Skip to main content
Database Administrators

Return to Question

Commonmark migration
Source Link
Community Bot
Community Bot
  • 1

###Scenario

Scenario

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

###Question

Question

Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

###Background

Background

We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

###Scenario

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

###Question

Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

###Background

We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Scenario

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

Question

Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

Background

We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Notice removed Reward existing answer by Paul White♦
Bounty Ended with sql_handle's answer chosen by Paul White♦
Notice added Reward existing answer by Paul White♦
Bounty Started worth 250 reputation by Paul White♦
Tweeted twitter.com/#!/StackDBAs/status/634583235855536128
Improved title (for search), tags, formatting
Source Link
Paul White ♦
Paul White ♦
  • 90.3k
  • 30
  • 424
  • 663

SQL Server and Does CPU utilization affect the cost of foreign NUMA access?

Scenario:###Scenario

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

Question:###Question

Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

Background:###Background

We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Thanks!

SQL Server and NUMA

Scenario:

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

Question: Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

Background: We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Thanks!

Does CPU utilization affect the cost of foreign NUMA access?

###Scenario

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

###Question

Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

###Background

We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Source Link
xav
xav
  • 407
  • 2
  • 8

SQL Server and NUMA

Scenario:

Let's assume I have a SQL Server with 4 sockets with each 1 NUMA node. Each socket has 4 physical cores. There is 512 GB of memory total so each NUMA node has 128 GB of RAM.

A key table is loaded into the first NUMA node.

Question: Let's assume we have a lot of traffic reading from that table. If all physical cores of the socket that owns the NUMA node have 100 percent CPU utilization, does that negatively influence the cost of non-local NUMA access coming from other sockets? Or on the other hand is the cost of non-local NUMA access is irrespective of how busy that socket is?

I hope my question makes sense. Please let me know if it doesn't I will try to clarify.

Background: We had a database issue in our production server last week and some of our business processed appeared more impacted than others. We had queries with few logical reads taking more than 1 minute. We looked at overall CPU utilization which was around 60 percent. We did not look at socket specific CPU metrics. I/O metrics were average.

Thanks!