summaryrefslogtreecommitdiff
path: root/src/lib
diff options
context:
space:
mode:
authorDimitri Staessens <dimitri@ouroboros.rocks>2020-12-01 19:19:04 +0100
committerSander Vrijders <sander@ouroboros.rocks>2020-12-02 19:21:29 +0100
commit8e1c0e62feb4832dca2b53e51ab0e1cb8f48e5b1 (patch)
treece90e18277c38e7ee592d441ae4de197081c6476 /src/lib
parentaef6bdb1eadf8779173145710306ea5b6d81b8ec (diff)
downloadouroboros-8e1c0e62feb4832dca2b53e51ab0e1cb8f48e5b1.tar.gz
ouroboros-8e1c0e62feb4832dca2b53e51ab0e1cb8f48e5b1.zip
ipcpd: Add congestion avoidance policies
This adds congestion avoidance policies to the unicast IPCP. The default policy is a multi-bit explicit congestion avoidance algorithm based on data-center TCP congestion avoidance (DCTCP) to relay information about the maximum queue depth that packets experienced to the receiver. There's also a "nop" policy to disable congestion avoidance for testing and benchmarking purposes. The (initial) API for congestion avoidance policies is: void * (* ctx_create)(void); void (* ctx_destroy)(void * ctx); These calls create / and or destroy a context for congestion control for a specific flow. Thread-safety of the context is the responsability of the flow allocator (operations on the ctx should be performed under a lock). ca_wnd_t (* ctx_update_snd)(void * ctx, size_t len); This is the sender call to update the context, and should be called for every packet that is sent on the flow. The len parameter in this API is the packet length, which allows calculating the bandwidth. It returns an opaque union type that is used for the call to check/wait if the congestion window is open or closed (and allowing to release locks before waiting). bool (* ctx_update_rcv)(void * ctx, size_t len, uint8_t ecn, uint16_t * ece); This is the call to update the flow congestion context on the receiver side. It should be called for every received packet. It gets the ecn value from the packet and its length, and returns the ECE (explicit congestion experienced) value to be sent to the sender in case of congestion. The boolean returned signals whether or not a congestion update needs to be sent. void (* ctx_update_ece)(void * ctx, uint16_t ece); This is the call for the sending side top update the context when it receives an ECE update from the receiver. void (* wnd_wait)(ca_wnd_t wnd); This is a (blocking) call that waits for the congestion window to clear. It should be stateless (to avoid waiting under locks). This may change later on if passing the context is needed for different algorithms. uint8_t (* calc_ecn)(int fd, size_t len); This is the call that intermediate IPCPs(routers) should use to update the ECN field on passing packets. The multi-bit ECN policy bases the value for the ECN field on the depth of the rbuff queue packets will be sent on. I created another call to grab the queue depth as fccntl is write-locking the application. We can further optimize this to avoid most locking on the rbuff. Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks> Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
Diffstat (limited to 'src/lib')
-rw-r--r--src/lib/dev.c15
-rw-r--r--src/lib/ipcp_config.proto13
-rw-r--r--src/lib/irm.c2
3 files changed, 24 insertions, 6 deletions
diff --git a/src/lib/dev.c b/src/lib/dev.c
index 4b78c1db..a6be762b 100644
--- a/src/lib/dev.c
+++ b/src/lib/dev.c
@@ -1768,6 +1768,21 @@ int ipcp_flow_get_qoscube(int fd,
return 0;
}
+size_t ipcp_flow_queued(int fd)
+{
+ size_t q;
+
+ pthread_rwlock_rdlock(&ai.lock);
+
+ assert(ai.flows[fd].flow_id >= 0);
+
+ q = shm_rbuff_queued(ai.flows[fd].tx_rb);
+
+ pthread_rwlock_unlock(&ai.lock);
+
+ return q;
+}
+
ssize_t local_flow_read(int fd)
{
ssize_t ret;
diff --git a/src/lib/ipcp_config.proto b/src/lib/ipcp_config.proto
index 23c65e94..7bf5329e 100644
--- a/src/lib/ipcp_config.proto
+++ b/src/lib/ipcp_config.proto
@@ -36,15 +36,16 @@ message ipcp_config_msg {
optional uint32 max_ttl = 5;
optional uint32 addr_auth_type = 6;
optional uint32 routing_type = 7;
+ optional uint32 cong_avoid = 8;
// Config for UDP
- optional uint32 ip_addr = 8;
- optional uint32 dns_addr = 9;
- optional uint32 clt_port = 10;
- optional uint32 srv_port = 11;
+ optional uint32 ip_addr = 9;
+ optional uint32 dns_addr = 10;
+ optional uint32 clt_port = 11;
+ optional uint32 srv_port = 12;
// Config for the Ethernet
- optional string dev = 12;
+ optional string dev = 13;
// Config for DIX Ethernet
- optional uint32 ethertype = 13;
+ optional uint32 ethertype = 14;
}
enum enroll_code {
diff --git a/src/lib/irm.c b/src/lib/irm.c
index 08dffb6c..42ad74fa 100644
--- a/src/lib/irm.c
+++ b/src/lib/irm.c
@@ -132,6 +132,8 @@ int irm_bootstrap_ipcp(pid_t pid,
config.addr_auth_type = conf->addr_auth_type;
config.has_routing_type = true;
config.routing_type = conf->routing_type;
+ config.has_cong_avoid = true;
+ config.cong_avoid = conf->cong_avoid;
break;
case IPCP_UDP:
config.has_ip_addr = true;