* [dpdk-stable] [PATCH v2] net/vhost: fix xstats wrong after clearing stats [not found] <20200902170309.16513-1-drc@linux.vnet.ibm.com> @ 2020-10-06 21:23 ` David Christensen 2020-10-09 3:13 ` Xia, Chenbo 2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen 0 siblings, 2 replies; 6+ messages in thread From: David Christensen @ 2020-10-06 21:23 UTC (permalink / raw) To: dev, maxime.coquelin, chenbo.xia, zhihong.wang Cc: stable, David Christensen, zhiyong.yang The PMD API allows stats and xstats values to be cleared separately. This is a problem for the vhost PMD since some of the xstats values are derived from existing stats values. For example: testpmd> show port xstats all ... tx_unicast_packets: 17562959 ... testpmd> clear port stats all ... show port xstats all ... tx_unicast_packets: 18446744073709551615 ... Modify the driver so that stats and xstats values are stored, updated, and cleared separately. Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") Cc: zhiyong.yang@intel.com Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> --- v2: * Removed newly unused vq loops * Added "fixes" message * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets drivers/net/vhost/rte_eth_vhost.c | 70 +++++++++++++++---------------- 1 file changed, 35 insertions(+), 35 deletions(-) diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c index e55278af6..163cf9409 100644 --- a/drivers/net/vhost/rte_eth_vhost.c +++ b/drivers/net/vhost/rte_eth_vhost.c @@ -73,6 +73,9 @@ enum vhost_xstats_pkts { VHOST_BROADCAST_PKT, VHOST_MULTICAST_PKT, VHOST_UNICAST_PKT, + VHOST_PKT, + VHOST_BYTE, + VHOST_MISSED_PKT, VHOST_ERRORS_PKT, VHOST_ERRORS_FRAGMENTED, VHOST_ERRORS_JABBER, @@ -149,11 +152,11 @@ struct vhost_xstats_name_off { /* [rx]_is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -189,11 +192,11 @@ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { /* [tx]_ is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -287,23 +290,6 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, if (n < nxstats) return nxstats; - for (i = 0; i < dev->data->nb_rx_queues; i++) { - vq = dev->data->rx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } - for (i = 0; i < dev->data->nb_tx_queues; i++) { - vq = dev->data->tx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - + vq->stats.missed_pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) { xstats[count].value = 0; for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -334,7 +320,7 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, } static inline void -vhost_count_multicast_broadcast(struct vhost_queue *vq, +vhost_count_xcast_packets(struct vhost_queue *vq, struct rte_mbuf *mbuf) { struct rte_ether_addr *ea = NULL; @@ -346,20 +332,27 @@ vhost_count_multicast_broadcast(struct vhost_queue *vq, pstats->xstats[VHOST_BROADCAST_PKT]++; else pstats->xstats[VHOST_MULTICAST_PKT]++; + } else { + pstats->xstats[VHOST_UNICAST_PKT]++; } } static void -vhost_update_packet_xstats(struct vhost_queue *vq, - struct rte_mbuf **bufs, - uint16_t count) +vhost_update_packet_xstats(struct vhost_queue *vq, struct rte_mbuf **bufs, + uint16_t count, uint64_t nb_bytes, + uint64_t nb_missed) { uint32_t pkt_len = 0; uint64_t i = 0; uint64_t index; struct vhost_stats *pstats = &vq->stats; + pstats->xstats[VHOST_BYTE] += nb_bytes; + pstats->xstats[VHOST_MISSED_PKT] += nb_missed; + pstats->xstats[VHOST_UNICAST_PKT] += nb_missed; + for (i = 0; i < count ; i++) { + pstats->xstats[VHOST_PKT]++; pkt_len = bufs[i]->pkt_len; if (pkt_len == 64) { pstats->xstats[VHOST_64_PKT]++; @@ -375,7 +368,7 @@ vhost_update_packet_xstats(struct vhost_queue *vq, else if (pkt_len > 1522) pstats->xstats[VHOST_1523_TO_MAX_PKT]++; } - vhost_count_multicast_broadcast(vq, bufs[i]); + vhost_count_xcast_packets(vq, bufs[i]); } } @@ -385,6 +378,7 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_rx = 0; uint16_t nb_receive = nb_bufs; + uint64_t nb_bytes = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -419,10 +413,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) if (r->internal->vlan_strip) rte_vlan_strip(bufs[i]); - r->stats.bytes += bufs[i]->pkt_len; + nb_bytes += bufs[i]->pkt_len; } - vhost_update_packet_xstats(r, bufs, nb_rx); + r->stats.bytes += nb_bytes; + vhost_update_packet_xstats(r, bufs, nb_rx, nb_bytes, 0); out: rte_atomic32_set(&r->while_queuing, 0); @@ -436,6 +431,8 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_tx = 0; uint16_t nb_send = 0; + uint64_t nb_bytes = 0; + uint64_t nb_missed = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -476,20 +473,23 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) break; } + for (i = 0; likely(i < nb_tx); i++) + nb_bytes += bufs[i]->pkt_len; + + nb_missed = nb_bufs - nb_tx; + r->stats.pkts += nb_tx; + r->stats.bytes += nb_bytes; r->stats.missed_pkts += nb_bufs - nb_tx; - for (i = 0; likely(i < nb_tx); i++) - r->stats.bytes += bufs[i]->pkt_len; - - vhost_update_packet_xstats(r, bufs, nb_tx); + vhost_update_packet_xstats(r, bufs, nb_tx, nb_bytes, nb_missed); /* According to RFC2863 page42 section ifHCOutMulticastPkts and * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast" * are increased when packets are not transmitted successfully. */ for (i = nb_tx; i < nb_bufs; i++) - vhost_count_multicast_broadcast(r, bufs[i]); + vhost_count_xcast_packets(r, bufs[i]); for (i = 0; likely(i < nb_tx); i++) rte_pktmbuf_free(bufs[i]); -- 2.18.4 ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dpdk-stable] [PATCH v2] net/vhost: fix xstats wrong after clearing stats 2020-10-06 21:23 ` [dpdk-stable] [PATCH v2] net/vhost: fix xstats wrong after clearing stats David Christensen @ 2020-10-09 3:13 ` Xia, Chenbo 2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen 1 sibling, 0 replies; 6+ messages in thread From: Xia, Chenbo @ 2020-10-09 3:13 UTC (permalink / raw) To: David Christensen, dev, maxime.coquelin, Wang, Zhihong Cc: stable, Yang, Zhiyong Hi David, > -----Original Message----- > From: David Christensen <drc@linux.vnet.ibm.com> > Sent: Wednesday, October 7, 2020 5:23 AM > To: dev@dpdk.org; maxime.coquelin@redhat.com; Xia, Chenbo > <chenbo.xia@intel.com>; Wang, Zhihong <zhihong.wang@intel.com> > Cc: stable@dpdk.org; David Christensen <drc@linux.vnet.ibm.com>; Yang, > Zhiyong <zhiyong.yang@intel.com> > Subject: [PATCH v2] net/vhost: fix xstats wrong after clearing stats > > The PMD API allows stats and xstats values to be cleared separately. > This is a problem for the vhost PMD since some of the xstats values are > derived from existing stats values. For example: > > testpmd> show port xstats all > ... > tx_unicast_packets: 17562959 > ... > testpmd> clear port stats all > ... > show port xstats all > ... > tx_unicast_packets: 18446744073709551615 > ... > > Modify the driver so that stats and xstats values are stored, updated, > and cleared separately. > > Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") > Cc: zhiyong.yang@intel.com Better to replace this Cc with 'Cc: stable@dpdk.org' as other fix patches do. You can cc zhiyong with git send-email command. > > Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> > --- > v2: > * Removed newly unused vq loops > * Added "fixes" message > * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets > > drivers/net/vhost/rte_eth_vhost.c | 70 +++++++++++++++---------------- > 1 file changed, 35 insertions(+), 35 deletions(-) > > diff --git a/drivers/net/vhost/rte_eth_vhost.c > b/drivers/net/vhost/rte_eth_vhost.c > index e55278af6..163cf9409 100644 > --- a/drivers/net/vhost/rte_eth_vhost.c > +++ b/drivers/net/vhost/rte_eth_vhost.c > @@ -73,6 +73,9 @@ enum vhost_xstats_pkts { > VHOST_BROADCAST_PKT, > VHOST_MULTICAST_PKT, > VHOST_UNICAST_PKT, > + VHOST_PKT, > + VHOST_BYTE, > + VHOST_MISSED_PKT, > VHOST_ERRORS_PKT, > VHOST_ERRORS_FRAGMENTED, > VHOST_ERRORS_JABBER, > @@ -149,11 +152,11 @@ struct vhost_xstats_name_off { > /* [rx]_is prepended to the name string here */ > static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { > {"good_packets", > - offsetof(struct vhost_queue, stats.pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, > {"total_bytes", > - offsetof(struct vhost_queue, stats.bytes)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, > {"missed_pkts", > - offsetof(struct vhost_queue, stats.missed_pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, > {"broadcast_packets", > offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, > {"multicast_packets", > @@ -189,11 +192,11 @@ static const struct vhost_xstats_name_off > vhost_rxport_stat_strings[] = { > /* [tx]_ is prepended to the name string here */ > static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { > {"good_packets", > - offsetof(struct vhost_queue, stats.pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, > {"total_bytes", > - offsetof(struct vhost_queue, stats.bytes)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, > {"missed_pkts", > - offsetof(struct vhost_queue, stats.missed_pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, > {"broadcast_packets", > offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, > {"multicast_packets", > @@ -287,23 +290,6 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct > rte_eth_xstat *xstats, > if (n < nxstats) > return nxstats; > > - for (i = 0; i < dev->data->nb_rx_queues; i++) { > - vq = dev->data->rx_queues[i]; > - if (!vq) > - continue; > - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts > - - (vq->stats.xstats[VHOST_BROADCAST_PKT] > - + vq->stats.xstats[VHOST_MULTICAST_PKT]); > - } > - for (i = 0; i < dev->data->nb_tx_queues; i++) { > - vq = dev->data->tx_queues[i]; > - if (!vq) > - continue; > - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts > - + vq->stats.missed_pkts > - - (vq->stats.xstats[VHOST_BROADCAST_PKT] > - + vq->stats.xstats[VHOST_MULTICAST_PKT]); > - } > for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) { > xstats[count].value = 0; > for (i = 0; i < dev->data->nb_rx_queues; i++) { > @@ -334,7 +320,7 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct > rte_eth_xstat *xstats, > } > > static inline void > -vhost_count_multicast_broadcast(struct vhost_queue *vq, > +vhost_count_xcast_packets(struct vhost_queue *vq, > struct rte_mbuf *mbuf) > { > struct rte_ether_addr *ea = NULL; > @@ -346,20 +332,27 @@ vhost_count_multicast_broadcast(struct vhost_queue > *vq, > pstats->xstats[VHOST_BROADCAST_PKT]++; > else > pstats->xstats[VHOST_MULTICAST_PKT]++; > + } else { > + pstats->xstats[VHOST_UNICAST_PKT]++; > } > } > > static void > -vhost_update_packet_xstats(struct vhost_queue *vq, > - struct rte_mbuf **bufs, > - uint16_t count) > +vhost_update_packet_xstats(struct vhost_queue *vq, struct rte_mbuf **bufs, > + uint16_t count, uint64_t nb_bytes, > + uint64_t nb_missed) > { > uint32_t pkt_len = 0; > uint64_t i = 0; > uint64_t index; > struct vhost_stats *pstats = &vq->stats; > > + pstats->xstats[VHOST_BYTE] += nb_bytes; > + pstats->xstats[VHOST_MISSED_PKT] += nb_missed; > + pstats->xstats[VHOST_UNICAST_PKT] += nb_missed; > + > for (i = 0; i < count ; i++) { > + pstats->xstats[VHOST_PKT]++; > pkt_len = bufs[i]->pkt_len; > if (pkt_len == 64) { > pstats->xstats[VHOST_64_PKT]++; > @@ -375,7 +368,7 @@ vhost_update_packet_xstats(struct vhost_queue *vq, > else if (pkt_len > 1522) > pstats->xstats[VHOST_1523_TO_MAX_PKT]++; > } > - vhost_count_multicast_broadcast(vq, bufs[i]); > + vhost_count_xcast_packets(vq, bufs[i]); > } > } > > @@ -385,6 +378,7 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t > nb_bufs) > struct vhost_queue *r = q; > uint16_t i, nb_rx = 0; > uint16_t nb_receive = nb_bufs; > + uint64_t nb_bytes = 0; > > if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) > return 0; > @@ -419,10 +413,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, > uint16_t nb_bufs) > if (r->internal->vlan_strip) > rte_vlan_strip(bufs[i]); > > - r->stats.bytes += bufs[i]->pkt_len; > + nb_bytes += bufs[i]->pkt_len; > } > > - vhost_update_packet_xstats(r, bufs, nb_rx); > + r->stats.bytes += nb_bytes; > + vhost_update_packet_xstats(r, bufs, nb_rx, nb_bytes, 0); > > out: > rte_atomic32_set(&r->while_queuing, 0); > @@ -436,6 +431,8 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t > nb_bufs) > struct vhost_queue *r = q; > uint16_t i, nb_tx = 0; > uint16_t nb_send = 0; > + uint64_t nb_bytes = 0; > + uint64_t nb_missed = 0; > > if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) > return 0; > @@ -476,20 +473,23 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, > uint16_t nb_bufs) > break; > } > > + for (i = 0; likely(i < nb_tx); i++) > + nb_bytes += bufs[i]->pkt_len; > + > + nb_missed = nb_bufs - nb_tx; > + > r->stats.pkts += nb_tx; > + r->stats.bytes += nb_bytes; > r->stats.missed_pkts += nb_bufs - nb_tx; > > - for (i = 0; likely(i < nb_tx); i++) > - r->stats.bytes += bufs[i]->pkt_len; > - > - vhost_update_packet_xstats(r, bufs, nb_tx); > + vhost_update_packet_xstats(r, bufs, nb_tx, nb_bytes, nb_missed); > > /* According to RFC2863 page42 section ifHCOutMulticastPkts and > * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast" > * are increased when packets are not transmitted successfully. > */ I think the above comment should be updated because in the below function, we also update unicast pkts too (Based on RFC2863). Thanks! Chenbo > for (i = nb_tx; i < nb_bufs; i++) > - vhost_count_multicast_broadcast(r, bufs[i]); > + vhost_count_xcast_packets(r, bufs[i]); > > for (i = 0; likely(i < nb_tx); i++) > rte_pktmbuf_free(bufs[i]); > -- > 2.18.4 ^ permalink raw reply [flat|nested] 6+ messages in thread
* [dpdk-stable] [PATCH v3] net/vhost: fix xstats wrong after clearing stats 2020-10-06 21:23 ` [dpdk-stable] [PATCH v2] net/vhost: fix xstats wrong after clearing stats David Christensen 2020-10-09 3:13 ` Xia, Chenbo @ 2020-10-15 17:49 ` David Christensen 2020-10-16 1:38 ` Xia, Chenbo ` (2 more replies) 1 sibling, 3 replies; 6+ messages in thread From: David Christensen @ 2020-10-15 17:49 UTC (permalink / raw) To: dev, maxime.coquelin, chenbo.xia, zhihong.wang; +Cc: stable, David Christensen The PMD API allows stats and xstats values to be cleared separately. This is a problem for the vhost PMD since some of the xstats values are derived from existing stats values. For example: testpmd> show port xstats all ... tx_unicast_packets: 17562959 ... testpmd> clear port stats all ... show port xstats all ... tx_unicast_packets: 18446744073709551615 ... Modify the driver so that stats and xstats values are stored, updated, and cleared separately. Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") Cc: stable@dpdk.org Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> --- v3: * Modified comment that unicast packets include unsent packets * Change Cc: to stable@dpdk.org v2: * Removed newly unused vq loops * Added "fixes" message * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets drivers/net/vhost/rte_eth_vhost.c | 76 +++++++++++++++---------------- 1 file changed, 38 insertions(+), 38 deletions(-) diff --git a/drivers/net/vhost/rte_eth_vhost.c b/drivers/net/vhost/rte_eth_vhost.c index e55278af6..886b3afe0 100644 --- a/drivers/net/vhost/rte_eth_vhost.c +++ b/drivers/net/vhost/rte_eth_vhost.c @@ -73,6 +73,9 @@ enum vhost_xstats_pkts { VHOST_BROADCAST_PKT, VHOST_MULTICAST_PKT, VHOST_UNICAST_PKT, + VHOST_PKT, + VHOST_BYTE, + VHOST_MISSED_PKT, VHOST_ERRORS_PKT, VHOST_ERRORS_FRAGMENTED, VHOST_ERRORS_JABBER, @@ -149,11 +152,11 @@ struct vhost_xstats_name_off { /* [rx]_is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -189,11 +192,11 @@ static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { /* [tx]_ is prepended to the name string here */ static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { {"good_packets", - offsetof(struct vhost_queue, stats.pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, {"total_bytes", - offsetof(struct