Questions about monitoring server hardware and software performance, or network performance.

learn more… | top users | synonyms

4
votes
1answer
789 views

ZFS ARC size vs target size

I am trying to understand the inner workings of the ZFS ARC. However, I am confused with several things: actual (zfs:0:arcstats:size) vs target size (zfs:0:arcstats:c). I understand that actual size ...
3
votes
1answer
143 views

Can I configure PCP (Performance Co-pilot) clients to report to a monitoring server from behind a firewall

I have several computers that are running applications. These computers are on the internet, in that they can connect out to the general internet over port 80. These computers have dynamic IP ...
2
votes
1answer
322 views

nmon NFS Performance Counters/Metrics

I have recently used nmon to record NFS client performance data from a suse 10 SP4 host and now need help understanding what the captured read & write figures truly indicate. With other ...
2
votes
1answer
4k views

Running perfmon continuously with periodic reports

I have a question very similar to this one, but I want to continuously run perfmon, during reboots and throughout the day. Further, I'd like to generate a perfmon report every 10 mins or so. The ...
2
votes
1answer
217 views

Tool to shows server workload status (ASP.NET + MS SQL)

I want to provide our testers with tool to see live server load, like memory usage, processor usage, database etc via webpage. There are a lot of tools which are installed on server for admin, But ...
2
votes
1answer
858 views

SQL Server “Long running transaction” performance counter: why no workee?

Please explain to me the following observation: I have the following piece of T-SQL code that I run from SSMS: BEGIN TRAN SELECT COUNT (*) FROM m WHERE m.[x] = 123456 or m.[y] IN (SELECT f.x FROM ...
1
vote
1answer
22 views

Why can't I view or add SQL and Network Performance Counters in Performance Monitor?

I'm trying to add the below Performance Counters to a user-defined data collector set in a Performance Monitor on Windows Server 2012 R2. I can see them when I dump them to a file (eg typeperf -q -o "...
1
vote
1answer
64 views

Tracking memory problems

I'm experiencing some trouble with my Windows Server 2008. We're using it for hosting a bunch (~50) of Web GIS applications on IIS. This setup usually works very well, but when certain applications ...
1
vote
1answer
3k views

Active Sessions Performance Counter for Web Server

I would like to monitor the number of active sessions for my ASP.Net 4.0. It is hosted on IIS7 Windows 2008 Server. When I looked at the Performance counter, I saw many instances. How could I know ...
4
votes
0answers
245 views

How do I get an aggregate of all the stats from all uWSGI vassals using uwsgitop?

TL;DR Can anyone tell me how I may get uwsgitop to monitor all of my vassals in my emperor-vassal setup in one shot? I have an emperor-vassal setup for my uWSGI server, and I need to monitor all ...
4
votes
0answers
57 views

Breakdown Windows Network IO by network adapter and by process

What I'm trying to do is breakdown the Network IO by network adapter and by Process. The goal is to identify which processes are generating the most IO on a certain network adapter. Resource Monitor ...
4
votes
0answers
2k views

Use perfmon to monitor a specific ASP.NET webapp across worker process restarts, IIS restarts, etc.?

I have a few perfmon performance counters that I'd like to track for a specific ASP.NET application over an extended period of time, say a week or a month. The trouble is that perfmon counters are ...
3
votes
0answers
41 views

ASP.NET Performance Counters Temporarily Drop To Zero

Having some performance issues with a VM Image (I do not have access to the VM Host, only the guest OS). Trying to determine why there are periods of time ranging from 10-60 seconds where the server ...
3
votes
0answers
95 views

Investigating Citrix app server “slowless”

Currently have a client stating that the 5 users on a 2cpu, 4gb mem app server are experiencing slowness and often, locking up for moments at a clip. Framework is a VM running in vSphere 5.5 [intel ...
2
votes
0answers
274 views

Benchmarking for DISK I/O Writes Per Second - ElasticSearch and MySQL

During working on our project we needed to decide should we use "ElasticSearch" or "MySQL" to record the audit/trail logs of the system. Searching speed is not an issue here, we needed to see the disk ...
2
votes
0answers
474 views

What could be cause of ASP.NET State Server timeout?

I recently migrated an app from SQL Server backed sessions to the ASP.NET State Server. About once a week there is a brief failure of ASP.NET to connect to the state server. These last from 20 ...
1
vote
0answers
6 views

Is there a way to check resource utilization on a cluster running SLURM?

