RE: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

. Thomas From: Ben Slater [mailto:ben.sla...@instaclustr.com] Sent: Freitag, 12. Jänner 2018 23:37 To: user@cassandra.apache.org Subject: Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra? We’re seeing evidence across our fleet that AWS has rolled something out in the last 24 hours

RE: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

g as well: https://blog.appoptics.com/visualizing-meltdown-aws/ Regards, Thomas *From:* Ben Slater [mailto:ben.sla...@instaclustr.com] *Sent:* Freitag, 12. Jänner 2018 23:37 *To:* user@cassandra.apache.org *Subject:* Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra? We’re seeing evi

RE: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

.org> Subject: Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra? Make sure you pick instances with PCID cpu capability, their TLB overhead flush overhead is much smaller On Tue, Jan 9, 2018 at 2:04 AM, Steinmaurer, Thomas <thomas.steinmau...@dynatrace.com<mailto:thomas.stein

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

have the production > instances patched at OS/VM level (yet). > > Thomas > > *From:* Dor Laor [mailto:d...@scylladb.com <d...@scylladb.com>] > *Sent:* Dienstag, 09. Jänner 2018 19:30 > *To:* user@cassandra.apache.org > *Subject:* Re: Meltdown/Spectre Linux patch - Perfor

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

ve the production > instances patched at OS/VM level (yet). <> > > Thomas > > From: Dor Laor [mailto:d...@scylladb.com] > Sent: Dienstag, 09. Jänner 2018 19:30 > To: user@cassandra.apache.org > Subject: Re: Meltdown/Spectre Linux patch - Performance impact on

RE: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

[mailto:d...@scylladb.com] Sent: Dienstag, 09. Jänner 2018 19:30 To: user@cassandra.apache.org Subject: Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra? Make sure you pick instances with PCID cpu capability, their TLB overhead flush overhead is much smaller On Tue, Jan 9, 2018 at 2:04

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Longer than that. Years. Check /proc/cpuinfo -- Jeff Jirsa > On Jan 9, 2018, at 11:19 PM, daemeon reiydelle wrote: > > Good luck with that. Pcid out since mid 2017 as I recall? > > > Daemeon (Dæmœn) Reiydelle > USA 1.415.501.0198 > > On Jan 9, 2018 10:31 AM, "Dor

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Hard to tell from the first 10 google search results which Intel CPUs has it so I went to ask my /proc/cpuinfo, turns out my >1 year Dell XPS laptop has it. AWS's i3 has it too. flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Good luck with that. Pcid out since mid 2017 as I recall? Daemeon (Dæmœn) Reiydelle USA 1.415.501.0198 On Jan 9, 2018 10:31 AM, "Dor Laor" wrote: Make sure you pick instances with PCID cpu capability, their TLB overhead flush overhead is much smaller On Tue, Jan 9, 2018 at

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Hi All,Has anyone seen any test results for SQL Server? Although I am a Cassandra user I do use SQL Server for other companies. Thanks,-Tony From: Dor Laor <d...@scylladb.com> To: user@cassandra.apache.org Sent: Tuesday, January 9, 2018 10:31 AM Subject: Re: Meltdown/Spectre

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Make sure you pick instances with PCID cpu capability, their TLB overhead flush overhead is much smaller On Tue, Jan 9, 2018 at 2:04 AM, Steinmaurer, Thomas < thomas.steinmau...@dynatrace.com> wrote: > Quick follow up. > > > > Others in AWS reporting/seeing something similar, e.g.: >

RE: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Quick follow up. Others in AWS reporting/seeing something similar, e.g.: https://twitter.com/BenBromhead/status/950245250504601600 So, while we have seen an relative CPU increase of ~ 50% since Jan 4, 2018, we now also have applied a kernel update at OS/VM level on a single node (loadtest and

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Thanks for the insight, Romain, and providing those numbers. Looking forward to others posting their stats here. We are running up some tests and will share when available. Cheers! On Sat, Jan 6, 2018 at 3:44 AM, Romain Hardouin wrote: > Hi, > > We also noticed an

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Hi, We also noticed an increase of CPU - both system and user - on our c3.4xlarge fleet. So far it's really visible with max(%user) and especially max(%system), it has doubled!I graphed a ratio "write/s / %system", it's interesting to see how the value dropped yesterday, you can see it here:

Re: Meltdown/Spectre Linux patch - Performance impact on Cassandra?

Hi Thomas, No clue about AWS, and it is of course highly dependent on hardware, but on CentOS 7 on bare metal, the patched kernel (kernel-3.10.0-693.11.6.el7.x86_64) seems to have a roughly 50% CPU increase compared to an unpatched kernel (kernel-3.10.0-693.11.1.el7.x86_64). On a happier note,