From: x-fn-spp@sl.ntt-tx.co.jp
To: spp@dpdk.org
Subject: [spp] [PATCH 16/30] doc: add description for explanation section
Date: Tue, 16 Jan 2018 14:16:27 +0900 [thread overview]
Message-ID: <201801160516.w0G5GgGH009170@imss03.silk.ntt-tx.co.jp> (raw)
In-Reply-To: <3e13a243-6c3f-d849-f2f4-67732e5a44cb@intel.com>
From: Hiroyuki Nakamura <nakamura.hioryuki@po.ntt-tx.co.jp>
Add details explanation for essential parts of spp_vf for
developers.
Signed-off-by: Naoki Takada <takada.naoki@lab.ntt.co.jp>
---
docs/spp_vf/spp_vf.md | 221 ++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 214 insertions(+), 7 deletions(-)
diff --git a/docs/spp_vf/spp_vf.md b/docs/spp_vf/spp_vf.md
index 786e712..19ea403 100644
--- a/docs/spp_vf/spp_vf.md
+++ b/docs/spp_vf/spp_vf.md
@@ -4,8 +4,8 @@ SPP_VF is a SR-IOV like network functionality using DPDK for NFV.
## Overview
-The application distributes incoming packets depends on MAC address
-similar to SR-IOV functionality.
+The application distributes incoming packets referring virtual MAC
+address similar to SR-IOV functionality.
Network configuration is defined in JSON config file which is imported
while launching the application.
The configuration is able to change after initialization by sending
@@ -13,14 +13,14 @@ commnad from spp controller.
SPP_VF is a multi-thread application.
It consists of manager thread and forwarder threads.
-There are three types of forwarder for 1:1, 1:N and N:1.
+There are three types of forwarder for 1:1, 1:N and N:1 as following.
* forward: 1:1
* classifier_mac: 1:N (Destination is determined by MAC address)
* merge: N:1
This is an example of network configration, in which one classifier_mac,
-one merger and four forwarders are runnig in spp_vf process for two
+one merger and four forwarders are runnig in SPP_VF process for two
destinations of vhost interface.
Incoming packets from rx on host1 are sent to each of vhosts on guest
by looking MAC address in the packet..
@@ -95,9 +95,15 @@ file and return json_t object as a result.
In spp_config_load_file(), configuration of classifier table and
resource assignment of threads are loaded into config of spp.
-After importing config, each of threads are launched.
+### Forwarding
+
+SPP_VF supports three types of forwarding, for 1:1, 1:N and N:1.
+After importing config, each of forwarding threads are launched
+from`rte_eal_remote_launch()`.
```c
+ /* spp_vf.c */
+
/* Start thread */
unsigned int lcore_id = 0;
RTE_LCORE_FOREACH_SLAVE(lcore_id) {
@@ -113,9 +119,210 @@ After importing config, each of threads are launched.
}
```
-### Forwarding
+`spp_classifier_mac_do()` is a forwarding function of 1:N defined in
+`classifier_mac.c`.
+Configuration of destination is managed as a table structured info.
+`classifier_mac_info` and `classifier_mac_mng_info` struct are for
+the purpose.
+
+TODO(yasufum) add desc for table structure and it's doubled for
+redundancy.
+
+ ```c
+ /* classifier_mac.c */
+
+ /* classifier information */
+ struct classifier_mac_info {
+ struct rte_hash *classifier_table;
+ int num_active_classified;
+ int active_classifieds[RTE_MAX_ETHPORTS];
+ int default_classified;
+ };
+
+ /* classifier management information */
+ struct classifier_mac_mng_info {
+ struct classifier_mac_info info[NUM_CLASSIFIER_MAC_INFO];
+ volatile int ref_index;
+ volatile int upd_index;
+ struct classified_data classified_data[RTE_MAX_ETHPORTS];
+ };
+ ```
+
+In `spp_classifier_mac_do()`, it receives packets from rx port and send them
+to destinations with `classify_packet()`.
+`classifier_info` is an argument of `classify_packet()` and is used to decide
+the destinations.
+
+ ```c
+ /* classifier_mac.c */
+
+ while(likely(core_info->status == SPP_CORE_IDLE) ||
+ likely(core_info->status == SPP_CORE_FORWARD)) {
+
+ while(likely(core_info->status == SPP_CORE_FORWARD)) {
+ /* change index of update side */
+ change_update_index(classifier_mng_info, lcore_id);
+
+ /* decide classifier infomation of the current cycle */
+ classifier_info = classifier_mng_info->info +
+ classifier_mng_info->ref_index;
+
+ /* drain tx packets, if buffer is not filled for interval */
+ cur_tsc = rte_rdtsc();
+ if (unlikely(cur_tsc - prev_tsc > drain_tsc)) {
+ for (i = 0; i < n_classified_data; i++) {
+ if (unlikely(classified_data[i].num_pkt != 0)) {
+ RTE_LOG(DEBUG, SPP_CLASSIFIER_MAC,
+ "transimit packets (drain). "
+ "index=%d, "
+ "num_pkt=%hu, "
+ "interval=%lu\n",
+ i,
+ classified_data[i].num_pkt,
+ cur_tsc - prev_tsc);
+ transmit_packet(&classified_data[i]);
+ }
+ }
+ prev_tsc = cur_tsc;
+ }
+
+ /* retrieve packets */
+ n_rx = rte_eth_rx_burst(core_info->rx_ports[0].dpdk_port, 0,
+ rx_pkts, MAX_PKT_BURST);
+ if (unlikely(n_rx == 0))
+ continue;
+
+#ifdef SPP_RINGLATENCYSTATS_ENABLE
+ if (core_info->rx_ports[0].if_type == RING)
+ spp_ringlatencystats_calculate_latency(
+ core_info->rx_ports[0].if_no, rx_pkts, n_rx);
+#endif
+
+ /* classify and transmit (filled) */
+ classify_packet(rx_pkts, n_rx, classifier_info, classified_data);
+ }
+ }
+ ```
+
+On the other hand, `spp_forward` is for 1:1 or N:1 (called as merge)
+forwarding defined in `spp_forward.c`.
+Source and destination ports are decided from `core_info`
+and given to `set_use_interface()` in which first argment is
+destination info and second one is source.
+
+ ```c
+ /* spp_forward.c */
+
+ /* RX/TX Info setting */
+ rxtx_num = core_info->num_rx_port;
+ for (if_cnt = 0; if_cnt < rxtx_num; if_cnt++) {
+ set_use_interface(&patch[if_cnt].rx,
+ &core_info->rx_ports[if_cnt]);
+ if (core_info->type == SPP_CONFIG_FORWARD) {
+ /* FORWARD */
+ set_use_interface(&patch[if_cnt].tx,
+ &core_info->tx_ports[if_cnt]);
+ } else {
+ /* MERGE */
+ set_use_interface(&patch[if_cnt].tx,
+ &core_info->tx_ports[0]);
+ }
+ }
+ ```
+
+ After ports are decided, forwarding is executed.
+
+ ```c
+ /* spp_forward.c */
+
+ int cnt, nb_rx, nb_tx, buf;
+ struct spp_core_port_info *rx;
+ struct spp_core_port_info *tx;
+ struct rte_mbuf *bufs[MAX_PKT_BURST];
+ while (likely(core_info->status == SPP_CORE_IDLE) ||
+ likely(core_info->status == SPP_CORE_FORWARD)) {
+ while (likely(core_info->status == SPP_CORE_FORWARD)) {
+ for (cnt = 0; cnt < rxtx_num; cnt++) {
+ rx = &patch[cnt].rx;
+ tx = &patch[cnt].tx;
+
+ /* Packet receive */
+ nb_rx = rte_eth_rx_burst(rx->dpdk_port, 0, bufs, MAX_PKT_BURST);
+ if (unlikely(nb_rx == 0)) {
+ continue;
+ }
+
+#ifdef SPP_RINGLATENCYSTATS_ENABLE
+ if (rx->if_type == RING) {
+ /* Receive port is RING */
+ spp_ringlatencystats_calculate_latency(rx->if_no,
+ bufs, nb_rx);
+ }
+ if (tx->if_type == RING) {
+ /* Send port is RING */
+ spp_ringlatencystats_add_time_stamp(tx->if_no,
+ bufs, nb_rx);
+ }
+#endif /* SPP_RINGLATENCYSTATS_ENABLE */
+
+ /* Send packet */
+ nb_tx = rte_eth_tx_burst(tx->dpdk_port, 0, bufs, nb_rx);
+
+ /* Free any unsent packets. */
+ if (unlikely(nb_tx < nb_rx)) {
+ for (buf = nb_tx; buf < nb_rx; buf++) {
+ rte_pktmbuf_free(bufs[buf]);
+ }
+ }
+ }
+ }
+ }
+ ```
+### L2 Multicast Support
-### Packet Cloning
+Multicast for resolving ARP requests is also supported in SPP_VF.
+It is implemented as `handle_l2multicast_packet()` and called from
+`classify_packet()` for incoming multicast packets.
+ ```c
+ /* classify_packet() in classifier_mac.c */
+
+ /* L2 multicast(include broadcast) ? */
+ if (unlikely(is_multicast_ether_addr(ð->d_addr))) {
+ RTE_LOG(DEBUG, SPP_CLASSIFIER_MAC,
+ "multicast mac address.\n");
+ handle_l2multicast_packet(rx_pkts[i],
+ classifier_info, classified_data);
+ continue;
+ }
+ ```
+
+For distributing multicast packet, it is cloned with
+`rte_mbuf_refcnt_update()`.
+ ```c
+ /* classifier_mac.c */
+
+ /* handle L2 multicast(include broadcast) packet */
+ static inline void
+ handle_l2multicast_packet(struct rte_mbuf *pkt,
+ struct classifier_mac_info *classifier_info,
+ struct classified_data *classified_data)
+ {
+ int i;
+
+ if (unlikely(classifier_info->num_active_classified == 0)) {
+ RTE_LOG(ERR, SPP_CLASSIFIER_MAC, "No mac address.(l2multicast packet)\n");
+ rte_pktmbuf_free(pkt);
+ return;
+ }
+
+ rte_mbuf_refcnt_update(pkt, classifier_info->num_active_classified);
+
+ for (i= 0; i < classifier_info->num_active_classified; i++) {
+ push_packet(pkt, classified_data +
+ (long)classifier_info->active_classifieds[i]);
+ }
+ }
+ ```
--
1.9.1
next prev parent reply other threads:[~2018-01-16 5:16 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-25 4:41 [spp] Proposal - spp_vf(SR-IOV like feature) addition to SPP Nakamura Hioryuki
2017-12-26 1:54 ` Yasufumi Ogawa
2017-12-28 4:55 ` [spp] [PATCH 01/57] spp_vf: add vf functions x-fn-spp
2017-12-28 8:49 ` Yasufumi Ogawa
2017-12-28 4:55 ` [spp] [PATCH 02/57] spp_vf: support multi process x-fn-spp
2018-02-07 16:50 ` Ferruh Yigit
2018-02-08 1:21 ` Yasufumi Ogawa
2018-02-08 6:44 ` [spp] [spp 02168] " Nakamura Hioryuki
2017-12-28 4:55 ` [spp] [PATCH 03/57] spp_vf: comment out check of using cores x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 04/57] spp_vf: modify classifier for upd command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 05/57] spp_vf: add procedure that mac address is null x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 06/57] spp_vf: change config format for upd command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 07/57] spp_vf: fix compiler warning in classifier_mac.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 08/57] spp_vf: modify data struct for upd command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 09/57] spp_vf: add functions of command acceptance x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 10/57] spp_vf: add command acceptance calling x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 11/57] spp_vf: fix compiler warning in command_proc.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 12/57] " x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 13/57] spp_vf: refactor command acceptance/decode x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 14/57] spp_vf: fix return value overwrite problem x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 15/57] spp_vf: initialize message buffer x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 16/57] spp_vf: add const keyword to parameter x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 17/57] spp_vf: fix wrong comparison operator x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 18/57] spp_vf: fix wrong variable to be assigned x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 19/57] spp_vf: refactor parsing server ip address x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 20/57] spp_vf: fix error in command decode x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 21/57] spp_vf: fix comparison operator in spp_vf.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 22/57] spp_vf: check upper limit to the number of process x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 23/57] spp_vf: display usage message x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 24/57] spp_vf: split command processing source file x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 25/57] spp_vf: add new log and line break x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 26/57] spp_vf: support get-process-id command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 27/57] spp_vf: update socket creation procedure x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 28/57] spp_vf: change log level and add line break x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 29/57] spp_vf: replace unsupported jansson api x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 30/57] spp_vf: change order of command result in json object x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 31/57] spp_vf: use prediction keywords x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 32/57] spp_vf: fix wrong comparison x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 33/57] spp_vf: update sending error status x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 34/57] spp_vf: modify conditional statement x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 35/57] spp_vf: add proc on receiving l2 multicast x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 36/57] spp_vf: extend limit on number of usable