Remove printf
# HG changeset patch
# User Liu Qiao <qiao.liu@intel.com>
# Date 1599735293 14400
# Thu Sep 10 06:54:53 2020 -0400
# Node ID c2eabe9168d0cbefc030807a0808568d86c93e4f
# Parent da5e3f5b16733167142b599b6af3ce9469a07d52
Use BPF to distribute packet to different work thread.
Use Berkeley Packet Filter to get packet queue_mapping number,
and use this queue_mapping number to distribute the packet to
different work thread, this will improve CPU utilization and http
latency.
Author: Samudrala, Sridhar <sridhar.samudrala@intel.com>
diff -r da5e3f5b1673 -r c2eabe9168d0 auto/os/linux
--- a/auto/os/linux Wed Sep 02 23:13:36 2020 +0300
+++ b/auto/os/linux Thu Sep 10 06:54:53 2020 -0400
@@ -32,6 +32,10 @@
have=NGX_HAVE_POSIX_FADVISE . auto/nohave
fi
+if [ $version -lt 263680 ]; then
+ have=NGX_HAVE_REUSEPORT_CBPF . auto/nohave
+fi
+
# epoll, EPOLLET version
ngx_feature="epoll"
diff -r da5e3f5b1673 -r c2eabe9168d0 auto/unix
--- a/auto/unix Wed Sep 02 23:13:36 2020 +0300
+++ b/auto/unix Thu Sep 10 06:54:53 2020 -0400
@@ -331,6 +331,17 @@
ngx_feature_test="setsockopt(0, SOL_SOCKET, SO_REUSEPORT, NULL, 0)"
. auto/feature
+ngx_feature="SO_REUSEPORT_CBPF"
+ngx_feature_name="NGX_HAVE_REUSEPORT_CBPF"
+ngx_feature_run=no
+ngx_feature_incs="#include <sys/socket.h>
+ #include <linux/filter.h>
+ #include <error.h>"
+ngx_feature_path=
+ngx_feature_libs=
+ngx_feature_test="setsockopt(0, SOL_SOCKET, SO_ATTACH_REUSEPORT_CBPF, NULL, 0)"
+. auto/feature
+
ngx_feature="SO_ACCEPTFILTER"
ngx_feature_name="NGX_HAVE_DEFERRED_ACCEPT"
diff -r da5e3f5b1673 -r c2eabe9168d0 src/core/ngx_connection.c
--- a/src/core/ngx_connection.c Wed Sep 02 23:13:36 2020 +0300
+++ b/src/core/ngx_connection.c Thu Sep 10 06:54:53 2020 -0400
@@ -8,7 +8,10 @@
#include <ngx_config.h>
#include <ngx_core.h>
#include <ngx_event.h>
-
+#if (NGX_HAVE_REUSEPORT_CBPF)
+#include <linux/filter.h>
+#include <error.h>
+#endif
ngx_os_io_t ngx_io;
@@ -708,6 +711,35 @@
return NGX_OK;
}
+#if(NGX_HAVE_REUSEPORT)
+#if(NGX_HAVE_REUSEPORT_CBPF)
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+#endif
+
+static ngx_int_t attach_bpf(int fd, uint16_t n)
+{
+ struct sock_filter code[] = {
+ /* A = skb->queue_mapping */
+ { BPF_LD | BPF_W | BPF_ABS, 0, 0, SKF_AD_OFF + SKF_AD_QUEUE },
+ /* A = A % n */
+ { BPF_ALU | BPF_MOD, 0, 0, n },
+ /* return A */
+ { BPF_RET | BPF_A, 0, 0, 0 },
+ };
+ struct sock_fprog p = {
+ .len = ARRAY_SIZE(code),
+ .filter = code,
+ };
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_CBPF, &p, sizeof(p)))
+ return NGX_ERROR;
+ else
+ return NGX_OK;
+}
+#endif
+#endif
+
void
ngx_configure_listening_sockets(ngx_cycle_t *cycle)
@@ -719,6 +751,11 @@
#if (NGX_HAVE_DEFERRED_ACCEPT && defined SO_ACCEPTFILTER)
struct accept_filter_arg af;
#endif
+#if (NGX_HAVE_REUSEPORT)
+#if (NGX_HAVE_REUSEPORT_CBPF)
+ ngx_core_conf_t* ccf ;
+#endif
+#endif
ls = cycle->listening.elts;
for (i = 0; i < cycle->listening.nelts; i++) {
@@ -1011,6 +1048,31 @@
}
#endif
+#if (NGX_HAVE_REUSEPORT)
+#if (NGX_HAVE_REUSEPORT_CBPF)
+ if(ls[i].reuseport)
+ {
+ ccf = (ngx_core_conf_t *) ngx_get_conf(cycle->conf_ctx,ngx_core_module);
+ if(ccf)
+ {
+ if( NGX_OK == attach_bpf(ls[i].fd, ccf->worker_processes) )
+ {
+ ngx_log_error(NGX_LOG_INFO,cycle->log ,ngx_socket_errno,\
+ "bpf prog attached to fd:%d\n", ls[i].fd);
+ }
+ else
+ {
+ ngx_log_error(NGX_LOG_ERR,cycle->log ,ngx_socket_errno,\
+ "failed to set SO_ATTACH_REUSEPORT_CBPF\n");
+ }
+ }
+ else
+ ngx_log_error(NGX_LOG_ERR,cycle->log ,ngx_socket_errno,\
+ "can not get config, attach bpf failed\n");
+
+ }
+#endif
+#endif
}
return;
-----Original Message-----
From: Liu, Qiao
Sent: Tuesday, September 15, 2020 10:09 AM
To: nginx-devel@nginx.org
Subject: RE: [PATCH] Use BPF to distribute packet to different work thread.
