From mboxrd@z Thu Jan 1 00:00:00 1970 From: NeilBrown Subject: [PATCH] md - 3 of 3 - Handle concurrent failure of two drives in raid5 Date: Wed, 18 Jun 2003 10:28:46 +1000 Sender: linux-raid-owner@vger.kernel.org Message-ID: Return-path: To: Marcelo Tosatti Cc: linux-raid@vger.kernel.org List-Id: linux-raid.ids ### Comments for ChangeSet If two drives both fail during a write request, raid5 doesn't cope properly and will eventually oops. With this patch, blocks that have already been 'written' are failed when double drive failure is noticed, as well as blocks that are about to be written. ----------- Diffstat output ------------ ./drivers/md/raid5.c | 10 +++++++++- 1 files changed, 9 insertions(+), 1 deletion(-) diff ./drivers/md/raid5.c~current~ ./drivers/md/raid5.c --- ./drivers/md/raid5.c~current~ 2003-06-18 10:04:15.000000000 +1000 +++ ./drivers/md/raid5.c 2003-06-18 10:04:15.000000000 +1000 @@ -882,7 +882,7 @@ static void handle_stripe(struct stripe_ /* check if the array has lost two devices and, if so, some requests might * need to be failed */ - if (failed > 1 && to_read+to_write) { + if (failed > 1 && to_read+to_write+written) { for (i=disks; i--; ) { /* fail all writes first */ if (sh->bh_write[i]) to_write--; @@ -891,6 +891,14 @@ static void handle_stripe(struct stripe_ bh->b_reqnext = return_fail; return_fail = bh; } + /* and fail all 'written' */ + if (sh->bh_written[i]) written--; + while ((bh = sh->bh_written[i])) { + sh->bh_written[i] = bh->b_reqnext; + bh->b_reqnext = return_fail; + return_fail = bh; + } + /* fail any reads if this device is non-operational */ if (!conf->disks[i].operational) { spin_lock_irq(&conf->device_lock);