Not sure if this question fits better here or at Unix.SE but I figured it feels more appropriate here. I am running some computation-heavy research on a national cluster which uses SLURM for ...
1
vote
0answers
41 views

Physical memory runs out after sql changes

We have an 2008 r2 server working for 5 years, its physical memory was always around 70% but after our last site code and SQL stored procedures and functions updates it got to 94-96% and all the pages ...
1
vote
0answers
188 views

100% CPU, load average 0 - how is this possible?

Here's the top output: top - 19:20:47 up 1 day, 4:30, 1 user, load average: 0.01, 0.07, 0.12 Tasks: 170 total, 1 running, 169 sleeping, 0 stopped, 0 zombie %Cpu(s): 0.6 us, 0.9 sy, 0.0 ni,...
1
vote
0answers
109 views

Performance Monitor Processor Time counter blank data

I setup a simple data collector with Performance Monitor to collect Processor time(CPU Usage in %) and SQL Statistics: Batch Requests/sec @ 15 second intervals to see if i can get some baselines and ...
1
vote
0answers
18 views

What is involved in adding ZFS cache stats to orca?

I am interested in looking to add ZFS cache stats into existing orca performance monitoring that we have. Particularly, I am interested in the output of echo ::memstat | mdb -k Am still in the early ...
1
vote
0answers
83 views

PRTG Network Monitor custom sensor - return grouped data

I have an IBM DS3512 storage system that I want to monitor. So far I was able to create a custom XML sensor on Powershell, that grabs performance data saved by smcli.exe (the only known way to reach ...
1
vote
0answers
397 views

High CPU caused by system interrupts

We have a three day old Idacentre A740 AIO PC. (windows 8.1 pro) The system is up-to-date. After we start the PC and "do notthing" the system interrupts taken 40% CPU time approximately. Tried to ...
1
vote
0answers
198 views

Logman user switch confusion

I'm setting up a powershell script that installs a logman counter on several servers that are in dire need of some performance monitoring. The documentation states that the -u switch works with ...
1
vote
0answers
197 views

Why does Process Explorer cause highly targeted failure of some applications / basic UI functions in a high-power EC2 Windows instance?

Update: I have determined that Process Explorer itself - the program I am using to debug a performance issue - seems to be the cause of the issue. See note, with updated question, at end. I am ...
1
vote
0answers
118 views

IIS httpTracing setting has no effect

I'm trying to troubleshoot some performance issues we are having on a specific ASP.NET page with Microsoft's Perfecto Tool on IIS 7.5. Perfecto uses the ETW hooks build in to IIS to report on specific ...
1
vote
0answers
71 views

How can I get a windows server to collate and email 4 daily reports/graphs for server performance

I run a windows 2008 webserver and would like to setup the most basic performance monitoring in the world. What i would like is: a plot of ASP.Net request time for each w3wp process for a 24hour ...
1
vote
0answers
195 views

Increasing collection level for performance counters in vCenter 5

I want to simply increase the collection level of some of the Network performance counters to 4, when I look in performance for the host, and click 'Advanced', switch to look at the Network ...
1
vote
0answers
142 views

Windows 2008 R2 - how to optimise performance monitoring?

It seems there are quite a few "default" monitoring threads running. I have W2008R2 and when I opened Performance Monitor I can see 6 Event Trace Sessions in the System collector sets. This is ...
1
vote
0answers
109 views

How do I make Performance Monitor always log the time AND date?

I have been using Performance Monitor to keep an eye on Non-Paged Memory usage over the last few months. From the csv files generated I have been creating graphs to make it easy to pin point problem ...
1
vote
0answers
78 views

Configuring PA Server Monitor for Windows monitoring

My company got PA Server Monitor to monitor 6 servers. I have few questions regarding configuration. So far I've made disk space and ping monitors. Generally two servers are IIS 7, two are SQL Server ...
1
vote
0answers
67 views

What to check for IIS Performance Monitoring

I'm trying to discover why an internet server is running on the slow side. One thing that the site does is to use an external data source, and we know those queries are slow, but these long queries ...
1
vote
0answers
693 views

Physical Disk counters not showing up in PerfMon results

I am trying to diagnose some issues for a customer, but i notice that none of the disk related counters show up in my PerfMon results (graph or csv format). I found this article (http://blogs.msdn....
1
vote
0answers
51 views

