Home / ubuntu / Questions / 1128505
In Process
Milano
Asked: 2019-03-26 03:45:53 +0800 CST

Help me to diagnose performance issues (top, htop doesn't help)

  • 772

EDIT4 So most of the times, this problem seems to happen when something is loading into the memory.

I tried to run stress test:

stress --cpu 8 --io 4 --vm 4 --vm-bytes 1024M --timeout 10s

This didn't do anything but when I double (sometimes it needs more) the --vm-bytes everything freeze for those 10 seconds. So I suppose there is a memory issue but I don't what to do next.

END OF EDIT4

I have problems with Ubuntu 18.04 and I can't debug this problem for weeks. I hope you could help me to diagnose it because I really tried everything except reinstalling Ubuntu.

It randomly (approximately one time per minute) freezes for a very short time and sound starts crackling. It feels like CPU or GPU problem but I can't figure out where is the problem. It happens mostly when I open window or refresh chrome tab etc but sometimes when I do not anything.

Moreover, video players likes to freeze whole Ubuntu sometimes.

I have three monitors connected to GPU but it happens even with two monitors. GTX 1060 6GB

Things like htop or top don't help - I would have to checking it realtime and even then it isn't much helpful.

Isn't there something which detects CPU, RAM, DISK peaks and logs it somewhere alongside information about which process caused it?

Here are some information:

  1. CPUs are probably ok - they are not on constant 800 Mhz enter image description here

  2. syslog doesn't log anything at times the crackling and short freezing happens (last happend 12:38:11) - this is the end of syslog

enter image description here

  1. I've disabled gnome extension
  2. I've reinstalled NVIDIA drivers

enter image description here

  1. Tried if it happens when chrome is closed, confirmed, happens
  2. I don't see something like 100% CPU in top when it happens

top enter image description here

EDIT

The freezing/crackling is not caused by any cron job, it clearly happens mostly when I do something like opening windos, refreshing chrome etc.

Removing swap file didn't help.

