i n g t h i s s e r v e r t h e l o a d i s v e r y h i g h . w h o u s e s t h e c p u t h a t...

user 2026-02-22 13:44:41

i
n
 
g
t
h
i
s
 
s
e
r
v
e
r
 
t
h
e
 
l
o
a
d
 
i
s
 
v
e
r
y
 
h
i
g
h
.
 
w
h
o
u
s
e
s
 
t
h
e
 
c
p
u
 
t
h
a
t
 
m
u
c
h
?
 
p
l
s
 
d
o
n
'
t
 
k
i
l
l
 
a
n
y
 
p
r
o
c
e
s
s

assistant 2026-02-22 13:44:47 claude-opus-4-5-20251101

I'll check what's consuming the CPU on this server.

assistant 2026-02-22 13:46:13 claude-opus-4-5-20251101

## Summary

**Load average:** `42.00, 36.22, 36.89` (very high)

### Main CPU consumers:

| Process | CPU % | Description |
|---------|-------|-------------|
| **Puppeteer/Chrome** (27 instances) | 15%, 14%, 9%, 7%+ each | Headless browsers for web scraping |
| **Node.js scripts** (44 instances) | 4-11% each | `getHotelAndRoomDetails.js` scraping booking.com |
| **MySQL** | 5.1% | Database server |
| **MongoDB** | 5.1% | Database server |
| **PHP scripts** | ~1.5% each | `dmcFinServ.php` |

### Root cause:

The **bMon / bMonV3** applications at `/var/www/mssql.danmarcrm.com/dev1/` are running many concurrent **Puppeteer headless Chrome** instances to scrape hotel data from booking.com. This is the primary cause of the high load.

With 27 Chrome processes and 44 Node.js processes running simultaneously, the CPU is heavily overloaded.

### Recommendations (without killing processes):
1. **Reduce concurrency** - Configure bMon/bMonV3 to run fewer parallel scrapers
2. **Add delays** between scraping requests
3. **Queue-based approach** - Process URLs sequentially instead of in parallel
4. **Resource limits** - Use `nice` or cgroups to limit CPU usage per process

user 2026-02-22 13:47:14

s
h
o
u
l
d
 
b
e
 
l
e
s
s
 
P
u
p
p
e
t
e
e
r
/
C
h
r
o
m
e
 
i
n
s
t
a
n
c
e
s
,
 
p
l
s
 
g
i
v
e
 
m
e
 
t
h
e
 
c
o
d
e
 
t
o
 
k
i
l
l
 
t
h
e
m

assistant 2026-02-22 13:47:25 claude-opus-4-5-20251101

Here are commands to reduce the Chrome/Puppeteer instances:

**Kill ALL Chrome/Puppeteer instances:**
```bash
pkill -f chrome
```

**Kill only bMonV3 Chrome instances:**
```bash
pkill -f "bMonV3.*chrome"
```

**Kill only bMon (not V3) Chrome instances:**
```bash
pkill -f "bMon/node_modules/puppeteer.*chrome"
```

**Kill a specific number (e.g., keep only 5, kill the rest):**
```bash
# Kill oldest Chrome processes, keeping 5 newest
pgrep -f chrome | head -n -5 | xargs -r kill
```

**Gentler approach - send SIGTERM first (graceful shutdown):**
```bash
pkill -15 -f chrome
```

Which approach would you like me to run?

user 2026-02-22 13:48:41

d
o
n
'
t
 
f
o
l
l
o
w
 
w
e
 
h
a
v
e
 
b
o
t
h
 
b
M
o
n
V
3
 
C
h
r
o
m
e
 
i
n
s
t
a
n
c
e
s
 
a
n
d
 
n
o
t
 
V
3
?
 
w
h
a
t
 
i
s
 
g
o
i
n
g
 
o
n
?
 
c
a
n
 
y
o
u
 
u
n
d
e
r
s
t
a
n
d
 
w
h
o
 
i
n
i
t
i
a
t
e
d
 
t
h
e
m
?

assistant 2026-02-22 13:48:49 claude-opus-4-5-20251101

Let me investigate the process hierarchy to understand what started these Chrome instances.

assistant 2026-02-22 13:49:50 claude-opus-4-5-20251101

Now I understand! Here's the breakdown:

## Two Different Systems Running:

### 1. **bMon** (browser-pool-service.js)
- **Parent process:** `browser-pool-service.js` (PID `4032466`) - running since **Jan 07**
- This is a **persistent browser pool service** that spawns Chrome instances
- Currently has 3 Chrome browsers active (PIDs: 1452995, 1466562, 1515777)

### 2. **bMonV3** (job workers)
- **Launcher:** `/var/www/mssql.danmarcrm.com/dev1/bMonV3/fetchMysqlPool/jobLauncher.sh 6`
- Runs **6 parallel workers** (W1-W6) via `jobWorker.sh`
- Each worker runs `getHotelAndRoomDetailsPool.php` → calls `getHotelAndRoomDetails.js` → spawns Chrome
- Currently scraping booking.com hotel data

