O servidor é o HP DL360 G7 com controlador de disco P410i. 2xE5620 CPU's 16 GB de RAM. Linux mysql 2.6.32-5-amd64 # 1 SMP seg 25 de fevereiro 00:26:11 UTC 2013 x86_64 GNU / Linux (Debian 6.0.7)
hpacucli "ctrl mostrar status"
Smart Array P410i in Slot 0 (Embedded)
Controller Status: OK
Cache Status: OK
Battery/Capacitor Status: OK
hpacucli "ctrl mostrar configuração"
Smart Array P410i in Slot 0 (Embedded) (sn: 5001438014555B80)
array A (SAS, Unused Space: 0 MB)
logicaldrive 1 (136.7 GB, RAID 1+0, OK)
physicaldrive 1I:1:1 (port 1I:box 1:bay 1, SAS, 72 GB, OK)
physicaldrive 1I:1:2 (port 1I:box 1:bay 2, SAS, 72 GB, OK)
physicaldrive 1I:1:3 (port 1I:box 1:bay 3, SAS, 72 GB, OK)
physicaldrive 1I:1:4 (port 1I:box 1:bay 4, SAS, 72 GB, OK)
SEP (Vendor ID PMCSIERA, Model SRC 8x6G) 250 (WWID: 5001438014555B8F)
hpacucli "ctrl slot = 0 ld todos os programas"
Smart Array P410i in Slot 0 (Embedded)
array A
logicaldrive 1 (136.7 GB, RAID 1+0, OK)
Eu corro o script abaixo pela noite:
#!/bin/bash
mkdir -p /isotest
for i in {1..200}; do
for j in {1..55}; do cp -v /root/ubuntu.iso /isotest/ubuntu.iso${j}; done
rm /isotest/ubuntu.iso*;
done
O tamanho de
/root/ubuntu.iso é de 2 GB.
no syslog tem alguns erros. Eu acho que está relacionado ao controlador de disco:
Mar 28 06:59:17 mysql kernel: [850337.524306] INFO: task mandb:25565 blocked for more than 120 seconds.
Mar 28 06:59:17 mysql kernel: [850337.524337] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Mar 28 06:59:17 mysql kernel: [850337.524381] mandb D ffff88022740fa20 0 25565 25197 0x00000000
Mar 28 06:59:17 mysql kernel: [850337.524385] ffff88041ec4b880 0000000000000082 0000000000000000 000000009d778d11
Mar 28 06:59:17 mysql kernel: [850337.524388] ffffea000defe260 ffffea000defe260 000000000000f9e0 ffff88014d913fd8
Mar 28 06:59:17 mysql kernel: [850337.524390] 00000000000157c0 00000000000157c0 ffff88013228a350 ffff88013228a648
Mar 28 06:59:17 mysql kernel: [850337.524393] Call Trace:
Mar 28 06:59:17 mysql kernel: [850337.524404] [<ffffffff810168ec>] ? read_tsc+0xa/0x20
Mar 28 06:59:17 mysql kernel: [850337.524408] [<ffffffff8106bdca>] ? timekeeping_get_ns+0xe/0x2e
Mar 28 06:59:17 mysql kernel: [850337.524412] [<ffffffff810b4761>] ? sync_page+0x0/0x46
Mar 28 06:59:17 mysql kernel: [850337.524416] [<ffffffff812fc8f2>] ? io_schedule+0x73/0xb7
Mar 28 06:59:17 mysql kernel: [850337.524418] [<ffffffff810b47a2>] ? sync_page+0x41/0x46
Mar 28 06:59:17 mysql kernel: [850337.524421] [<ffffffff812fcd02>] ? __wait_on_bit_lock+0x3f/0x84
Mar 28 06:59:17 mysql kernel: [850337.524423] [<ffffffff810b472e>] ? __lock_page+0x5d/0x63
Mar 28 06:59:17 mysql kernel: [850337.524426] [<ffffffff810652e0>] ? wake_bit_function+0x0/0x23
Mar 28 06:59:17 mysql kernel: [850337.524428] [<ffffffff810b473d>] ? lock_page+0x9/0x1f
Mar 28 06:59:17 mysql kernel: [850337.524431] [<ffffffff810b4853>] ? find_lock_page+0x25/0x45
Mar 28 06:59:17 mysql kernel: [850337.524433] [<ffffffff810b4e63>] ? filemap_fault+0x1a5/0x2f6
Mar 28 06:59:17 mysql kernel: [850337.524438] [<ffffffff810cadf2>] ? __do_fault+0x54/0x3c3
Mar 28 06:59:17 mysql kernel: [850337.524455] [<ffffffffa01702d2>] ? __ext3_journal_stop+0x1f/0x3d [ext3]
Mar 28 06:59:17 mysql kernel: [850337.524458] [<ffffffff810cd146>] ? handle_mm_fault+0x3b8/0x80f
Mar 28 06:59:17 mysql kernel: [850337.524461] [<ffffffff81101d8e>] ? notify_change+0x2b3/0x2c5
Mar 28 06:59:17 mysql kernel: [850337.524464] [<ffffffff81103eb5>] ? mntput_no_expire+0x23/0xee
Mar 28 06:59:17 mysql kernel: [850337.524467] [<ffffffff81300096>] ? do_page_fault+0x2e0/0x2fc
Mar 28 06:59:17 mysql kernel: [850337.524469] [<ffffffff812fdf35>] ? page_fault+0x25/0x30
Não há outras mensagens de erro.
Ou esse erro pode estar relacionado à memória? Eu já rodei o memtest86 + nesse servidor por vários dias e não houve erros.
Quando o servidor estava no datacenter, não consigo inicializar o servidor. Mostra todo o erro do tempo:
Fatal PCI Express Device Error PCI ? B00/D00/F00
Depois de transportá-lo para o meu trabalho, ele inicializa normalmente. No log de eventos do ILO tem erros seguintes:
Uncorrectable PCI Express Error (Embedded device, Bus 0, Device 0, Function 0, Error status 0x00000000)
Uncorrectable Memory Error ((Processor 1, Memory Module 2))
Uncorrectable Memory Error ((Processor 1, Memory Module 3))
An Unrecoverable System Error (NMI) has occurred (System error code 0x00000000, 0x00000000)
Eu já atualizei o bios, o controlador de disco e os firmwares de disco para as versões mais recentes.