search for: declare_ewma

From: Johannes Berg <johannes.berg at intel.com> Declaring the factor is counter-intuitive, and people are prone to using small(-ish) values even when that makes no sense. Change the DECLARE_EWMA() macro to take the fractional precision, in bits, rather than a factor, and update all users. While at it, add some more documentation. Signed-off-by: Johannes Berg <johannes.berg at intel.com> --- Unless I hear any objections, I will take this through my tree. --- drivers/net/virtio_net....

From: Johannes Berg <johannes.berg at intel.com> Declaring the factor is counter-intuitive, and people are prone to using small(-ish) values even when that makes no sense. Change the DECLARE_EWMA() macro to take the fractional precision, in bits, rather than a factor, and update all users. While at it, add some more documentation. Signed-off-by: Johannes Berg <johannes.berg at intel.com> --- Unless I hear any objections, I will take this through my tree. --- drivers/net/virtio_net....

Sorry, forgot to Cc Michael and the virt list - patch reproduced below in full. johannes >From 22500fbcf722748fe3471b2e4c6156db47aade15 Mon Sep 17 00:00:00 2001 From: Johannes Berg <johannes.berg at intel.com> Date: Wed, 19 Aug 2015 09:25:18 +0200 Subject: [PATCH] virtio_net: use DECLARE_EWMA Instead of using the out-of-line EWMA calculation, use DECLARE_EWMA() to create static inlines. On x86/64 this results in no change in code size for me, but reduces the struct receive_queue size by the two unsigned long values that store the parameters. Signed-off-by: Johannes Berg <johannes.b...

Sorry, forgot to Cc Michael and the virt list - patch reproduced below in full. johannes >From 22500fbcf722748fe3471b2e4c6156db47aade15 Mon Sep 17 00:00:00 2001 From: Johannes Berg <johannes.berg at intel.com> Date: Wed, 19 Aug 2015 09:25:18 +0200 Subject: [PATCH] virtio_net: use DECLARE_EWMA Instead of using the out-of-line EWMA calculation, use DECLARE_EWMA() to create static inlines. On x86/64 this results in no change in code size for me, but reduces the struct receive_queue size by the two unsigned long values that store the parameters. Signed-off-by: Johannes Berg <johannes.b...

...l S. Tsirkin wrote: > I'll need to look at this more, in particular the feature > bit is missing here. For now one question: > > On Mon, Dec 18, 2017 at 04:40:36PM -0800, Sridhar Samudrala wrote: >> @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); >> */ >> DECLARE_EWMA(pkt_len, 0, 64) >> >> +#define VF_TAKEOVER_INT (HZ / 10) >> + >> #define VIRTNET_DRIVER_VERSION "1.0.0" >> >> static const unsigned long guest_offloads[] = { > Why is this delay necessary? And why by 100ms? This is based on netvsc implemen...

...l S. Tsirkin wrote: > I'll need to look at this more, in particular the feature > bit is missing here. For now one question: > > On Mon, Dec 18, 2017 at 04:40:36PM -0800, Sridhar Samudrala wrote: >> @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); >> */ >> DECLARE_EWMA(pkt_len, 0, 64) >> >> +#define VF_TAKEOVER_INT (HZ / 10) >> + >> #define VIRTNET_DRIVER_VERSION "1.0.0" >> >> static const unsigned long guest_offloads[] = { > Why is this delay necessary? And why by 100ms? This is based on netvsc implemen...

...n particular the feature > > > bit is missing here. For now one question: > > > > > > On Mon, Dec 18, 2017 at 04:40:36PM -0800, Sridhar Samudrala wrote: > > >> @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); > > >> */ > > >> DECLARE_EWMA(pkt_len, 0, 64) > > >> > > >> +#define VF_TAKEOVER_INT (HZ / 10) > > >> + > > >> #define VIRTNET_DRIVER_VERSION "1.0.0" > > >> > > >> static const unsigned long guest_offloads[] = { > > > Why is t...

...n particular the feature > > > bit is missing here. For now one question: > > > > > > On Mon, Dec 18, 2017 at 04:40:36PM -0800, Sridhar Samudrala wrote: > > >> @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); > > >> */ > > >> DECLARE_EWMA(pkt_len, 0, 64) > > >> > > >> +#define VF_TAKEOVER_INT (HZ / 10) > > >> + > > >> #define VIRTNET_DRIVER_VERSION "1.0.0" > > >> > > >> static const unsigned long guest_offloads[] = { > > > Why is t...

...s/net/virtio_net.c | 64 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 63 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 765920905226..6e70864f5899 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -66,6 +66,8 @@ DECLARE_EWMA(pkt_len, 0, 64) #define VIRTNET_DRIVER_VERSION "1.0.0" +static const u32 ethtool_coalesce_napi_mask = (1UL << 10); + static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, @@ -1444,7 +1446,10 @@ static int virtnet_poll_tx(struct n...