cores x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 37/57] spp_vf: add restart procedure for vhost client x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 38/57] spp_vf: fix classifier mbuf handling x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 39/57] spp_vf: add status command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 40/57] spp_vf: add output source information in error log x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 41/57] spp_vf: change function names x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 42/57] spp_vf: change how to request commands x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 43/57] spp_vf: update command decode procedure x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 44/57] spp_vf: remove debug log output procedures x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 45/57] spp_vf: improve command_decoder program code x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 46/57] spp_vf: fix a bug in status command x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 47/57] spp_vf: add spp_vf.py instead of spp.py x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 48/57] spp_vf: refactor for commnets in spp_vf.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 49/57] spp_vf: refactor comments in classifier_mac.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 50/57] spp_vf: refactor comments in spp_forward.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 51/57] spp_vf: refactor for commnets in spp_config.c x-fn-spp
2017-12-28 4:55 ` [spp] [PATCH 52/57] spp_vf: refactor no self-explanatory comments x-fn-spp
2017-12-28 4:56 ` [spp] [PATCH 53/57] spp_vf: correct typo of function name x-fn-spp
2017-12-28 4:56 ` [spp] [PATCH 54/57] spp_vf: support new command x-fn-spp
2017-12-28 4:56 ` [spp] [PATCH 55/57] spp_vf: add display of status command x-fn-spp
2017-12-28 4:56 ` [spp] [PATCH 56/57] spp_vf: fix " x-fn-spp
2017-12-28 4:56 ` [spp] [PATCH 57/57] spp_vf: fix l2 multicast packet forwarding x-fn-spp
2018-01-15 11:04 ` [spp] Proposal - spp_vf(SR-IOV like feature) addition to SPP Ferruh Yigit
2018-01-16 5:16 ` [spp] [PATCH 01/30] doc: add setup guide x-fn-spp
2018-01-19 0:52 ` Yasufumi Ogawa
2018-01-22 14:37 ` Ferruh Yigit
2018-01-23 0:25 ` Yasufumi Ogawa
2018-01-16 5:16 ` [spp] [PATCH 02/30] doc: add how_to_use.md x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 03/30] doc: add config_manual.md x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 04/30] doc: add spp_vf.md x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 05/30] doc: revise spp_vf.md x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 06/30] doc: add config section x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 07/30] doc: update jp setup manual x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 08/30] doc: modify figure in spp_vf_overview x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 09/30] doc: fix " x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 10/30] doc: fix figure in overview x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 11/30] doc: add sample usage x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 12/30] doc: revice path descs x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 13/30] doc: add network configuration diagram x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 14/30] doc: update user account x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 15/30] doc: update descriptions for todo x-fn-spp
2018-01-16 5:16 ` x-fn-spp [this message]
2018-01-16 5:16 ` [spp] [PATCH 17/30] doc: add spp_sample_usage_svg in docs/spp_vf/ x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 18/30] doc: add explanation for terminating spp app x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 19/30] doc: add explanations on options of spp x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 20/30] doc: update description for the latest spp version x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 21/30] doc: update description on dpdk version x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 22/30] doc: fix vm setup procedure for network config x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 23/30] doc: update jansson installation procedure x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 24/30] doc: fix required network configuration x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 25/30] doc: add how to use vhost-user support x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 26/30] doc: add references to hugepages and isolcpus x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 27/30] doc: remove description on classifier_table x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 28/30] doc: fix typos and erros in texts x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 29/30] doc: update sample config section x-fn-spp
2018-01-16 5:16 ` [spp] [PATCH 30/30] doc: align figure title position x-fn-spp
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=201801160516.w0G5GgGH009170@imss03.silk.ntt-tx.co.jp \
--to=x-fn-spp@sl.ntt-tx.co.jp \
--cc=spp@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).