[OpenSIPS-Users] Autoscaler in 3.2.x

Yury Kirsanov y.kirsanov at gmail.com
Sat Sep 3 15:54:06 UTC 2022


Hi Bogdan,
This has finally happened, OS is stuck again in 100% for one of its
processes. Here's the output of load: command:

opensips-cli -x mi get_statistics load:
{
    "load:load-proc-1": 0,
    "load:load1m-proc-1": 0,
    "load:load10m-proc-1": 0,
    "load:load-proc-2": 0,
    "load:load1m-proc-2": 0,
    "load:load10m-proc-2": 0,
    "load:load-proc-3": 0,
    "load:load1m-proc-3": 0,
    "load:load10m-proc-3": 0,
    "load:load-proc-4": 0,
    "load:load1m-proc-4": 0,
    "load:load10m-proc-4": 0,
    "load:load-proc-5": 0,
    "load:load1m-proc-5": 0,
    "load:load10m-proc-5": 8,
    "load:load-proc-6": 0,
    "load:load1m-proc-6": 0,
    "load:load10m-proc-6": 6,
    "load:load-proc-13": 0,
    "load:load1m-proc-13": 0,
    "load:load10m-proc-13": 0,
    "load:load-proc-14": 0,
    "load:load1m-proc-14": 0,
    "load:load10m-proc-14": 0,
    "load:load-proc-21": 0,
    "load:load1m-proc-21": 0,
    "load:load10m-proc-21": 0,
    "load:load-proc-22": 0,
    "load:load1m-proc-22": 0,
    "load:load10m-proc-22": 0,
    "load:load-proc-23": 0,
    "load:load1m-proc-23": 0,
    "load:load10m-proc-23": 0,
    "load:load-proc-24": 100,
    "load:load1m-proc-24": 100,
    "load:load10m-proc-24": 100,
    "load:load": 12,
    "load:load1m": 12,
    "load:load10m": 14,
    "load:load-all": 10,
    "load:load1m-all": 10,
    "load:load10m-all": 11,
    "load:processes_number": 13
}

As you can see, process 24 is consuming 100% of time for more than a minute
already

Here's the output of process list, it's a UDP socket listener on internal
interface that's stuck at 100% load:

opensips-cli -x mi ps
{
    "Processes": [
        {
            "ID": 0,
            "PID": 5457,
            "Type": "attendant"
        },
        {
            "ID": 1,
            "PID": 5463,
            "Type": "HTTPD 10.x.x.x:8888"
        },
        {
            "ID": 2,
            "PID": 5464,
            "Type": "MI FIFO"
        },
        {
            "ID": 3,
            "PID": 5465,
            "Type": "time_keeper"
        },
        {
            "ID": 4,
            "PID": 5466,
            "Type": "timer"
        },
        {
            "ID": 5,
            "PID": 5467,
            "Type": "SIP receiver udp:10.x.x.x:5060"
        },
        {
            "ID": 6,
            "PID": 5470,
            "Type": "SIP receiver udp:10.x.x.x:5060"
        },
        {
            "ID": 13,
            "PID": 5477,
            "Type": "SIP receiver udp:103.x.x.x:7060"
        },
        {
            "ID": 14,
            "PID": 5478,
            "Type": "SIP receiver udp:103.x.x.x:7060"
        },
        {
            "ID": 21,
            "PID": 5485,
            "Type": "TCP receiver"
        },
        {
            "ID": 22,
            "PID": 5486,
            "Type": "Timer handler"
        },
        {
            "ID": 23,
            "PID": 5487,
            "Type": "TCP main"
        },
        {
            "ID": 24,
            "PID": 5759,
            "Type": "SIP receiver udp:10.x.x.x:5060"
        }
    ]
}

opensips -V
version: opensips 3.2.8 (x86_64/linux)
flags: STATS: On, DISABLE_NAGLE, USE_MCAST, SHM_MMAP, PKG_MALLOC, Q_MALLOC,
F_MALLOC, HP_MALLOC, DBG_MALLOC, FAST_LOCK-ADAPTIVE_WAIT
ADAPTIVE_WAIT_LOOPS=1024, MAX_RECV_BUFFER_SIZE 262144, MAX_LISTEN 16,
MAX_URI_SIZE 1024, BUF_SIZE 65535
poll method support: poll, epoll, sigio_rt, select.
git revision: d2496fed5
main.c compiled on 16:17:53 Aug 24 2022 with gcc 9

This time server has some load but still it's not heavy at all plus I'm
using async requests for REST queries.

