High Packet Drops to De-CIX Mumbai Cloudflare

All requests like, web page request, icmp ping, dns requests and other services that require multiple calls to Cloudflare Servers have abnormally high packet drops.
Traceroute to hostname ping and dns, gives Cloudflare Server in Mumbai via IX of De-CIX.

Tracing route to one.one.one.one [1.1.1.1]
over a maximum of 30 hops:

   1     2 ms     2 ms     2 ms  1.186.60.1.dvois.com [1.186.60.1]
   2     2 ms     2 ms     2 ms  114.79.129.109.dvois.com [114.79.129.109]
   3     4 ms     *        3 ms  103.27.170.48
   4     3 ms     2 ms     3 ms  one.one.one.one [1.1.1.1]
 
 Trace complete.
 Tracing route to 580f3ae28f8746c4b3255919242623b1.pacloudflare.com [172.65.200.88]
 over a maximum of 30 hops:
 
   1     2 ms     2 ms     1 ms  1.186.60.1.dvois.com [1.186.60.1]
   2     2 ms     2 ms     2 ms  114.79.129.109.dvois.com [114.79.129.109]
   3     4 ms     *        *     103.27.170.48
   4     3 ms     3 ms     2 ms  172.65.200.88
 
 Trace complete.
 Ping statistics for 1.1.1.1:
     Packets: Sent = 196, Received = 176, Lost = 20 (10% loss),
 Approximate round trip times in milli-seconds:
     Minimum = 2ms, Maximum = 23ms, Average = 3ms

failrate
Due to having failrate of about 13%, packet sensitive applications have high errors, requesting to look into to so the issue can be resolved. Thank you.

TLDR; also to note that, there are no packet drops from the route of my desktop - to my ISP - to the De-CIX exchange. Proof below:

Ping statistics for 103.27.170.96:
    Packets: Sent = 111, Received = 111, Lost = 0 (0% loss),
Approximate round trip times in milli-seconds:
    Minimum = 2ms, Maximum = 24ms, Average = 3ms

Using CL Warp, resolves the ping drop issue upto a certain extent but there are atleast 5% drops, but this is not a solution, please help.

2 Likes

it could be related to your ISP. Traceroute and Ping from other site of the world are working fine right now.

%> ip2trace -p 1.1.1.1 -d /usr/share/ip2location/DB4.BIN

IP2Location Geolocation Traceroute (ip2trace) Version 8.0.0
Copyright (c) 2021 IP2Location.com [MIT License]
https://www.ip2location.com/free/traceroute-application

1. 50.97.82.1 0.664 ms ["US", "United States of America", "Texas", "Dallas", "SoftLayer Technologies Inc.]
2. 173.192.118.144 0.466 ms ["US", "United States of America", "Texas", "Dallas", "SoftLayer Technologies Inc.]
3. 173.192.18.214 0.947 ms ["US", "United States of America", "Texas", "Dallas", "SoftLayer Technologies Inc.]
4. 206.223.118.145 30.017 ms ["US", "United States of America", "Texas", "Dallas", "Equinix Inc.]
5. 1.1.1.1 1.736 ms ["US", "United States of America", "California", "Los Angeles", "APNIC and CloudFlare DNS Resolver Project]

The issue is not a global Cloduflare issue, it’s related to performance with Cloudflare Mumbai Servers ONLY!
Manually routing myself to other Cloudflare servers stabilizes the network, but also adds added latency which is not good for service applications.

Massive Ping spikes and high packet drop rate.

This is not! a ISP issue or an issue on my side, as can proved via the my pings to other services, which work just fine.

222

1 Like

If taken a look carefully, where the tracert is loosing a lot of icmp responses, from the IP (103.27.170.48) is also a Clouflare Port for De-Cix Exchange.
133

334
Using a different ISP, gives the same output. The issue persists.

Same here.

Massive increase in packet drops and latency.
Issue remains the same over WARP.

Colocation: Asia (Mumbai, India - (BOM))
1

I was using 1.1.1.1 with warp to play games, and the latency was usually around 55-60ms. But from yesterday i has jumped to 350ms. I tried pinging to other dns, but they are giving me around 60ms latencies but 1.1.1.1 is pinging around 300-350ms everytime. I’m facing this issue from yesterday.

same issue with me also

1 Like

bro ping me i got solution discord-🄲🄻🄰🅂🄷#0105

I’ve added you in discord. Check

Try to do tracert, do share the results here.
Having the same issue, Cloudflare is being routed for me to Singapore.

Thanks


Here are the ping and tracert.
The problem is still there.

Seems there is also high added load from the Jio Side too, did you try restarting your router, so it gets a fresh ip?
The cloudflare issue for me is resolved, the pings have stabilised since morning 6am.

Pinging 1.1.1.1 with 32 bytes of data:
Reply from 1.1.1.1: bytes=32 time=3ms TTL=64
Reply from 1.1.1.1: bytes=32 time=3ms TTL=64
Reply from 1.1.1.1: bytes=32 time=3ms TTL=64
Reply from 1.1.1.1: bytes=32 time=3ms TTL=64

Ping statistics for 1.1.1.1:
    Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),
Approximate round trip times in milli-seconds:
    Minimum = 3ms, Maximum = 3ms, Average = 3ms

I tried restarting the router, but it still remains the same.
however it went to 50ms for a minute but then it went back to 300ms.

Yea things are going north again… Damn…
failure

Capture
Mine seem to be little better

Try doing an extended ping. using “-t”
I also tried pinging via Vodafone and Jio (mobile network) all packets went to Request Timed Out.

A week later, issue still persists.

1