On Mon, Nov 04, 2002, Robert Collins wrote:
> > Any suggestions on where to look in the 2.5 branch?
>
> I've not yet reviewed in detail the attached patch, but it looks good to
> me at first glance.
Ooer.
>
> After weeks of poking around in the code, I've finally figured out what was causing download corruption in Squid 2.4 and 2.5.
>
Whoa. This person is .. insane. Insane, insane, insane.
I wonder if diskd suffers from this at all.
> Although I never heard back from the squid developers as to whether they were working on this, hopefully they will have something to say now that it has (ostensibly) been solved. Hello...anybody there?
Grr. He never sent it to squid-dev? :)
> -Phil Oester
> (not a squid developer, but I did sleep at a Holiday Inn express last night)
How does this make sense? :)
I'm happy with the following patch. It makes sense to me. Does
anyone have any issues with it?
> --- original/src/fs/aufs/store_io_aufs.c Sun Aug 11 16:14:35 2002
> +++ fixed/src/fs/aufs/store_io_aufs.c Mon Oct 28 14:39:32 2002
> @@ -286,6 +286,10 @@
> aiostate->fd = fd;
> commSetCloseOnExec(fd);
> fd_open(fd, FD_FILE, storeAufsDirFullPath(INDEXSD(sio->swap_dirn), sio->swap_filen, NULL));
> + if (aiostate->flags.close_request) {
> + storeAufsIOCallback(sio, errflag);
> + return;
> + }
> if (FILE_MODE(sio->mode) == O_WRONLY) {
> if (storeAufsKickWriteQueue(sio))
> return;
> @@ -293,8 +297,6 @@
> if (storeAufsKickReadQueue(sio))
> return;
> }
> - if (aiostate->flags.close_request)
> - storeAufsIOCallback(sio, errflag);
> debug(79, 3) ("storeAufsOpenDone: exiting\n");
> }
>
Received on Sun Nov 03 2002 - 20:29:18 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:18:37 MST