This is my autoscaling section:

# Scaling section
auto_scaling_profile = PROFILE_UDP_PUB
     scale up to 16 on 70% for 4 cycles within 5
     scale down to 2 on 20% for 5 cycles

auto_scaling_profile = PROFILE_UDP_PRIV
     scale up to 16 on 70% for 4 cycles within 5
     scale down to 2 on 20% for 5 cycles

auto_scaling_profile = PROFILE_TCP
     scale up to 16 on 70% for 4 cycles within 5
     scale down to 2 on 20% for 10 cycles

And that's how I apply it to sockets, I'm not applying it to UDP workers at
all:

socket=udp:10.x.x.x:5060 use_auto_scaling_profile PROFILE_UDP_PRIV
socket=udp:103.x.x.x:7060 use_auto_scaling_profile PROFILE_UDP_PUB

tcp_workers = 1 use_auto_scaling_profile PROFILE_TCP

I can't get this process unstuck until I restart OpenSIPS.

Just to add - if I turn off auto scaling and enable 16 UDP and 16 TCP
workers and just specify sockets without any parameters - load goes to 0,
see graph attached, load was at 25% all the time until I restarted OpenSIPS
in normal mode, then it's immediately 0:

[image: image.png]

Here's an output of load:

opensips-cli -x mi get_statistics load:
{
    "load:load-proc-1": 0,
    "load:load1m-proc-1": 0,
    "load:load10m-proc-1": 0,
    "load:load-proc-2": 0,
    "load:load1m-proc-2": 0,
    "load:load10m-proc-2": 0,
    "load:load-proc-3": 0,
    "load:load1m-proc-3": 0,
    "load:load10m-proc-3": 0,
    "load:load-proc-4": 0,
    "load:load1m-proc-4": 0,
    "load:load10m-proc-4": 0,
    "load:load-proc-5": 0,
    "load:load1m-proc-5": 0,
    "load:load10m-proc-5": 2,
    "load:load-proc-6": 0,
    "load:load1m-proc-6": 0,
    "load:load10m-proc-6": 0,
    "load:load-proc-7": 0,
    "load:load1m-proc-7": 0,
    "load:load10m-proc-7": 1,
    "load:load-proc-8": 0,
    "load:load1m-proc-8": 0,
    "load:load10m-proc-8": 1,
    "load:load-proc-9": 0,
    "load:load1m-proc-9": 0,
    "load:load10m-proc-9": 1,
    "load:load-proc-10": 0,
    "load:load1m-proc-10": 0,
    "load:load10m-proc-10": 0,
    "load:load-proc-11": 0,
    "load:load1m-proc-11": 0,
    "load:load10m-proc-11": 3,
    "load:load-proc-12": 0,
    "load:load1m-proc-12": 0,
    "load:load10m-proc-12": 2,
    "load:load-proc-13": 0,
    "load:load1m-proc-13": 0,
    "load:load10m-proc-13": 1,
    "load:load-proc-14": 0,
    "load:load1m-proc-14": 0,
    "load:load10m-proc-14": 3,
    "load:load-proc-15": 0,
    "load:load1m-proc-15": 0,
    "load:load10m-proc-15": 2,
    "load:load-proc-16": 0,
    "load:load1m-proc-16": 0,
    "load:load10m-proc-16": 1,
    "load:load-proc-17": 0,
    "load:load1m-proc-17": 0,
    "load:load10m-proc-17": 4,
    "load:load-proc-18": 0,
    "load:load1m-proc-18": 0,
    "load:load10m-proc-18": 2,
    "load:load-proc-19": 0,
    "load:load1m-proc-19": 0,
    "load:load10m-proc-19": 3,
    "load:load-proc-20": 0,
    "load:load1m-proc-20": 0,
    "load:load10m-proc-20": 2,
    "load:load-proc-21": 0,
    "load:load1m-proc-21": 0,
    "load:load10m-proc-21": 0,
    "load:load-proc-22": 0,
    "load:load1m-proc-22": 0,
    "load:load10m-proc-22": 0,
    "load:load-proc-23": 0,
    "load:load1m-proc-23": 0,
    "load:load10m-proc-23": 0,
    "load:load-proc-24": 0,
    "load:load1m-proc-24": 0,
    "load:load10m-proc-24": 0,
    "load:load-proc-25": 0,
    "load:load1m-proc-25": 0,
    "load:load10m-proc-25": 0,
    "load:load-proc-26": 0,
    "load:load1m-proc-26": 0,
    "load:load10m-proc-26": 0,
    "load:load-proc-27": 0,
    "load:load1m-proc-27": 0,
    "load:load10m-proc-27": 0,
    "load:load-proc-28": 0,
    "load:load1m-proc-28": 0,
    "load:load10m-proc-28": 0,
    "load:load-proc-29": 0,
    "load:load1m-proc-29": 0,
    "load:load10m-proc-29": 0,
    "load:load-proc-30": 0,
    "load:load1m-proc-30": 0,
    "load:load10m-proc-30": 0,
    "load:load-proc-31": 0,
    "load:load1m-proc-31": 0,
    "load:load10m-proc-31": 0,
    "load:load-proc-32": 0,
    "load:load1m-proc-32": 0,
    "load:load10m-proc-32": 0,
    "load:load-proc-33": 0,
    "load:load1m-proc-33": 0,
    "load:load10m-proc-33": 0,
    "load:load-proc-34": 0,
    "load:load1m-proc-34": 0,
    "load:load10m-proc-34": 0,
    "load:load-proc-35": 3,
    "load:load1m-proc-35": 0,
    "load:load10m-proc-35": 0,
    "load:load-proc-36": 0,
    "load:load1m-proc-36": 0,
    "load:load10m-proc-36": 0,
    "load:load-proc-37": 0,
    "load:load1m-proc-37": 0,
    "load:load10m-proc-37": 0,
    "load:load-proc-38": 0,
    "load:load1m-proc-38": 0,
    "load:load10m-proc-38": 0,
    "load:load-proc-39": 0,
    "load:load1m-proc-39": 0,
    "load:load10m-proc-39": 0,
    "load:load-proc-40": 0,
    "load:load1m-proc-40": 0,
    "load:load10m-proc-40": 0,
    "load:load-proc-41": 0,
    "load:load1m-proc-41": 0,
    "load:load10m-proc-41": 0,
    "load:load-proc-42": 0,
    "load:load1m-proc-42": 0,
    "load:load10m-proc-42": 0,
    "load:load-proc-43": 0,
    "load:load1m-proc-43": 0,
    "load:load10m-proc-43": 0,
    "load:load-proc-44": 0,
    "load:load1m-proc-44": 0,
    "load:load10m-proc-44": 0,
    "load:load-proc-45": 0,
    "load:load1m-proc-45": 0,
    "load:load10m-proc-45": 0,
    "load:load-proc-46": 0,
    "load:load1m-proc-46": 0,
    "load:load10m-proc-46": 0,
    "load:load-proc-47": 0,
    "load:load1m-proc-47": 0,
    "load:load10m-proc-47": 0,
    "load:load-proc-48": 0,
    "load:load1m-proc-48": 0,
    "load:load10m-proc-48": 0,
    "load:load-proc-49": 0,
    "load:load1m-proc-49": 0,
    "load:load10m-proc-49": 0,
    "load:load-proc-50": 0,
    "load:load1m-proc-50": 0,
    "load:load10m-proc-50": 0,
    "load:load-proc-51": 0,
    "load:load1m-proc-51": 0,
    "load:load10m-proc-51": 0,
    "load:load-proc-52": 0,
    "load:load1m-proc-52": 0,
    "load:load10m-proc-52": 0,
    "load:load-proc-53": 0,
    "load:load1m-proc-53": 0,
    "load:load10m-proc-53": 0,
    "load:load-proc-54": 0,
    "load:load1m-proc-54": 0,
    "load:load10m-proc-54": 0,
    "load:load": 0,
    "load:load1m": 0,
    "load:load10m": 0,
    "load:load-all": 0,
    "load:load1m-all": 0,
    "load:load10m-all": 0,
    "load:processes_number": 55
}