vhost_queue, stats.bytes)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, {"missed_pkts", - offsetof(struct vhost_queue, stats.missed_pkts)}, + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, {"broadcast_packets", offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, {"multicast_packets", @@ -287,23 +290,6 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, if (n < nxstats) return nxstats; - for (i = 0; i < dev->data->nb_rx_queues; i++) { - vq = dev->data->rx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } - for (i = 0; i < dev->data->nb_tx_queues; i++) { - vq = dev->data->tx_queues[i]; - if (!vq) - continue; - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts - + vq->stats.missed_pkts - - (vq->stats.xstats[VHOST_BROADCAST_PKT] - + vq->stats.xstats[VHOST_MULTICAST_PKT]); - } for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) { xstats[count].value = 0; for (i = 0; i < dev->data->nb_rx_queues; i++) { @@ -334,7 +320,7 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct rte_eth_xstat *xstats, } static inline void -vhost_count_multicast_broadcast(struct vhost_queue *vq, +vhost_count_xcast_packets(struct vhost_queue *vq, struct rte_mbuf *mbuf) { struct rte_ether_addr *ea = NULL; @@ -346,20 +332,27 @@ vhost_count_multicast_broadcast(struct vhost_queue *vq, pstats->xstats[VHOST_BROADCAST_PKT]++; else pstats->xstats[VHOST_MULTICAST_PKT]++; + } else { + pstats->xstats[VHOST_UNICAST_PKT]++; } } static void -vhost_update_packet_xstats(struct vhost_queue *vq, - struct rte_mbuf **bufs, - uint16_t count) +vhost_update_packet_xstats(struct vhost_queue *vq, struct rte_mbuf **bufs, + uint16_t count, uint64_t nb_bytes, + uint64_t nb_missed) { uint32_t pkt_len = 0; uint64_t i = 0; uint64_t index; struct vhost_stats *pstats = &vq->stats; + pstats->xstats[VHOST_BYTE] += nb_bytes; + pstats->xstats[VHOST_MISSED_PKT] += nb_missed; + pstats->xstats[VHOST_UNICAST_PKT] += nb_missed; + for (i = 0; i < count ; i++) { + pstats->xstats[VHOST_PKT]++; pkt_len = bufs[i]->pkt_len; if (pkt_len == 64) { pstats->xstats[VHOST_64_PKT]++; @@ -375,7 +368,7 @@ vhost_update_packet_xstats(struct vhost_queue *vq, else if (pkt_len > 1522) pstats->xstats[VHOST_1523_TO_MAX_PKT]++; } - vhost_count_multicast_broadcast(vq, bufs[i]); + vhost_count_xcast_packets(vq, bufs[i]); } } @@ -385,6 +378,7 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_rx = 0; uint16_t nb_receive = nb_bufs; + uint64_t nb_bytes = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -419,10 +413,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) if (r->internal->vlan_strip) rte_vlan_strip(bufs[i]); - r->stats.bytes += bufs[i]->pkt_len; + nb_bytes += bufs[i]->pkt_len; } - vhost_update_packet_xstats(r, bufs, nb_rx); + r->stats.bytes += nb_bytes; + vhost_update_packet_xstats(r, bufs, nb_rx, nb_bytes, 0); out: rte_atomic32_set(&r->while_queuing, 0); @@ -436,6 +431,8 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) struct vhost_queue *r = q; uint16_t i, nb_tx = 0; uint16_t nb_send = 0; + uint64_t nb_bytes = 0; + uint64_t nb_missed = 0; if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) return 0; @@ -476,20 +473,23 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t nb_bufs) break; } + for (i = 0; likely(i < nb_tx); i++) + nb_bytes += bufs[i]->pkt_len; + + nb_missed = nb_bufs - nb_tx; + r->stats.pkts += nb_tx; + r->stats.bytes += nb_bytes; r->stats.missed_pkts += nb_bufs - nb_tx; - for (i = 0; likely(i < nb_tx); i++) - r->stats.bytes += bufs[i]->pkt_len; - - vhost_update_packet_xstats(r, bufs, nb_tx); + vhost_update_packet_xstats(r, bufs, nb_tx, nb_bytes, nb_missed); - /* According to RFC2863 page42 section ifHCOutMulticastPkts and - * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast" - * are increased when packets are not transmitted successfully. + /* According to RFC2863, ifHCOutUcastPkts, ifHCOutMulticastPkts and + * ifHCOutBroadcastPkts counters are increased when packets are not + * transmitted successfully. */ for (i = nb_tx; i < nb_bufs; i++) - vhost_count_multicast_broadcast(r, bufs[i]); + vhost_count_xcast_packets(r, bufs[i]); for (i = 0; likely(i < nb_tx); i++) rte_pktmbuf_free(bufs[i]); -- 2.18.4 ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dpdk-stable] [PATCH v3] net/vhost: fix xstats wrong after clearing stats 2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen @ 2020-10-16 1:38 ` Xia, Chenbo 2020-10-23 10:54 ` Maxime Coquelin 2020-10-23 11:22 ` Maxime Coquelin 2 siblings, 0 replies; 6+ messages in thread From: Xia, Chenbo @ 2020-10-16 1:38 UTC (permalink / raw) To: David Christensen, dev, maxime.coquelin, Wang, Zhihong; +Cc: stable > -----Original Message----- > From: David Christensen <drc@linux.vnet.ibm.com> > Sent: Friday, October 16, 2020 1:50 AM > To: dev@dpdk.org; maxime.coquelin@redhat.com; Xia, Chenbo > <chenbo.xia@intel.com>; Wang, Zhihong <zhihong.wang@intel.com> > Cc: stable@dpdk.org; David Christensen <drc@linux.vnet.ibm.com> > Subject: [PATCH v3] net/vhost: fix xstats wrong after clearing stats > > The PMD API allows stats and xstats values to be cleared separately. > This is a problem for the vhost PMD since some of the xstats values are > derived from existing stats values. For example: > > testpmd> show port xstats all > ... > tx_unicast_packets: 17562959 > ... > testpmd> clear port stats all > ... > show port xstats all > ... > tx_unicast_packets: 18446744073709551615 > ... > > Modify the driver so that stats and xstats values are stored, updated, > and cleared separately. > > Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") > Cc: stable@dpdk.org > > Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> > --- > v3: > * Modified comment that unicast packets include unsent packets > * Change Cc: to stable@dpdk.org > v2: > * Removed newly unused vq loops > * Added "fixes" message > * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets > > drivers/net/vhost/rte_eth_vhost.c | 76 +++++++++++++++---------------- > 1 file changed, 38 insertions(+), 38 deletions(-) > > diff --git a/drivers/net/vhost/rte_eth_vhost.c > b/drivers/net/vhost/rte_eth_vhost.c > index e55278af6..886b3afe0 100644 > --- a/drivers/net/vhost/rte_eth_vhost.c > +++ b/drivers/net/vhost/rte_eth_vhost.c > @@ -73,6 +73,9 @@ enum vhost_xstats_pkts { > VHOST_BROADCAST_PKT, > VHOST_MULTICAST_PKT, > VHOST_UNICAST_PKT, > + VHOST_PKT, > + VHOST_BYTE, > + VHOST_MISSED_PKT, > VHOST_ERRORS_PKT, > VHOST_ERRORS_FRAGMENTED, > VHOST_ERRORS_JABBER, > @@ -149,11 +152,11 @@ struct vhost_xstats_name_off { > /* [rx]_is prepended to the name string here */ > static const struct vhost_xstats_name_off vhost_rxport_stat_strings[] = { > {"good_packets", > - offsetof(struct vhost_queue, stats.pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, > {"total_bytes", > - offsetof(struct vhost_queue, stats.bytes)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, > {"missed_pkts", > - offsetof(struct vhost_queue, stats.missed_pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, > {"broadcast_packets", > offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, > {"multicast_packets", > @@ -189,11 +192,11 @@ static const struct vhost_xstats_name_off > vhost_rxport_stat_strings[] = { > /* [tx]_ is prepended to the name string here */ > static const struct vhost_xstats_name_off vhost_txport_stat_strings[] = { > {"good_packets", > - offsetof(struct vhost_queue, stats.pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_PKT])}, > {"total_bytes", > - offsetof(struct vhost_queue, stats.bytes)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_BYTE])}, > {"missed_pkts", > - offsetof(struct vhost_queue, stats.missed_pkts)}, > + offsetof(struct vhost_queue, stats.xstats[VHOST_MISSED_PKT])}, > {"broadcast_packets", > offsetof(struct vhost_queue, stats.xstats[VHOST_BROADCAST_PKT])}, > {"multicast_packets", > @@ -287,23 +290,6 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct > rte_eth_xstat *xstats, > if (n < nxstats) > return nxstats; > > - for (i = 0; i < dev->data->nb_rx_queues; i++) { > - vq = dev->data->rx_queues[i]; > - if (!vq) > - continue; > - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts > - - (vq->stats.xstats[VHOST_BROADCAST_PKT] > - + vq->stats.xstats[VHOST_MULTICAST_PKT]); > - } > - for (i = 0; i < dev->data->nb_tx_queues; i++) { > - vq = dev->data->tx_queues[i]; > - if (!vq) > - continue; > - vq->stats.xstats[VHOST_UNICAST_PKT] = vq->stats.pkts > - + vq->stats.missed_pkts > - - (vq->stats.xstats[VHOST_BROADCAST_PKT] > - + vq->stats.xstats[VHOST_MULTICAST_PKT]); > - } > for (t = 0; t < VHOST_NB_XSTATS_RXPORT; t++) { > xstats[count].value = 0; > for (i = 0; i < dev->data->nb_rx_queues; i++) { > @@ -334,7 +320,7 @@ vhost_dev_xstats_get(struct rte_eth_dev *dev, struct > rte_eth_xstat *xstats, > } > > static inline void > -vhost_count_multicast_broadcast(struct vhost_queue *vq, > +vhost_count_xcast_packets(struct vhost_queue *vq, > struct rte_mbuf *mbuf) > { > struct rte_ether_addr *ea = NULL; > @@ -346,20 +332,27 @@ vhost_count_multicast_broadcast(struct vhost_queue > *vq, > pstats->xstats[VHOST_BROADCAST_PKT]++; > else > pstats->xstats[VHOST_MULTICAST_PKT]++; > + } else { > + pstats->xstats[VHOST_UNICAST_PKT]++; > } > } > > static void > -vhost_update_packet_xstats(struct vhost_queue *vq, > - struct rte_mbuf **bufs, > - uint16_t count) > +vhost_update_packet_xstats(struct vhost_queue *vq, struct rte_mbuf **bufs, > + uint16_t count, uint64_t nb_bytes, > + uint64_t nb_missed) > { > uint32_t pkt_len = 0; > uint64_t i = 0; > uint64_t index; > struct vhost_stats *pstats = &vq->stats; > > + pstats->xstats[VHOST_BYTE] += nb_bytes; > + pstats->xstats[VHOST_MISSED_PKT] += nb_missed; > + pstats->xstats[VHOST_UNICAST_PKT] += nb_missed; > + > for (i = 0; i < count ; i++) { > + pstats->xstats[VHOST_PKT]++; > pkt_len = bufs[i]->pkt_len; > if (pkt_len == 64) { > pstats->xstats[VHOST_64_PKT]++; > @@ -375,7 +368,7 @@ vhost_update_packet_xstats(struct vhost_queue *vq, > else if (pkt_len > 1522) > pstats->xstats[VHOST_1523_TO_MAX_PKT]++; > } > - vhost_count_multicast_broadcast(vq, bufs[i]); > + vhost_count_xcast_packets(vq, bufs[i]); > } > } > > @@ -385,6 +378,7 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, uint16_t > nb_bufs) > struct vhost_queue *r = q; > uint16_t i, nb_rx = 0; > uint16_t nb_receive = nb_bufs; > + uint64_t nb_bytes = 0; > > if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) > return 0; > @@ -419,10 +413,11 @@ eth_vhost_rx(void *q, struct rte_mbuf **bufs, > uint16_t nb_bufs) > if (r->internal->vlan_strip) > rte_vlan_strip(bufs[i]); > > - r->stats.bytes += bufs[i]->pkt_len; > + nb_bytes += bufs[i]->pkt_len; > } > > - vhost_update_packet_xstats(r, bufs, nb_rx); > + r->stats.bytes += nb_bytes; > + vhost_update_packet_xstats(r, bufs, nb_rx, nb_bytes, 0); > > out: > rte_atomic32_set(&r->while_queuing, 0); > @@ -436,6 +431,8 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, uint16_t > nb_bufs) > struct vhost_queue *r = q; > uint16_t i, nb_tx = 0; > uint16_t nb_send = 0; > + uint64_t nb_bytes = 0; > + uint64_t nb_missed = 0; > > if (unlikely(rte_atomic32_read(&r->allow_queuing) == 0)) > return 0; > @@ -476,20 +473,23 @@ eth_vhost_tx(void *q, struct rte_mbuf **bufs, > uint16_t nb_bufs) > break; > } > > + for (i = 0; likely(i < nb_tx); i++) > + nb_bytes += bufs[i]->pkt_len; > + > + nb_missed = nb_bufs - nb_tx; > + > r->stats.pkts += nb_tx; > + r->stats.bytes += nb_bytes; > r->stats.missed_pkts += nb_bufs - nb_tx; > > - for (i = 0; likely(i < nb_tx); i++) > - r->stats.bytes += bufs[i]->pkt_len; > - > - vhost_update_packet_xstats(r, bufs, nb_tx); > + vhost_update_packet_xstats(r, bufs, nb_tx, nb_bytes, nb_missed); > > - /* According to RFC2863 page42 section ifHCOutMulticastPkts and > - * ifHCOutBroadcastPkts, the counters "multicast" and "broadcast" > - * are increased when packets are not transmitted successfully. > + /* According to RFC2863, ifHCOutUcastPkts, ifHCOutMulticastPkts and > + * ifHCOutBroadcastPkts counters are increased when