df -h

Filesystem      Size  Used Avail Use% Mounted on
udev            7,8G     0  7,8G   0% /dev
tmpfs           1,6G  3,0M  1,6G   1% /run
/dev/nvme0n1p1  440G  257G  161G  62% /
tmpfs           7,8G  238M  7,6G   3% /dev/shm
tmpfs           5,0M  4,0K  5,0M   1% /run/lock
tmpfs           7,8G     0  7,8G   0% /sys/fs/cgroup
/dev/loop1      441M  441M     0 100% /snap/wine-platform/103
/dev/loop0      133M  133M     0 100% /snap/postman/81
/dev/loop2      128K  128K     0 100% /snap/cncra2yr/35
/dev/loop4      153M  153M     0 100% /snap/ramboxpro/6
/dev/loop3       92M   92M     0 100% /snap/core/6531
/dev/loop5      145M  145M     0 100% /snap/wavebox/163
/dev/loop6      156M  156M     0 100% /snap/brave/57
/dev/loop8      144M  144M     0 100% /snap/wavebox/161
/dev/loop7      5,2M  5,2M     0 100% /snap/htop/1066
/dev/loop12      91M   91M     0 100% /snap/core/6405
/dev/loop9      100M  100M     0 100% /snap/sensors-unity/75
/dev/loop10      35M   35M     0 100% /snap/gtk-common-themes/1122
/dev/loop13     100M  100M     0 100% /snap/qxmledit/129
/dev/loop11      13M   13M     0 100% /snap/gnome-characters/124
/dev/loop14     112M  112M     0 100% /snap/rambox/2
/dev/loop17      98M   98M     0 100% /snap/docker/321
/dev/loop15     5,9M  5,9M     0 100% /snap/htop/1168
/dev/loop16     144M  144M     0 100% /snap/wavebox/162
/dev/loop22      15M   15M     0 100% /snap/gnome-logs/43
/dev/loop19     145M  145M     0 100% /snap/slack/11
/dev/loop20      54M   54M     0 100% /snap/core18/782
/dev/loop23     4,2M  4,2M     0 100% /snap/gnome-calculator/352
/dev/loop24     402M  402M     0 100% /snap/redis-desktop-manager/191
/dev/loop26     144M  144M     0 100% /snap/gnome-3-28-1804/23
/dev/loop25      54M   54M     0 100% /snap/core18/731
/dev/loop18     340M  340M     0 100% /snap/pycharm-professional/121
/dev/loop21     288M  288M     0 100% /snap/datagrip/40
/dev/loop27     441M  441M     0 100% /snap/wine-platform/105
/dev/loop28     340M  340M     0 100% /snap/pycharm-professional/112
/dev/loop29     128K  128K     0 100% /snap/cncra2yr/34
/dev/loop30      15M   15M     0 100% /snap/gnome-logs/45
/dev/loop31      91M   91M     0 100% /snap/core/6350
/dev/loop32     2,3M  2,3M     0 100% /snap/gnome-calculator/238
/dev/loop33     3,8M  3,8M     0 100% /snap/gnome-system-monitor/57
/dev/loop34      13M   13M     0 100% /snap/gnome-characters/139
/dev/loop35     141M  141M     0 100% /snap/gnome-3-26-1604/78
/dev/loop37     100M  100M     0 100% /snap/qxmledit/125
/dev/loop36     141M  141M     0 100% /snap/gnome-3-26-1604/82
/dev/loop38     2,3M  2,3M     0 100% /snap/gnome-calculator/260
/dev/loop40     153M  153M     0 100% /snap/brave/44
/dev/loop39      35M   35M     0 100% /snap/gtk-common-themes/818
/dev/loop41      93M   93M     0 100% /snap/sensors-unity/67
/dev/loop43     131M  131M     0 100% /snap/postman/80
/dev/loop42     340M  340M     0 100% /snap/pycharm-professional/116
/dev/loop44     110M  110M     0 100% /snap/rambox/1
/dev/loop46     1,0M  1,0M     0 100% /snap/gnome-logs/57
/dev/loop45     158M  158M     0 100% /snap/brave/58
/dev/loop47     4,9M  4,9M     0 100% /snap/htop/959
/dev/loop48     141M  141M     0 100% /snap/gnome-3-26-1604/74
/dev/loop50     100M  100M     0 100% /snap/qxmledit/115
/dev/loop49     142M  142M     0 100% /snap/slack/10
/dev/loop52      36M   36M     0 100% /snap/gtk-common-themes/1198
/dev/loop51     3,8M  3,8M     0 100% /snap/gnome-system-monitor/54
/dev/loop53     441M  441M     0 100% /snap/wine-platform/101
/dev/loop54     145M  145M     0 100% /snap/slack/12
/dev/loop56     128K  128K     0 100% /snap/cncra2yr/36
/dev/loop59      15M   15M     0 100% /snap/gnome-characters/206
/dev/loop55     290M  290M     0 100% /snap/datagrip/42
/dev/loop57     275M  275M     0 100% /snap/datagrip/39
/dev/sdb2        95M   30M   66M  32% /boot/efi
/dev/loop58     3,8M  3,8M     0 100% /snap/gnome-system-monitor/70
tmpfs           1,6G   16K  1,6G   1% /run/user/121
tmpfs           1,6G  164K  1,6G   1% /run/user/1000
/dev/sdc1       932G  491G  442G  53% /media/milano/Milano Disk

Output from psensor

enter image description here

EDIT2

For some reason I can't check SSD SMART data on disk-utility but this is output from command line:

milano@milano-PC:~$ sudo smartctl -x /dev/nvme0n1p1 
smartctl 6.6 2016-05-31 r4324 [x86_64-linux-4.15.0-46-generic] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Model Number:                       KINGSTON SA1000M8480G
Serial Number:                      50026B7282169510
Firmware Version:                   E8FK11.L
PCI Vendor/Subsystem ID:            0x2646
IEEE OUI Identifier:                0x0026b7
Total NVM Capacity:                 480 103 981 056 [480 GB]
Unallocated NVM Capacity:           0
Controller ID:                      0
Number of Namespaces:               1
Namespace 1 Size/Capacity:          480 103 981 056 [480 GB]
Namespace 1 Formatted LBA Size:     512
Local Time is:                      Mon Mar 25 14:28:10 2019 CET
Firmware Updates (0x02):            1 Slot
Optional Admin Commands (0x0007):   Security Format Frmw_DL
Optional NVM Commands (0x001e):     Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat
Maximum Data Transfer Size:         512 Pages
Warning  Comp. Temp. Threshold:     90 Celsius
Critical Comp. Temp. Threshold:     94 Celsius

