On 27/11/18 23:42, Eric Dumazet wrote:
Jean-Louis Dupond reported poor iscsi TCP receive performance
that we tracked to backlog drops.
Apparently we fail to send window updates reflecting the
fact that we are under stress.
Note that we might lack a proper window increase when
backlog is fully
Hi,
Was somebody able to check this?
Really think this should be fixed :)
Thanks
Jean-Louis
On 3/11/18 16:59, Jean-Louis Dupond wrote:
Hi All,
On recent kernels we noticed a way lower throughput to our SAN system
than before.
While on pre 4.18 kernels we had 400-700MB/sec read speed
Hi All,
On recent kernels we noticed a way lower throughput to our SAN system
than before.
While on pre 4.18 kernels we had 400-700MB/sec read speed, on 4.18+ we
only had 70-120MB/sec.
The SAN is connected via iSCSI over a 10G network (ixgbe/X520 NICS if it
matters).
After some debugging,
e host. The rescheduling will be done in the
timer callback function.
Reported-by: Jean-Louis Dupond <jean-lo...@dupond.be>
Signed-off-by: Wei Liu <wei.l...@citrix.com>
Tested-by: Jean-Louis Dupond <jean-lo...@dupond.be>
Applied.
Could this get applied to stable & LTS kernels also?
Hi,
Any chance on this? As it gives a possible freeze on all Xen machines
that use rate-limiting, I really think we should backport this straight
forward patch.
Thanks
Jean-Louis
Op 11-07-17 om 11:47 schreef Jean-Louis Dupond:
Hi All,
Is there a chance the following patch
(https
Hi All,
Is there a chance the following patch
(https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git/commit/?id=dfa523ae9f2542bee4cddaea37b3be3e157f6e6b)
can get backported to the current LTS kernels (including 4.9.x)?
The commit message might not be completely showing the
