| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4A568444.7010307@itcare.pl>
Date: Fri, 10 Jul 2009 01:59:00 +0200
From: Paweł Staszewski <pstaszewski@...are.pl>
To: Jarek Poplawski <jarkao2@...il.com>
CC: Eric Dumazet <dada1@...mosbay.com>,
Eric Dumazet <eric.dumazet@...il.com>,
Linux Network Development list <netdev@...r.kernel.org>
Subject: Re: weird problem
Today i make other tests with change of
/proc/sys/net/ipv4/rt_cache_rebuild_count and kernel 2.6.30.1
And when rt_cache_rebuild_count is set to "-1" i have always load on
x86_64 machine approx 40-50% of each cpu where network card is binded by
irq_aff
when rt_cache_rebuild_count is set to more than "-1" i have 15 to 20 sec
of 1 to 3% cpu and after 40-50% cpu
I attach some oprofile output for
rt_cache_rebuild_count = 4 - oprofile_rt_cache_rebuild_count_4.txt
and
rt_cache_rebuild_count = -1 - oprofile_rt_cache_rebuild_count_-1.txt
Regards
Pawel Staszewski
Paweł Staszewski pisze:
> Jarek Poplawski pisze:
>> Pawel Staszewski wrote, On 06/30/2009 10:36 AM:
>> ...
>>
>>>>>>> rt_worker_func() taking 13% of cpu0 is an alarm for me :)
>>>>>>> And 21% of cpu0 and 34% of cpu6 taken by oprofiled seems odd too...
>>>>>>>
>>
>> Pawel, here is a patch which changes this function (or what it calls)
>> back to 2.6.28 version; I'm not sure it's OK, so try it very
>> cautiously...
>>
>> Cheers,
>> Jarek P.
>> --- (for debugging only; apply to 2.6.29.5 or .6)
>>
>>
> I added this patch 30min ago - all is working but problem still exist.
>
> There is only one change - without this patch cpu load was rising from
> 40 to 50%
> With this patch there is 15 to 25% cpu load.
>
>
>> diff -Nurp a/net/ipv4/route.c b/net/ipv4/route.c
>> --- a/net/ipv4/route.c 2009-07-08 23:42:15.000000000 +0200
>> +++ b/net/ipv4/route.c 2009-07-08 22:47:52.000000000 +0200
>> @@ -769,24 +769,11 @@ static void rt_do_flush(int process_cont
>> }
>> }
>>
>> -/*
>> - * While freeing expired entries, we compute average chain length
>> - * and standard deviation, using fixed-point arithmetic.
>> - * This to have an estimation of rt_chain_length_max
>> - * rt_chain_length_max = max(elasticity, AVG + 4*SD)
>> - * We use 3 bits for frational part, and 29 (or 61) for magnitude.
>> - */
>> -
>> -#define FRACT_BITS 3
>> -#define ONE (1UL << FRACT_BITS)
>> -
>> static void rt_check_expire(void)
>> {
>> static unsigned int rover;
>> unsigned int i = rover, goal;
>> - struct rtable *rth, *aux, **rthp;
>> - unsigned long samples = 0;
>> - unsigned long sum = 0, sum2 = 0;
>> + struct rtable *rth, **rthp;
>> u64 mult;
>>
>> mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
>> @@ -797,7 +784,6 @@ static void rt_check_expire(void)
>> goal = rt_hash_mask + 1;
>> for (; goal > 0; goal--) {
>> unsigned long tmo = ip_rt_gc_timeout;
>> - unsigned long length;
>>
>> i = (i + 1) & rt_hash_mask;
>> rthp = &rt_hash_table[i].chain;
>> @@ -805,14 +791,10 @@ static void rt_check_expire(void)
>> if (need_resched())
>> cond_resched();
>>
>> - samples++;
>> -
>> if (*rthp == NULL)
>> continue;
>> - length = 0;
>> spin_lock_bh(rt_hash_lock_addr(i));
>> while ((rth = *rthp) != NULL) {
>> - prefetch(rth->u.dst.rt_next);
>> if (rt_is_expired(rth)) {
>> *rthp = rth->u.dst.rt_next;
>> rt_free(rth);
>> @@ -821,46 +803,23 @@ static void rt_check_expire(void)
>> if (rth->u.dst.expires) {
>> /* Entry is expired even if it is in use */
>> if (time_before_eq(jiffies, rth->u.dst.expires)) {
>> -nofree:
>> tmo >>= 1;
>> rthp = &rth->u.dst.rt_next;
>> - /*
>> - * We only count entries on
>> - * a chain with equal hash inputs once
>> - * so that entries for different QOS
>> - * levels, and other non-hash input
>> - * attributes don't unfairly skew
>> - * the length computation
>> - */
>> - for (aux = rt_hash_table[i].chain;;) {
>> - if (aux == rth) {
>> - length += ONE;
>> - break;
>> - }
>> - if (compare_hash_inputs(&aux->fl, &rth->fl))
>> - break;
>> - aux = aux->u.dst.rt_next;
>> - }
>> continue;
>> }
>> - } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
>> - goto nofree;
>> + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
>> + tmo >>= 1;
>> + rthp = &rth->u.dst.rt_next;
>> + continue;
>> + }
>>
>> /* Cleanup aged off entries. */
>> *rthp = rth->u.dst.rt_next;
>> rt_free(rth);
>> }
>> spin_unlock_bh(rt_hash_lock_addr(i));
>> - sum += length;
>> - sum2 += length*length;
>> - }
>> - if (samples) {
>> - unsigned long avg = sum / samples;
>> - unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
>> - rt_chain_length_max = max_t(unsigned long,
>> - ip_rt_gc_elasticity,
>> - (avg + 4*sd) >> FRACT_BITS);
>> }
>> + rt_chain_length_max = ip_rt_gc_elasticity;
>> rover = i;
>> }
>>
>>
>>
>>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
>
View attachment "oprofile_rt_cache_rebuild_count_4.txt" of type "text/plain" (5411 bytes)
View attachment "oprofile_rt_cache_rebuild_count_-1.txt" of type "text/plain" (5414 bytes)
Powered by blists - more mailing lists