Below is 5 times test result compare, 112 threads, 10000 connections, 1M object http request. Seems P99 have great improvement, and Max is also reduced
AVG Stdev Max P99
test 1 1.32s 447.09ms 5.48s 2.82s
BPF test 2 1.39s 513.8ms 9.42s 3.1s
test 3 1.4s 341.38ms 5.63s 2.55s
test 4 1.41s 407.45ms 6.96s 2.77s
test 5 1.29s 644.81ms 9.45s 3.74s
Average 1.362s 470.906ms 7.388s 2.996s
NonBPF test 1 1.48s 916.88ms 9.44s 5.08s
test 2 1.43s 658.48ms 9.54s 3.92s
test 3 1.41s 650.38ms 8.63s 3.59s
test 4 1.29s 1010ms 10s 5.21s
test 5 1.31s 875.01ms 9.53s 4.39s
Average 1.384s 822.15ms 9.428s 4.438s
Thanks
LQ
-----Original Message-----
From: nginx-devel <nginx-devel-bounces@nginx.org> On Behalf Of Liu, Qiao
Sent: Monday, September 14, 2020 9:18 AM
To: nginx-devel@nginx.org
Subject: RE: [PATCH] Use BPF to distribute packet to different work thread.
Hi, Maxim Dounin:
Thanks for your reply, this server is random selected, we just do BPF and no-BPF test, I think the latency based on server configuration, not related with BPF patch, also the NIC of the server is Mellanox, not ADQ capable hardware , we will do more test Thanks LQ
-----Original Message-----
From: nginx-devel <nginx-devel-bounces@nginx.org> On Behalf Of Maxim Dounin
Sent: Monday, September 14, 2020 7:40 AM
To: nginx-devel@nginx.org
Subject: Re: [PATCH] Use BPF to distribute packet to different work thread.
Hello!
On Fri, Sep 11, 2020 at 05:41:47AM +0000, Liu, Qiao wrote:
> Hi, Vladimir Homutov:
> The below is our WRK test result output with BPF enable
>
> 112 threads and 10000 connections
> Thread Stats Avg Stdev Max +/- Stdev
> Latency 608.23ms 820.71ms 10.00s 87.48%
> Connect 16.52ms 54.53ms 1.99s 94.73%
> Delay 153.13ms 182.17ms 2.00s 90.74%
> Req/Sec 244.79 142.32 1.99k 68.40%
> Latency Distribution
> 50.00% 293.50ms
> 75.00% 778.33ms
> 90.00% 1.61s
> 99.00% 3.71s
> 99.90% 7.03s
> 99.99% 8.94s
> Connect Distribution
> 50.00% 1.93ms
> 75.00% 2.85ms
> 90.00% 55.76ms
> 99.00% 229.19ms
> 99.90% 656.79ms
> 99.99% 1.43s
> Delay Distribution
> 50.00% 110.96ms
> 75.00% 193.67ms
> 90.00% 321.77ms
> 99.00% 959.27ms
> 99.90% 1.57s
> 99.99% 1.91s
> Compared with no BPF but enable reuseport as below
>
> 112 threads and 10000 connections
> Thread Stats Avg Stdev Max +/- Stdev
> Latency 680.50ms 943.69ms 10.00s 87.18%
> Connect 58.44ms 238.08ms 2.00s 94.58%
> Delay 158.84ms 256.28ms 2.00s 90.92%
> Req/Sec 244.51 151.00 1.41k 69.67%
> Latency Distribution
> 50.00% 317.61ms
> 75.00% 913.52ms
> 90.00% 1.90s
> 99.00% 4.30s
> 99.90% 6.52s
> 99.99% 8.80s
> Connect Distribution
> 50.00% 1.88ms
> 75.00% 2.21ms
> 90.00% 55.94ms
> 99.00% 1.45s
> 99.90% 1.95s
> 99.99% 2.00s
> Delay Distribution
> 50.00% 73.01ms
> 75.00% 190.40ms
> 90.00% 387.01ms
> 99.00% 1.34s
> 99.90% 1.86s
> 99.99% 1.99s
>
>
> From the above results, there shows almost 20% percent latency
> reduction. P99 latency of BPF is 3.71s , but without BPF is 4.3s.
Thank you for the results.
Given that latency stdev is way higher than the average latency, I don't think the "20% percent latency reduction" observed is statistically significant. Please try running several tests and use ministat(1) to check the results.
Also, the latency values look very high, and request rate very low. What's on the server side?
--
Maxim Dounin
http://mdounin.ru/
_______________________________________________
nginx-devel mailing list
nginx-devel@nginx.org
http://mailman.nginx.org/mailman/listinfo/nginx-devel
_______________________________________________
nginx-devel mailing list
nginx-devel@nginx.org
http://mailman.nginx.org/mailman/listinfo/nginx-devel
_______________________________________________
nginx-devel mailing list
nginx-devel@nginx.org
http://mailman.nginx.org/mailman/listinfo/nginx-devel