Updates on Test Data

Announcements
1748

I guess this is because of the new node selection algorithm. When serving only one satellite there is a better chance to be constantly selected and the benefit seems to be bigger than the penalty for not serving the other 3 satellites.

Next test will be 4 nodes per HDD but only one satellite each. BTW: This should not be a problem for data security (TOS) because satellites are independent.

1 Like
1749

Ah… a few days to experience natural free-range organic traffic again: I had forgotten what it was like! Artisanal ones and zeroes from a small selection of actual paying customers!

A reminder that the “new normal” is not yet normal… :wink:

3 Likes
1750

Or to process bloom filters if only there were any… :wink:

2 Likes
1751

In my had I was adding sugar free :smiley:

1 Like
1752

Is it possible we can get a new round of garbage collection for this weekend?

3 Likes
1753

bf

11 Likes
1754

This is mean that someone deleted the TTL data before expire, so the garbage collector moved it to the trash and now the TTL is expired, but the piece already removed. So, kind of expected.

1755

12,600,000 IOPS? :astonished: What’s model?
Or is it an amount of pieces?

1756

It’s a super old Crucial m4 120GB ssd from 2013. Here are my logs:

2024-07-02T22:42:17Z	INFO	db.migration.58	Remove unused trash column	{"Process": "storagenode"}
2024-07-02T22:43:28Z	INFO	db.migration.59	Remove unused deletion_failed_at column	{"Process": "storagenode"}
2024-07-02T22:44:51Z	INFO	db.migration.60	Overhaul piece_expirations	{"Process": "storagenode"}
2024-07-02T22:46:26Z	INFO	db.migration	Database Version	{"Process": "storagenode", "version": 60}

This is running on ZFS with compression enabled so it might just be doing everything in RAM, while I did observe 200 MB/s writes to the SSD during migration. I have also migrated another node whose SSD is on XFS (Samsung 840 250GB), and it takes about 10 minutes, with 40 MB/s writes.

Edit: Now that I read your question more carefully, 12600k is an Intel CPU xd

1 Like
1757

Intel 12600k I suppose

4 Likes
1758

Thank you for clarification, I just wondered was there a mistype or I just missed something.

1759

Could you guys have a topic where all these infos are announced only?

There are just too many topics in parallel with a lotof conversations and its hard to find infos/facts what is your plans, like how much test data is planned, how long, why is it stopped and what are yours current focus and a lot of reading is neccessary just to get these.

5 Likes
1760

They’re using the “Announcements” Category. There’s a post about test data. And another about business plans.

Two threads in the same Category. That’s too much to keep up with?

The only required reading is checking email for “Your Node has Gone Offline” messages. Anything else is optional because you’re curious… in which case don’t expect to be spoon-fed :stuck_out_tongue_closed_eyes:

2 Likes
1761

This thread has over 1600 replies, it may be a bit much for someone who does not read it all the time.

3 Likes
1762

Yes, as someone who doesn’t visit the forum often it would be tedious to get all the information. I would like to suggest to visit the Storjling’s profile and read their activity which shows their replies.

1 Like
1763

Yes this is my main point, and sometimes days goes by when there is only talk about specific systems or builds, logs etc and then 1 single comment with an update what is gonna happen and then again a few hundred comment on a sidetopic.

2 Likes
1764

So lets continue some small talk to make this thread even longer? :smiley:

1 Like
1765

What did you have for breakfast today? :sweat_smile:

1766

In 2024, they should have a Telegram channel with announcements, not a forum topic.

3 Likes
1767

Roger that.