TLDR; MongoDB Atlas on Azure (smaller instances with smaller storage) works but comes with a number of pitfalls you should be aware of. You'd save a lot of headaches hosting MongoDB Atlas on AWS/GCP instead.
The intention of this post is to point out a number of issues we have experienced over the past 2 years using MongoDB Atlas on Azure, having 2 main objectives in mind 1:
- Shorten your/others' troubleshooting path if you happen to go the same way
- Gather inputs from other customers of MongoDB Atlas on Azure
But you might ask immediately - why MongoDB Atlas on Azure instead of using the native CosmosDB? The reasons for us were:
- Bloated document size + charging based on non-compressed data 0,25$/Gb/month - during our testing with CosmosDB a simple 180 byte json document was somehow taking 981 bytes in the end storage wise
- Missing real atomic updates (findOneAndUpdate, supported by the MongoDB API for Cosmos DB) in the standard SQL API, in particular in stored procedures - see this and this for more information.
- Partition-First is mandatory - every table must be partitioned, with the partition key usually unable to satisfy both good distribution and queries by another attribute. MongoDB allows you to start with single and unlimited partitions and you can add sharding later on.
- Partitioning Limitations - 10k RUs and 20GB per partition only
- Limited database transaction support - only within a single partition.
- This post is discussing only small instances - M10-M30 (no need/experience yet for/with bigger ones)!
- Write Concern = Majority is assumed in below discussions. In our case written data has to mean "durable on at least 2 out of 3 nodes", as we cannot afford losing "written/ACK-ed" data upon node failover.
The following issues will be discussed in detail below:
- Limited IOPS for small storage sizes when setting up new MongoDB Atlas cluster on Azure
- (UPDATE 22th Feb 2022) Sudden Disk Latencies of up to 15 seconds, with missing/misleading metrics (metrics resolved)
- Burstable CPU with Missing CPU Steal Metric
- Oplog deletion upon storage downgrade
- Different Operation Processing Time with different primary nodes
- CPU Spikes every 15 minutes
- Downtime during cluster upgrade (resolved)
- Random node failovers (resolved)
- Node "stalled" (froze) for 45 seconds
- Sudden but long-lasting Disk Utilizition Percent/Disk Latencies
Limited IOPS for small storage sizes on new clusters
Inadequate storage IOPS when using small storage sizes (< 512Gb) is the elephant in the room.
When starting with MongoDB Atlas on Azure one of the first important questions I had was - is the pricing similar to that for AWS/GCP, or is it higher (I have experienced quite a few Azure services incl. basic infrastructure ones are in reality more expensive than AWS/GCP ...). At a first glance I thought it's all relatively similar:
MongoDB Atlas Pricing on Azure Netherlands (westeurope), small instances:
MongoDB Atlas Pricing on AWS Ireland (eu-west-1), small instances:
MongoDB Atlas Pricing on GCP Belgium (europe-west1), small instances:
Yes, Azure is still the most expensive hosting for MongoDB, but the difference does not seem gigantic at a first glance ... This is until you expand the details for M20 for example and check the IOPS value in there:
Did you notice the difference? Azure gives you only 120 IOPS for starters vs. 2000+ IOPS on AWS and GCP! And 120 IOPS do cause regular invisible in the metrics storage throttling, which results in (single document write) operations taking occasionally up to 2-3 seconds (usually 7-8ms with write concern majority)!!
What is the solution for Azure currently? Even if you do not need it, increase your storage to 128Gb (gives you 500 IOPS) or 256Gb (gives you 1100 IOPS - more is not possible on M20) but that of course increases dramatically the cost of M20 to $0,34/hour or $0,45/hour respectively ...
Sudden Disk Latencies of up to 15 seconds, Missing/Misleading Metrics (metrics resolved)
The story about low disk IOPS with small storage sizes does not end here though. The problem is made worse by having no way to see when the IOPS are throttled. This is how the Disk IOPS metric looks for the a M20 primary node:
Doesn't the above graph give you the impression that not 120, but even 20 IOPS will be enough? Yes ... but actually not, and you may see in db logs or in the MongoDB Atlas Profiler (visual) the following or worse:
(UPDATE 8th Oct 2021) MongoDB have added Max Values for all hardware metrics (thanks @MongoDB Atlas Team!), so now you can see more clearly how the IOPS are fully utilized from time to time (for some yet
Note 1: The peak coincides with the regular every 15-minutes "chef scripts" run by MongoDB Atlas, see below for more info)
Note 2: Dev.to corrupts the resolution of the uploaded images ... otherwise you would see the higher blue-green line on the CPU metrics being iowait.
Important: Even with 128Gb (500 IOPS) and normal (=low) opcounters (no peaks!) we have experienced within 1 week 2 cases of single small document insert taking up to 7-15 seconds (yes, seconds!, instead of 6-8 ms in average) when something happens to the IOPS ..
After several km-long support cases based on scarce comments and internal metrics provided by MongoDB Support my conclusion is that IOPS limits are hit by the primary or secondary nodes when the write operation must be confirmed by primary + at least 1 secondary, and the secondary cannot confirm because the oplog has not been synced yet due to IOPS throttling.
(UPDATE 8th Oct 2021) Turns out all Azure Premium SSDs support bursting up to 3500 IOPS for up to 30 minutes (even confirmed by MongoDB Atlas Support Engineer!), but the $1mln question is then why, oh why, do we experience still these 7-15 seconds (not milliseconds) disk latency (insert of single small document, no db trx or anything) then??
Trying to find someone @MongoDB Atlas to access the underlying Azure VM Disk Metrics and check the values of the following ones, which can throw some light if burstable credits are exhausted from time to time (but I don't really believe that this is happening in our case ..):
- Data Disk Used Burst IO Credits Percentage (Max)
- OS Disk Used Burst IO Credits Percentage (Max)
- Data Disk IOPS Consumed Percentage (Max)
- OS Disk IOPS Consumed Percentage (Max)
(UPDATE 11th Oct 2021) Even after storage upgrade to 256Gb / 1100 IOPS still getting randomly hit by single-document insert/replace operations taking 100-200x more than usual, e.g. 1600+ ms instead of 6-8ms ... Happens couple of times per day when the load is relatively low - single-digit business operations per second, every business operation = about 10 single-document read/write db operations.
(UPDATE 4th Jan 2022) The last statement about the root cause of the intermittent disk latency issues is that the regular 15-minute Ansible monitoring/management scripts hit hard the OS Disk of the Standard_B2s VM (in case of M20) which causes a delayed (after about 7 minutes??) disk throttling affecting also the MongoDB process ...
(UPDATE 22th Feb 2022) After many months of investigations we are back at square 1: the Ansible monitoring/management process running every 15 minutes is not the reason for the slowdowns, root cause is not stated (=> unknown?), we should upgrade to M30 or change the cloud provider ...
(UPDATE 4th March 2022) Problem still occurring after upgrade to M30, contrary to statement that the problem would be solved by upgrade to M30 ...
(FINAL UPDATE 31st Oct 2022) Problem can NOT be resolved, issue lies with Azure Infrastructure (Disks) and not with MongoDB Atlas itself. Only options are move to AWS/GCP or wait for new generation Azure disks ...
Burstable CPU with Missing CPU Steal Metric
M10 and M20 instances are using B-series Azure VMs (e.g. M20 is using
Standard_B2s). These are burstable VMs where you have for
Standard_B2s 40% CPU baseline performance guaranteed (40% = 2 vCPUs * 20% CPU utilization each). If you use less than 40% you accumulate credits and every credit gives you the right to burst above the 40% (e.g. to 100% = 1 vCPU fully utilized or 200% = both vCPUs fully utilized) for certain period of time until credits reach 0.
There is a CPU Steal % metric in MongoDB Atlas which should be 0 if all good, and should start increasing in case you need more CPU but you cannot get it because you are throttled to your baseline performance (= no available credits for bursting). An alert can be configured once this metric reaches certain threshold (e.g. above 0 for several minutes) ...