Supported Power States
St Op     Max   Active     Idle   RL RT WL WT  Ent_Lat  Ex_Lat
 0 +     7.90W  0.0790W       -    0  0  0  0      600     600
 1 +     7.90W  0.0790W       -    0  0  0  0      600     600
 2 +     7.90W  0.0790W       -    0  0  0  0      600     600
 3 -   0.1000W  0.0790W       -    3  3  3  3     1000    1000
 4 -   0.0050W  0.0790W       -    4  4  4  4   400000   90000

Supported LBA Sizes (NSID 0x1)
Id Fmt  Data  Metadt  Rel_Perf
 0 +     512       0         1
 1 -    4096       0         0

=== START OF SMART DATA SECTION ===
Read NVMe SMART/Health Information failed: NVMe Status 0x02

EDIT3

milano@milano-PC:~$ sudo smartctl -x /dev/nvme0
smartctl 6.6 2016-05-31 r4324 [x86_64-linux-4.15.0-46-generic] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Model Number:                       KINGSTON SA1000M8480G
Serial Number:                      50026B7282169510
Firmware Version:                   E8FK11.L
PCI Vendor/Subsystem ID:            0x2646
IEEE OUI Identifier:                0x0026b7
Total NVM Capacity:                 480 103 981 056 [480 GB]
Unallocated NVM Capacity:           0
Controller ID:                      0
Number of Namespaces:               1
Namespace 1 Size/Capacity:          480 103 981 056 [480 GB]
Namespace 1 Formatted LBA Size:     512
Local Time is:                      Mon Mar 25 14:31:22 2019 CET
Firmware Updates (0x02):            1 Slot
Optional Admin Commands (0x0007):   Security Format Frmw_DL
Optional NVM Commands (0x001e):     Wr_Unc DS_Mngmt Wr_Zero Sav/Sel_Feat
Maximum Data Transfer Size:         512 Pages
Warning  Comp. Temp. Threshold:     90 Celsius
Critical Comp. Temp. Threshold:     94 Celsius

Supported Power States
St Op     Max   Active     Idle   RL RT WL WT  Ent_Lat  Ex_Lat
 0 +     7.90W  0.0790W       -    0  0  0  0      600     600
 1 +     7.90W  0.0790W       -    0  0  0  0      600     600
 2 +     7.90W  0.0790W       -    0  0  0  0      600     600
 3 -   0.1000W  0.0790W       -    3  3  3  3     1000    1000
 4 -   0.0050W  0.0790W       -    4  4  4  4   400000   90000

Supported LBA Sizes (NSID 0x1)
Id Fmt  Data  Metadt  Rel_Perf
 0 +     512       0         1
 1 -    4096       0         0

=== START OF SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

SMART/Health Information (NVMe Log 0x02, NSID 0xffffffff)
Critical Warning:                   0x00
Temperature:                        34 Celsius
Available Spare:                    100%
Available Spare Threshold:          100%
Percentage Used:                    1%
Data Units Read:                    10 140 359 [5,19 TB]
Data Units Written:                 11 376 845 [5,82 TB]
Host Read Commands:                 169 519 743
Host Write Commands:                205 066 508
Controller Busy Time:               1 117
Power Cycles:                       211
Power On Hours:                     953
Unsafe Shutdowns:                   12
Media and Data Integrity Errors:    0
Error Information Log Entries:      3
Warning  Comp. Temperature Time:    0
Critical Comp. Temperature Time:    0
Temperature Sensor 2:               34 Celsius

Error Information (NVMe Log 0x01, max 16 entries)
Num   ErrCount  SQId   CmdId  Status  PELoc          LBA  NSID    VS
  0          3     0  0x001d  0x0004      -      8323074     1     -
  1          2     0  0x001d  0x0005      -      8323074     1     -
  2          1     0  0x001d  0x0005      -      8323074     1     -
gnome performance cpu 18.04

1 Answers

    1. htop is perfect for understanding CPU and memory hogs. Please make sure to remove the need for swap. Swap is using your hard disk and CPU which will make it work slower at times to cope with all I/O.
    2. iotop --only -d0.1 is pretty good at showing you what uses your disks.
    3. use df -h to get the info about the hard disk usage. e.g: It's known for SSD to work slower when the free space is mostly occupied. Make sure to have around 10% disk always available/free.

    My current guess based on what you said is this is about some cron script running every minute, but that's still a guess.

    There's a pending bug report about your system.log snap package: https://bugs.launchpad.net/ubuntu/+source/gnome-system-monitor/+bug/1791454 Make sure to subscribe to it and watch how to resolve.

    • 0