Realmente, deixar essa server off é inviável.

Mas quando tive a oportunidade, desliguei e fiz a limpeza dos bancos de memória e dos pentes em cada banco, nao resolveu.

Tb acredito ser algum tipo de problema físico, mas difícil diagnosticar por ser memória ECC.

--
Eduardo Schoedler
Enviado via iPhone


Em 06/12/2011, às 12:33, Daniel da Veiga <danieldaveiga@gmail.com> escreveu:

> Sem analisar mais completamente, eu diria que existe algum problema físico na memória, mas testar (memtest) esses GBs num server é praticamente inviável (demora e o server fica off)...
> 
> Talvez retirar pentes seletivamente?
> 
> 2011/12/6 Eduardo Schoedler <listas@esds.com.br>
> Notei que não acontece somente no mysqld, vejam o "swapper" (pid 0):
> 
> [2317646.822785] swapper: page allocation failure. order:1, mode:0x20
> [2317646.822792] Pid: 0, comm: swapper Not tainted 2.6.39-gentoo-r3 #1
> [2317646.822796] Call Trace:
> [2317646.822799]  <IRQ>  [<ffffffff8109f349>] 0xffffffff8109f349
> [2317646.822807]  [<ffffffff810ce49d>] 0xffffffff810ce49d
> [2317646.822810]  [<ffffffff810cf61b>] 0xffffffff810cf61b
> [2317646.822813]  [<ffffffff810cf3fd>] 0xffffffff810cf3fd
> [2317646.822816]  [<ffffffff810cf973>] 0xffffffff810cf973
> [2317646.822819]  [<ffffffff814cedbf>] 0xffffffff814cedbf
> [2317646.822822]  [<ffffffff814cef7d>] 0xffffffff814cef7d
> [2317646.822825]  [<ffffffff815481c3>] 0xffffffff815481c3
> [2317646.822828]  [<ffffffff81561a44>] 0xffffffff81561a44
> [2317646.822831]  [<ffffffff81560768>] 0xffffffff81560768
> [2317646.822834]  [<ffffffff81561792>] 0xffffffff81561792
> [2317646.822837]  [<ffffffff8155f964>] 0xffffffff8155f964
> [2317646.822840]  [<ffffffff81528dee>] ? 0xffffffff81528dee
> [2317646.822843]  [<ffffffff81560013>] 0xffffffff81560013
> [2317646.822846]  [<ffffffff8151b456>] ? 0xffffffff8151b456
> [2317646.822849]  [<ffffffff8153e3c0>] ? 0xffffffff8153e3c0
> [2317646.822852]  [<ffffffff8153e41f>] 0xffffffff8153e41f
> [2317646.822855]  [<ffffffff8153e5c8>] 0xffffffff8153e5c8
> [2317646.822858]  [<ffffffff8153dec1>] 0xffffffff8153dec1
> [2317646.822860]  [<ffffffff8153e2fd>] 0xffffffff8153e2fd
> [2317646.822864]  [<ffffffff814dbb4a>] 0xffffffff814dbb4a
> [2317646.822866]  [<ffffffff81009479>] ? 0xffffffff81009479
> [2317646.822870]  [<ffffffff814dbf68>] 0xffffffff814dbf68
> [2317646.822873]  [<ffffffff814dc098>] 0xffffffff814dc098
> [2317646.822875]  [<ffffffff814dc5c5>] 0xffffffff814dc5c5
> [2317646.822878]  [<ffffffff81416555>] 0xffffffff81416555
> [2317646.822881]  [<ffffffff81418d54>] ? 0xffffffff81418d54
> [2317646.822884]  [<ffffffff812af390>] ? 0xffffffff812af390
> [2317646.822888]  [<ffffffff81417414>] 0xffffffff81417414
> [2317646.822891]  [<ffffffff814dc741>] 0xffffffff814dc741
> [2317646.822894]  [<ffffffff81047849>] 0xffffffff81047849
> [2317646.822897]  [<ffffffff8163ee1c>] 0xffffffff8163ee1c
> [2317646.822899]  [<ffffffff810049f5>] 0xffffffff810049f5
> [2317646.822902]  [<ffffffff810476e6>] 0xffffffff810476e6
> [2317646.822905]  [<ffffffff810041c1>] 0xffffffff810041c1
> [2317646.822908]  [<ffffffff8163d553>] 0xffffffff8163d553
> [2317646.822910]  <EOI>  [<ffffffff810628a8>] ? 0xffffffff810628a8
> [2317646.822915]  [<ffffffff8100a77e>] ? 0xffffffff8100a77e
> [2317646.822918]  [<ffffffff81001f50>] ? 0xffffffff81001f50
> [2317646.822921]  [<ffffffff81001fbf>] 0xffffffff81001fbf
> [2317646.822924]  [<ffffffff816125fd>] 0xffffffff816125fd
> [2317646.822926]  [<ffffffff81bc8c23>] 0xffffffff81bc8c23
> [2317646.822929]  [<ffffffff81bc831a>] 0xffffffff81bc831a
> [2317646.822932]  [<ffffffff81bc841f>] 0xffffffff81bc841f
> 
> 
> 
> > -----Mensagem original-----
> > De: Thiago Nunes [mailto:thiagonunesrs@gmail.com]
> > Enviada em: segunda-feira, 5 de dezembro de 2011 21:22
> > Para: gentoo-user-br@lists.gentoo.org
> > Assunto: Re: [gentoo-user-br] Problemas no Gentoo
