The following commit has been merged in the linux branch: commit 4b27e1bb442e964903f8a3fa6bdf33a602dc0941 Author: Shaohua Li shaohua.li@intel.com Date: Tue Nov 3 20:25:02 2009 +0100

cfq-iosched: limit coop preemption

CFQ has an optimization for cooperated applications. if several io-context have close requests, they will get boost. But the optimization get abused. Considering thread a, b, which work on one file. a reads sectors s, s+2, s+4, ...; b reads sectors s+1, s+3, s +5, ... Both a and b are sequential read, so they can open idle window. a reads a sector s and goes to idle window and wakeup b. b reads sector s+1, since in current implementation, cfq_should_preempt() thinks a and b are cooperators, b will preempt a. b then reads sector s+1 and goes to idle window and wakeup a. for the same reason, a will preempt b and reads s+2. a and b will continue the circle. The circle will be very long, and a and b will occupy whole disk queue. Other applications will nearly have no chance to run.

Fix this limiting coop preempt until a queue is scheduled normally again.

Signed-off-by: Shaohua Li shaohua.li@intel.com Acked-by: Jeff Moyer jmoyer@redhat.com Signed-off-by: Jens Axboe jens.axboe@oracle.com

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 5802e32..aa1e953 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -196,6 +196,7 @@ enum cfqq_state_flags { CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */ CFQ_CFQQ_FLAG_sync, /* synchronous queue */ CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */ + CFQ_CFQQ_FLAG_coop_preempt, /* coop preempt */ };

#define CFQ_CFQQ_FNS(name) \ @@ -222,6 +223,7 @@ CFQ_CFQQ_FNS(prio_changed); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); CFQ_CFQQ_FNS(coop); +CFQ_CFQQ_FNS(coop_preempt); #undef CFQ_CFQQ_FNS

#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ @@ -945,10 +947,13 @@ static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, { if (!cfqq) { cfqq = cfq_get_next_queue(cfqd); - if (cfqq) + if (cfqq && !cfq_cfqq_coop_preempt(cfqq)) cfq_clear_cfqq_coop(cfqq); }

+ if (cfqq) + cfq_clear_cfqq_coop_preempt(cfqq); + __cfq_set_active_queue(cfqd, cfqq); return cfqq; } @@ -2066,8 +2071,16 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * if this request is as-good as one we would expect from the * current cfqq, let it preempt */ - if (cfq_rq_close(cfqd, rq)) + if (cfq_rq_close(cfqd, rq) && (!cfq_cfqq_coop(new_cfqq) || + cfqd->busy_queues == 1)) { + /* + * Mark new queue coop_preempt, so its coop flag will not be + * cleared when new queue gets scheduled at the very first time + */ + cfq_mark_cfqq_coop_preempt(new_cfqq); + cfq_mark_cfqq_coop(new_cfqq); return true; + }

return false; }