| Message ID | 20230627120854.971475-3-chengming.zhou@linux.dev (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | blk-mq: optimize the size of struct request | expand |
On Tue, Jun 27, 2023 at 08:08:52PM +0800, chengming.zhou@linux.dev wrote: > From: Chengming Zhou <zhouchengming@bytedance.com> > > The flush state machine use a double list to link all inflight > flush_data requests, to avoid issuing separate post-flushes for > these flush_data requests which shared PREFLUSH. > > So we can't reuse rq->queuelist, this is why we need rq->flush.list > > In preparation of the next patch that reuse rq->queuelist for flush > state machine, we change the double linked list to a u64 counter, > which count all inflight flush_data requests. > > This is ok since we only need to know if there is any inflight > flush_data request, so a u64 counter is good. The only problem I can > think of is that u64 counter may overflow, which should be unlikely happen. It won't overflow, q->nr_requests is 'unsigned long', which should have been limited to one more reasonable value, such as 2 * BLK_MQ_MAX_DEPTH, so u16 should be big enough in theory. > > Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> > --- > block/blk-flush.c | 9 +++++---- > block/blk.h | 5 ++--- > 2 files changed, 7 insertions(+), 7 deletions(-) > > diff --git a/block/blk-flush.c b/block/blk-flush.c > index dba392cf22be..bb7adfc2a5da 100644 > --- a/block/blk-flush.c > +++ b/block/blk-flush.c > @@ -187,7 +187,8 @@ static void blk_flush_complete_seq(struct request *rq, > break; > > case REQ_FSEQ_DATA: > - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); > + list_del_init(&rq->flush.list); > + fq->flush_data_in_flight++; > spin_lock(&q->requeue_lock); > list_add_tail(&rq->queuelist, &q->flush_list); > spin_unlock(&q->requeue_lock); > @@ -299,7 +300,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, > return; > > /* C2 and C3 */ > - if (!list_empty(&fq->flush_data_in_flight) && > + if (fq->flush_data_in_flight && > time_before(jiffies, > fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) > return; > @@ -374,6 +375,7 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, > * the comment in flush_end_io(). > */ > spin_lock_irqsave(&fq->mq_flush_lock, flags); > + fq->flush_data_in_flight--; > blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); > spin_unlock_irqrestore(&fq->mq_flush_lock, flags); > > @@ -445,7 +447,7 @@ bool blk_insert_flush(struct request *rq) > blk_rq_init_flush(rq); > rq->flush.seq |= REQ_FSEQ_POSTFLUSH; > spin_lock_irq(&fq->mq_flush_lock); > - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); > + fq->flush_data_in_flight++; > spin_unlock_irq(&fq->mq_flush_lock); > return false; > default: > @@ -496,7 +498,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, > > INIT_LIST_HEAD(&fq->flush_queue[0]); > INIT_LIST_HEAD(&fq->flush_queue[1]); > - INIT_LIST_HEAD(&fq->flush_data_in_flight); > > return fq; > > diff --git a/block/blk.h b/block/blk.h > index 608c5dcc516b..686712e13835 100644 > --- a/block/blk.h > +++ b/block/blk.h > @@ -15,15 +15,14 @@ struct elevator_type; > extern struct dentry *blk_debugfs_root; > > struct blk_flush_queue { > + spinlock_t mq_flush_lock; > unsigned int flush_pending_idx:1; > unsigned int flush_running_idx:1; > blk_status_t rq_status; > unsigned long flush_pending_since; > struct list_head flush_queue[2]; > - struct list_head flush_data_in_flight; > + unsigned long flush_data_in_flight; > struct request *flush_rq; > - > - spinlock_t mq_flush_lock; > }; The part of replacing inflight data rq list with counter looks fine. Thanks, Ming
On 2023/6/28 12:13, Ming Lei wrote: > On Tue, Jun 27, 2023 at 08:08:52PM +0800, chengming.zhou@linux.dev wrote: >> From: Chengming Zhou <zhouchengming@bytedance.com> >> >> The flush state machine use a double list to link all inflight >> flush_data requests, to avoid issuing separate post-flushes for >> these flush_data requests which shared PREFLUSH. >> >> So we can't reuse rq->queuelist, this is why we need rq->flush.list >> >> In preparation of the next patch that reuse rq->queuelist for flush >> state machine, we change the double linked list to a u64 counter, >> which count all inflight flush_data requests. >> >> This is ok since we only need to know if there is any inflight >> flush_data request, so a u64 counter is good. The only problem I can >> think of is that u64 counter may overflow, which should be unlikely happen. > > It won't overflow, q->nr_requests is 'unsigned