Hope this is all the information you need! Thanks!

Best regards,
Yury.

On Thu, Aug 25, 2022 at 8:24 PM Bogdan-Andrei Iancu <bogdan at opensips.org>
wrote:

> Hi Yury,
>
> And when that scaling up happens, do you actually have traffic ? or your
> OpenSIPS is idle ?
>
> Also, could you run `opensips-cli -x mi get_statistics load:` (not the
> colon at the end).
>
> Regards,
>
> Bogdan-Andrei Iancu
>
> OpenSIPS Founder and Developer
>   https://www.opensips-solutions.com
> OpenSIPS Summit 27-30 Sept 2022, Athens
>   https://www.opensips.org/events/Summit-2022Athens/
>
> On 8/25/22 10:57 AM, Yury Kirsanov wrote:
>
> Hi all,
> I've ran into a strange issue, if I enable autoscaler on OpenSIPS 3.2.x
> (tried 5,6,7 and now 8) on a server without any load using 'socket'
> statement like this:
>
> auto_scaling_profile = PROFILE_UDP_PRIV
>      scale up to 16 on 30% for 4 cycles within 5
>      scale down to 2 on 10% for 5 cycles
>
> udp_workers=4
>
> socket=udp:10.x.x.x:5060 use_auto_scaling_profile PROFILE_UDP_PRIV
>
> then after a while OpenSIPS load goes up to some high number, autoscaler
> starts to open new processes up to a maximum number specified in profile
> and them load stays at that number, for example:
>
> opensips-cli -x mi get_statistics load
> {
>     "load:load": 60
> }
>
> It never changes and looks just 'stuck'.
>
> Any ideas why this is happening in my case? Or should I file a bug report?
> Thanks.
>
> Regards,
> Yury.
>
> _______________________________________________
> Users mailing listUsers at lists.opensips.orghttp://lists.opensips.org/cgi-bin/mailman/listinfo/users
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.opensips.org/pipermail/users/attachments/20220904/85d37b04/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 24725 bytes
Desc: not available
URL: <http://lists.opensips.org/pipermail/users/attachments/20220904/85d37b04/attachment-0001.png>


More information about the Users mailing list