我们有4个Redhat Box Dell PowerEdge R630(比如a,b,c,d)具有以下操作系统/软件包.
RedHat EL 6.5 MySql Enterprise 5.6 DRBD 8.4 Corosync 1.4.7
我们设置了4路堆叠drbd资源,如下所示：
群集群集-1：服务器a和b彼此连接本地lan群集群集-2：服务器c和d
Cluster Cluster-1和Cluster-2通过堆叠drbd通过虚拟IP连接,是不同数据中心的一部分.
drbd0磁盘已在每台服务器1GB上本地创建,并进一步连接到drbd10.
整体设置包括4层：Tomcat前端应用 – > rabbitmq – > memcache – > MysqL的/ DRBD
我们正在经历非常高的磁盘IO,即使活动也不是必须的.但是流量/活动将在几周内增加,因此我们担心它会对性能造成非常不利的影响. I / O使用率仅在堆叠的站点上高(有时为90％及以上).辅助站点没有这个问题.当应用程序理想时,使用率很高.
resource clusterdb {
protocol C;
handlers {
pri-on-incon-degr "/usr/lib/drbd/notify-pri-on-incon-degr.sh; /usr/lib/drbd/notifyemergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
pri-lost-after-sb "/usr/lib/drbd/notify-pri-lost-after-sb.sh; /usr/lib/drbd/notifyemergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
local-io-error "/usr/lib/drbd/notify-io-error.sh; /usr/lib/drbd/notify-emergencyshutdown.sh; echo o > /proc/sysrq-trigger ; halt -f";
fence-peer "/usr/lib/drbd/crm-fence-peer.sh";
}
startup {
degr-wfc-timeout 120; # 2 minutes.
outdated-wfc-timeout 2; # 2 seconds.
}
disk {
on-io-error detach;
no-disk-barrier;
no-md-flushes;
}
net {
cram-hmac-alg "sha1";
shared-secret "clusterdb";
after-sb-0pri disconnect;
after-sb-1pri disconnect;
after-sb-2pri disconnect;
rr-conflict disconnect;
}
syncer {
rate 10M;
al-extents 257;
on-no-data-accessible io-error;
}
on sever-1 {
device /dev/drbd0;
disk /dev/sda2;
address 10.170.26.28:7788;
Meta-disk internal;
}
on ever-2 {
device /dev/drbd0;
disk /dev/sda2;
address 10.170.26.27:7788;
Meta-disk internal;
}
}
堆叠配置： –
resource clusterdb_stacked {
protocol A;
handlers {
pri-on-incon-degr "/usr/lib/drbd/notify-pri-on-incon-degr.sh; /usr/lib/drbd/notifyemergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
pri-lost-after-sb "/usr/lib/drbd/notify-pri-lost-after-sb.sh; /usr/lib/drbd/notifyemergency-reboot.sh; echo b > /proc/sysrq-trigger ; reboot -f";
local-io-error "/usr/lib/drbd/notify-io-error.sh; /usr/lib/drbd/notify-emergencyshutdown.sh; echo o > /proc/sysrq-trigger ; halt -f";
fence-peer "/usr/lib/drbd/crm-fence-peer.sh";
}
startup {
degr-wfc-timeout 120; # 2 minutes.
outdated-wfc-timeout 2; # 2 seconds.
}
disk {
on-io-error detach;
no-disk-barrier;
no-md-flushes;
}
net {
cram-hmac-alg "sha1";
shared-secret "clusterdb";
after-sb-0pri disconnect;
after-sb-1pri disconnect;
after-sb-2pri disconnect;
rr-conflict disconnect;
}
syncer {
rate 10M;
al-extents 257;
on-no-data-accessible io-error;
}
stacked-on-top-of clusterdb {
device /dev/drbd10;
address 10.170.26.28:7788;
}
stacked-on-top-of clusterdb_DR {
device /dev/drbd10;
address 10.170.26.60:7788;
}
}
请求的数据： –
Date || svctm(w_wait)|| %util 10:32:01 3.07 55.23 94.11 10:33:01 3.29 50.75 96.27 10:34:01 2.82 41.44 96.15 10:35:01 3.01 72.30 96.86 10:36:01 4.52 40.41 94.24 10:37:01 3.80 50.42 83.86 10:38:01 3.03 72.54 97.17 10:39:01 4.96 37.08 89.45 10:41:01 3.55 66.48 70.19 10:45:01 2.91 53.70 89.57 10:46:01 2.98 49.49 94.73 10:55:01 3.01 48.38 93.70 10:56:01 2.98 43.47 97.26 11:05:01 2.80 61.84 86.93 11:06:01 2.67 43.35 96.89 11:07:01 2.68 37.67 95.41
根据评论更新问题： –
它实际上是比较本地和堆叠.