> >
> > O core dump dá logo que levanta o mysql ou depois de um tempo rodando?
> >
> > Em 5 de dezembro de 2011 19:53, Eduardo Schoedler <listas@esds.com.br>
> > escreveu:
> > > São varias placas com vários pentes de memória. Ela usa memória ECC.
> > > Já cogitei problema de mal contato, tirei todos os pentes de todos os
> > > bancos de memória e limpei, nao resolveu.
> > >
> > > --
> > > Eduardo Schoedler
> > > Enviado via iPhone
> > >
> > > Em 05/12/2011, às 18:50, Daniel da Veiga <danieldaveiga@gmail.com>
> > escreveu:
> > >
> > > Essa máquina roda 64 bits, presumo eu? Passa mais info (quantos bancos
> > > de memória, por exemplo).
> > >
> > > On Mon, Dec 5, 2011 at 18:46, Eduardo Schoedler <listas@esds.com.br>
> > wrote:
> > >>
> > >> Pessoal.
> > >>
> > >> Alguém já passou por esse problema?
> > >> Administro um Dell R900 octa-core com 16GB RAM.
> > >> Porém, do nada, aparece um core-dump:
> > >>
> > >> [2317687.527391] mysqld: page allocation failure. order:1, mode:0x20
> > >> [2317687.527399] Pid: 16959, comm: mysqld Not tainted
> > >> 2.6.39-gentoo-r3 #1 [2317687.527402] Call Trace:
> > >> [2317687.527405]  <IRQ>  [<ffffffff8109f349>] 0xffffffff8109f349
> > >> [2317687.527413]  [<ffffffff810ce49d>] 0xffffffff810ce49d
> > >> [2317687.527416]  [<ffffffff810cf61b>] 0xffffffff810cf61b
> > >> [2317687.527420]  [<ffffffff810cf3fd>] 0xffffffff810cf3fd
> > >> [2317687.527422]  [<ffffffff810cf973>] 0xffffffff810cf973
> > >> [2317687.527425]  [<ffffffff814cedbf>] 0xffffffff814cedbf
> > >> [2317687.527428]  [<ffffffff814cef7d>] 0xffffffff814cef7d
> > >> [2317687.527431]  [<ffffffff815481c3>] 0xffffffff815481c3
> > >> [2317687.527434]  [<ffffffff81561a44>] 0xffffffff81561a44
> > >> [2317687.527437]  [<ffffffff81560768>] 0xffffffff81560768
> > >> [2317687.527440]  [<ffffffff81561792>] 0xffffffff81561792
> > >> [2317687.527443]  [<ffffffff8155f964>] 0xffffffff8155f964
> > >> [2317687.527446]  [<ffffffff81528dee>] ? 0xffffffff81528dee
> > >> [2317687.527449]  [<ffffffff81560013>] 0xffffffff81560013
> > >> [2317687.527452]  [<ffffffff8151b456>] ? 0xffffffff8151b456
> > >> [2317687.527455]  [<ffffffff8153e3c0>] ? 0xffffffff8153e3c0
> > >> [2317687.527458]  [<ffffffff8153e41f>] 0xffffffff8153e41f
> > >> [2317687.527461]  [<ffffffff8153e5c8>] 0xffffffff8153e5c8
> > >> [2317687.527464]  [<ffffffff8153dec1>] 0xffffffff8153dec1
> > >> [2317687.527467]  [<ffffffff8153e2fd>] 0xffffffff8153e2fd
> > >> [2317687.527470]  [<ffffffff814dbb4a>] 0xffffffff814dbb4a
> > >> [2317687.527472]  [<ffffffff81086bcd>] ? 0xffffffff81086bcd
> > >> [2317687.527475]  [<ffffffff81009479>] ? 0xffffffff81009479
> > >> [2317687.527478]  [<ffffffff814dbf68>] 0xffffffff814dbf68
> > >> [2317687.527481]  [<ffffffff814dc098>] 0xffffffff814dc098
> > >> [2317687.527484]  [<ffffffff814dc5c5>] 0xffffffff814dc5c5
> > >> [2317687.527487]  [<ffffffff81416555>] 0xffffffff81416555
> > >> [2317687.527490]  [<ffffffff81418d54>] ? 0xffffffff81418d54
> > >> [2317687.527493]  [<ffffffff812af390>] ? 0xffffffff812af390
> > >> [2317687.527497]  [<ffffffff81417414>] 0xffffffff81417414
> > >> [2317687.527500]  [<ffffffff814dc741>] 0xffffffff814dc741
> > >> [2317687.527503]  [<ffffffff81047849>] 0xffffffff81047849
> > >> [2317687.527506]  [<ffffffff8163ee1c>] 0xffffffff8163ee1c
> > >> [2317687.527508]  [<ffffffff810049f5>] 0xffffffff810049f5
> > >> [2317687.527511]  [<ffffffff810476e6>] 0xffffffff810476e6
> > >> [2317687.527514]  [<ffffffff810041c1>] 0xffffffff810041c1
> > >> [2317687.527517]  [<ffffffff8163d553>] 0xffffffff8163d553
> > >> [2317687.527519]  <EOI>
> > >>
> > >> Fui atrás e não encontrei muita coisa.
> > >> O que poderia ser?
> > >>
> > >> Obrigado.
> > >>
> > >> --
> > >> Eduardo Schoedler
> > >>
> > >
> > >
> > >
> > > --
> > > Daniel da Veiga
> 
> 
> 
> 
> 
> 
> -- 
> Daniel da Veiga