct sk_buff *skb; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 2a46e4009f62..eaa72eb0399c 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -222,6 +222,21 @@ static int set_default_qdisc(struct ctl_table *table, int write, } #endif +static int proc_do_dev_weight(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (ret != 0) + return ret; + + dev_rx_weight = weight_p * dev_weight_rx_bias; + dev_tx_weight = weight_p * dev_weight_tx_bias; + + return ret; +} + static int proc_do_rss_key(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -273,7 +288,21 @@ static struct ctl_table net_core_table[] = { .data = &weight_p, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_do_dev_weight, + }, + { + .procname = "dev_weight_rx_bias", + .data = &dev_weight_rx_bias, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_do_dev_weight, + }, + { + .procname = "dev_weight_tx_bias", + .data = &dev_weight_tx_bias, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_do_dev_weight, }, { .procname = "netdev_max_backlog", |