long', which should have > been limited to one more reasonable value, such as 2 * BLK_MQ_MAX_DEPTH, so > u16 should be big enough in theory. Ah, right. q->nr_requests is 'unsigned long' and q->queue_depth is 'unsigned int', so 'unsigned long' counter here won't overflow. Should I change it to smaller 'unsigned short' or just leave it as 'unsigned long' ? (Now the size of struct blk_flush_queue is exactly 64 bytes) Thanks. > >> >> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> >> --- >> block/blk-flush.c | 9 +++++---- >> block/blk.h | 5 ++--- >> 2 files changed, 7 insertions(+), 7 deletions(-) >> >> diff --git a/block/blk-flush.c b/block/blk-flush.c >> index dba392cf22be..bb7adfc2a5da 100644 >> --- a/block/blk-flush.c >> +++ b/block/blk-flush.c >> @@ -187,7 +187,8 @@ static void blk_flush_complete_seq(struct request *rq, >> break; >> >> case REQ_FSEQ_DATA: >> - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); >> + list_del_init(&rq->flush.list); >> + fq->flush_data_in_flight++; >> spin_lock(&q->requeue_lock); >> list_add_tail(&rq->queuelist, &q->flush_list); >> spin_unlock(&q->requeue_lock); >> @@ -299,7 +300,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, >> return; >> >> /* C2 and C3 */ >> - if (!list_empty(&fq->flush_data_in_flight) && >> + if (fq->flush_data_in_flight && >> time_before(jiffies, >> fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) >> return; >> @@ -374,6 +375,7 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, >> * the comment in flush_end_io(). >> */ >> spin_lock_irqsave(&fq->mq_flush_lock, flags); >> + fq->flush_data_in_flight--; >> blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); >> spin_unlock_irqrestore(&fq->mq_flush_lock, flags); >> >> @@ -445,7 +447,7 @@ bool blk_insert_flush(struct request *rq) >> blk_rq_init_flush(rq); >> rq->flush.seq |= REQ_FSEQ_POSTFLUSH; >> spin_lock_irq(&fq->mq_flush_lock); >> - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); >> + fq->flush_data_in_flight++; >> spin_unlock_irq(&fq->mq_flush_lock); >> return false; >> default: >> @@ -496,7 +498,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, >> >> INIT_LIST_HEAD(&fq->flush_queue[0]); >> INIT_LIST_HEAD(&fq->flush_queue[1]); >> - INIT_LIST_HEAD(&fq->flush_data_in_flight); >> >> return fq; >> >> diff --git a/block/blk.h b/block/blk.h >> index 608c5dcc516b..686712e13835 100644 >> --- a/block/blk.h >> +++ b/block/blk.h >> @@ -15,15 +15,14 @@ struct elevator_type; >> extern struct dentry *blk_debugfs_root; >> >> struct blk_flush_queue { >> + spinlock_t mq_flush_lock; >> unsigned int flush_pending_idx:1; >> unsigned int flush_running_idx:1; >> blk_status_t rq_status; >> unsigned long flush_pending_since; >> struct list_head flush_queue[2]; >> - struct list_head flush_data_in_flight; >> + unsigned long flush_data_in_flight; >> struct request *flush_rq; >> - >> - spinlock_t mq_flush_lock; >> }; > > The part of replacing inflight data rq list with counter looks fine. > > Thanks, > Ming >
On Wed, Jun 28, 2023 at 12:55:49PM +0800, Chengming Zhou wrote: > On 2023/6/28 12:13, Ming Lei wrote: > > On Tue, Jun 27, 2023 at 08:08:52PM +0800, chengming.zhou@linux.dev wrote: > >> From: Chengming Zhou <zhouchengming@bytedance.com> > >> > >> The flush state machine use a double list to link all inflight > >> flush_data requests, to avoid issuing separate post-flushes for > >> these flush_data requests which shared PREFLUSH. > >> > >> So we can't reuse rq->queuelist, this is why we need rq->flush.list > >> > >> In preparation of the next patch that reuse rq->queuelist for flush > >> state machine, we change the double linked list to a u64 counter, > >> which count all inflight flush_data requests. > >> > >> This is ok since we only need to know if there is any inflight > >> flush_data request, so a u64 counter is good. The only problem I can > >> think of is that u64 counter may overflow, which should be unlikely happen. > > > > It won't overflow, q->nr_requests is 'unsigned long', which should have > > been limited to one more reasonable value, such as 2 * BLK_MQ_MAX_DEPTH, so > > u16 should be big enough in theory. > > Ah, right. q->nr_requests is 'unsigned long' and q->queue_depth is 'unsigned int', > so 'unsigned long' counter here won't overflow. Not like q->nr_requests, q->queue_depth usually means the whole queue's depth, which may cover all hw queue's depth. And it is only used by scsi, but it should be held in "unsigned short" too. > > Should I change it to smaller 'unsigned short' or just leave it as 'unsigned long' ? > (Now the size of struct blk_flush_queue is exactly 64 bytes) You have to limit q->nr_requests first, which may need a bit more work for avoiding compiling warning or sort of thing. And 64k is big enough for holding per-queue scheduler request. Once it is done, it is fine to define this counter as 'unsigned short'. Thanks, Ming
On 2023/6/28 15:22, Ming Lei wrote: > On Wed, Jun 28, 2023 at 12:55:49PM +0800, Chengming Zhou wrote: >> On 2023/6/28 12:13, Ming Lei wrote: >>> On Tue, Jun 27, 2023 at 08:08:52PM +0800, chengming.zhou@linux.dev wrote: >>>> From: Chengming Zhou <zhouchengming@bytedance.com> >>>> >>>> The flush state machine use a double list to link all inflight >>>> flush_data requests, to avoid issuing separate post-flushes for >>>> these flush_data requests which shared PREFLUSH. >>>> >>>> So we can't reuse rq->queuelist, this is why we need rq->flush.list >>>> >>>> In preparation of the next patch that reuse rq->queuelist for flush >>>> state machine, we change the double linked list to a u64 counter, >>>> which count all inflight flush_data requests. >>>> >>>> This is ok since we only need to know if there is any inflight >>>> flush_data request, so a u64 counter is good. The only problem I can >>>> think of is that u64 counter may overflow, which should be unlikely happen. >>> >>> It won't overflow, q->nr_requests is 'unsigned long', which should have >>> been limited to one more reasonable value, such as 2 * BLK_MQ_MAX_DEPTH, so >>> u16 should be big enough in theory. >> >> Ah, right. q->nr_requests is 'unsigned long' and q->queue_depth is 'unsigned int', >> so 'unsigned long' counter here won't overflow. > > Not like q->nr_requests, q->queue_depth usually means the whole queue's depth, > which may cover all hw queue's depth. And it is only used by scsi, but it > should be held in "unsigned short" too. > >> >> Should I change it to smaller 'unsigned short' or just leave it as 'unsigned long' ? >> (Now the size of struct blk_flush_queue is exactly 64 bytes) > > You have to limit q->nr_requests first, which may need a bit more work for avoiding > compiling warning or sort of thing. And 64k is big enough for holding per-queue > scheduler request. > > Once it is done, it is fine to define this counter as 'unsigned short'. > Ok, I looked around these related code, found it maybe subtle to me for now. So I'd better just leave it 'unsigned long' here. :) Thanks.
diff --git a/block/blk-flush.c b/block/blk-flush.c index dba392cf22be..bb7adfc2a5da 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -187,7 +187,8 @@ static void blk_flush_complete_seq(struct request *rq, break; case REQ_FSEQ_DATA: - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); + list_del_init(&rq->flush.list); + fq->flush_data_in_flight++; spin_lock(&q->requeue_lock); list_add_tail(&rq->queuelist, &q->flush_list); spin_unlock(&q->requeue_lock); @@ -299,7 +300,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, return; /* C2 and C3 */ - if (!list_empty(&fq->flush_data_in_flight) && + if (fq->flush_data_in_flight && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return; @@ -374,6 +375,7 @@ static enum rq_end_io_ret mq_flush_data_end_io(struct request *rq, * the comment in flush_end_io(). */ spin_lock_irqsave(&fq->mq_flush_lock, flags); + fq->flush_data_in_flight--; blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); @@ -445,7 +447,7 @@ bool blk_insert_flush(struct request *rq) blk_rq_init_flush(rq); rq->flush.seq |= REQ_FSEQ_POSTFLUSH; spin_lock_irq(&fq->mq_flush_lock); - list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); + fq->flush_data_in_flight++; spin_unlock_irq(&fq->mq_flush_lock); return false; default: @@ -496,7 +498,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, INIT_LIST_HEAD(&fq->flush_queue[0]); INIT_LIST_HEAD(&fq->flush_queue[1]); - INIT_LIST_HEAD(&fq->flush_data_in_flight); return fq; diff --git a/block/blk.h b/block/blk.h index 608c5dcc516b..686712e13835 100644 --- a/block/blk.h +++ b/block/blk.h @@ -15,15 +15,14 @@ struct elevator_type; extern struct dentry *blk_debugfs_root; struct blk_flush_queue { + spinlock_t mq_flush_lock; unsigned int flush_pending_idx:1; unsigned int flush_running_idx:1; blk_status_t rq_status; unsigned long flush_pending_since; struct list_head flush_queue[2]; - struct list_head flush_data_in_flight; + unsigned long flush_data_in_flight; struct request *flush_rq; - - spinlock_t mq_flush_lock; }; bool is_flush_rq(struct request *req);