@@ -208,7 +208,7 @@ The counter in rps_dev_flow_table values records the length of the current
208208CPU's backlog when a packet in this flow was last enqueued. Each backlog
209209queue has a head counter that is incremented on dequeue. A tail counter
210210is computed as head counter + queue length. In other words, the counter
211- in rps_dev_flow_table [i] records the last element in flow i that has
211+ in rps_dev_flow [i] records the last element in flow i that has
212212been enqueued onto the currently designated CPU for flow i (of course,
213213entry i is actually selected by hash and multiple flows may hash to the
214214same entry i).
@@ -224,7 +224,7 @@ following is true:
224224
225225- The current CPU's queue head counter >= the recorded tail counter
226226 value in rps_dev_flow[i]
227- - The current CPU is unset (equal to NR_CPUS )
227+ - The current CPU is unset (equal to RPS_NO_CPU )
228228- The current CPU is offline
229229
230230After this check, the packet is sent to the (possibly updated) current
235235
236236==== RFS Configuration
237237
238- RFS is only available if the kconfig symbol CONFIG_RFS is enabled (on
238+ RFS is only available if the kconfig symbol CONFIG_RPS is enabled (on
239239by default for SMP). The functionality remains disabled until explicitly
240240configured. The number of entries in the global flow table is set through:
241241
@@ -258,7 +258,7 @@ For a single queue device, the rps_flow_cnt value for the single queue
258258would normally be configured to the same value as rps_sock_flow_entries.
259259For a multi-queue device, the rps_flow_cnt for each queue might be
260260configured as rps_sock_flow_entries / N, where N is the number of
261- queues. So for instance, if rps_flow_entries is set to 32768 and there
261+ queues. So for instance, if rps_sock_flow_entries is set to 32768 and there
262262are 16 configured receive queues, rps_flow_cnt for each queue might be
263263configured as 2048.
264264
0 commit comments