Centos7 - dev sda 上的缓冲区 I/O 错误，逻辑块 xxxxxxxxx，丢失异步页面写入

Question

我有一个 Web 服务器，其中包含 HP MSA2040 存储（10 TB 总存储）中的内容。

我不断收到如下错误

Jul 31 19:06:24 xxxxxxxx*** kernel: blk_update_request: I/O error, dev sda, sector 7094923416
Jul 31 19:06:24 xxxxxxxx*** kernel: buffer_io_error: 1110 callbacks suppressed
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865171, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865172, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865173, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865174, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865175, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865176, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865177, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865178, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865179, lost async page write
Jul 31 19:06:24 xxxxxxxx*** kernel: Buffer I/O error on dev sda, logical block 886865180, lost async page write

我尝试在 /dev/sda 上运行 xfs_repair，这是我的 MSA2040 存储，这是我得到的报告

Phase 1 - find and verify superblock...
Phase 2 - using internal log
        - zero log...
        - scan filesystem freespace and inode maps...
        - found root inode chunk
Phase 3 - for each AG...
        - scan (but don't clear) agi unlinked lists...
        - process known inodes and perform inode discovery...
        - agno = 0
        - agno = 1
        - agno = 2
        - agno = 3
        - agno = 4
        - agno = 5
        - agno = 6
        - agno = 7
        - agno = 8
        - agno = 9
        - process newly discovered inodes...
Phase 4 - check for duplicate blocks...
        - setting up duplicate extent list...
        - check for inodes claiming duplicate blocks...
        - agno = 0
        - agno = 1
        - agno = 2
        - agno = 3
        - agno = 4
        - agno = 5
        - agno = 6
        - agno = 7
        - agno = 8
        - agno = 9
No modify flag set, skipping phase 5
Phase 6 - check inode connectivity...
        - traversing filesystem ...
        - traversal finished ...
        - moving disconnected inodes to lost+found ...
Phase 7 - verify link counts...

我什至试图运行xfs_repaif -L我可以访问我的数据，但一段时间后它卡住了。我还检查了 MSA 的界面，一切似乎都很顺利。

有没有办法解决这个问题？

提前致谢。

编辑* 这也是 smartctl 报告

=== START OF INFORMATION SECTION ===
Vendor:               HP
Product:              MSA 2040 SAN
Revision:             G210
User Capacity:        10,239,998,951,424 bytes [10.2 TB]
Logical block size:   512 bytes
LU is thin provisioned, LBPRZ=1
Rotation Rate:        15000 rpm
Logical Unit id:      0x600xxxxxxxxxxxxxxxef5701000000
Serial number:        00c0ff27xxxxxxxxxxxx701000000
Device type:          disk
Transport protocol:   Fibre channel (FCP-2)
Local Time is:        Mon Jul 31 19:22:30 2017 +03
SMART support is:     Available - device has SMART capability.
SMART support is:     Disabled
Temperature Warning:  Disabled or Not Supported

=== START OF READ SMART DATA SECTION ===
SMART Health Status: OK

Elements in grown defect list: 0

Error Counter logging not supported

Device does not support Self Test logging

Edit2* 请求的输出

[root@xxxxxxxx*** thumbs]# lsblk
NAME            MAJ:MIN RM  SIZE RO TYPE MOUNTPOINT
sda               8:0    0  9.3T  0 disk /msa10tb
sdb               8:16   0  1.8T  0 disk
??sdb1            8:17   0  200M  0 part /boot/efi
??sdb2            8:18   0  500M  0 part /boot
??sdb3            8:19   0  1.8T  0 part
  ??centos-root 253:0    0   50G  0 lvm  /
  ??centos-swap 253:1    0  7.8G  0 lvm  [SWAP]
  ??centos-home 253:2    0  1.8T  0 lvm  /home
sr0              11:0    1 1024M  0 rom
[root@xxxxxxxx*** thumbs]# pvs
  PV         VG     Fmt  Attr PSize PFree
  /dev/sdb3  centos lvm2 a--  1.82t 64.00m
[root@xxxxxxxx*** thumbs]# vgs
  VG     #PV #LV #SN Attr   VSize VFree
  centos   1   3   0 wz--n- 1.82t 64.00m
[root@xxxxxxxx*** thumbs]# lvs
  LV   VG     Attr       LSize  Pool Origin Data%  Meta%  Move Log Cpy%Sync Convert
  home centos -wi-ao----  1.76t
  root centos -wi-ao---- 50.00g
  swap centos -wi-ao----  7.75g
[root@xxxxxxxx*** thumbs]#

编辑*3 - 当我检查 journalctl 时，现在我不断收到这些日志；

Jul 31 19:29:46 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1461891501:1461898801 (repaired)
Jul 31 19:29:48 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1461891501:1461898801 (repaired)
Jul 31 19:29:50 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1461891501:1461898801 (repaired)
Jul 31 19:29:54 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1461891501:1461898801 (repaired)
Jul 31 19:30:03 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1461891501:1461898801 (repaired)
Jul 31 19:30:25 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1462932481:1462952921 (repaired)
Jul 31 19:30:27 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1462932481:1462952921 (repaired)
Jul 31 19:30:29 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1462932481:1462952921 (repaired)
Jul 31 19:30:30 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:5e37:2374:63273/443 unexpectedly shrunk window 3861953537:3862015916 (repaired)
Jul 31 19:30:31 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:5e37:2374:63273/443 unexpectedly shrunk window 3861953537:3862015916 (repaired)
Jul 31 19:30:32 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:5e37:2374:63273/443 unexpectedly shrunk window 3861953537:3862015916 (repaired)
Jul 31 19:30:33 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:1885:f5b0:30313/443 unexpectedly shrunk window 1462932481:1462952921 (repaired)
Jul 31 19:30:34 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:5e37:2374:63273/443 unexpectedly shrunk window 3861953537:3862015916 (repaired)
Jul 31 19:30:38 xxxxxxxx*** kernel: Peer 0000:0000:0000:0000:0000:ffff:5e37:2374:63273/443 unexpectedly shrunk window 3861953537:3862015916 (repaired)

Answer 1

消息作为

Buffer I/O error on dev sda, logical block 886865171, lost async page write

意味着异步写入（即：脏页回写或缓冲写入）失败。您在发现这些错误dmesg或/var/log/message因失败的异步写入不能，由于其本身的性质，通知其提交的写在首位的原始应用程序。

它们通常是由无法写入某些块的介质引起的。这可能是由于：

• 损坏的磁盘盘片/单元
• 连接问题（即：电缆损坏、“丢失”的 iSCSI 目标等）
• 父池空间耗尽的精简配置块设备

您sda直接使用顶部的文件系统，没有头节点端 LVM，因此我们可以排除错误的设备映射表作为问题源（至少在头节点上）。

如果您的存储节点的物理属性正常（即：没有故障磁盘等），我强烈建议您检查任何精简配置的卷及其父池。