sched: fix port time rounding

The QoS scheduler works off port time that is computed from the number
of CPU cycles that have elapsed since the last time the port was
polled.   It divides the number of elapsed cycles to calculate how
many bytes can be sent, however this division can generate rounding
errors, where some fraction of a byte sent may be lost.

Lose enough of these fractional bytes and the QoS scheduler
underperforms.  The problem is worse with low bandwidths.

To compensate for this rounding error this fix doesn't advance the
port's time_cpu_cycles by the number of cycles that have elapsed,
but by multiplying the computed number of bytes that can be sent
(which has been rounded down) by number of cycles per byte.
This will mean that port's time_cpu_cycles will lag behind the CPU
cycles momentarily.  At the next poll, the lag will be taken into
account.

Fixes: de3cfa2c98 ("sched: initial import")
Cc: stable@dpdk.org
Signed-off-by: Alan Dewar <alan.dewar@att.com>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>

diff --git a/lib/librte_sched/rte_sched.c b/lib/librte_sched/rte_sched.c
index 68a171b..0fa0741 100644 (file)
--- a/lib/librte_sched/rte_sched.c
+++ b/lib/librte_sched/rte_sched.c
@@ -222,6 +222,7 @@ struct rte_sched_port {
        uint64_t time_cpu_bytes;      /* Current CPU time measured in bytes */
        uint64_t time;                /* Current NIC TX time measured in bytes */
        struct rte_reciprocal inv_cycles_per_byte; /* CPU cycles per byte */
+       uint64_t cycles_per_byte;
 
        /* Grinders */
        struct rte_mbuf **pkts_out;
@@ -852,6 +853,7 @@ rte_sched_port_config(struct rte_sched_port_params *params)
        cycles_per_byte = (rte_get_tsc_hz() << RTE_SCHED_TIME_SHIFT)
                / params->rate;
        port->inv_cycles_per_byte = rte_reciprocal_value(cycles_per_byte);
+       port->cycles_per_byte = cycles_per_byte;
 
        /* Grinders */
        port->pkts_out = NULL;
@@ -2673,16 +2675,21 @@ static inline void
 rte_sched_port_time_resync(struct rte_sched_port *port)
 {
        uint64_t cycles = rte_get_tsc_cycles();
-       uint64_t cycles_diff = cycles - port->time_cpu_cycles;
+       uint64_t cycles_diff;
        uint64_t bytes_diff;
        uint32_t i;
 
+       if (cycles < port->time_cpu_cycles)
+               port->time_cpu_cycles = 0;
+
+       cycles_diff = cycles - port->time_cpu_cycles;
        /* Compute elapsed time in bytes */
        bytes_diff = rte_reciprocal_divide(cycles_diff << RTE_SCHED_TIME_SHIFT,
                                           port->inv_cycles_per_byte);
 
        /* Advance port time */
-       port->time_cpu_cycles = cycles;
+       port->time_cpu_cycles +=
+               (bytes_diff * port->cycles_per_byte) >> RTE_SCHED_TIME_SHIFT;
        port->time_cpu_bytes += bytes_diff;
        if (port->time < port->time_cpu_bytes)
                port->time = port->time_cpu_bytes;