Re: [patch] pktgen: bug when calling ndelay in x86 architectures
From: Daniel Turull <hidden>
Date: 2011-10-20 13:23:04
Possibly related (same subject, not in this thread)
- 2011-10-20 · Re: [patch] pktgen: bug when calling ndelay in x86 architectures · David Miller <davem@davemloft.net>
- 2011-10-20 · Re: [patch] pktgen: bug when calling ndelay in x86 architectures · Eric Dumazet <hidden>
- 2011-10-20 · Re: [patch] pktgen: bug when calling ndelay in x86 architectures · David Miller <davem@davemloft.net>
- 2011-10-18 · Re: [patch] pktgen: bug when calling ndelay in x86 architectures · Eric Dumazet <hidden>
- 2011-10-18 · Re: [patch] pktgen: bug when calling ndelay in x86 architectures · Ben Hutchings <hidden>
Hi, I tested the patch and it works well. On 10/19/2011 12:13 PM, Eric Dumazet wrote:
Le mercredi 19 octobre 2011 à 11:33 +0200, Daniel Turull a écrit :quoted
Hi, then if we want to use the spin more often. maybe we can increase the constant from 100000 (0.1ms) to 1000000 (1ms)? How was the current value chosen?Based on user needs ;)
I think if we increase the constant to 1ms, we will reduce the jitter if we have a rate between 1kpps and 10 kpps, but I guess is not a big deal. I've plot this new graph with this patch: http://tslab.ssvl.kth.se/pktgen/img/inter_eric1.eps
quoted hunk ↗ jump to hunk
quoted
I did some measurements of the inter-arrival time between packets and with bigger values the maximal is reduced in the rates between 2kpps and 20kpps.ndelay()/udelay() have some inaccuracies, for 'long' values, because of rounding errors. If we spin, just call ktime_now() in a loop until spin_until is reached... That way you get max possible resolution, given kernel time service constraints. Untested patch :diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 38d6577..5c7e900 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c@@ -2145,9 +2145,11 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) } start_time = ktime_now(); - if (remaining < 100000) - ndelay(remaining); /* really small just spin */ - else { + if (remaining < 100000) { + do { + end_time = ktime_now(); + } while (ktime_lt(end_time, spin_until)); + } else { /* see do_nanosleep */ hrtimer_init_sleeper(&t, current); do {@@ -2162,8 +2164,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_cancel(&t.timer); } while (t.task && pkt_dev->running && !signal_pending(current)); __set_current_state(TASK_RUNNING); + end_time = ktime_now(); } - end_time = ktime_now(); pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
Daniel