packets are not > + * transmitted successfully. > */ > for (i = nb_tx; i < nb_bufs; i++) > - vhost_count_multicast_broadcast(r, bufs[i]); > + vhost_count_xcast_packets(r, bufs[i]); > > for (i = 0; likely(i < nb_tx); i++) > rte_pktmbuf_free(bufs[i]); > -- > 2.18.4 Reviewed-by: Chenbo Xia <chenbo.xia@intel.com> ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dpdk-stable] [PATCH v3] net/vhost: fix xstats wrong after clearing stats 2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen 2020-10-16 1:38 ` Xia, Chenbo @ 2020-10-23 10:54 ` Maxime Coquelin 2020-10-23 11:22 ` Maxime Coquelin 2 siblings, 0 replies; 6+ messages in thread From: Maxime Coquelin @ 2020-10-23 10:54 UTC (permalink / raw) To: David Christensen, dev, chenbo.xia, zhihong.wang; +Cc: stable On 10/15/20 7:49 PM, David Christensen wrote: > The PMD API allows stats and xstats values to be cleared separately. > This is a problem for the vhost PMD since some of the xstats values are > derived from existing stats values. For example: > > testpmd> show port xstats all > ... > tx_unicast_packets: 17562959 > ... > testpmd> clear port stats all > ... > show port xstats all > ... > tx_unicast_packets: 18446744073709551615 > ... > > Modify the driver so that stats and xstats values are stored, updated, > and cleared separately. > > Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") > Cc: stable@dpdk.org > > Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> > --- > v3: > * Modified comment that unicast packets include unsent packets > * Change Cc: to stable@dpdk.org > v2: > * Removed newly unused vq loops > * Added "fixes" message > * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets > > drivers/net/vhost/rte_eth_vhost.c | 76 +++++++++++++++---------------- > 1 file changed, 38 insertions(+), 38 deletions(-) > Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Thanks, Maxime ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [dpdk-stable] [PATCH v3] net/vhost: fix xstats wrong after clearing stats 2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen 2020-10-16 1:38 ` Xia, Chenbo 2020-10-23 10:54 ` Maxime Coquelin @ 2020-10-23 11:22 ` Maxime Coquelin 2 siblings, 0 replies; 6+ messages in thread From: Maxime Coquelin @ 2020-10-23 11:22 UTC (permalink / raw) To: David Christensen, dev, chenbo.xia, zhihong.wang; +Cc: stable On 10/15/20 7:49 PM, David Christensen wrote: > The PMD API allows stats and xstats values to be cleared separately. > This is a problem for the vhost PMD since some of the xstats values are > derived from existing stats values. For example: > > testpmd> show port xstats all > ... > tx_unicast_packets: 17562959 > ... > testpmd> clear port stats all > ... > show port xstats all > ... > tx_unicast_packets: 18446744073709551615 > ... > > Modify the driver so that stats and xstats values are stored, updated, > and cleared separately. > > Fixes: 4d6cf2ac93dc ("net/vhost: add extended statistics") > Cc: stable@dpdk.org > > Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> > --- > v3: > * Modified comment that unicast packets include unsent packets > * Change Cc: to stable@dpdk.org > v2: > * Removed newly unused vq loops > * Added "fixes" message > * Renamed vhost_count_multicast_broadcast to vhost_count_xcast_packets > > drivers/net/vhost/rte_eth_vhost.c | 76 +++++++++++++++---------------- > 1 file changed, 38 insertions(+), 38 deletions(-) Applied to dpdk-next-virtio/main. Thanks, Maxime ^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2020-10-23 11:22 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20200902170309.16513-1-drc@linux.vnet.ibm.com>
2020-10-06 21:23 ` [dpdk-stable] [PATCH v2] net/vhost: fix xstats wrong after clearing stats David Christensen
2020-10-09 3:13 ` Xia, Chenbo
2020-10-15 17:49 ` [dpdk-stable] [PATCH v3] " David Christensen
2020-10-16 1:38 ` Xia, Chenbo
2020-10-23 10:54 ` Maxime Coquelin
2020-10-23 11:22 ` Maxime Coquelin
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).