/var/log/DMIT-NOC.log
4.73K subscribers
189 photos
6 files
117 links
Download Telegram
LAX Ceph migration is closed to full completion.
The IOPS limit of LAX VM will be tripled; the burstable IOPS be increased to six times than now after Ceph migration completion.

HKG is waiting for our on-site engineer to install RAM and SSD to another 2 servers.
Once we finished the migration, the IOPS limit will be doubled, and the burstable IOPS will be quadrupled.
80% of HKG VM already be migrated to AMD EPYC node and Ceph and running well.
/var/log/DMIT-NOC.log
LAX Ceph migration is closed to full completion. The IOPS limit of LAX VM will be tripled; the burstable IOPS be increased to six times than now after Ceph migration completion. HKG is waiting for our on-site engineer to install RAM and SSD to another 2…
We complete almost all tasks for LAX, due to disk cache mode change and the ceph cluster performance improvement needed.

DMIT NOC will reboot some nodes / VMs at Oct 27 4PM(EST).

After this action, all tasks are complete.
/var/log/DMIT-NOC.log
We complete almost all tasks for LAX, due to disk cache mode change and the ceph cluster performance improvement needed. DMIT NOC will reboot some nodes / VMs at Oct 27 4PM(EST). After this action, all tasks are complete.
We also found another tiny issue. You can ignore it if you don't care about #IO_Latency

Please install ioping on your VM by:
YUM based
yum install ioping
ioping /dev/vda1

If ioping is not found, please do
yum install epel-release

APT based:
apt install ioping
ioping /dev/vda1

Please reinstall the system if you found the latency over than 900us and you care about it.
The maintenance recent for HKG and LAX has been completed.
Thanks for your patience
Please read the #IO_Latency above, it works for HKG and LAX.
/var/log/DMIT-NOC.log pinned «The maintenance recent for HKG and LAX has been completed. Thanks for your patience Please read the #IO_Latency above, it works for HKG and LAX.»
Email copy:

Notice of Completion of High Reliability Reconstruction

DMIT NOC made a reconstruction for our LAX and HKG datacenter recently.

- DMIT upgrades all racks in HKG and LAX to 2 switches with vPC configuration. It improved the redundancy to avoid single device error like transceiver or switch failure.
- DMIT swapped from ZFS to the Ceph Cluster solution. It helps to avoid single-node failure, like some cases we had in HKG before.
- DMIT joined the AMD EPYC family in both HKG and LAX locations. All DMIT Hyper servers are powered by AMD EPYC 2nd GEN.


The route-map of DMIT:
- New location launch
- Move to DMIT self-developed client area system.
-- Simple UI;
-- Batter task performance
-- Client self-service BGP support
-- Client self-service rDNS support
-- HA support (current DMIT only offer High Reliability)
- etc..

Thanks to all DMIT clients for the support and trust us.
DMIT HKG IP re-arrange notice:

We will arrange you a new IP address if your IP is in the below subnet:
103.135.248.0/24
103.135.249.0/24
103.135.250.0/24
103.135.251.0/24

There are lots of unused IPs in these subnets; to improve usability and to offer different types of services. We will need to swap your IP to a new one. You will receive a ticket and email for the detail of the rearranging.
Thanks for all client's support on our PVM.HKG.Lite services.

The hardware resource in HK is closed to be used up soon.

DMIT ordered 4 more sets of EPYC nodes today. It will be ready to use within 3 weeks. 🥳
As the order quantity of PVM.HKG.Lite over than our expectations

DMIT NOC needs to reboot some nodes in Hong Kong to upgrade the hardware configuration.

ETA: 30mins per nodes, your VM will down 10mins (up to 1 hour)

Because it's emergency maintenance, we are still waiting for the delivery of hardware; it's not able to give a confirmed time

Date/Time:
Hong Kong Time;
Between Nov 13, 6 P.M and Nov 16, 10 P.M.
There is a huge packet loss between LAX-CAN on the CN2 backbone. DMIT is no way to fix it. As our experience, China Telecom and China Telecom America at least take 1 week to fix it generally.
DMIT NOC needs to reboot some nodes in Los Angeles to upgrade the hardware configuration.

ETA: 30mins per nodes, your VM will down 20 mins (up to 1 hour)

Date/Time:
Pacific Standard Time;
Nov 17, 3:00 P.M ~ 5:00 P.M
/var/log/DMIT-NOC.log pinned «DMIT NOC needs to reboot some nodes in Los Angeles to upgrade the hardware configuration. ETA: 30mins per nodes, your VM will down 20 mins (up to 1 hour) Date/Time: Pacific Standard Time; Nov 17, 3:00 P.M ~ 5:00 P.M»