Join us for a virtual Nutanix User Group meeting with Jarian Gibson as he covers Nutanix Cloud Clusters (NC2) on Azure and AWS with Citrix. <\/span><\/p>

Jarian will take a deep dive into NC2 on Azure architecture and Citrix on NC2 on Azure\u00a0that helps you strengthen your business continuity and disaster recovery position. He\u2019ll also provide the latest updates for NC2 on AWS.<\/span><\/p>

Plus, we're\u00a0giving away a Nutanix suitcase to one lucky winner!\u00a0Opt-in when you register\u00a0to be entered to win.\u00a0<\/p>","author":{"id":113632,"url":"\/members\/karlie-beil-113632","name":"Karlie Beil","avatar":"https:\/\/uploads-us-west-2.insided.com\/nutanix-us\/icon\/200x200\/1581aab3-bcf6-49f4-b2fb-3d11e8c010dc.png","userTitle":"Community Manager","rank":{"isBold":false,"isItalic":false,"isUnderline":false,"name":"Community Manager","color":"#0873ba"},"userLevel":4},"type":"Webinar","url":"https:\/\/next.nutanix.com\/events\/global-nug-nc2-on-azure-and-aws-with-citrix-151","image":"https:\/\/uploads-us-west-2.insided.com\/nutanix-us\/attachment\/f9693b5b-436b-427a-9b98-531b4040ff24_thumb.png","location":"","startsAt":1678298400,"endsAt":1678302000,"contentType":"event","attendees":[],"attendeeCount":0,"isLoggedInUserAttendee":false,"createdAt":"1675974969"},"phrases":{"Forum":{"{n} year|{n} years":"{n} year|{n} years","{n} month|{n} months":"{n} month|{n} months","{n} day|{n} days":"{n} day|{n} days","{n} hour|{n} hours":"{n} hour|{n} hours","{n} minute|{n} minutes":"{n} minute|{n} minutes","just":"just now","{plural} ago":"{plural} ago"}}}">

在VDI POC中写下延迟

s
徽章 +6
我们使用3节点Dell XC720XD群集在客户站点上执行POC。从vCenter获取的统计数据显示，在1 ms左右的平均读取率和一个5-6 ms的写入延迟。



写潜伏期似乎太高了，因为它应该仅在SSD上制作2个写作（基础和副本）。我想知道CVM是否有一个计时器，然后才将待处理的写入给OPLOG。



这通常可以帮助减少I/O的数量并增加对SSD有益的大小。



不幸的是，在我们的POC中，我们正在用Fusion-io PCI卡与当前对服务器的配置作斗争，这种方法可能是一个劣势。



另一个重要参数是当前系统上平均在35-40秒的登录时间，并使用Nutanix达到75秒。



加快Nutanix群集的任何建议可能正在修改某些参数吗？

\n

\nThe write latency seems way too high since it should just make 2 writes (base and replica) on SSD. I wonder if the CVM has a timer before it flushes the pending writes to the oplog.

\n

\nThis could help generally speaking to reduce the number of I\/O and increase the size which is good for SSD.

\n

\nUnfortunatey in our POC we are fighting against the current configuration of server with Fusion-IO PCI cards and this approach could be a disadvantage.

\n

\nAnother important parameter is the logon time which average at 35-40 sec on the current system and goes up to 75 sec with Nutanix.

\n

\nAny suggestion to speed up the Nutanix Cluster may be modifying some parameter?","quoteUsername":"steve57","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
该主题已关闭以供评论

6个答复

dlink7
Userlevel 4
徽章 +19
嗨



您是否在同一广告中使用同一图像？棱镜中的“存储”选项卡上显示的延迟是什么？

\n

\nAre you using the same image in the same AD OU? What is the latency showing on the storage tab in PRISM?","quoteUsername":"dlink7","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
s
徽章 +6
是的，



这是一个图像。桌面不持久，并分配给登录处的用户。他们在外部存储上使用漫游配置文件和文件夹重定向。用户配置文件的下载触发了登录时间大量写入。如今，随着18-20个活动台式/节点的负载增加，平均写入潜伏期最高为7.5毫秒，平均读取延迟高达2.3 m。



更糟糕的是观察到峰值潜伏期。我们监视了一个“非常活跃”的特定虚拟桌面。它的写入/秒为40到80，写潜伏期最高为20毫秒。



我认为肯定有问题，因为总负载平均为240 IO/秒。但是，每个请求的峰值都会导致潜伏期激增。



最后一句话：最小写潜伏期永远不会低于6 ms。



我们没有从Prism的“存储”选项卡中的数据，因为我们可以获取数据，只要求客户为我们获取它们，而他不知道如何使用Prism。我们可以安排指示他获取数据表Prism。我们已经看到了Delta nd的大小低于4 GB，因此4x45用户是180GB，应该舒适地保持在SSD层。



客户的主要抱怨是登录时间是当前环境的两倍。由于每个VM平均执行6-8 IO/sec，因此6 ms平均写入潜伏期不应该是登录后的问题，但是我们已经看到了一定的请求峰值，这立即将延迟提高到20 ms。



当然，这些结果在POC中造成了一个问题。

\n

\nit is a single image. The desktops are non persistent and are assigned to the users at the logon. They are using roaming profiles and folder redirection on an external storage. This download of the user profile triggers a high number of writes at logon time. Today with an increased load of around 18-20 active desktop\/node the average write latency is up to 7.5 ms and the average read latency is up to 2.3 m.