...s/net/virtio_net.c | 64 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 63 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 765920905226..6e70864f5899 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -66,6 +66,8 @@ DECLARE_EWMA(pkt_len, 0, 64) #define VIRTNET_DRIVER_VERSION "1.0.0" +static const u32 ethtool_coalesce_napi_mask = (1UL << 10); + static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, @@ -1444,7 +1446,10 @@ static int virtnet_poll_tx(struct n...

So for mergeable bufs, we use ewma machinery to guess the correct buffer size. If we don't guess correctly, XDP has to do aggressive copies. Problem is, xdp paths do not update the ewma at all, except sometimes with XDP_PASS. So whatever we happen to have before we attach XDP, will mostly stay around. The fix is probably to update ewma unconditionally. -- MST

So for mergeable bufs, we use ewma machinery to guess the correct buffer size. If we don't guess correctly, XDP has to do aggressive copies. Problem is, xdp paths do not update the ewma at all, except sometimes with XDP_PASS. So whatever we happen to have before we attach XDP, will mostly stay around. The fix is probably to update ewma unconditionally. -- MST

...+++++++++++++++++++++++++++++++++---- > 1 file changed, 65 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index e732bd6..d970c2d 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -57,6 +57,11 @@ DECLARE_EWMA(pkt_len, 0, 64) > > #define VIRTNET_DRIVER_VERSION "1.0.0" > > +const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, > + VIRTIO_NET_F_GUEST_TSO6, > + VIRTIO_NET_F_GUEST_ECN, > + VIRTIO_NET_F_GUEST_UFO }; > + > struct virtnet_sta...

...+++++++++++++++++++++++++++++++++---- > 1 file changed, 65 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index e732bd6..d970c2d 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -57,6 +57,11 @@ DECLARE_EWMA(pkt_len, 0, 64) > > #define VIRTNET_DRIVER_VERSION "1.0.0" > > +const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, > + VIRTIO_NET_F_GUEST_TSO6, > + VIRTIO_NET_F_GUEST_ECN, > + VIRTIO_NET_F_GUEST_UFO }; > + > struct virtnet_sta...

...+++++++++++++++++++++++++++++++++---- > 1 file changed, 65 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index b3fc01d..5fbd15e 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -57,6 +57,11 @@ DECLARE_EWMA(pkt_len, 0, 64) > > #define VIRTNET_DRIVER_VERSION "1.0.0" > > +const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, > + VIRTIO_NET_F_GUEST_TSO6, > + VIRTIO_NET_F_GUEST_ECN, > + VIRTIO_NET_F_GUEST_UFO }; > + > struct virtnet_sta...

...+++++++++++++++++++++++++++++++++---- > 1 file changed, 65 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c > index b3fc01d..5fbd15e 100644 > --- a/drivers/net/virtio_net.c > +++ b/drivers/net/virtio_net.c > @@ -57,6 +57,11 @@ DECLARE_EWMA(pkt_len, 0, 64) > > #define VIRTNET_DRIVER_VERSION "1.0.0" > > +const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, > + VIRTIO_NET_F_GUEST_TSO6, > + VIRTIO_NET_F_GUEST_ECN, > + VIRTIO_NET_F_GUEST_UFO }; > + > struct virtnet_sta...

...lt;linux/average.h> #include <linux/filter.h> #include <net/route.h> +#include <linux/netdevice.h> +#include <linux/netpoll.h> static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); */ DECLARE_EWMA(pkt_len, 0, 64) +#define VF_TAKEOVER_INT (HZ / 10) + #define VIRTNET_DRIVER_VERSION "1.0.0" static const unsigned long guest_offloads[] = { @@ -117,6 +121,15 @@ struct receive_queue { char name[40]; }; +struct virtnet_vf_pcpu_stats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_p...

...lt;linux/average.h> #include <linux/filter.h> #include <net/route.h> +#include <linux/netdevice.h> +#include <linux/netpoll.h> static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); */ DECLARE_EWMA(pkt_len, 0, 64) +#define VF_TAKEOVER_INT (HZ / 10) + #define VIRTNET_DRIVER_VERSION "1.0.0" static const unsigned long guest_offloads[] = { @@ -117,6 +121,15 @@ struct receive_queue { char name[40]; }; +struct virtnet_vf_pcpu_stats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_p...

.../net/virtio_net.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 94f94f3..824dd95 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -53,17 +53,6 @@ module_param(gso, bool, 0444); */ DECLARE_EWMA(pkt_len, 0, 64) -/* With mergeable buffers we align buffer address and use the low bits to - * encode its true size. Buffer size is up to 1 page so we need to align to - * square root of page size to ensure we reserve enough bits to encode the true - * size. - */ -#define MERGEABLE_BUFFER_MIN_ALI...

I'll need to look at this more, in particular the feature bit is missing here. For now one question: On Mon, Dec 18, 2017 at 04:40:36PM -0800, Sridhar Samudrala wrote: > @@ -56,6 +58,8 @@ module_param(napi_tx, bool, 0644); > */ > DECLARE_EWMA(pkt_len, 0, 64) > > +#define VF_TAKEOVER_INT (HZ / 10) > + > #define VIRTNET_DRIVER_VERSION "1.0.0" > > static const unsigned long guest_offloads[] = { Why is this delay necessary? And why by 100ms?