linux上下文切换过多,在新的Linux内核中，上下文切换要慢得多

也许变慢的是futex，它是条件变量的构建块。这将阐明一些内容：

strace -r ./test_latency 0 1 &> test_latency_strace & sleep 8 && killall test_latency

然后

for i in futex nanosleep rt_sig;do echo $i;grep $i test_latency_strace | sort -rn;done

它将显示有趣的系统调用所花费的微秒，按时间排序。

在内核2.6.32上

$ for i in futex nanosleep rt_sig;do echo $i;grep $i test_latency_strace | sort -rn;done

futex

1.000140 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000129 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000124 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000119 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000106 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000103 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000102 futex(0x601ac4, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601ac0, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

0.000125 futex(0x7f98ce4c0b88, FUTEX_WAKE_PRIVATE, 2147483647) = 0

0.000042 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000038 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000037 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000030 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000029 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 0

0.000028 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000027 futex(0x601b00, FUTEX_WAKE_PRIVATE, 1) = 1

0.000018 futex(0x7fff82f0ec3c, FUTEX_WAKE_PRIVATE, 1) = 0

nanosleep

0.000027 nanosleep({1, 0}, {1, 0}) = 0

0.000019 nanosleep({1, 0}, {1, 0}) = 0

0.000019 nanosleep({1, 0}, {1, 0}) = 0

0.000018 nanosleep({1, 0}, {1, 0}) = 0

0.000018 nanosleep({1, 0}, {1, 0}) = 0

0.000018 nanosleep({1, 0}, {1, 0}) = 0

0.000018 nanosleep({1, 0}, 0x7fff82f0eb40) = ? ERESTART_RESTARTBLOCK (To be restarted)

0.000017 nanosleep({1, 0}, {1, 0}) = 0

rt_sig

0.000045 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000040 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000038 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000035 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000034 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000033 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000032 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000032 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000031 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000031 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000028 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000028 rt_sigaction(SIGRT_1, {0x37f8c052b0, [], SA_RESTORER|SA_RESTART|SA_SIGINFO, 0x37f8c0e4c0}, NULL, 8) = 0

0.000027 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000027 rt_sigaction(SIGRTMIN, {0x37f8c05370, [], SA_RESTORER|SA_SIGINFO, 0x37f8c0e4c0}, NULL, 8) = 0

0.000027 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000025 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000025 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000023 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000023 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000022 rt_sigprocmask(SIG_UNBLOCK, [RTMIN RT_1], NULL, 8) = 0

0.000022 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000021 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000021 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000021 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000021 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000021 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000019 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

在内核3.1.9上

$ for i in futex nanosleep rt_sig;do echo $i;grep $i test_latency_strace | sort -rn;done

futex

1.000129 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000126 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000122 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000115 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000114 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000112 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

1.000109 futex(0x601764, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0x601760, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1

0.000139 futex(0x3f8b8f2fb0, FUTEX_WAKE_PRIVATE, 2147483647) = 0

0.000043 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

0.000041 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

0.000037 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

0.000036 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

0.000034 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

0.000034 futex(0x601720, FUTEX_WAKE_PRIVATE, 1) = 1

nanosleep

0.000025 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000022 nanosleep({1, 0}, {0, 3925413}) = ? ERESTART_RESTARTBLOCK (Interrupted by signal)

0.000021 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000017 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000017 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000017 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000017 nanosleep({1, 0}, 0x7fff70091d00) = 0

0.000017 nanosleep({1, 0}, 0x7fff70091d00) = 0

rt_sig

0.000045 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000044 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000043 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000040 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000038 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000037 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000036 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000036 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000035 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000035 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000035 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000035 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000034 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000031 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000027 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000027 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000027 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000027 rt_sigaction(SIGRT_1, {0x3f892067b0, [], SA_RESTORER|SA_RESTART|SA_SIGINFO, 0x3f8920f500}, NULL, 8) = 0

0.000026 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000026 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000025 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000024 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000023 rt_sigprocmask(SIG_UNBLOCK, [RTMIN RT_1], NULL, 8) = 0

0.000023 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0

0.000022 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0

0.000021 rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0

0.000019 rt_sigaction(SIGRTMIN, {0x3f89206720, [], SA_RESTORER|SA_SIGINFO, 0x3f8920f500}, NULL, 8) = 0

我发现此具有5年历史的错误报告包含一个“乒乓”性能测试，该测试将

单线程libpthread互斥体

libpthread条件变量

普通的旧Unix信号

我必须添加

#include

为了进行编译，我使用此命令

g++ -O3 -o condvar-perf condvar-perf.cpp -lpthread -lrt

在内核2.6.32上

$ ./condvar-perf 1000000

NPTL

mutex elapsed: 29085 us; per iteration: 29 ns / 9.4e-05 context switches.

c.v. ping-pong test elapsed: 4771993 us; per iteration: 4771 ns / 4.03 context switches.

signal ping-pong test elapsed: 8685423 us; per iteration: 8685 ns / 4.05 context switches.

在内核3.1.9上

$ ./condvar-perf 1000000

NPTL

mutex elapsed: 26811 us; per iteration: 26 ns / 8e-06 context switches.

c.v. ping-pong test elapsed: 10930794 us; per iteration: 10930 ns / 4.01 context switches.

signal ping-pong test elapsed: 10949670 us; per iteration: 10949 ns / 4.01 context switches.

我得出的结论是，内核2.6.32和3.1.9之间的上下文切换确实放慢了速度，尽管没有您在内核3.2中观察到的那么快。我知道这还不能回答您的问题，我会继续研究。

编辑：我发现更改进程(两个线程)的实时优先级可以提高3.1.9的性能以匹配2.6.32。但是，在2.6.32上设置相同的优先级会使它变慢。

现在是我的结果：

在内核2.6.32上

$ ./condvar-perf 1000000

NPTL

mutex elapsed: 29629 us; per iteration: 29 ns / 0.000418 context switches.

c.v. ping-pong test elapsed: 6225637 us; per iteration: 6225 ns / 4.1 context switches.

signal ping-pong test elapsed: 5602248 us; per iteration: 5602 ns / 4.09 context switches.

$ chrt -f 1 ./condvar-perf 1000000

NPTL

mutex elapsed: 29049 us; per iteration: 29 ns / 0.000407 context switches.

c.v. ping-pong test elapsed: 16131360 us; per iteration: 16131 ns / 4.29 context switches.

signal ping-pong test elapsed: 11817819 us; per iteration: 11817 ns / 4.16 context switches.

$

在内核3.1.9上

$ ./condvar-perf 1000000

NPTL

mutex elapsed: 26830 us; per iteration: 26 ns / 5.7e-05 context switches.

c.v. ping-pong test elapsed: 12812788 us; per iteration: 12812 ns / 4.01 context switches.

signal ping-pong test elapsed: 13126865 us; per iteration: 13126 ns / 4.01 context switches.

$ chrt -f 1 ./condvar-perf 1000000

NPTL

mutex elapsed: 27025 us; per iteration: 27 ns / 3.7e-05 context switches.

c.v. ping-pong test elapsed: 5099885 us; per iteration: 5099 ns / 4 context switches.

signal ping-pong test elapsed: 5508227 us; per iteration: 5508 ns / 4 context switches.

$

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！