diff options
Diffstat (limited to 'Documentation/networking/scaling.txt')
-rw-r--r-- | Documentation/networking/scaling.txt | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt index 58fd7414e6c..fe67b5c79f0 100644 --- a/Documentation/networking/scaling.txt +++ b/Documentation/networking/scaling.txt | |||
@@ -27,7 +27,7 @@ applying a filter to each packet that assigns it to one of a small number | |||
27 | of logical flows. Packets for each flow are steered to a separate receive | 27 | of logical flows. Packets for each flow are steered to a separate receive |
28 | queue, which in turn can be processed by separate CPUs. This mechanism is | 28 | queue, which in turn can be processed by separate CPUs. This mechanism is |
29 | generally known as “Receive-side Scaling” (RSS). The goal of RSS and | 29 | generally known as “Receive-side Scaling” (RSS). The goal of RSS and |
30 | the other scaling techniques to increase performance uniformly. | 30 | the other scaling techniques is to increase performance uniformly. |
31 | Multi-queue distribution can also be used for traffic prioritization, but | 31 | Multi-queue distribution can also be used for traffic prioritization, but |
32 | that is not the focus of these techniques. | 32 | that is not the focus of these techniques. |
33 | 33 | ||
@@ -186,10 +186,10 @@ are steered using plain RPS. Multiple table entries may point to the | |||
186 | same CPU. Indeed, with many flows and few CPUs, it is very likely that | 186 | same CPU. Indeed, with many flows and few CPUs, it is very likely that |
187 | a single application thread handles flows with many different flow hashes. | 187 | a single application thread handles flows with many different flow hashes. |
188 | 188 | ||
189 | rps_sock_table is a global flow table that contains the *desired* CPU for | 189 | rps_sock_flow_table is a global flow table that contains the *desired* CPU |
190 | flows: the CPU that is currently processing the flow in userspace. Each | 190 | for flows: the CPU that is currently processing the flow in userspace. |
191 | table value is a CPU index that is updated during calls to recvmsg and | 191 | Each table value is a CPU index that is updated during calls to recvmsg |
192 | sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage() | 192 | and sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage() |
193 | and tcp_splice_read()). | 193 | and tcp_splice_read()). |
194 | 194 | ||
195 | When the scheduler moves a thread to a new CPU while it has outstanding | 195 | When the scheduler moves a thread to a new CPU while it has outstanding |
@@ -243,7 +243,7 @@ configured. The number of entries in the global flow table is set through: | |||
243 | 243 | ||
244 | The number of entries in the per-queue flow table are set through: | 244 | The number of entries in the per-queue flow table are set through: |
245 | 245 | ||
246 | /sys/class/net/<dev>/queues/tx-<n>/rps_flow_cnt | 246 | /sys/class/net/<dev>/queues/rx-<n>/rps_flow_cnt |
247 | 247 | ||
248 | == Suggested Configuration | 248 | == Suggested Configuration |
249 | 249 | ||