And why asking - it comes when it comes anyways

borka wrote:tyvm for keeping on Loftar! - i'm eager to see the answers on the ML
loftar wrote:I'm still pondering the lag on my own, but in the meantime, I also posted to the LKML about it, so in case anyone is interested, you can read my description of it over there.
loftar wrote:I'm still pondering the lag on my own, but in the meantime, I also posted to the LKML about it, so in case anyone is interested, you can read my description of it over there.
loftar wrote:I'm still pondering the lag on my own, but in the meantime, I also posted to the LKML about it, so in case anyone is interested, you can read my description of it over there.
Sarchi wrote:loftar wrote:I'm still pondering the lag on my own, but in the meantime, I also posted to the LKML about it, so in case anyone is interested, you can read my description of it over there.
It'll be amusing if it turns out to be something extremely simple.
Eric Wong wrote:So try lowering these sysctls to 2.6.26 levels (or lower) and see if
that helps.
Fwiw, I usually use dirty_ratio=2 dirty_background_ratio=1 on servers
with a few gigs of RAM (or appropriately low dirty*bytes values).
Lowering dirty*ratio helps servers get more consistent performance under
constant I/O pressure and aggressively throttles processes before a
large amount of dirty pages becomes a problem (as you've noticed).
High dirty*ratio is good for some bursty desktop workloads and some
benchmarks, though...
Users browsing this forum: Claude [Bot], Semrush [Bot] and 3 guests