![]() Page faults / sec is the sum of hard and soft page faults. In truth, if you put 5 experts in the same room, they could all spot a memory bottleneck, but when they wrote up their notes, they would use different time slices and different thresholds, consequently, it would seem that there was a conflict where none actually existed. Moreover, I would not trust pages /sec as an indicator of a bottleneck without confirmation from low Available bytes. I am reluctant to disagree with other authorities, but from my experience, I would put the threshold as high as 20 pages /sec, before blaming paging as the bottleneck. This counter measures ‘hard’ page faults, in other words the page in nowhere in memory, so the VMM (Virtual Memory Manager) has to fetch the data from the pagefile on the disk in computing terms that takes an age. Most authorities agree that Memory: Pages / sec is a key memory counter. The less paging the better your server’s performance. Two problems with monitoring in general, firstly no counter should be taken in isolation, secondly spikes should be ignored, or at least played down. ![]() ![]() Take care to distinguish between these two paging counters:Ģ) Page Faults /sec counter is likely to be at least twice the value of the above. Three paging counters in performance monitor 1) Memory: Pages / sec This is why a large pool of free memory is so important to an application server. The operating system provides this memory at least 100 times faster using RAM, than it could using a disk based pagefile. Suppose a spreadsheet wants to start a new thread or a database needs to sort data, what each needs is memory. As long as the trace indicates more than 10MB of free memory, then I conclude that the server has sufficient RAM.ĭiagram 1 shows a white descending line, and the legend confirms that Available bytes are down to 3MB. When I check a server’s memory with performance monitor, the first counter that I add to the log is Memory\Available bytes. The more available memory the faster the server can respond. Identify the root cause of a memory bottleneck.Pure domain controllers are less likely to experience memory problems. Email servers also require plenty of RAM. The servers most likely to suffer from memory shortage are pure database servers for example, Oracle or SQL. So once you have had a quick look at memory, remember to check the processor and disk counters. Even with these sensory clues, it is still worth while monitoring memory with Performance Logs. On old servers, lack of memory would give you the full sensory input, you could hear the disk paging, see the light flashing, and ‘Mad’ Mick swears you could smell the disk thrashing. A bonus of plenty of memory is, that to a degree, abundant RAM compensates for strain on other resources. Another way of looking at server performance, is that machines with plenty of RAM rarely give problems. If ever your Windows 2003 server is running slowly, then the first place to look for a bottleneck is memory.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |