[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14277979#comment-14277979 ] Swapnil Daingade commented on YARN-2791: Hi [~kasha]] and [~vinodkv]], Went over the latest design doc for YARN-2139 and posted my comments. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: Sub-task Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14276107#comment-14276107 ] Vinod Kumar Vavilapalli commented on YARN-2791: --- Okay folks, I've read the design docs on both YARN-2791 (this JIRA) and YARN-2139. This is indeed part of YARN-2139, and a direct dup of YARN-2618 and other tickets. Yes YARN-2139 is a much larger effort but it encompasses both scheduling and isolation. The important tickets of YARN-2139 already were created before this JIRA. I am going to close this as a duplicate in a day unless I see specific tasks that are not covered under YARN-2139. If there are things that are not covered indeed, I urge Swapnil Daingade, Santosh Marellaand and Yuliya Feldman to file sub-tasks under YARN-2791. As Karthik appealed before, let's have the design discussion over at YARN-2139, merging things that are only here and missing in that JIRA. Due credit will be given to all contributors to the design and implementation there. I am oblivious who contributes code, but let's work together please! Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14276156#comment-14276156 ] Yuliya Feldman commented on YARN-2791: -- Thank you Vinod for your comment, as [~sdaingade] suggested in his previous comment let's make this JIRA as subtask of [YARN-2139 | https://issues.apache.org/jira/browse/YARN-2139 ] and do design discussion and code walk through if necessary to determine whether it fits into existing subtask or it will continue being it's own. Yes we definitely understand you opened YARN-2139 first. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14276218#comment-14276218 ] Karthik Kambatla commented on YARN-2791: I have no reservations against making this a sub-task of YARN-2139, I just did so. However, I still am not clear on what we are accomplishing in this subtask. I was hoping (so is Vinod) that we could identify items that are not covered under YARN-2139 and file sub-tasks for those and give due credit for filing and fixing them. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: Sub-task Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14274007#comment-14274007 ] M. C. Srivas commented on YARN-2791: The scope in https://issues.apache.org/jira/browse/YARN-2139 is just too bloated. We have this problem immediately with YARN overprovisioning since it doesn't take into account how performance is impacted by the number of disks on each node. We need this fix now, not later. YARN-2139 is too elaborate, and is trying to do too much. On the the other hand, it doesn't take into account how running DataNodes on the same spindles will impact shuffle performance. I would say get this piece of work done, and we can wait on YARN-2139 whenever it gets done. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14274171#comment-14274171 ] Wei Yan commented on YARN-2791: --- [~srivas], YARN-2618 is a simple solution that limits the maximum allowed running containers on each node. Each DataNode is configured with a maximum disk value, and YARN treats each container's disk request is 1. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14206993#comment-14206993 ] Karthik Kambatla commented on YARN-2791: Thanks [~sdaingade] for sharing the design doc. Well articulated. The designs on YARN-2139 and YARN-2791 are very similar, except for the disk resources are called vdisks in YARN-2139 and spindles in YARN-2791. In addition to the items specified here, YARN-2139 talks about isolation as well. Other than that, do you see any major items YARN-2791 covers that YARN-2139? The WebUI is good and very desirable, we should definitely include it. Also, I suggest we make this (as is - or split into multiple JIRAs) a sub-task of YARN-2139. Discussing the high-level details on one JIRA helps with aligning on one final design doc based on everyone's suggestions. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14207080#comment-14207080 ] Swapnil Daingade commented on YARN-2791: Thanks Karthik Kambatla. Sure, lets make this a sub-task of YARN-2139. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Attachments: DiskDriveAsResourceInYARN.pdf Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200739#comment-14200739 ] Wei Yan commented on YARN-2791: --- Hi, [~yufeldman], this jira is same to YARN-2139. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200823#comment-14200823 ] Aditya Kishore commented on YARN-2791: -- I think the summary of this JIRA may seem as duplicate of YARN-2139 but they are not. YARN-2139 aims to address throttling/isolation of disk IO on individual container basis. However, from the description it seems that the purpose of this JIRA is to include the node's disks as a parameter in the capacity calculation of the node alongside with its memory and CPU cores. May be the summary should be reworded to reflect this. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200829#comment-14200829 ] Karthik Kambatla commented on YARN-2791: [~adityakishore] - from reading the description, I believe there is at least a significant overlap between the two JIRAs. I think we would benefit from consolidating them and working together, than take multiple paths. [~sdaingade] - nice to know you have something working. Could you look through the design doc on YARN-2139 so we can refine it. If it is significantly different from what is posted there, can you also post your design so we can evaluate which one is better and move forward. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200849#comment-14200849 ] Yuliya Feldman commented on YARN-2791: -- [~kasha] I agree that consolidating both and working together is a way to go here. Let's initiate this. What I don't quite understand is how https://issues.apache.org/jira/browse/YARN-2817 is different from this one or from https://issues.apache.org/jira/browse/YARN-2139 Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200900#comment-14200900 ] Karthik Kambatla commented on YARN-2791: bq. how https://issues.apache.org/jira/browse/YARN-2817 is different from this one or from https://issues.apache.org/jira/browse/YARN-2139 I personally don't think it is. Even if we want to address a simpler usecase, I would suggest we do to that as part of YARN-2139. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14200961#comment-14200961 ] Swapnil Daingade commented on YARN-2791: Karthik Kambatla - I'll go through the design doc for YARN-2139 and post our design document here as well. We can then decide if we should have two JIRA's or combine them as Aditya Kishore suggested. However I fully support combining our efforts on this. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14201101#comment-14201101 ] Karthik Kambatla commented on YARN-2791: [~adityakishore] - unfortunately, YARN-2139 didn't have a description this far. I just added a very succinct one. If you look at the design doc itself and the sub-tasks created, you would see that YARN-2139 includes adding disk as a resource to the resource-request-vector, the node-capacities, and the scheduler. [~sdaingade] - looking forward to you hear your thoughts and see a design doc. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14201113#comment-14201113 ] Aditya Kishore commented on YARN-2791: -- Great! I think this JIRA should be added as a sub-task as non of the other sub-tasks cover this aspect. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Assignee: Yuliya Feldman Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14192536#comment-14192536 ] Wei Yan commented on YARN-2791: --- Hi, [~sdaingade]. Is this a duplicate of YARN-2139? We have worked on the disk I/O scheduling for a while, and will post patches soon after more experiments. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (YARN-2791) Add Disk as a resource for scheduling
[ https://issues.apache.org/jira/browse/YARN-2791?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14192537#comment-14192537 ] Wei Yan commented on YARN-2791: --- And very welcome for your comments for the design doc at YARN-2139. Add Disk as a resource for scheduling - Key: YARN-2791 URL: https://issues.apache.org/jira/browse/YARN-2791 Project: Hadoop YARN Issue Type: New Feature Components: scheduler Affects Versions: 2.5.1 Reporter: Swapnil Daingade Currently, the number of disks present on a node is not considered a factor while scheduling containers on that node. Having large amount of memory on a node can lead to high number of containers being launched on that node, all of which compete for I/O bandwidth. This multiplexing of I/O across containers can lead to slower overall progress and sub-optimal resource utilization as containers starved for I/O bandwidth hold on to other resources like cpu and memory. This problem can be solved by considering disk as a resource and including it in deciding how many containers can be concurrently run on a node. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
