Messages in this thread | | | Date | Thu, 26 Jul 2007 17:16:24 +0200 | From | John Sigler <> | Subject | Re: Pin-pointing the root of unusual application latencies |
| |
[ Adding linux-net to the mix ]
John Sigler wrote:
> ( check_dektec_in-1095 |#0): new 271 us user-latency. > ( check_dektec_in-1095 |#0): new 275 us user-latency. > ( check_dektec_in-1095 |#0): new 290 us user-latency. > ( check_dektec_in-1095 |#0): new 297 us user-latency. > ( check_dektec_in-1095 |#0): new 345 us user-latency. > ( check_dektec_in-1095 |#0): new 358 us user-latency. > ( check_dektec_in-1095 |#0): new 384 us user-latency. > ( check_dektec_in-1095 |#0): new 392 us user-latency. > ( check_dektec_in-1095 |#0): new 395 us user-latency. > ( check_dektec_in-1095 |#0): new 396 us user-latency. > ( check_dektec_in-1095 |#0): new 1031 us user-latency. > ( check_dektec_in-1095 |#0): new 1100 us user-latency. > ( check_dektec_in-1095 |#0): new 1105 us user-latency. > ( check_dektec_in-1095 |#0): new 1106 us user-latency. > > Here's the function trace for the 1106-µs latency: > > http://linux.kernel.free.fr/latency/1106-us-trace.txt > > These two lines repeat ~2000 times for ~800 µs: > > softirq--4 0.... 272us : __lock_text_start (rt_run_flush) > softirq--4 0.... 272us : rt_spin_unlock (rt_run_flush) > > With a pair of the following in the middle: > > softirq--4 0.... 670us : call_rcu (rt_run_flush) > softirq--4 0D..1 670us : __rcu_advance_callbacks (call_rcu)
Could someone explain why the kernel is "spinning" in rt_run_flush. http://lxr.linux.no/source/net/ipv4/route.c#L692 What is the kernel trying to do?
Is the kernel in the following loop?
701 for (i = rt_hash_mask; i >= 0; i--) { 702 spin_lock_bh(rt_hash_lock_addr(i)); 703 rth = rt_hash_table[i].chain; 704 if (rth) 705 rt_hash_table[i].chain = NULL; 706 spin_unlock_bh(rt_hash_lock_addr(i));
Line 702 would be __lock_text_start (rt_run_flush) Line 706 would be rt_spin_unlock Is that correct?
And this would be done 2000 times because rt_hash_mask=2000?
Regards. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |