Commit Graph

376 Commits

Author SHA1 Message Date
Łukasz Magiera
03fa955e9e Cleanup imports 2022-01-18 11:37:24 +01:00
Łukasz Magiera
f2496d87c9 post workers: Snapdeals updates 2022-01-18 11:25:04 +01:00
Łukasz Magiera
0c062f9c08 Merge remote-tracking branch 'origin/master' into feat/post-worker 2022-01-18 10:49:42 +01:00
Łukasz Magiera
4a874eff70 post workers: Cleanup, tests 2022-01-14 14:17:52 +01:00
Aayush Rajasekaran
d645c5fbab Remove unnecessary params from VerifyWinningPost 2022-01-11 12:06:39 -05:00
Łukasz Magiera
e216aefd23 fix make gen 2022-01-10 18:24:00 +01:00
zenground0
33f2d24f54 Snap Deals Integration
- FSM handles the actual cc upgrade process including error states
- PoSting (winning and window) works over upgraded and upgrading sectors
- Integration test and changes to itest framework to reduce flakes
- Update CLI to handle new upgrade
- Update dependencies
2022-01-10 15:39:38 +05:30
mz-sirius
793b5c7cc3 fix ci err 2022-01-05 21:41:21 +08:00
mz-sirius
3fd55fa56b decoupling winningpost and windowpost from lotus-miner 2022-01-05 01:50:49 +08:00
shotcollin
d10d0a20b1
fix typo in log warning
very minor but this warning comes up a lot so it'd be nicer if it wasn't a grammatical error too
2021-12-19 17:07:11 -07:00
Aayush Rajasekaran
80d5e52923 Merge branch 'master' into next 2021-12-13 13:24:28 -05:00
Łukasz Magiera
e8ef39e734 stores: Reduce log spam during retrievals 2021-12-10 11:28:04 +01:00
Łukasz Magiera
c31f4de7d5 Fix mock ReadPiece 2021-12-09 16:26:59 +01:00
Łukasz Magiera
6fd1609410 fr32: Reduce MTTresh from 32M to 512k per core
This results in 64x less bytes allocated when spawning new readers
for larger pieces.

Results in about 30% speedup in 1G unpad benchmark on AMD TR 2950x
2021-12-09 16:14:47 +01:00
Łukasz Magiera
9c75a3aaa8 piecereader: Avoid allocating 1024MB slices per read 2021-12-09 15:49:43 +01:00
Łukasz Magiera
a3d8494a04 piecereader: Avoid redundant roundtrips when seeking 2021-12-09 14:52:33 +01:00
Łukasz Magiera
13b260e7f7 piecereader: Move closer to storage 2021-12-08 23:20:20 +01:00
zenground0
a5be80828a RemoveData and Decode
- Unsealing replica update with sector key works and tested
- Sector key generation added and tested
2021-12-03 15:21:06 -05:00
Łukasz Magiera
727765b248 Command to list active sector locks 2021-12-03 12:33:23 +01:00
Łukasz Magiera
71329f6c41 Address Scheduler enhancements (#7703) review 2021-11-30 20:50:40 +01:00
zenground0
40d16a8f88 Review Response 2021-11-30 13:53:37 -05:00
zenground0
f88fcdbcfc WIP 2021-11-30 12:40:14 -05:00
Łukasz Magiera
001ecbb561 fix lint 2021-11-30 02:06:58 +01:00
Łukasz Magiera
a597b072b8 fix sched tests 2021-11-30 02:06:58 +01:00
Łukasz Magiera
f25efecb74 worker: Test resource table overrides 2021-11-30 02:06:58 +01:00
Łukasz Magiera
6d52d8552b Fix docsgen 2021-11-30 02:06:58 +01:00
Łukasz Magiera
c9a2ff4007 cleanup worker resource overrides 2021-11-30 02:06:58 +01:00
Łukasz Magiera
b961e1aab5 sched resources: Separate Parallelism defaults depending on GPU presence 2021-11-30 02:06:58 +01:00
Łukasz Magiera
36868a8749 sched: C2 is not all-core load 2021-11-30 02:06:58 +01:00
Clint Armstrong
4ef8543128 Permit workers to override resource table
In an environment with heterogenious worker nodes, a universal resource
table for all workers does not allow effective scheduling of tasks. Some
workers may have different proof cache settings, changing the required
memory for different tasks. Some workers may have a different count of
CPUs per core-complex, changing the max parallelism of PC1.

This change allows workers to customize these parameters with
environment variables. A worker could set the environment variable
PC1_MIN_MEMORY for example to customize the minimum memory requirement
for PC1 tasks. If no environment variables are specified, the resource
table on the miner is used, except for PC1 parallelism.

If PC1_MAX_PARALLELISM is not specified, and
FIL_PROOFS_USE_MULTICORE_SDR is set, PC1_MAX_PARALLELSIM will
automatically be set to FIL_PROOFS_MULTICORE_SDR_PRODUCERS + 1.
2021-11-30 02:06:58 +01:00
Clint Armstrong
93e4656a27 Use a float to represent GPU utilization
Before this change workers can only be allocated one GPU task,
regardless of how much of the GPU resources that task uses, or how many
GPUs are in the system.

This makes GPUUtilization a float which can represent that a task needs
a portion, or multiple GPUs. GPUs are accounted for like RAM and CPUs so
that workers with more GPUs can be allocated more tasks.

A known issue is that PC2 cannot use multiple GPUs. And even if the
worker has multiple GPUs and is allocated multiple PC2 tasks, those
tasks will only run on the first GPU.

This could result in unexpected behavior when a worker with multiple
GPUs is assigned multiple PC2 tasks. But this should not suprise any
existing users who upgrade, as any existing users who run workers with
multiple GPUs should already know this and be running a worker per GPU
for PC2. But now those users have the freedom to customize the GPU
utilization of PC2 to be less than one and effectively run multiple PC2
processes in a single worker.

C2 is capable of utilizing multiple GPUs, and now workers can be
customized for C2 accordingly.
2021-11-30 02:06:58 +01:00
Clint Armstrong
c4f46171ae Report memory used and swap used in worker res
Attempting to report "memory used by other processes" in the MemReserved
field fails to take into account the fact that the system's memory used
includes memory used by ongoing tasks.

To properly account for this, worker should report the memory and swap
used, then the scheduler that is aware of the memory requirements for a
task can determine if there is sufficient memory available for a task.
2021-11-30 02:06:58 +01:00
Clint Armstrong
e2a1ca7caa Use cgroup limits in worker memory calculations
Worker processes may have memory limitations imposed by Systemd. But
/proc/meminfo shows the entire system memory regardless of these limits.
This results in the scheduler believing the worker has the entire system
memory avaliable and the worker being allocated too many tasks.

This change attempts to read cgroup memory limits for the worker
process. It supports cgroups v1 and v2, and compares cgroup limits
against the system memory and returns the most conservative values to
prevent the worker from being allocated too many tasks and potentially
triggering an OOM event.
2021-11-30 02:06:58 +01:00
Łukasz Magiera
d21c44e266 ffiwrapper: Validate PC2 by calling C1 with random seeds 2021-11-30 01:33:05 +01:00
zenground0
7d2b3f05db WIP sector storage and integration test 2021-11-29 10:24:00 -05:00
Łukasz Magiera
05aa860459 Request correct read size with startOffset in pieceProvider 2021-11-27 00:05:45 +01:00
Łukasz Magiera
743ce5a40f Add startOffset support to mock SectorMgr.ReadPiece 2021-11-26 18:48:52 +01:00
Łukasz Magiera
f6de16e95a Fix sector-storage tests 2021-11-26 18:16:53 +01:00
Łukasz Magiera
8d955d5f30 dagstore mount: Add random access support 2021-11-26 17:40:53 +01:00
Łukasz Magiera
8454abcf45 storage: Use 1M buffers for Tar transfers 2021-11-24 20:08:37 +01:00
Łukasz Magiera
2a1505b364 storage: Test StorageFindSector with groups 2021-11-23 16:11:04 +01:00
Łukasz Magiera
8b548ac02f storage: Check allowlists in StorageFindSector 2021-11-23 16:11:04 +01:00
Łukasz Magiera
5c77c25747 storage: Add Group tags to StorageInfo 2021-11-23 16:11:04 +01:00
Łukasz Magiera
d1a63e4173 remote store: Remove debug printf 2021-11-22 17:50:12 +01:00
Aayush Rajasekaran
8665e32221 Update deps 2021-11-17 15:55:14 -05:00
Aayush Rajasekaran
07f1be0ff6 Plug in the FFI call 2021-11-17 15:55:14 -05:00
Aayush Rajasekaran
1449644c34 Integrate v7 actors 2021-11-17 15:55:14 -05:00
Łukasz Magiera
e508055dc1 make gen 2021-10-19 11:13:23 +02:00
Łukasz Magiera
080aa3356a Fix locks in worker-tracked 2021-10-18 20:19:21 +02:00
Łukasz Magiera
70589e4406 Block work in tracked worker before it is started 2021-10-18 18:44:56 +02:00