DPDK
2.2.0
|
Go to the source code of this file.
Macros | |
#define | RTE_DISTRIBUTOR_NAMESIZE 32 |
Functions | |
struct rte_distributor * | rte_distributor_create (const char *name, unsigned socket_id, unsigned num_workers) |
int | rte_distributor_process (struct rte_distributor *d, struct rte_mbuf **mbufs, unsigned num_mbufs) |
int | rte_distributor_returned_pkts (struct rte_distributor *d, struct rte_mbuf **mbufs, unsigned max_mbufs) |
int | rte_distributor_flush (struct rte_distributor *d) |
void | rte_distributor_clear_returns (struct rte_distributor *d) |
struct rte_mbuf * | rte_distributor_get_pkt (struct rte_distributor *d, unsigned worker_id, struct rte_mbuf *oldpkt) |
int | rte_distributor_return_pkt (struct rte_distributor *d, unsigned worker_id, struct rte_mbuf *mbuf) |
void | rte_distributor_request_pkt (struct rte_distributor *d, unsigned worker_id, struct rte_mbuf *oldpkt) |
struct rte_mbuf * | rte_distributor_poll_pkt (struct rte_distributor *d, unsigned worker_id) |
RTE distributor
The distributor is a component which is designed to pass packets one-at-a-time to workers, with dynamic load balancing.
Definition in file rte_distributor.h.
#define RTE_DISTRIBUTOR_NAMESIZE 32 |
Length of name for instance
Definition at line 49 of file rte_distributor.h.
|
read |
Function to create a new distributor instance
Reserves the memory needed for the distributor operation and initializes the distributor to work with the configured number of workers.
name | The name to be given to the distributor instance. |
socket_id | The NUMA node on which the memory is to be allocated |
num_workers | The maximum number of workers that will request packets from this distributor |
int rte_distributor_process | ( | struct rte_distributor * | d, |
struct rte_mbuf ** | mbufs, | ||
unsigned | num_mbufs | ||
) |
Process a set of packets by distributing them among workers that request packets. The distributor will ensure that no two packets that have the same flow id, or tag, in the mbuf will be procesed at the same time.
The user is advocated to set tag for each mbuf before calling this function. If user doesn't set the tag, the tag value can be various values depending on driver implementation and configuration.
This is not multi-thread safe and should only be called on a single lcore.
d | The distributor instance to be used |
mbufs | The mbufs to be distributed |
num_mbufs | The number of mbufs in the mbufs array |
int rte_distributor_returned_pkts | ( | struct rte_distributor * | d, |
struct rte_mbuf ** | mbufs, | ||
unsigned | max_mbufs | ||
) |
Get a set of mbufs that have been returned to the distributor by workers
This should only be called on the same lcore as rte_distributor_process()
d | The distributor instance to be used |
mbufs | The mbufs pointer array to be filled in |
max_mbufs | The size of the mbufs array |
int rte_distributor_flush | ( | struct rte_distributor * | d | ) |
Flush the distributor component, so that there are no in-flight or backlogged packets awaiting processing
This should only be called on the same lcore as rte_distributor_process()
d | The distributor instance to be used |
void rte_distributor_clear_returns | ( | struct rte_distributor * | d | ) |
Clears the array of returned packets used as the source for the rte_distributor_returned_pkts() API call.
This should only be called on the same lcore as rte_distributor_process()
d | The distributor instance to be used |
|
read |
API called by a worker to get a new packet to process. Any previous packet given to the worker is assumed to have completed processing, and may be optionally returned to the distributor via the oldpkt parameter.
d | The distributor instance to be used |
worker_id | The worker instance number to use - must be less that num_workers passed at distributor creation time. |
oldpkt | The previous packet, if any, being processed by the worker |
int rte_distributor_return_pkt | ( | struct rte_distributor * | d, |
unsigned | worker_id, | ||
struct rte_mbuf * | mbuf | ||
) |
API called by a worker to return a completed packet without requesting a new packet, for example, because a worker thread is shutting down
d | The distributor instance to be used |
worker_id | The worker instance number to use - must be less that num_workers passed at distributor creation time. |
mbuf | The previous packet being processed by the worker |
void rte_distributor_request_pkt | ( | struct rte_distributor * | d, |
unsigned | worker_id, | ||
struct rte_mbuf * | oldpkt | ||
) |
API called by a worker to request a new packet to process. Any previous packet given to the worker is assumed to have completed processing, and may be optionally returned to the distributor via the oldpkt parameter. Unlike rte_distributor_get_pkt(), this function does not wait for a new packet to be provided by the distributor.
NOTE: after calling this function, rte_distributor_poll_pkt() should be used to poll for the packet requested. The rte_distributor_get_pkt() API should not be used to try and retrieve the new packet.
d | The distributor instance to be used |
worker_id | The worker instance number to use - must be less that num_workers passed at distributor creation time. |
oldpkt | The previous packet, if any, being processed by the worker |
|
read |
API called by a worker to check for a new packet that was previously requested by a call to rte_distributor_request_pkt(). It does not wait for the new packet to be available, but returns NULL if the request has not yet been fulfilled by the distributor.
d | The distributor instance to be used |
worker_id | The worker instance number to use - must be less that num_workers passed at distributor creation time. |