Hyper-V Performance Monitors Not Working as Data Collectors

I'm trying to monitor vCPU performance in Hyper-V using data collectors and while I can view the real time monitors (Hyper-V Hypervisor Virtual Processor\% Guest Run Time), whenever I try to add the ...
0
votes
0answers
11 views

data collector set from template “the security id may be not assigned”

I want to create data collector set from template on my windows server 2012 R2 (virtual machine). At last step (where you need to specify user to run this test) I'm getting this error: My ...
0
votes
0answers
16 views

Task Manager shows high kernel time

Foreward: Hardware: dual-socket Intel Xeon, 128gb memory, hardware RAID-1 SSD OS: Windows 2012 R2 Standard w/ Remote Desktop Services The Task Manager for one of our terminal/application servers ...
0
votes
0answers
21 views

SCOM 2012 - understanding rules vs. monitors?

In SCOM 2012, I have a subscription that was setup by one of my admins who is no longer here. I'm a little confused by the subscription and while I've read multiple times the differences between ...
0
votes
0answers
16 views

How to check that VMWare virtual machine is receiving sufficient resources from the physical server?

We have VMWare virtual machine in data center but applications on it suddenly started to be slow after one weekend. We are considering possibility that data center has moved virtual machine to other ...
0
votes
0answers
23 views

CPU utiliation in summary and task areas differ

We have a Cisco UCS-B200-M3 server with 48 cores under high load. The curious thing is a mismatch in top output. Here are the initial lines from top: top - 14:14:06 up 35 days, 18:11, 0 users, load ...
0
votes
0answers
92 views

IIS time-taken and \ASP.NET\Request Execution Time relation

I am aware that the IIS log entry time-taken field will also report network-time (under certain conditions). I use the PerfMon counter \ASP.NET\Request Execution Time that reports The number of ...
0
votes
0answers
17 views

Is it possible to get performance metrics out of hitachi san array or out of tuning manager?

Has several hitachi san arrays ( AMS, HUS ) and virtualizers ( VSP, USPV ). Hitachi Command Suite had installed. Tuning Manager quite usefull, but i want to get statistics out of it ( automatic way, ...
0
votes
0answers
160 views

How to monitor request timeouts/drops between IIS and nginx

An NGINX reverse proxy is load balancing multiple Windows IIS/ASP.NET servers. Let's say the servers are under heavy load and might drop connections/requests. I see upstream timed out errors in nginx'...
0
votes
0answers
10 views

How to show delta of a counter metric in PCP between time A and B?

For simple metric like disk.all.read it is enough to do something like this: $ pmval -a ... -S 11:50 -s 2 -t10m -r disk.all.read metric: disk.all.read ... start: Tue Feb 23 11:50:00 2016 end: ...
0
votes
0answers
14 views

drop in nmon top monitoring

We've had an incident in production and while looking at the nmon TOP graphs for some java program, I was surprised to notice drops in the data collection, see the picture: As you can guess (since ...
0
votes
0answers
15 views

Error Running pcp on Cent OS

I am installing pcp and pcp-webapi using the following command [vagrant@localhost ~]$ sudo yum -y install pcp-webapi It installs successfully, however when I try to start the service using sudo ...
0
votes
0answers
37 views

Establishing performance baseline with SCOM 2012 APM

We're lookign at establishing a performance baseline for our production environment. This could be as simple as establishing highest measured TPS for MS SQL environment and highest measured RPS for ...
0
votes
0answers
23 views

How to set IIS Logging to best fit this scenario

I need to monitor a IIS 7 App Pool (WCF is running on it) and I would like to read messages like: Request A Received. Pool is down. Starting Pool. Request B Received. Pool going up. Request C ...
0
votes
0answers
21 views

Orca yearly graph is not showing correct results

We are using Orca for performance monitoring on a number of solaris servers. We've got plots for hourly, daily, weekly, monthly, quarterly and yearly. However, the yearly plot is displaying hour ...
0
votes
0answers
101 views

Hadoop - On the Wire Performance Monitoring?

I have been tasked with implementing an 'on the wire' monitoring solution for a large Hadoop installation. The source of data will be a combination of taps and SPANs throughout the environment. My ...
0
votes
0answers
55 views

top output seems fine, yet server is overloaded

This server I am benchmarking gives no obvious signs of getting overloaded at a first glance. top output: top - 22:48:25 up 5 days, 3:41, 3 users, load average: 3.19, 3.34, 3.25 Tasks: 146 total, ...