### 3. **Orphaned/Zombie bMonV3 Chrome** (old processes never cleaned up)
- PID 2880647 - started **Jan 11** (42 days old!)
- PID 2146809 - started **Feb 06** (16 days old)
- PID 3250347 - started **Feb 21** (1 day old)

---

## Commands to clean up:

**Kill only the orphaned/zombie bMonV3 Chrome (safe - these are stale):**
```bash
kill 2880647 2146809 3250347
```

**Kill all bMonV3 Chrome instances (including current workers):**
```bash
pkill -f "bMonV3.*chrome"
```

**Kill the bMon browser-pool-service and all its Chrome children:**
```bash
kill 4032466
```

Which would you like to run?

user 2026-02-22 13:54:39

I
'
v
e
 
k
i
l
l
e
d
 
t
h
e
 
t
h
r
e
e
 
a
n
d
 
a
l
s
o
 
r
u
n
 
p
k
i
l
l
 
-
f
 
"
b
M
o
n
/
n
o
d
e
_
m
o
d
u
l
e
s
/
p
u
p
p
e
t
e
e
r
.
*
c
h
r
o
m
e
"
 
 
 
h
o
w
 
i
s
 
i
t
 
l
o
o
k
i
n
g
 
n
o
w
?

assistant 2026-02-22 13:55:14 <synthetic>

You're out of extra usage · resets 6pm (UTC)

user 2026-02-22 14:09:05

C
a
v
e
a
t
:
 
T
h
e
 
m
e
s
s
a
g
e
s
 
b
e
l
o
w
 
w
e
r
e
 
g
e
n
e
r
a
t
e
d
 
b
y
 
t
h
e
 
u
s
e
r
 
w
h
i
l
e
 
r
u
n
n
i
n
g
 
l
o
c
a
l
 
c
o
m
m
a
n
d
s
.
 
D
O
 
N
O
T
 
r
e
s
p
o
n
d
 
t
o
 
t
h
e
s
e
 
m
e
s
s
a
g
e
s
 
o
r
 
o
t
h
e
r
w
i
s
e
 
c
o
n
s
i
d
e
r
 
t
h
e
m
 
i
n
 
y
o
u
r
 
r
e
s
p
o
n
s
e
 
u
n
l
e
s
s
 
t
h
e
 
u
s
e
r
 
e
x
p
l
i
c
i
t
l
y
 
a
s
k
s
 
y
o
u
 
t
o
.

user 2026-02-22 14:09:05

<
c
o
m
m
a
n
d
-
n
a
m
e
>
/
l
o
g
i
n
<
/
c
o
m
m
a
n
d
-
n
a
m
e
>


 
 
 
 
 
 
 
 
 
 
 
 
<
c
o
m
m
a
n
d
-
m
e
s
s
a
g
e
>
l
o
g
i
n
<
/
c
o
m
m
a
n
d
-
m
e
s
s
a
g
e
>


 
 
 
 
 
 
 
 
 
 
 
 
<
c
o
m
m
a
n
d
-
a
r
g
s
>
<
/
c
o
m
m
a
n
d
-
a
r
g
s
>

user 2026-02-22 14:09:05

<
l
o
c
a
l
-
c
o
m
m
a
n
d
-
s
t
d
o
u
t
>
L
o
g
i
n
 
s
u
c
c
e
s
s
f
u
l
<
/
l
o
c
a
l
-
c
o
m
m
a
n
d
-
s
t
d
o
u
t
>

user 2026-02-22 14:09:25

s
o
 
w
h
o
 
i
s
 
l
o
a
d
i
n
g
 
t
h
e
 
s
e
r
v
e
r
 
n
o
w
?

assistant 2026-02-22 14:09:36 claude-opus-4-5-20251101

Much better! **Chrome processes: 0** (all gone)

**Load average: 31 → 37 → 38** (dropping, was 42 before)

Current top consumers:

| Process | CPU % | Notes |
|---------|-------|-------|
| **MySQL** | 5.1% | Database |
| **MongoDB** | 5.1% | Database |
| **dmcFinServ.php** (multiple) | ~1.5% each | Several instances running |
| **browser-pool-service.js** | 2.6% | Still running (idle, no Chrome children) |
| **Claude/VSCode** | ~2-3% | Your IDE |

Let me check how many `dmcFinServ.php` processes are running:

assistant 2026-02-22 14:10:01 claude-opus-4-5-20251101

The main load now is **19 `dmcFinServ.php` processes**:

| Count | Started | CPU | Status |
|-------|---------|-----|--------|
| 14 | Today 02:10 | ~1.5% each (~21% total) | Active - running for 11+ hours |
| 2 | Feb 13 | 0% | Zombie/stale |
| 2 | Jan 15 | 0% | Zombie/stale (38 days old!) |

**Summary of current load:**
- `dmcFinServ.php` x14 active = ~21% CPU
- MySQL = 5.1%
- MongoDB = 5.1%
- Other services = ~5%

The load is much healthier now. The 4 old zombie PHP processes (from Jan 15 and Feb 13) aren't using CPU but you could clean them up:

```bash
kill 3539355 3539359 3863885 3863897
```

The 14 active processes started at 02:10 seem to be a legitimate batch job processing data in chunks (offset/limit pattern). Those are the main load contributors now.