本地服务器之间
[root@pri-site-valsql-a]#ping pri-site-valsql-b PING pri-site-valsql-b.csn.infra.sm (10.170.24.23) 56(84) bytes of data. 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=1 ttl=64 time=0.143 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=2 ttl=64 time=0.145 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=3 ttl=64 time=0.132 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=4 ttl=64 time=0.145 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=5 ttl=64 time=0.150 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=6 ttl=64 time=0.145 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=7 ttl=64 time=0.132 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=8 ttl=64 time=0.127 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=9 ttl=64 time=0.134 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=10 ttl=64 time=0.149 ms 64 bytes from pri-site-valsql-b.csn.infra.sm (10.170.24.23): icmp_seq=11 ttl=64 time=0.147 ms ^C --- pri-site-valsql-b.csn.infra.sm ping statistics --- 11 packets transmitted,11 received,0% packet loss,time 10323ms rtt min/avg/max/mdev = 0.127/0.140/0.150/0.016 ms
两个堆叠的服务器之间
[root@pri-site-valsql-a]#ping dr-site-valsql-b PING dr-site-valsql-b.csn.infra.sm (10.170.24.48) 56(84) bytes of data. 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=1 ttl=64 time=9.68 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=2 ttl=64 time=4.51 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=3 ttl=64 time=4.53 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=4 ttl=64 time=4.51 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=5 ttl=64 time=4.51 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=6 ttl=64 time=4.52 ms 64 bytes from dr-site-valsql-b.csn.infra.sm (10.170.24.48): icmp_seq=7 ttl=64 time=4.52 ms ^C --- dr-site-valsql-b.csn.infra.sm ping statistics --- 7 packets transmitted,7 received,time 6654ms rtt min/avg/max/mdev = 4.510/5.258/9.686/1.808 ms [root@pri-site-valsql-a]#
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util drbd0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 avg-cpu: %user %nice %system %iowait %steal %idle 0.00 0.00 0.06 0.00 0.00 99.94 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util drbd0 0.00 0.00 0.00 2.00 0.00 16.00 8.00 0.90 1.50 452.25 90.45 avg-cpu: %user %nice %system %iowait %steal %idle 0.25 0.00 0.13 0.50 0.00 99.12 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util drbd0 0.00 0.00 1.00 44.00 8.00 352.00 8.00 1.07 2.90 18.48 83.15 avg-cpu: %user %nice %system %iowait %steal %idle 0.13 0.00 0.06 0.25 0.00 99.56 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util drbd0 0.00 0.00 0.00 31.00 0.00 248.00 8.00 1.01 2.42 27.00 83.70 avg-cpu: %user %nice %system %iowait %steal %idle 0.19 0.00 0.06 0.00 0.00 99.75 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util drbd0 0.00 0.00 0.00 2.00 0.00 16.00 8.00 0.32 1.50 162.25 32.45
disk {
on-io-error detach;
no-disk-barrier;
no-disk-flushes;
no-md-flushes;
c-plan-ahead 0;
c-fill-target 24M;
c-min-rate 80M;
c-max-rate 300M;
al-extents 3833;
}
net {
cram-hmac-alg "sha1";
shared-secret "clusterdb";
after-sb-0pri disconnect;
after-sb-1pri disconnect;
after-sb-2pri disconnect;
rr-conflict disconnect;
max-epoch-size 20000;
max-buffers 20000;
unplug-watermark 16;
}
syncer {
rate 100M;
on-no-data-accessible io-error;
}
解决方法
我没有在配置中看到堆叠资源.你也没有提到任何版本号,但看到如此低的范围让我觉得你正在运行古老的东西(8.3.x)或者遵循一些非常古老的指令.
无论如何,假设您正在使用协议A进行堆叠设备的复制(异步),当IO缓冲时,您仍然会快速填充TCP发送缓冲区,因此在缓冲区刷新时会等待IO等待; DRBD需要将其复制的写入放在某处,并且只能在飞行中有这么多未经确认的复制写入.
IO等待有助于系统负载.如果暂时断开堆叠资源,系统负载是否已解决？这是验证这是问题的一种方法.您还可以使用netstat或ss等查看TCP缓冲区,以查看负载较高时的TCP缓冲区.
除非您的站点之间的连接的延迟和吞吐量是惊人的(暗光纤或其他东西),否则您可能需要/想要使用LINBIT中的DRBD代理;它让你使用系统内存缓冲写入.