That is all fine and good, but the problem is that MongoDB Atlas seems to have implemented the CPU Steal % metric/alert only for AWS ... so in Azure there is no way to detect and alert such an important situation ...
Oplog deletion upon storage downgrade
While testing different combinations of instance size (e.g. M20, M30) and storage size (16, 64, 128Gb) we had to downgrade the storage a couple of times (e.g. from 128 back to 16Gb). Usually upgrade operations worked flawlessly - MongoDB Atlas takes one node after the other offline, replaces, syncs with primary and puts back in cluster, no data loss. In case of storage downgrade we lost all the data in the Oplog, which is of critical importance for our application built on top of MongoDB Change Streams for all the async event publishing functionality. This means our K8s pods waiting for change events lost their resume tokens (saved checkpoints) as the latter were pointing to non-existent oplog positions ...
According to MongoDB this happens when
- "An Azure machine is migrated to a new instance family"
- "A user requests a disk decrease on Azure instances"
and I have the feeling the above is again Azure-specific. My request for changing that behavior on Azure has not been honoured yet.
Different Operation Processing Time with different primary nodes
While testing with different instance and storage sizes I noticed that in a standard 3-node cluster I get different average business operation (1 business operation contains 2-3 single document
find and 7-8
modify operations) processing times depending on which node is primary:
You see 15-20ms difference in average times, meaning up to 25%, which is huge! My suspicion is that this is because of some networking overhead due to putting the different nodes in different Availability Zones, however my client applications are running on 3 Kubernetes nodes split in the same way to the 3 different Azure Availability as the MongoDB nodes ... Wouldn't be surprised if this is another Azure idiosyncrasy ...
CPU Spikes every 15 minutes
This is how the CPU looks like on all of our M20 clusters:
What are these regular CPU spikes every 15 minutes you might ask - is there some heavy regular application activity? The answer is no, our application is not doing anything, however there is some MongoDB Atlas Monitoring cron job (aka "Chef scripts") which is doing some heavy work every 15 minutes. Remember: M20 is a burstable instance with baseline of 40%, so every 15 minutes this monitoring process is "stealing" 1-2 minutes of CPU, for which you have paid ...
I had a couple of tickets with MongoDB Support on this topic suspecting that this is the reason for the randomly slow operation processing times, not clear if it is correlated or not (several disk latency occurrences happened at the same time, but a few also not), however it still feels like unoptimized admin intervention ...
Downtime during cluster upgrade (resolved)
With MongoDB Azure we were suffering for more than 6-months from downtimes (applications could not connect anymore to the cluster and needed to be manually restarted!) during cluster maintenances. This happened exactly at the point of time when the 3rd node was getting replaced (all fine with 1st and 2nd).
It took tons of discussions (incl. with an Account Manager) and paying for Professional Services until this problem was fixed in the .NET Driver, but only after another big customer complained.
Random node failovers
For a week now we are experiencing random node failovers. Activity Feed in Atlas Portal shows only this:
The current explanation by MongoDB Support (as far as I have understood it) is that there are network issues between the nodes and a node triggers re-election. But how come one of the most stable cloud components (network) is having so many outages, and what is the resolution? No answer yet ...
(Update 8 Oct 2021): After MongoDB Atlas Support talked to Azure Support network reconfiguration was performed. Since then we have not experienced additional unexpected failovers, so (assuming this has been integrated in the setup scripts for new MongoDB Atlas clusters on Azure) the problem can be treated as resolved.
(Update 22 Feb 2022): We had another such case 2 weeks ago, which caused some of our business operations to take 25 seconds instead of 70 ms (still were successful though). Turns out the network configuration performed previously was not persistent (after VM reboot gone), which I was not told at the time. Now MongoDB Support has repeated the network config but in a persistent manner, let's see ...
Node "stalled" (froze) for 45 seconds
Another case from past week - the primary node just "stalled" or froze for 45 seconds, and then continued working. Of course, during that time all business operations were affected, and some of them timed out. According to MongoDB Support something happened to the node's disk - it just physically stopped working. What can be done so that this does not happen again? Nothing ... if it happens again the node can be replaced ...
And another case of 3 seconds disk "stalling" or whatever - disk queue went up, db operations got 100 slower:
Was this due to exceeding Disk IOPS and being throttled by Azure Storage - if the metric is to be believed (and I don't) - No ..:
I understand, that cloud VMs may go away or freeze in case the host crashes, but somehow too many strange things happen lately with our MongoDB Atlas clusters on Azure - can Azure be that unstable??
Sudden but long-lasting Disk Utilizition Percent/Disk Latencies
A picture is worth a thousand words:
Disk Utilization % - from all processes running on the node
Opcounters - absolutely no load ...
Happens already for the 2nd time in the past few days, the solution last time was to fail over manually to another node, and wait 30-45 minutes (!??!)
The astute reader may have already concluded from the above that the performance and stability of the M20 MongoDB Atlas instance on Azure is a joke, and this due to disk-related issues.
As recommended multiple times by MongoDB Support and Account Management, MongoDB Atlas should rather be used in conjunction with hosting on AWS/GCP where it seems to be much more stable, fast and also cheap.
This is something that was not crystal-clear to me when I decided for Azure and implemented the rest of the infrastructure there. Also a quick look at the different MongoDB Atlas hosting options did not explicitly warn me that one gets much less IOPS and a bunch of additional problems on Azure.
If CosmosDB didn't have some of the issues (bloated/expensive storage, lack of atomic update, enforced partitioning from the start, etc.) we would have moved to it long ago. Migration to GCP/AWS is something I will be actively investigating, however there are some goodies we are using (AKS, App Insights, Azure Data Explorer/Kusto) which need more work.
I have read that Azure has a weak offering of low-level IaaS, but why it is so lagging behind AWS/GCP when it comes to IOPS for smaller disks is beyond my understanding (read about the software layer they have put on top of it, but I don't care). Or rather - I cannot wrap my head around the question why Azure is not working day and night to fix this big gap in such an important fundamental/enabling service.
I wish Azure could fix this and additionally expose CPU Steal % and other metrics, so that MongoDB Atlas could level up its Azure hosting. I wish additionally that MongoDB Atlas could invest a little bit more in its Azure hosting (15 minutes heavy cron jobs can be optimized, additional metrics can be added even with the current Azure API I guess). But I have learnt the hard way that such wishes usually end up sitting in glorious Product Feedback Lists for ages ...
Have you experienced similar issues like the above? Or have you found other solutions? Would be happy to get such input from other Azure MongoDB Atlas customers!
P.S. Please vote for the following MongoDB feedback ideas:
- Higher IOPS for small disk sizes (MongoDB Atlas on Azure)
- Burstable IOPS for MongoDB Atlas on Azure
- CPU Steal % on Azure
- Preserve Oplog upon storage downgrade in Azure
OK, you got me, additionally I have a secret hope that if someone from MongoDB Atlas and Azure reads this (s)he might trigger some internal improvement ... but realistically this never works that way, we all know that :( ↩
Top comments (17)
Does your app require MongoDB / NoSQL in general or you could use PostgreSQL instead?
Could probably make it work with PostreSQL as well, however MongoDB does have some goodies like:
Sure, imagine you have a domain object/aggregate root/whatever called AccountingTransaction, which has some properties like Id, State, CreatedOn, and a list of AccountingEntries, where each Entry has Type (Debit/Credit), AccountId (reference), Amount, Currency. In a standard relational database I would need by default somehow to map this entity to more than 1 table - probably I would create AccountingTransactions and AccountingEntries tables, with 1:N relationship between them, then insert 1 row in the first table and maybe 2-3 rows in the second for a single domain object. Moreover, the inserts must happen in a db transaction. In contrast, in a NoSQL db like MongoDB I am just inserting a single document, which has nested "entries" array inside, without a db transaction ...
Really, PostgreSQL is faster than MongoDB on the same basic hardware (e.g. M20 which is 2 Standard_B2s core + 4GB RAM)? That is really surprising to me, thought PostreSQL needs more to run normally .. Is there something on the Internet which can give me more info on that (testing it myself is quite time-consuming ...) ...