\n

\nWhat is worse is the peak latency observed. We monitored a specific Virtual Desktop that was \"very active\" . It has from 40 to 80 write\/sec and the write latency was up to over 20 msec.

\n

\nI think there is surely something wrong because the total load is very low an average of 240 IO\/sec. But every peak of requests produces a surge in the latency.

\n

\nOne last word: the minimum write latency never goes below 6 ms....

\n

\nWe have not the data from the storage tab of Prism because we can get the data only asking the customer to get them for us and he doesn't know how to use Prism. We can arrange to instruct him to get the data form Prism. we have seen the size of the Delta nd they are below 4 GB so 4x45 user is 180GB that should comfortably stay on the SSD tier.

\n

\nThe main complain from the customer is the login time which is twice that of the current environment. Since each VM performs on average 6-8 IO\/sec the 6 ms average write latency should not be an issue after the logon but we have seen some peak of request and this immediately increases the latency up to 20 ms.

\n

\nOf course these results are creating a problem in the POC.","quoteUsername":"steve57","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
F
UserLevel 3
徽章 +19
我无法评论写潜伏期，但是我遇到了Xendesktop POC之一以及GPO和文件夹重定向问题的问题。我必须创建新的GPO并应用而不是使用现有的GPO，并且能够在10秒以下的登录时间。



VF.P

\n

\nvF.P","quoteUsername":"farhanparkar","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
dlink7
Userlevel 4
徽章 +19
是的，有些不对劲，会打开支持票。我怀疑Flash Tier是否已满，因此此时可能是一个全闪存的阵列。我会从这个问题中倒退。我会阻止AD中的Inhertieance，创建一个新用户，而不是使用Romaing Cromiles，文件夹重定向。然后慢速添加东西。



什么是全新的台式机，没有附在域的外观上。我知道，当使用最小的GPO时，我的登录时间低于4s。



您也可以运行NCC来verfiry。我还会确认DNS不会与您搞砸。

\n

\nwhat's a brand new desktop not attached to a domain looking like. I know I have got logon times below 4s when minimal GPO's are used.

\n

\nYou can run NCC to verfiry everything as well. I would also confirm DNS is not screwing around with you.","quoteUsername":"dlink7","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
s
徽章 +6
嗨



由于POC是基于戴尔电器的，所以我昨天要求戴尔打开支持票。



在客户环境中可能会有很多改进，但这并不能解释应取决于存储的Nutanix实现的写入潜伏期。此外，读取可以在SSD上或HDD层上进行，但是在此环境中的所有写入都应该转到SSD层，该层应具有延迟左右。

\n

\nSince the POC is based on DELL appliances I have asked yesterday DELL to open a support Ticket.

\n

\nThere can be a lot to be improved in the customer environment but this does not explain the write latencies that should depend on the Nutanix implementation of the storage. Additionally the read could go on the SSD or on the HDD tier but ALL the write in this environmente should go to the SSD tier which should have latencies around 1 ms...","quoteUsername":"steve57","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
b
徽章 +1
嗨，史蒂夫，



您是否曾经找出在POC期间经历的Flash层上写潜伏期的来源？我很想知道决议是什么。谢谢

\n

\nDid you ever figure out the source of the write latency on the flash tier that you were experiencing during the POC? I would be curious to know what the resolution was. Thanks","quoteUsername":"beggertdp","translations":{"Common":{"like":"Like","unlike":"Unlike"},"Forum":{"Quote":"Quote","Share":"Share"}}}">
条款和条件
Learn more about our cookies.<\/a>","cookiepolicy.button":"Accept cookies","cookiepolicy.button.deny":"Deny all","cookiepolicy.link":"Cookie settings","cookiepolicy.modal.title":"Cookie settings","cookiepolicy.modal.content":"We use 3 different kinds of cookies. You can choose which cookies you want to accept. We need basic cookies to make this site work, therefore these are the minimum you can select. Learn more about our cookies.<\/a>","cookiepolicy.modal.level1":"Basic
Functional","cookiepolicy.modal.level2":"Normal
Functional + analytics","cookiepolicy.modal.level3":"Complete
Functional + analytics + social media + embedded videos"}}}">
Baidu