[ 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-net" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
