Hi Mikhail,
Added 'sendfile on' & 'aio off' test result with previous table:
Following is the test result with 100KB and 1MB: (4KB to be test)
Nginx worker_processes 1:
4k 100k 1M
Io_uring220MB/s1GB/s1.3GB/s
Libaio70MB/s
Hi Mikhail,
I think it could be the kernel difference. I'll try to repro with your kernel.
I directly build the kernel from kernel org. This is the commit id I used:
commit 6b9830fecd4a87d7ebb4d93484fef00f46d0fa0f (HEAD -> linux-5.7.y, tag:
v5.7.19, origin/linux-5.7.y)
Author: Greg Kroah-Hartma
Hello,
I just spent more time than I care to admit troubleshooting a make
issue after naively using `./configure --builddir=build` (make target
inadvertently matches this directory name).
Not sure if taking a dep on POSIX sed in the build system is kosher or
not, but if it is I figure this patch
Hi Zhao Ping,
My test is much simpler than yours. I created
/usr/local/html/(1...9) files on SSD (100 kb size) and wrote
small lua script for wrk that adds 5 random digits to request. There are
no such errors without patch with aio enabled.
These files does not change during test.
I'