I tried these patches and I still don’t see barriers working. Do I have to enable to device mapper to see the effect ? -------- log ----- ~ # ~ # mount -o barrier=1 /dev/md0 /mnt/tmpmnt/ kjournald starting. Commit interval 5 seconds EXT3 FS on md0, internal journal EXT3-fs: mounted filesystem with writeback data mode. ~ # touch /mnt/tmpmnt/test ~ # sync JBD: barrier-based sync failed on md0 - disabling barriers ~ # From: linux-raid-owner@xxxxxxxxxxxxxxx [mailto:linux-raid-owner@xxxxxxxxxxxxxxx] On Behalf Of NeilBrown Sent: Thursday, December 03, 2009 10:48 PM To: linux-raid@xxxxxxxxxxxxxxx Subject: [md PATCH 05/22] md/raid5: don't complete make_request on barrieruntil writes are scheduled This message has been archived. View the original item <http://sdcmailvault.ad.amcc.com/EnterpriseVault/ViewMessage.asp?VaultId=1E9560FDB597EB744B7F046F24F9462D91110000sdcmailvault.ad.amcc.com&SavesetId=821000000000000~200912040648020000~0~73C17918B4764F9EBF4C8875EC1437B> The post-barrier-flush is sent be md as soon as make_request on the barrier write completes. For raid5, the data might not be in the per-device queues yet. So for barrier requests, wait for any pre-reading to be done so that the request will be in the per-device queues. We use the 'preread_active' count to check that nothing is still in the preread phase, and delay the decrement of this count until after write requests have been submitted to the underlying devices. Signed-off-by: NeilBrown <neilb@xxxxxxx> --- drivers/md/raid5.c | 51 +++++++++++++++++++++++++++++++++++++++------------ 1 files changed, 39 insertions(+), 12 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ecf89c8..8c772b2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2947,6 +2947,7 @@ static void handle_stripe5(struct stripe_head *sh) struct r5dev *dev; mdk_rdev_t *blocked_rdev = NULL; int prexor; + int dec_preread_active = 0; memset(&s, 0, sizeof(s)); pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d " @@ -3096,12 +3097,8 @@ static void handle_stripe5(struct stripe_head *sh) set_bit(STRIPE_INSYNC, &sh->state); } } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < - IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + dec_preread_active = 1; } /* Now to consider new write requests and what else, if anything @@ -3208,6 +3205,16 @@ static void handle_stripe5(struct stripe_head *sh) ops_run_io(sh, &s); + if (dec_preread_active) { + /* We delay this until after ops_run_io so that if make_request + * is waiting on a barrier, it won't continue until the writes + * have actually been submitted. + */ + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } return_io(return_bi); } @@ -3221,6 +3228,7 @@ static void handle_stripe6(struct stripe_head *sh) struct r6_state r6s; struct r5dev *dev, *pdev, *qdev; mdk_rdev_t *blocked_rdev = NULL; + int dec_preread_active = 0; pr_debug("handling stripe %llu, state=%#lx cnt=%d, " "pd_idx=%d, qd_idx=%d, check:%d, reconstruct:%d", @@ -3380,12 +3388,8 @@ static void handle_stripe6(struct stripe_head *sh) set_bit(STRIPE_INSYNC, &sh->state); } } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < - IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + dec_preread_active = 1; } /* Now to consider new write requests and what else, if anything @@ -3494,6 +3498,18 @@ static void handle_stripe6(struct stripe_head *sh) ops_run_io(sh, &s); + + if (dec_preread_active) { + /* We delay this until after ops_run_io so that if make_request + * is waiting on a barrier, it won't continue until the writes + * have actually been submitted. + */ + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } + return_io(return_bi); } @@ -3996,6 +4012,9 @@ static int make_request(struct request_queue *q, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); + if (mddev->barrier && + !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) + atomic_inc(&conf->preread_active_stripes); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4015,6 +4034,14 @@ static int make_request(struct request_queue *q, struct bio * bi) bio_endio(bi, 0); } + + if (mddev->barrier) { + /* We need to wait for the stripes to all be handled. + * So: wait for preread_active_stripes to drop to 0. + */ + wait_event(mddev->thread->wqueue, + atomic_read(&conf->preread_active_stripes) == 0); + } return 0; } -- 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
<<winmail.dat>>
