[
https://issues.apache.org/jira/browse/CASSANDRA-7882?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14146132#comment-14146132
]
Jay Patel edited comment on CASSANDRA-7882 at 9/24/14 10:22 AM:
----------------------------------------------------------------
Hey Benedict,
I've attached the first cut. Pls. help review.
Below are some code changes and design choices/trade-offs.
* Wait-free region scaling and allocations:
** Instead of one global queue of 1 MB race allocated regions, there’re are now
set of global queues, one for each region size (8K, 16K, ..1MB). All queues are
global (not per memtable) so memtables across all the tables can reuse the race
allotted regions. Race allocated regions will never be cleaned during memtable
flushes.
** Thread who wins in the race of setting new region as the current region,
also scales the region size (if it’s not already at the max). This avoids need
for extra synchronization for scaling region size atomically.
* Region size per memtable:
Have region size per memtable instead of global. From what I understand from
the code, each memtable creates its own NativeAllocator object. So, I think
keeping a region size as a member variable of NativeAllocator makes the region
size per memtable. Pls. let me know if that is not the case & I’ll fix it
accordingly.
I don’t think below can be the issue, but want to share in case you see any
problems:
* In the race of allocating & setting the current region, there is a very
slight chance of allocating next region with the same size (instead of 2x).
Consider the below case:
Thread1: allocates 16K region but has not yet reached to CAS for the current
region
Thread 2: allocates 16K, does CAS for the current region. Current region gets
filled up and set back to null by allocate() method.
Thread 1: reaches the CAS. Now, this will set current region to 16K region,
instead of 32K.
This sounds a corner case. Btw, even if this happens, there is no harm & next
allocation will be directly of 64K to catch up since we never miss scaling the
region size.
To further guard against this, you'll see a below check in the code just before
CAS.
if(region.capacity == regionSize * SCALE_FACTOR || region.capacity ==
MAX_REGION_SIZE)
* Unslab allocation will happen only after we hit 1 MB region size. Until then,
huge payload can quickly grow the region size & allocate new region. I think
this behavior is good but slight side effect is that we may end up with few
partially filled (or not filled?) regions before we scale up to the proper
region size for a given payload. One option I though of is to have unslabbed
allocation threshold and count for each region size, in addition to the
MAX_CLONED_SIZE for the 1MB region size. For instance, with 8K region, anything
beyond 4K will be unslabbed and if we see 1000 (threshold) of unslab
allocations, we increase the region size. But, not too excited about this since
anyway flush may happen before that to reset the region size. I don’t see much
issue leaving this as is for now, but let me know if you can think of a better
way to address this.
fyi, below line will print how region allocation works if you want to test. I
did quick test with 1 to 100 static tables and payload size from 100 to 2KB. In
a week or two, planning to try out with 10s of thousands of tables including
longevity tests.
logger.info("{} size region allocated in {}", regionSize, this);
This change takes care of only off-heap objects. For other slab allocator
(on-heap?), not sure if it makes sense to do region scaling.
TODO: Convert multiplication to shifting. Change logger.info to logger.trace.
Any refactoring or suggestions you've..
was (Author: pateljay3001):
Hey Benedict,
I've attached the first cut. Pls. help review.
Below are some code changes and design choices/trade-offs.
* Wait-free region scaling and allocations:
** Instead of one global queue of 1 MB race allocated regions, there’re are now
set of global queues, one for each region size (8K, 16K, ..1MB). All queues are
global (not per memtable) so memtables across all the tables can reuse the race
allotted regions. Race allocated regions will never be cleaned during memtable
flushes.
** Thread who wins in the race of setting new region as the current region,
also scales the region size (if it’s not already at the max). This avoids need
for extra synchronization for scaling region size atomically.
* Region size per memtable:
Moved region size per memtable instead of global. From what I understand from
the code, each memtable creates its own NativeAllocator object. So, I think
keeping a region size as a member variable of NativeAllocator makes the region
size per memtable. Pls. let me know if that is not the case & I’ll fix it
accordingly.
I don’t think below can be the issue, but want to share in case you see any
problems:
* In the race of allocating & setting the current region, in the extreme case
there is a slight chance of allocating next region with the same size (instead
of 2x). Consider the below case:
Thread1: allocates 16K region but has not yet reached to CAS for the current
region
Thread 2: allocates 16K, does CAS for the current region. Current region gets
filled up and set back to null by allocate() method.
Thread 1: reaches the CAS. Now, this will set current region to 16K region,
instead of 32K.
This sounds a corner case. Btw, even if this happens, there is no harm & next
allocation will be directly of 64K to catch up since we never miss scaling the
region size.
To further guard against this, you'll see a below check in the code just before
CAS:
if(region.capacity == regionSize * SCALE_FACTOR || region.capacity ==
MAX_REGION_SIZE)
* Unslab allocation will happen only after we hit 1 MB region size. Until then,
huge payload can quickly grow the region size & allocate new region. I think
this behavior is good but slight side effect is that we may end up with few
partially filled (or not filled?) regions before we scale up to the correct
region size for given the payload. One option I though of is to have unslabbed
allocation threshold and count for each region size, in addition to 1MB region
size. For instance, with 8K region, anything beyond 4K will be unslabbed and if
we see 1000 (threshold) of unslab allocations, we increase the region size.
But, not too excited about this since anyway flush may happen before that to
reset the region size. I don’t see much issue leaving as is for now, but let me
know if you can think of a better way to address this.
fyi, below line will print how region allocation works if you want to test. I
did quick test with 1 to 100 static tables and payload size from 100 to 2KB. In
a week or two, planning to try out with 10s of thousands of tables including
longevity tests.
logger.info("{} size region allocated in {}", regionSize, this);
This change takes care of only off-heap objects. For other slab allocator
(on-heap?), not sure if it makes sense to do region scaling.
TODO: Convert multiplication to shifting. Change logger.info to logger.trace.
Any refactoring or any suggestions you've..
> Memtable slab allocation should scale logarithmically to improve occupancy
> rate
> -------------------------------------------------------------------------------
>
> Key: CASSANDRA-7882
> URL: https://issues.apache.org/jira/browse/CASSANDRA-7882
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Reporter: Jay Patel
> Assignee: Jay Patel
> Labels: performance
> Fix For: 2.1.1
>
> Attachments: trunk-7882.txt
>
>
> CASSANDRA-5935 allows option to disable region-based allocation for on-heap
> memtables but there is no option to disable it for off-heap memtables
> (memtable_allocation_type: offheap_objects).
> Disabling region-based allocation will allow us to pack more tables in the
> schema since minimum of 1MB region won't be allocated per table. Downside can
> be more fragmentation which should be controllable by using better allocator
> like JEMalloc.
> How about below option in yaml?:
> memtable_allocation_type: unslabbed_offheap_objects
> Thanks.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
