Re: Cluster sizing guidelines
We can answer #3 at least: You can store about 2T of effective data per node in HBase, unless you have a mostly read-only load. See here for the reasoning: http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html For #1 we were traditionally bound by disk/network IO (due to the 2-way replication). With SSDs and 10ge networks that is no longer true, though. As Andy said, #1 and #2 depend heavily on your setup, and there a quite a few tuning knobs for particular setups. We did some throughput tests with our setup. I'll see whether we can get those published. But note that these are valid only for our particular setup and network topology and our workloads, and are likely not generally useful. Also, HBase is a row store. The number of rows or KeyValues per unit of data will also strongly influence the performance, there is a per KeyValue cost and even a per row cost for both read and write throughput. It also depends on how many parallel clients you use, as HBase currently does not stream data between client/server and server/server and hence cannot keep the network pipes full unless multiple clients are used. So it might be hard to present such metrics as a 2D graph. -- Lars From: Andrew Purtell apurt...@apache.org To: user@hbase.apache.org user@hbase.apache.org Sent: Wednesday, July 16, 2014 2:32 PM Subject: Re: Cluster sizing guidelines Those questions don't have pat answers. HBase has a few interesting load dependent tunables and the ceiling you'll encounter depends as much on the characteristics of the nodes (particularly, block devices) and the network, not merely the software. We can certainly, through experimentation, establish upper bounds on perf, optimizing either for throughput at a given payload size or latency within a given bound (your questions #1 and #2). I. e. using now-typical systems with 32 cores, 64-128 GB of RAM (and a fair amount allocated to bucket cache), and 2-4 solid state volumes, and a 10ge network, here are plots of the measured upper bound of metric M on the y-axis over number of slave cluster nodes on the X axis. Open questions: 1. Which measurement tool and test automation? 2. Where can we get ~100 decent nodes for a realistic assessment? 3. Who's going to fund the test dev and testbed? On Wed, Jul 16, 2014 at 1:41 PM, Amandeep Khurana ama...@gmail.com wrote: Thanks Lars. I'm curious how we'd answer questions like: 1. How many nodes do I need to sustain a write throughput of N reqs/sec with payload of size M KB? 2. How many nodes do I need to sustain a read throughput of N reqs/sec with payload of size M KB with a latency of X ms per read. 3. How many nodes do I need to store N TB of total data with one of the above constraints? This goes into looking at the bottlenecks that need to be taken into account during write and read times and also the max number of regions and region size that a single region server can host. What are your thoughts on this? -Amandeep On Wed, Jul 16, 2014 at 9:06 AM, lars hofhansl la...@apache.org wrote: This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep -- Best regards, - Andy Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White)
Re: Cluster sizing guidelines
Yeah. Right direction. Correct on 3 counts. Should have read all email before I replied to your earlier one. From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Thursday, July 17, 2014 11:36 AM Subject: Re: Cluster sizing guidelines On Wed, Jul 16, 2014 at 2:32 PM, Andrew Purtell apurt...@apache.org wrote: Those questions don't have pat answers. HBase has a few interesting load dependent tunables and the ceiling you'll encounter depends as much on the characteristics of the nodes (particularly, block devices) and the network, not merely the software. We can certainly, through experimentation, establish upper bounds on perf, optimizing either for throughput at a given payload size or latency within a given bound (your questions #1 and #2). I. e. using now-typical systems with 32 cores, 64-128 GB of RAM (and a fair amount allocated to bucket cache), and 2-4 solid state volumes, and a 10ge network, here are plots of the measured upper bound of metric M on the y-axis over number of slave cluster nodes on the X axis. Agreed. I'm trying to figure out what guidelines we can establish for a given hardware profile. From what I've seen and understood so far, it's a balancing act between the following factors for any given type of hardware: 1. Write throughput. You are basically bottlenecked on the WAL in this case. 2. Read latency. You want to keep as much in memory across if the requirements demand low latency. How does off-heap cache play in here and what are our experiences in using that in production? 3. Total storage requirement. What's the amount of data you can store per node? 12x3TB drives are becoming more common but can HBase leverage that level of storage density? 40GB regions * 100 regions per server (max) gets you to 4TB. Replicated, that becomes 12TB. This is pretty much the max load you want to put on a single server from a memory stand point to achieve high write throughput or low read latency (factors #1 and #2). Am I thinking in the right direction here? Open questions: 1. Which measurement tool and test automation? 2. Where can we get ~100 decent nodes for a realistic assessment? 3. Who's going to fund the test dev and testbed? On Wed, Jul 16, 2014 at 1:41 PM, Amandeep Khurana ama...@gmail.com wrote: Thanks Lars. I'm curious how we'd answer questions like: 1. How many nodes do I need to sustain a write throughput of N reqs/sec with payload of size M KB? 2. How many nodes do I need to sustain a read throughput of N reqs/sec with payload of size M KB with a latency of X ms per read. 3. How many nodes do I need to store N TB of total data with one of the above constraints? This goes into looking at the bottlenecks that need to be taken into account during write and read times and also the max number of regions and region size that a single region server can host. What are your thoughts on this? -Amandeep On Wed, Jul 16, 2014 at 9:06 AM, lars hofhansl la...@apache.org wrote: This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep -- Best regards, - Andy Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White)
Re: Cluster sizing guidelines
The i2.8xlarge and hs1.8xlarge EC2 instance types would provide opportunity for testing what really happens today when you attempt a high density storage architecture with HDFS and HBase. The hs1 type has 24 spinning disks. I think the i2.8xlarge better represents near-future challenges in effective utilization: it has 8 x 800 GB SSD and 244 GB of RAM. Would be hard to get ahold of and very expensive to operate though. On Jul 19, 2014, at 1:32 AM, lars hofhansl la...@apache.org wrote: Yeah. Right direction. Correct on 3 counts. Should have read all email before I replied to your earlier one. From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Thursday, July 17, 2014 11:36 AM Subject: Re: Cluster sizing guidelines On Wed, Jul 16, 2014 at 2:32 PM, Andrew Purtell apurt...@apache.org wrote: Those questions don't have pat answers. HBase has a few interesting load dependent tunables and the ceiling you'll encounter depends as much on the characteristics of the nodes (particularly, block devices) and the network, not merely the software. We can certainly, through experimentation, establish upper bounds on perf, optimizing either for throughput at a given payload size or latency within a given bound (your questions #1 and #2). I. e. using now-typical systems with 32 cores, 64-128 GB of RAM (and a fair amount allocated to bucket cache), and 2-4 solid state volumes, and a 10ge network, here are plots of the measured upper bound of metric M on the y-axis over number of slave cluster nodes on the X axis. Agreed. I'm trying to figure out what guidelines we can establish for a given hardware profile. From what I've seen and understood so far, it's a balancing act between the following factors for any given type of hardware: 1. Write throughput. You are basically bottlenecked on the WAL in this case. 2. Read latency. You want to keep as much in memory across if the requirements demand low latency. How does off-heap cache play in here and what are our experiences in using that in production? 3. Total storage requirement. What's the amount of data you can store per node? 12x3TB drives are becoming more common but can HBase leverage that level of storage density? 40GB regions * 100 regions per server (max) gets you to 4TB. Replicated, that becomes 12TB. This is pretty much the max load you want to put on a single server from a memory stand point to achieve high write throughput or low read latency (factors #1 and #2). Am I thinking in the right direction here? Open questions: 1. Which measurement tool and test automation? 2. Where can we get ~100 decent nodes for a realistic assessment? 3. Who's going to fund the test dev and testbed? On Wed, Jul 16, 2014 at 1:41 PM, Amandeep Khurana ama...@gmail.com wrote: Thanks Lars. I'm curious how we'd answer questions like: 1. How many nodes do I need to sustain a write throughput of N reqs/sec with payload of size M KB? 2. How many nodes do I need to sustain a read throughput of N reqs/sec with payload of size M KB with a latency of X ms per read. 3. How many nodes do I need to store N TB of total data with one of the above constraints? This goes into looking at the bottlenecks that need to be taken into account during write and read times and also the max number of regions and region size that a single region server can host. What are your thoughts on this? -Amandeep On Wed, Jul 16, 2014 at 9:06 AM, lars hofhansl la...@apache.org wrote: This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do
Re: Cluster sizing guidelines
We could at the very least come up with a set of experiments likely to produce actionable data for users or potential users. We can defer the question of how those experiments might come about until later. On Thu, Jul 17, 2014 at 11:36 AM, Amandeep Khurana ama...@gmail.com wrote: On Wed, Jul 16, 2014 at 2:32 PM, Andrew Purtell apurt...@apache.org wrote: Those questions don't have pat answers. HBase has a few interesting load dependent tunables and the ceiling you'll encounter depends as much on the characteristics of the nodes (particularly, block devices) and the network, not merely the software. We can certainly, through experimentation, establish upper bounds on perf, optimizing either for throughput at a given payload size or latency within a given bound (your questions #1 and #2). I. e. using now-typical systems with 32 cores, 64-128 GB of RAM (and a fair amount allocated to bucket cache), and 2-4 solid state volumes, and a 10ge network, here are plots of the measured upper bound of metric M on the y-axis over number of slave cluster nodes on the X axis. Agreed. I'm trying to figure out what guidelines we can establish for a given hardware profile. From what I've seen and understood so far, it's a balancing act between the following factors for any given type of hardware: 1. Write throughput. You are basically bottlenecked on the WAL in this case. 2. Read latency. You want to keep as much in memory across if the requirements demand low latency. How does off-heap cache play in here and what are our experiences in using that in production? 3. Total storage requirement. What's the amount of data you can store per node? 12x3TB drives are becoming more common but can HBase leverage that level of storage density? 40GB regions * 100 regions per server (max) gets you to 4TB. Replicated, that becomes 12TB. This is pretty much the max load you want to put on a single server from a memory stand point to achieve high write throughput or low read latency (factors #1 and #2). Am I thinking in the right direction here? Open questions: 1. Which measurement tool and test automation? 2. Where can we get ~100 decent nodes for a realistic assessment? 3. Who's going to fund the test dev and testbed? On Wed, Jul 16, 2014 at 1:41 PM, Amandeep Khurana ama...@gmail.com wrote: Thanks Lars. I'm curious how we'd answer questions like: 1. How many nodes do I need to sustain a write throughput of N reqs/sec with payload of size M KB? 2. How many nodes do I need to sustain a read throughput of N reqs/sec with payload of size M KB with a latency of X ms per read. 3. How many nodes do I need to store N TB of total data with one of the above constraints? This goes into looking at the bottlenecks that need to be taken into account during write and read times and also the max number of regions and region size that a single region server can host. What are your thoughts on this? -Amandeep On Wed, Jul 16, 2014 at 9:06 AM, lars hofhansl la...@apache.org wrote: This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep -- Best regards, - Andy Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White
Re: Cluster sizing guidelines
This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep
Re: Cluster sizing guidelines
Thanks Lars. I'm curious how we'd answer questions like: 1. How many nodes do I need to sustain a write throughput of N reqs/sec with payload of size M KB? 2. How many nodes do I need to sustain a read throughput of N reqs/sec with payload of size M KB with a latency of X ms per read. 3. How many nodes do I need to store N TB of total data with one of the above constraints? This goes into looking at the bottlenecks that need to be taken into account during write and read times and also the max number of regions and region size that a single region server can host. What are your thoughts on this? -Amandeep On Wed, Jul 16, 2014 at 9:06 AM, lars hofhansl la...@apache.org wrote: This is a somewhat fuzzy art. Some points to consider: 1. All data is replicated three ways. Or in other words, if you run three RegionServer/Datanodes each machine will get 100% of the writes. If you run 6, each gets 50% of the writes. From that aspect HBase clusters with less than 9 RegionServers are not really useful. 2. As for the machines themselves. Just go with any reasonable machine, and pick the cheapest you can find. At least 8 cores, at least 32GB of RAM, at least 6 disks, no RAID needed. (we have machines with 12 cores in 2 sockets, 96GB of RAM, 6 4TB drives, no HW RAID). HBase is not yet well tuned for SSDs. You also carefully need to consider your network topology. With HBase you'll see quite some east-west traffic (i.e. between racks). 10ge is good if you have it. We have 1ge everywhere so far, and we found this is a single most bottleneck for write performance. Also see this blog post about HBase memory sizing (shameless plug): http://hadoop-hbase.blogspot.de/2013/01/hbase-region-server-memory-sizing.html I'm planning a blog post about this topic with more details. -- Lars From: Amandeep Khurana ama...@gmail.com To: user@hbase.apache.org user@hbase.apache.org Sent: Tuesday, July 15, 2014 10:48 PM Subject: Cluster sizing guidelines Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep
Cluster sizing guidelines
Hi How do users usually go about sizing HBase clusters? What are the factors you take into account? What are typical hardware profiles you run with? Any data points you can share would help. Thanks Amandeep