https://bz.apache.org/bugzilla/show_bug.cgi?id=70320

--- Comment #5 from abernal <[email protected]> ---
Thank you for testing this so thoroughly. Since the same traffic shows up with
nginx, it is not specific to httpd: both servers simply open and read the files
from the CIFS share.

Your capture also lines up with that: the burst at 17:47:15 comes right after
the HTTPS connection from 23.110.173.186, which is the GET / at 17:47:16 in
your access log. The packets in that burst are small SMB requests and
responses, which look like metadata operations of the kernel CIFS client rather
than file content. So the CIFS mount options (cache=, actimeo=) or the NAS
itself are where I would look next, and keeping the files on local disk would
avoid it altogether.

I'll leave this open for now in case you find something that points back to
httpd.

-- 
You are receiving this mail because:
You are the assignee for the bug.
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to