diff options
| author | Kaike Wan <kaike.wan@intel.com> | 2017-07-24 17:45:37 +0300 |
|---|---|---|
| committer | Doug Ledford <dledford@redhat.com> | 2017-07-31 22:17:54 +0300 |
| commit | bcad29137a9731bfa5e16d64bf8e8a71a268ac88 (patch) | |
| tree | f7c1706567ae5e887a5046607a5e8d11f837ab24 /drivers/infiniband/hw/hfi1/user_sdma.c | |
| parent | cb51c5d2cda855302910ab352f3d391c1a00aba0 (diff) | |
| download | linux-bcad29137a9731bfa5e16d64bf8e8a71a268ac88.tar.xz | |
IB/hfi1: Serve the most starved iowait entry first
When an egress resource(SDMA descriptors, pio credits) is not available,
a sending thread will be put on the resource's wait queue. When the
resource becomes available again, up to a fixed number of sending threads
can be awakened sequentially and removed from the wait queue, depending
on the number of waiting threads and the number of free resources. Since
each awakened sending thread will send as many packets as possible, it
is highly likely that the first sending thread will consume all the
egress resources. Subsequently, it will be put back to the end of the wait
queue. Depending on the timing when the later sending threads wake up,
they may not be able to send any packet and be again put back to the end
of the wait queue sequentially, right behind the first sending thread.
This starvation cycle continues until some sending threads exceed their
retry limit and consequently fail.
This patch fixes the issue by two simple approaches:
(1) Any starved sending thread will be put to the head of the wait queue
while a served sending thread will be put to the tail;
(2) The most starved sending thread will be served first.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Diffstat (limited to 'drivers/infiniband/hw/hfi1/user_sdma.c')
| -rw-r--r-- | drivers/infiniband/hw/hfi1/user_sdma.c | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 8f7cfdd9e9ec..ea2993f93647 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -272,7 +272,8 @@ static int defer_packet_queue( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *txreq, - unsigned int seq); + uint seq, + bool pkts_sent); static void activate_packet_queue(struct iowait *wait, int reason); static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len); @@ -294,7 +295,8 @@ static int defer_packet_queue( struct sdma_engine *sde, struct iowait *wait, struct sdma_txreq *txreq, - unsigned seq) + uint seq, + bool pkts_sent) { struct hfi1_user_sdma_pkt_q *pq = container_of(wait, struct hfi1_user_sdma_pkt_q, busy); @@ -314,7 +316,7 @@ static int defer_packet_queue( xchg(&pq->state, SDMA_PKT_Q_DEFERRED); write_seqlock(&dev->iowait_lock); if (list_empty(&pq->busy.list)) - list_add_tail(&pq->busy.list, &sde->dmawait); + iowait_queue(pkts_sent, &pq->busy, &sde->dmawait); write_sequnlock(&dev->iowait_lock); return -EBUSY; eagain: |