Can't state the same about MongoDB Atlas on Azure. As mentioned in the post, we had quite a few random node failovers, and anyway, every scheduled cluster maintenance requires such ... I would not take a db which does not have a well-tested failover capability, as in the cloud everything can happen any time ...
What about pricing PostgreSQL vs MongoDB Atlas on Azure? Not that the latter is cheap, but I expect the former to be more expensive ..
Regarding AccountingTransaction, you can use PostgreSQL to store and query JSON and it's also faster than MongoDB from what I read postgresqltutorial.com/postgresql-...
And especially for accounting data updates and queries, breaking AccountingTransaciton to relational tables will provide huge benefits down the road. But even if you don't want do to that, you get the best of both worlds with PostgreSQL.
That being said, accounting and banking are probably the golden use cases for relational databases.
Not really, I used to think the same, but when it comes to concepts like Aggregate Root (and even Event Sourcing) storing the whole aggregate root (or event) as 1 single document (with 1 single db insert, no db trx) in the Write Model (CQRS) is unbeatable, IMHO.
@kyrylkov , you seem to know PostreSQL, I just took a look at the Azure hosting for PostreSQL, and stumbled upon some big limitations - e.g. are the connections really that limited (2 vcore instance on Azure allows only 100-145 user connections max??), and I need to use something like pgBouncer in between? Asking because one of my M20 instances has currently 625 open connections out of 3000 possible, and it does not even sweat ...
and one more - does PostreSQL have something like MongoDB Change Streams (which we use heavily)?
There is postgresql.org/docs/current/logica...
Regarding hosting options. Look at the difference in pricing between PostgreSQL and MongoDB scalegrid.io/pricing.html
So the question you have to answer is whether actual or perceived benefits you get with MongoDB are really worth it.
Don't believe the ScaleGrid website. Not only the pricing is off by 2x - e.g. I am paying for M20 cluster on Azure (2 cores, 4 Gb RAM) with 128Gb (500 IOPS provisioned, burstable up to 3500) around $250 (vs. $486 on the ScaleGrid website) but also the IOPS are incorrect ... And their competitor comparison page is completely outdated (from 2018) ...
The provide their services on top of multiple cloud providers, so of course, it's not what the cloud providers offer directly. But if you check directly cloud provider prices, they are correlated. For instance, heck for DigitalOcean charges for hosted MongoDB vs hosted PostgreSQL.
ScaleGrid provides their services on top of multiple cloud providers so you can easily migrate between them. Naturally ScaleGrid pricing is higher than what the cloud providers offer directly.
Check what DigitalOcean charges for hosted MongoDB vs hosted PostgreSQL. MongoDB is still more expensive and MongoDB data takes more space than PostgreSQL. There is no way around restrictive MongoDB licensing that stiffles competition. Before MongoDB changed their license there was mLab and many people used it. After the licensing change, mLab business went under and MongoDB acquihired it.
Sorry, was comparing my MongoDB Atlas charges vs what ScaleGrid would charge for PostreSQL on Azure.
If I compare PostreSQL vs MongoDB via ScaleGrid on Digital Ocean (for 3 node cluster in both cases, 2 cores, 4GB RAM) I see $140 vs $160, which does not sound like a big difference to me (also not a big difference compared with the $250 on MongoDB Atlas/Azure with more storage).
What I am not sure about PostreSQL though are these connection limits which I asked you about above, and how well it handles failovers from one node to another in case of VM failure, or simply maintenance etc.
of course, I am not aware of Digital Ocean's VM instance sizes, and whether their 2 core / 4 GB is fully dedicated/100% provisioned or burstable like in case of Azure ... if fully dedicated/not burstable then that would be a good cost advantage in favor of Digital Ocean, which is however anyway not a hosting provider I am looking at due to many other PaaS services we are after ..
Azure seems to suffer huge issues with disc performance (post from Nov 10, 2020) bunnyshell.com/blog/aws-google-clo...
DigitalOcean trumps all of the big 3, but Azure stands out in a bad way.
Atlas IOPS stats for Azure confirm this.