Implement parallel ARC eviction #16486

allanjude · 2024-08-29T17:29:19Z

Sponsored-by: Expensify, Inc.
Sponsored-by: Klara, Inc.

Motivation and Context

Read and write performance can become limited by the arc_evict process being single threaded.
Additional data cannot be added to the ARC until sufficient existing data is evicted.

On many-core systems with TBs of RAM, a single thread becomes a significant bottleneck.

With the change we see a 25% increase in read and write throughput

Description

Use a new taskq to run multiple multiple arc_evict() threads at once, each given a fraction of the desired memory to reclaim

How Has This Been Tested?

Benchmarking with a full ARC to measure the performance difference.

Types of changes

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Performance enhancement (non-breaking change which improves efficiency)
Code cleanup (non-breaking change which makes code smaller or more readable)
Breaking change (fix or feature that would cause existing functionality to change)
Library ABI change (libzfs, libzfs_core, libnvpair, libuutil and libzfsbootenv)
Documentation (a change to man pages or other documentation)

Checklist:

My code follows the OpenZFS code style requirements.
I have updated the documentation accordingly.
I have read the contributing document.
I have added tests to cover my changes.
I have run the ZFS Test Suite with this change applied.
All commit messages are properly formatted and contain Signed-off-by.

amotin · 2024-09-05T16:08:35Z

module/zfs/arc.c

+		uint64_t nchunks = ((left - 1) >> MIN_EVICT_PERTASK_SHIFT) + 1;
+		unsigned n = nchunks < num_sublists ? nchunks : num_sublists;
+		uint64_t fullrows = nchunks / n;
+		unsigned lastrowcols = nchunks % n;
+		unsigned k = (lastrowcols ? lastrowcols : n);
+
+		uint64_t bytes_pertask_low =
+		    fullrows << MIN_EVICT_PERTASK_SHIFT;
+		uint64_t bytes_pertask = bytes_pertask_low + (lastrowcols ?
+		    (1 << MIN_EVICT_PERTASK_SHIFT) : 0);


I think you are over-engineering here. I don't think eviction per taskq should really be a multiple of 1 << MIN_EVICT_PERTASK_SHIFT to complicate the logic, merely it should be bigger than one. So you could just use MIN_EVICT_PERTASK_SHIFT to decide number of tasks, and then split the eviction amount equally between them.

And I wonder if it would make sense to scale number of tasks with eviction not linearly, but in some logarithimic fashion to not spin too many threads at once, stressing the system more for diminishing return.

amotin · 2024-09-05T16:13:51Z

module/zfs/arc.c

+				uint64_t evict = i < k ? bytes_pertask :
+				    bytes_pertask_low;
+
+				ASSERT3S(n, <=, num_sublists);


While it is true, I think it is irrelevant here.

amotin · 2024-09-05T16:15:06Z

module/zfs/arc.c

+
+				ASSERT3S(n, <=, num_sublists);
+
+				memset(&evarg[i].tqe, 0, sizeof (evarg[i].tqe));


There is taskq_init_ent() for this.

amotin · 2024-09-05T16:24:56Z

module/zfs/arc.c

@@ -7737,12 +7871,19 @@ arc_init(void)

 	buf_init();

+	if (zfs_arc_evict_threads == 0)
+		zfs_arc_evict_threads = MIN(16, max_ncpus >> 1);


It is subjective, but IMHO 1/2 of CPUs for memory eviction is too much if system is doing anything else. And the current algorithm for non-trivial eviction would tend to use all of them quite often, stressing the system.

adamdmoss · 2024-09-12T02:26:07Z

I've been casually testing this out (combined with the parallel_dbuf_evict PR) over the last couple of weeks (most recently, 5b070d1 ).

I've not been hammering it hard or specifically, just letting it do its thing with my messing-around desktop system.

Hit a probable regression today, though: while mv'ing a meager 8GB of files from one pool to another, all my zfs IO got really high-latency, and an iotop showed that the copy part of the move (this being a mv across pools, so in reality it's a copy-and-remove) was running at a painful few 100KB/sec, and the zfs arc_evict thread was taking a whole core... but just one core.

In time it all cleared up and of course I can't conclusively blame this PR's changes, but I left with two fuzzy observations:

In many years of mucking around with ZFS I've never(?) seemed to get the 'arc_evict is pegging CPU badly' issue until I started testing this PR's changes (though I'm aware the issue occurs in the wild for folks on master/release ZFSes)
arc_evict was only using one core as far as I can tell, so I guess the parallelism which is the point of this PR just wasn't kicking-in for some reason anyway and/or the spinning was happening outside of the parallelized part

0mp · 2024-09-12T11:56:09Z

I have updated the patch with a different logic for picking the default maximum number of ARC eviction threads. The new logic aims to pick the number that is one-eighth of the available CPUs, with a minimum of 2 and a maximum of 16.

amotin · 2024-09-12T13:47:34Z

one-eighth of the available CPUs, with a minimum of 2 and a maximum of 16.

Why would we need two evict threads on a single-core system? In that case I would probably prefer to disable taskqs completely. If that is a way to make it more logarithmic, then I would think about highbit(), though then it will grow pretty slow for very large systems, so that the limit of 16 will never be reached. But I am not exactly sure the faster growth would make sense, since it may cause more lock contentions in memory allocator, etc.

allanjude · 2024-09-16T15:32:27Z

one-eighth of the available CPUs, with a minimum of 2 and a maximum of 16.

Why would we need two evict threads on a single-core system? In that case I would probably prefer to disable taskqs completely. If that is a way to make it more logarithmic, then I would think about highbit(), though then it will grow pretty slow for very large systems, so that the limit of 16 will never be reached. But I am not exactly sure the faster growth would make sense, since it may cause more lock contentions in memory allocator, etc.

Right now, this is only enabled by a separate tunable, to enable multiple threads. So for the single CPU case, we don't expect it to be enabled. But for something like 4-12 core systems, we would want it to use at least 2 threads, and then grow from there, reaching 16 threads at 128 cores.

amotin · 2024-09-16T15:51:42Z

Right now, this is only enabled by a separate tunable, to enable multiple threads. So for the single CPU case, we don't expect it to be enabled.

Now that you mentioned it, I've noticed its been disabled by default. I don't like the idea to tune it manually in production depending on system size. I would prefer to to have reasonable automatic defaults.

Read and write performance can become limited by the arc_evict process being single threaded. Additional data cannot be added to the ARC until sufficient existing data is evicted. On many-core systems with TBs of RAM, a single thread becomes a significant bottleneck. With the change we see a 25% increase in read and write throughput Sponsored-by: Expensify, Inc. Sponsored-by: Klara, Inc. Co-authored-by: Allan Jude <allan@klarasystems.com> Co-authored-by: Mateusz Piotrowski <mateusz.piotrowski@klarasystems.com> Signed-off-by: Alexander Stetsenko <alex.stetsenko@klarasystems.com> Signed-off-by: Allan Jude <allan@klarasystems.com> Signed-off-by: Mateusz Piotrowski <mateusz.piotrowski@klarasystems.com>

0mp · 2024-10-23T20:41:47Z

Hey! So, here's what changed in the patch:

Formula

There is now a different formula for automatically scaling the number of evict threads when the parameter is set to 0. The formula is:

MIN(MAX(max_ncpus > 6 ? 2 : 1, ilog2(max_ncpus) + (max_ncpus >> 6)), 16);

It looks like this (the x axis is the CPU count and the y axis is the evict thread count):

Here's also a table:

CPUs	`zfs_arc_evict_threads`	Evict threads count	Using taskq?
1	0	1 (autoscaled)	No
2	0	1 (autoscaled)	No
5	0	1 (autoscaled)	No
6	0	2 (autoscaled)	Yes
1024	0	16 (autoscaled)	Yes
(not using autoscaling, CPU count is irrelevant)	1	1	No
(not using autoscaling, CPU count is irrelevant)	32	32	Yes

Less parameters

zfs_arc_evict_threads is now the only parameter exposed to control the evict thread count. The zfs_arc_evict_threads_parallel has been removed in favor of enabling the use of taskqs when there are two or more evict threads.

This approach has been suggested by @tonyhutter in another PR (#16487 (comment)).

Stability improvements

It is no longer possible to modify the actual evict threads count during runtime. Since the evict taskqs are only created during arc_init(), the module saves the actual number of evict threads it is going to use and does not care about changes to zfs_arc_evict_threads from then on. This behavior has been documented in the manual page.

amotin

Thanks for automating it. Few comments to that part, and please take a look on my earlier comments.

amotin · 2024-10-30T17:54:43Z

man/man4/zfs.4

+The minimum number of threads is 1 and applies to systems from 1 to 5 CPU cores.
+Systems with 6 CPU cores get 2 eviction threads.
+ZFS on systems larger than that uses log2 of the CPU count
+plus the CPU count shifted 6 bits.


Suggested change

plus the CPU count shifted 6 bits.

plus one for each 64 CPUs.

amotin · 2024-10-30T17:58:54Z

module/zfs/arc.c

+	    MIN(zfs_arc_evict_threads_live, max_ncpus), defclsyspri,
+	    MIN(zfs_arc_evict_threads_live, max_ncpus), max_ncpus,


Do we need another set of limitations?

amotin · 2024-10-30T18:02:32Z

module/zfs/arc.c

+		zfs_arc_evict_threads_live = MIN(MAX(max_ncpus > 6 ? 2 : 1,
+		    arc_ilog2(max_ncpus) + (max_ncpus >> 6)), 16);


Do we really need the MAX(max_ncpus > 6 ? 2 : 1 part? ilog2(6) should already be 2.

amotin · 2024-10-30T18:04:08Z

module/zfs/arc.c

+static inline size_t
+arc_ilog2(int a)
+{
+	return (a > 1 ? 1 + arc_ilog2(a >> 1) : 0);


There is highbit() function, which should produce the similar result without recursion.

amotin · 2024-10-30T18:04:17Z

module/zfs/arc.c

+ZFS_MODULE_PARAM(zfs_arc, zfs_arc_, evict_threads, UINT, ZMOD_RW,
+	"Maximum number of arc_evict threads");


For read-only tunables there is ZMOD_RD, which should allow initial setting, but not later modification. After that you would not need zfs_arc_evict_threads_live.

allanjude force-pushed the parallel_arc_evict branch from 4cd510d to f45bf2e Compare August 29, 2024 18:19

rincebrain mentioned this pull request Aug 30, 2024

dmu_objset: replace dnode_hash impl with cityhash4 #16483

Closed

13 tasks

allanjude force-pushed the parallel_arc_evict branch from f45bf2e to 146fe45 Compare September 4, 2024 23:16

amotin reviewed Sep 5, 2024

View reviewed changes

0mp force-pushed the parallel_arc_evict branch from 146fe45 to e128026 Compare September 12, 2024 10:03

behlendorf added the Status: Code Review Needed Ready for review and testing label Sep 13, 2024

0mp force-pushed the parallel_arc_evict branch from e128026 to b6a65a2 Compare October 23, 2024 17:16

0mp force-pushed the parallel_arc_evict branch from b6a65a2 to e99733e Compare October 23, 2024 19:49

amotin reviewed Oct 30, 2024

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Implement parallel ARC eviction #16486

Implement parallel ARC eviction #16486

allanjude commented Aug 29, 2024

amotin Sep 5, 2024

amotin Sep 5, 2024

amotin Sep 5, 2024

amotin Sep 5, 2024

adamdmoss commented Sep 12, 2024 •

edited

Loading

0mp commented Sep 12, 2024

amotin commented Sep 12, 2024 •

edited

Loading

allanjude commented Sep 16, 2024

amotin commented Sep 16, 2024

0mp commented Oct 23, 2024

amotin left a comment

amotin Oct 30, 2024

0mp Oct 31, 2024

amotin Oct 30, 2024

amotin Oct 30, 2024

amotin Oct 30, 2024

amotin Oct 30, 2024


		ASSERT3S(n, <=, num_sublists);

		memset(&evarg[i].tqe, 0, sizeof (evarg[i].tqe));

	plus the CPU count shifted 6 bits.
	plus one for each 64 CPUs.

		MIN(zfs_arc_evict_threads_live, max_ncpus), defclsyspri,
		MIN(zfs_arc_evict_threads_live, max_ncpus), max_ncpus,

		zfs_arc_evict_threads_live = MIN(MAX(max_ncpus > 6 ? 2 : 1,
		arc_ilog2(max_ncpus) + (max_ncpus >> 6)), 16);

		ZFS_MODULE_PARAM(zfs_arc, zfs_arc_, evict_threads, UINT, ZMOD_RW,
		"Maximum number of arc_evict threads");

Implement parallel ARC eviction #16486

Are you sure you want to change the base?

Implement parallel ARC eviction #16486

Conversation

allanjude commented Aug 29, 2024

Motivation and Context

Description

How Has This Been Tested?

Types of changes

Checklist:

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

adamdmoss commented Sep 12, 2024 • edited Loading

0mp commented Sep 12, 2024

amotin commented Sep 12, 2024 • edited Loading

allanjude commented Sep 16, 2024

amotin commented Sep 16, 2024

0mp commented Oct 23, 2024

Formula

Less parameters

Stability improvements

amotin left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

adamdmoss commented Sep 12, 2024 •

edited

Loading

amotin commented Sep 12, 2024 •

edited

Loading