Re: and nicer too - Re: [PATCH] epoll more scalable than poll

From: bert hubert (ahu@ds9a.nl)
Date: Mon Oct 28 2002 - 19:18:43 EST

On Mon, Oct 28, 2002 at 03:45:06PM -0800, John Gardiner Myers wrote:

> As you have amply demonstrated, the current epoll API is error prone.
> The API should be fixed to test the poll condition and, if necessary,
> drop an event upon insertion to the set.

That is a semantics change and not an API/ABI change. To reiterate, you
mention the following scenario:

for(;;) {
        nfds = sys_epoll_wait(kdpfd, &pfds, -1);
        for(n = 0; n < nfds; ++n) {
                if((fd = pfds[n].fd) == s) {
                        /* 1: accept client (SYN/SYN|ACK/ACK completed) */
                        client = accept(s, (struct sockaddr*)&local, &addrlen);
                        if(client < 0){
                                perror("accept");
                                continue;
                        }

                        /* 2: packet comes in, client becomes readable */
                        /* 3: registering interest */
                        if (sys_epoll_ctl(kdpfd, EP_CTL_ADD, client, POLLIN ) < 0) {
                                fprintf(stderr, "sys_epoll set insertion error: fd=%d\n", client);
                                return -1;
                        }
                        
                        /* 4: interest only now registered, no edge will be
                           reported, our fd is lost */

                        fd = client;
                }
                do_use_fd(fd);
        }
}

There are lots of ways to solve this, I bet Davide knows best. Perhaps it is
solved already, you can't tell from only studying the API, the problem isn't
intrinsic to it.

An easy solution is to have sys_epoll_ctl check if there is there is data
ready and make sure there is an edge to report in that case to the next call
of sys_epoll_ctl().

Regards,

bert 

-- 
http://www.PowerDNS.com          Versatile DNS Software & Services
http://lartc.org           Linux Advanced Routing & Traffic Control HOWTO
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

This archive was generated by hypermail 2b29 : Thu Oct 31 2002 - 22:00:40 EST