Say you have 2 systems, "A" and "B". "A" is active, a network failure occurs, node "A" can't talk to "B" or the clients. The remote member of the array is failed. But "A" is still running, and maybe in the process of shutting down. The process of shutting down "A" will cause more writes to the disk. Even without a proper shutdown, disk writes can occur, cron jobs, log files, whatever, all occurring before the shutdown, or power off. At some point node "B" becomes active, and processes live data. Now, someone fixes the problem and you want to re-sync. Both "A" and "B" have done disk I/O that the other does not know about. Both bitmap must be used to re-sync, or a 100% re-sync must be done. I think what I have outlined above is quite reasonable. Guy -----Original Message----- From: linux-raid-owner@xxxxxxxxxxxxxxx [mailto:linux-raid-owner@xxxxxxxxxxxxxxx] On Behalf Of Peter T. Breuer Sent: Monday, March 21, 2005 3:45 PM To: linux-raid@xxxxxxxxxxxxxxx Subject: Re: [PATCH 1/2] md bitmap bug fixes Paul Clements <paul.clements@xxxxxxxxxxxx> wrote: > At any rate, this is all irrelevant given the second part of that email > reply that I gave. You still have to do the bitmap combining, regardless > of whether two systems were active at the same time or not. As I understand it, you want both bitmaps in order to make sure that on resync you wipe over whatever may have been accidentally dirtied on the other side by a clumsy admin or vicious gremlin (various guises - software bug, journal effects, design incompetency, etc.). Writing everything across (and ignoring the bitmap) would do the trick, but given that we are being efficient and using bitmaps to lower the write totals at resync time, we need to use both bitmaps so as not to miss out on overwriting anything we should be overwriting. But why don't we already know from the _single_ bitmap on the array node ("the node with the array") what to rewrite in total? All writes must go through the array. We know how many didn't go to both components. Thus we know how many to rewrite from the survivor to the component that we lost contact with. Might some of the writes we don't think made it to the faulty component actually have made it? Sure. But so what? On resync we will rewrite them because we don't think they made it. Puzzling! Peter - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
