News for hackers. Stuff that matters.
Re:Microsoft blames monster email outage on software defect ... by d_g_m on Monday November 16, 2026 @10:49PM (#50527198)
> "Our load testing tended to focus on weaker hardware with fewer cores....The contention issue is worsened on machines with more cores and newer hardware."

Does anyone know why the situation got worse on better machines instead of worse? Normally it is the other way around when it comes to test coverage of hardware specs

Re:Microsoft blames monster email outage on software defect ... by nl on Monday November 16, 2026 @11:05PM (#50527288)
From the report: "lock contention inside an internal process... The contention issue is worsened on machines with more cores and newer hardware; whereas our load testing tended to focus on our weaker hardware SKUs with fewer cores."

I don't think anyone would be astonished by this bug - lock contention is hard. https://www.itnews.com.au/news/kernel-crashing-noisytcp-bug-... is a recent example in the Linux kernel.

This is one of the areas that provably correct software can make a big different and is worth the cost (even before AI)

Re:Microsoft blames monster email outage on software defect ... by cowlevel on Tuesday November 17, 2026 @04:27AM (#50529275)
Lock contention genuinely sounds like something out of the problems with azure blog series: https://news.ycombinator.com/item?id=47616242
Re:Microsoft blames monster email outage on software defect ... by nl on Tuesday November 17, 2026 @08:14AM (#50530929)
Not really. This was introduced in July.

That whole series reads like sour grapes by someone bitter about how they left.

Re:Microsoft blames monster email outage on software defect ... by cowlevel on Wednesday November 18, 2026 @06:30AM (#50544994)
The issues have been going on for years and getting worse for years, its irrelevant that this particular instance is from July.
Re:Microsoft blames monster email outage on software defect ... by tremon on Tuesday November 17, 2026 @11:20AM (#50533665)
Lock contention is when multiple threads try to access the same (memory) resource. More cores == more threads accessing the resource, and faster execution == less time between resource access for each thread. Both factors increase the time spent waiting on said lock, in relative and in absolute terms.
Re:Microsoft blames monster email outage on software defect ... by malkia on Tuesday November 17, 2026 @12:19PM (#50534769)
My take is on NUMA cache line contention. It's real.