Commit 14a1eaa8 authored by Sunil Muthuswamy's avatar Sunil Muthuswamy Committed by David S. Miller

hv_sock: perf: loop in send() to maximize bandwidth

Currently, the hv_sock send() iterates once over the buffer, puts data into
the VMBUS channel and returns. It doesn't maximize on the case when there
is a simultaneous reader draining data from the channel. In such a case,
the send() can maximize the bandwidth (and consequently minimize the cpu
cycles) by iterating until the channel is found to be full.

Perf data:
Total Data Transfer: 10GB/iteration
Single threaded reader/writer, Linux hvsocket writer with Windows hvsocket
reader
Packet size: 64KB
CPU sys time was captured using the 'time' command for the writer to send
10GB of data.
'Send Buffer Loop' is with the patch applied.
The values below are over 10 iterations.

|--------------------------------------------------------|
|        |        Current        |   Send Buffer Loop    |
|--------------------------------------------------------|
|        | Throughput | CPU sys  | Throughput | CPU sys  |
|        | (MB/s)     | time (s) | (MB/s)     | time (s) |
|--------------------------------------------------------|
| Min    |     407    |   7.048  |    401     |  5.958   |
|--------------------------------------------------------|
| Max    |     455    |   7.563  |    542     |  6.993   |
|--------------------------------------------------------|
| Avg    |     440    |   7.411  |    451     |  6.639   |
|--------------------------------------------------------|
| Median |     446    |   7.417  |    447     |  6.761   |
|--------------------------------------------------------|

Observation:
1. The avg throughput doesn't really change much with this change for this
scenario. This is most probably because the bottleneck on throughput is
somewhere else.
2. The average system (or kernel) cpu time goes down by 10%+ with this
change, for the same amount of data transfer.
Signed-off-by: default avatarSunil Muthuswamy <sunilmut@microsoft.com>
Reviewed-by: default avatarDexuan Cui <decui@microsoft.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent ac383f58
...@@ -55,8 +55,9 @@ struct hvs_recv_buf { ...@@ -55,8 +55,9 @@ struct hvs_recv_buf {
}; };
/* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use /* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use
* a small size, i.e. HVS_SEND_BUF_SIZE, to minimize the dynamically-allocated * a smaller size, i.e. HVS_SEND_BUF_SIZE, to maximize concurrency between the
* buffer, because tests show there is no significant performance difference. * guest and the host processing as one VMBUS packet is the smallest processing
* unit.
* *
* Note: the buffer can be eliminated in the future when we add new VMBus * Note: the buffer can be eliminated in the future when we add new VMBus
* ringbuffer APIs that allow us to directly copy data from userspace buffer * ringbuffer APIs that allow us to directly copy data from userspace buffer
...@@ -674,7 +675,9 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, ...@@ -674,7 +675,9 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
struct hvsock *hvs = vsk->trans; struct hvsock *hvs = vsk->trans;
struct vmbus_channel *chan = hvs->chan; struct vmbus_channel *chan = hvs->chan;
struct hvs_send_buf *send_buf; struct hvs_send_buf *send_buf;
ssize_t to_write, max_writable, ret; ssize_t to_write, max_writable;
ssize_t ret = 0;
ssize_t bytes_written = 0;
BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K); BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
...@@ -682,10 +685,19 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, ...@@ -682,10 +685,19 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
if (!send_buf) if (!send_buf)
return -ENOMEM; return -ENOMEM;
/* Reader(s) could be draining data from the channel as we write.
* Maximize bandwidth, by iterating until the channel is found to be
* full.
*/
while (len) {
max_writable = hvs_channel_writable_bytes(chan); max_writable = hvs_channel_writable_bytes(chan);
if (!max_writable)
break;
to_write = min_t(ssize_t, len, max_writable); to_write = min_t(ssize_t, len, max_writable);
to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE); to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE);
/* memcpy_from_msg is safe for loop as it advances the offsets
* within the message iterator.
*/
ret = memcpy_from_msg(send_buf->data, msg, to_write); ret = memcpy_from_msg(send_buf->data, msg, to_write);
if (ret < 0) if (ret < 0)
goto out; goto out;
...@@ -694,8 +706,13 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg, ...@@ -694,8 +706,13 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
if (ret < 0) if (ret < 0)
goto out; goto out;
ret = to_write; bytes_written += to_write;
len -= to_write;
}
out: out:
/* If any data has been sent, return that */
if (bytes_written)
ret = bytes_written;
kfree(send_buf); kfree(send_buf);
return ret; return ret;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment