Używasz przestarzałej przeglądarki. Może ona nieprawidłowo wyświetlać tę lub inne strony. Powinieneś zaktualizować przeglądarkę lub użyć alternatywnej przeglądarki.
Goes away after a minute or two but ever since that partial loading patch thing or some other change not everything on a page will load, especially avatars. Specifically on safari on mobile iOS
EDIT: hard refresh earlier just seemed to hang and assets would never load. But since then, today, I didn’t change anything but everything is loading just fine and seemingly quite fast.
If anything changed, that was the fix.
Just dropping in to say that the site's performance has been phenomenal and the previous tech issues around uploading and buffering I reported are gone. Also consistently maxing out upload speeds from APAC region, almost no issues with uploads, fast buffering/playing of videos. Whatever you changed a week or two ago it's working great.
The issue was that openresty debian did not ship with the http slice module which allowed byte range requests. Since we have 200mb+ files, that means our local S3 had to serve 200MB requests, send them to the middle servers, and have those servers cache and send byte ranges out.
I assumed this was "a problem" but I didn't really appreciate just how big of a problem it was. When we started hitting 3000+ users again I realized there was a serious I/O issue and it was causing database errors. I gave the database ionice priority and that helped a lot, which surprised me because our storage is all SSDs. The SSDs were peaking at over 750Mbps of read. I assumed this was just the natural usage of the S3 server, since the IO was on that and not the webserver. At some point it clicked that all the problems were unified by a common theme of large files not sending as byte ranges and yelled at the vendors to ship with slice. It cut IO read down by more than 1/10th.
In retrospect I think that any person opening any page with videos caused the S3 to load and send the entire video just to generate the first bit of the byte range for a preview image, i.e. every video tag had a full download impact on S3.
So more than 10%? Reading your explanation I somehow thought it would be more given the constant downloading of any video on any active page. But I have very little experience with those levels of scaling.
Also if you have any before/after usage graphs for IO/net that would be interesting
So more than 10%? Reading your explanation I somehow thought it would be more given the constant downloading of any video on any active page. But I have very little experience with those levels of scaling.
Goes away after a minute or two but ever since that partial loading patch thing or some other change not everything on a page will load, especially avatars. Specifically on safari on mobile iOS
EDIT: hard refresh earlier just seemed to hang and assets would never load. But since then, today, I didn’t change anything but everything is loading just fine and seemingly quite fast.
Site has been very slow since yesterday. There are short windows of time where it isn't, but generally going to other pages, rating people, looking at bookmarks, pretty much anything takes longer than usual. Loading into the site itself takes like 30 seconds.
From my network view it looks like 94.177.106.7 is unreachable due to timeout.
Last 3 hops:
Kod:
ae2.2.edge2.bch1.neo.colt.net (171.75.10.162) 207.769 ms 207.691 ms 207.648 ms
213.249.122.142 (213.249.122.142) 201.996 ms 203.991 ms 203.720 ms
buc-vox-pr1.zet.net (103.246.249.1) 203.266 ms 200.926 ms 203.942 ms
* * *
I blacklisted(are we allowed to say that these days?) it in my DNS server and the site seems happier without it.
Can't tell if it's just blocked or dead. Next after KiwiFlare Jersh needs to write his own global DNS load balancing and fail over system.
Site has been very slow since yesterday. There are short windows of time where it isn't, but generally going to other pages, rating people, looking at bookmarks, pretty much anything takes longer than usual. Loading into the site itself takes like 30 seconds.
The behavior where you open a spoiler, scroll past it, and then your screen gets rolled back up is detrimental to my mental health. I was looking at the SRS surgery disasters thread and I kept being forced to look at the butchery again after every scroll.
No but seriously, it's also annoying in general. I don't even understand the use case for it. If you scroll past something it's because you're done with it, why auto scroll back up? Is it a default Xenforo feature that is way too difficult to circumvent?
